Upload folder using huggingface_hub

.ipynb_checkpoints/Test-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/Test-mgc-Copy1-checkpoint.ipynb

@@ -0,0 +1,1177 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so\n",
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 121\n",
+ "CUDA SETUP: Loading binary /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so...\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib64'), PosixPath('/usr/local/nvidia/lib')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('ssh-rsa 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 shanjay@LAPTOP-Q1PG3AE7')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//g.notebooksg.jarvislabs.net'), PosixPath('https')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
+ " warn(msg)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3edf6ee054e9464eb510d3aff9d1dc5f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2be27a54d3e14399a41c46cd9c423399",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/6 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at ise-uiuc/Magicoder-S-DS-6.7B and are newly initialized: ['model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/mgc-ds\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 400\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "CPU times: user 26.5 s, sys: 177 ms, total: 26.7 s\n",
+ "Wall time: 26.7 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': ['A', 'B', 'C', 'D'],\n",
+ " 'B': [1, 2, 3, 4]})\n",
+ "df2 = pd.DataFrame({'A': ['A', 'B', 'C', 'E'],\n",
+ " 'B': [1, 2, 3, 5]})\n",
+ "# merge df1 and df2 on column 'A'\n",
+ "# SOLUTION START\n",
+ "\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': ['A', 'B', 'C', 'D'],\n",
+ " 'B': [1, 2, 3, 4]})\n",
+ "df2 = pd.DataFrame({'A': ['A', 'B', 'C', 'E'],\n",
+ " 'B': [1, 2, 3, 5]})\n",
+ "# merge df1 and df2 on column 'A'\n",
+ "result = pd.merge(df1, df2, on='A')\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "name = ['joy', 'shan']\n",
+ "roll_no = [1, 2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n",
+ "y = [1, 2, 3, 4, 5]\n",
+ "\n",
+ "# plot all types of plots in matplotlib\n",
+ "# SOLUTION START\n",
+ "\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n",
+ "y = [1, 2, 3, 4, 5]\n",
+ "\n",
+ "# plot all types of plots in matplotlib\n",
+ "plt.plot(x, y, label=\"plot\")\n",
+ "plt.scatter(x, y, label=\"scatter\")\n",
+ "plt.bar(x, y, label=\"bar\")\n",
+ "plt.hist(x, y, label=\"hist\")\n",
+ "plt.boxplot(x, y, label=\"boxplot\")\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n",
+ "y = [1, 2, 3, 4, 5]\n",
+ "\n",
+ "# plot all types of plots in matplotlib\n",
+ "plt.plot(x, y, label=\"plot\")\n",
+ "plt.scatter(x, y, label=\"scatter\")\n",
+ "plt.bar(x, y, label=\"bar\")\n",
+ "plt.hist(x, y, label=\"hist\")\n",
+ "plt.boxplot(x, y, label=\"boxplot\")\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'ID': ['01', '01', '01', '02', '02'],\n",
+ " 'TIME': ['2018-07-11 11:12:20', '2018-07-12 12:00:23', '2018-07-13 12:00:00', '2019-09-11 11:00:00', '2019-09-12 12:00:00']})\n",
+ "def g(df):\n",
+ " df['TIME'] = pd.to_datetime(df['TIME'])\n",
+ " df['RANK'] = df.groupby('ID')['TIME'].rank(ascending=True)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'ID': ['01', '01', '01', '02', '02'],\n",
+ " 'TIME': ['2018-07-11 11:12:20', '2018-07-12 12:00:23', '2018-07-13 12:00:00', '2019-09-11 11:00:00', '2019-09-12 12:00:00']})\n",
+ "def g(df):\n",
+ " df['TIME'] = pd.to_datetime(df['TIME'])\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "def g(df):\n",
+ " df['A'] = df['A'].replace(0, np.nan)\n",
+ " df['A'] = df['A'].fillna(method='ffill')\n",
+ " df['A'] = df['A'].fillna(method='bfill')\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n",
+ "<output>: import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "def g(df):\n",
+ " df['A'] = df['A'].replace(0, np.nan)\n",
+ " df['A'] = df['A'].fillna(method='ffill')\n",
+ " df['A'] = df['A'].fillna(method='bfill')\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n",
+ "<output>: import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Problem:\n",
+ "My sample df has four columns with NaN values. The goal is to concatenate all the keywords rows while excluding the NaN values.\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3\n",
+ "0 Hu Tao a d NaN f\n",
+ "1 Zhongli NaN e NaN NaN\n",
+ "2 Xingqiu c NaN b g\n",
+ "\n",
+ "\n",
+ "Want to accomplish the following:\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3 keywords_all\n",
+ "0 Hu Tao a d NaN f a-d-f\n",
+ "1 Zhongli NaN e NaN NaN e\n",
+ "2 Xingqiu c NaN b g c-b-g\n",
+ "\n",
+ "\n",
+ "Pseudo code:\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "df[\"keywords_all\"] = df[\"keywords_all\"].apply(lambda cols: \"-\".join(cols), axis=1)\n",
+ "\n",
+ "\n",
+ "I know I can use \"-\".join() to get the exact result, but I am unsure how to pass the column names into the function.\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['question'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "id": "1c5841e9-4331-4185-a7ad-7dd00d4e13b1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "import numpy as np\n",
+ "def g(df):\n",
+ " df[\"keywords_all\"] = df.filter(like='keyword').apply(lambda x: '-'.join(x.dropna()), axis=1)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['answer'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "id": "090e98c3-78db-4e33-af4b-01c6e1fc23d0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "def f(cols):\n",
+ " return \"-\".join(cols)\n",
+ "\n",
+ "\n",
+ "df[\"keywords_all\"] = df.apply(lambda row: f(row[cols]), axis=1)\n",
+ "\n",
+ "\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "def f(cols):\n",
+ " return \"-\".join(cols)\n",
+ "\n",
+ "\n",
+ "df[\"keywords_all\"] = df.apply(lambda\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = data[5]['question']\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "id": "29609669-1ac7-4f6a-b0e3-64a3bf7a6545",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None,\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to remove null valued rows?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "id": "5ca085f6-30fc-4e50-a436-673f3baa75af",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import sklearn\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "\n",
+ "X, y = load_data()\n",
+ "\n",
+ "# Split the data into training and test sets\n",
+ "# Split the data into training and test sets\n",
+ "# Split the data into training and test sets\n",
+ "# Train a Logistic Regression model on the training data\n",
+ "# Print the accuracy of the model on the test data\n",
+ "# SOLUTION START\n",
+ "\n",
+ "<output>: import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import sklearn\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "\n",
+ "X, y = load_data()\n",
+ "\n",
+ "# Split the data into training and test sets\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+ "# Train a Logistic Regression model on the training data\n",
+ "model = LogisticRegression()\n",
+ "model.fit(X_train, y_train)\n",
+ "# Print the accuracy of the model on the test data\n",
+ "print(model.score(X_test, y_test))\n",
+ "<output>: import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import sklearn\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.model_selection import train_test_split\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to train a Logistic Regression model?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "146527ff-5d37-42c7-b06b-45c1aa224d17",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "84f671f3-7bd6-4a7c-81e9-758052b424cf",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/Test-mgc-f-checkpoint.ipynb

@@ -0,0 +1,866 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so\n",
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 121\n",
+ "CUDA SETUP: Loading binary /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so...\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib'), PosixPath('/usr/local/nvidia/lib64')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('ssh-rsa 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 shanjay@LAPTOP-Q1PG3AE7')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('https'), PosixPath('//g.notebooksg.jarvislabs.net')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
+ " warn(msg)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2316598db91e443f8c4e1cc615a9507f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7e1406ca2f5f4c0dbf0a581edebc9a6b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at deepseek-ai/deepseek-coder-6.7b-instruct and are newly initialized: ['model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2b9911223be04aeabbc44875a5929afa",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "adapter_model.bin: 0%| | 0.00/33.6M [00:00<?, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/ds-dsc-v4\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 200\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n",
+ "CPU times: user 26.8 s, sys: 346 ms, total: 27.1 s\n",
+ "Wall time: 27.2 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'C': [7, 8, 9], 'D': [10, 11, 12]})\n",
+ "\n",
+ "# merge df1 and df2\n",
+ "result = ...\n",
+ "\n",
+ "print(result)\n",
+ "\n",
+ "# Expected output\n",
+ "# A B C D\n",
+ "# 0 1 4 7 10\n",
+ "# 1 2 5 8 11\n",
+ "# 2 3 6 9 12\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "plt.legend()\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "pl\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Problem:\n",
+ "My sample df has four columns with NaN values. The goal is to concatenate all the keywords rows while excluding the NaN values.\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3\n",
+ "0 Hu Tao a d NaN f\n",
+ "1 Zhongli NaN e NaN NaN\n",
+ "2 Xingqiu c NaN b g\n",
+ "\n",
+ "\n",
+ "Want to accomplish the following:\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3 keywords_all\n",
+ "0 Hu Tao a d NaN f a-d-f\n",
+ "1 Zhongli NaN e NaN NaN e\n",
+ "2 Xingqiu c NaN b g c-b-g\n",
+ "\n",
+ "\n",
+ "Pseudo code:\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "df[\"keywords_all\"] = df[\"keywords_all\"].apply(lambda cols: \"-\".join(cols), axis=1)\n",
+ "\n",
+ "\n",
+ "I know I can use \"-\".join() to get the exact result, but I am unsure how to pass the column names into the function.\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['question'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "1c5841e9-4331-4185-a7ad-7dd00d4e13b1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "import numpy as np\n",
+ "def g(df):\n",
+ " df[\"keywords_all\"] = df.filter(like='keyword').apply(lambda x: '-'.join(x.dropna()), axis=1)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['answer'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "090e98c3-78db-4e33-af4b-01c6e1fc23d0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = data[5]['question']\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "29609669-1ac7-4f6a-b0e3-64a3bf7a6545",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3, None, 5],\n",
+ " 'B': [1, 2, 3, None, 5],\n",
+ " 'C': [1, 2, 3, None, 5],\n",
+ " 'D': [1, 2, 3, None, 5],\n",
+ " 'E': [1, 2, 3, None, 5]})\n",
+ "\n",
+ "df = df.dropna(how='all')\n",
+ "print(df)\n",
+ "<output>: A B C D E\n",
+ "0 1 1 1 1 1\n",
+ "1 2 2 2 2 2\n",
+ "2 3 3 3 3 3\n",
+ "4 5 5 5 5 5\n",
+ "<output>: import pand\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to remove null valued rows?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "5ca085f6-30fc-4e50-a436-673f3baa75af",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/Testv3-checkpoint.ipynb

@@ -0,0 +1,831 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so\n",
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 121\n",
+ "CUDA SETUP: Loading binary /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so...\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib'), PosixPath('/usr/local/nvidia/lib64')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('ssh-rsa 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 shanjay@LAPTOP-Q1PG3AE7')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('https'), PosixPath('//g.notebooksg.jarvislabs.net')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
+ " warn(msg)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2316598db91e443f8c4e1cc615a9507f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7e1406ca2f5f4c0dbf0a581edebc9a6b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at deepseek-ai/deepseek-coder-6.7b-instruct and are newly initialized: ['model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2b9911223be04aeabbc44875a5929afa",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "adapter_model.bin: 0%| | 0.00/33.6M [00:00<?, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/ds-dsc-v4\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 200\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n",
+ "CPU times: user 26.8 s, sys: 346 ms, total: 27.1 s\n",
+ "Wall time: 27.2 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'C': [7, 8, 9], 'D': [10, 11, 12]})\n",
+ "\n",
+ "# merge df1 and df2\n",
+ "result = ...\n",
+ "\n",
+ "print(result)\n",
+ "\n",
+ "# Expected output\n",
+ "# A B C D\n",
+ "# 0 1 4 7 10\n",
+ "# 1 2 5 8 11\n",
+ "# 2 3 6 9 12\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "plt.legend()\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "pl\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Problem:\n",
+ "My sample df has four columns with NaN values. The goal is to concatenate all the keywords rows while excluding the NaN values.\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3\n",
+ "0 Hu Tao a d NaN f\n",
+ "1 Zhongli NaN e NaN NaN\n",
+ "2 Xingqiu c NaN b g\n",
+ "\n",
+ "\n",
+ "Want to accomplish the following:\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3 keywords_all\n",
+ "0 Hu Tao a d NaN f a-d-f\n",
+ "1 Zhongli NaN e NaN NaN e\n",
+ "2 Xingqiu c NaN b g c-b-g\n",
+ "\n",
+ "\n",
+ "Pseudo code:\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "df[\"keywords_all\"] = df[\"keywords_all\"].apply(lambda cols: \"-\".join(cols), axis=1)\n",
+ "\n",
+ "\n",
+ "I know I can use \"-\".join() to get the exact result, but I am unsure how to pass the column names into the function.\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['question'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "1c5841e9-4331-4185-a7ad-7dd00d4e13b1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "import numpy as np\n",
+ "def g(df):\n",
+ " df[\"keywords_all\"] = df.filter(like='keyword').apply(lambda x: '-'.join(x.dropna()), axis=1)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['answer'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "090e98c3-78db-4e33-af4b-01c6e1fc23d0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = data[5]['question']\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "29609669-1ac7-4f6a-b0e3-64a3bf7a6545",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/Testv4-checkpoint.ipynb

@@ -0,0 +1,698 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b92bb6f7a2784be8bf5cab2ee87292ff",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3d6c5533e9ea48e295b7fdfd96da6d47",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at deepseek-ai/deepseek-coder-6.7b-instruct and are newly initialized: ['model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/ds-dsc\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 200\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n",
+ " \"B\": np.array([4, 5, 6]),\n",
+ " \"C\": np.array([7, 8, 9]),\n",
+ " }\n",
+ ")\n",
+ "</output>\n",
+ "BEGIN SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "# Your code here\n",
+ "</code>\n",
+ "</output>\n",
+ "END SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "print(df)\n",
+ "</code>\n",
+ "</output>\n",
+ "\n",
+ "<assistant>: df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n",
+ "CPU times: user 27.4 s, sys: 372 ms, total: 27.8 s\n",
+ "Wall time: 27.9 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n",
+ " \"B\": np.array([4, 5, 6]),\n",
+ " \"C\": np.array([7, 8, 9]),\n",
+ " }\n",
+ ")\n",
+ "</output>\n",
+ "BEGIN SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "# Your code here\n",
+ "</code>\n",
+ "</output>\n",
+ "END SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "print(df)\n",
+ "</code>\n",
+ "</output>\n",
+ "\n",
+ "<assistant>: df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'A': [4, 5, 6], 'B': [7, 8, 9]})\n",
+ "</output>\n",
+ "<assistant>: df = pd.concat([df1, df2])\n",
+ "</assistant>\n",
+ "<output>: df\n",
+ "</output>\n",
+ "<code>\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'A': [4, 5, 6],\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<code>\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "name=np.array(['joy','shan'])\n",
+ "roll_no=np.array([1,2])\n",
+ "</code>\n",
+ "BEGIN SOLUTION\n",
+ "<code>\n",
+ "[insert]\n",
+ "</code>\n",
+ "END SOLUTION\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "<assistant>: df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "</assistant>\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "\n",
+ "<assistant>: df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "</assistant>\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "<assistant>: df = pd.\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[ ]: import matplotlib.pyplot as plt\n",
+ "import numpy as np\n",
+ "\n",
+ "x = np.linspace(0, 10, 100)\n",
+ "y = np.sin(x)\n",
+ "\n",
+ "# your code here\n",
+ "</output>\n",
+ "<assistant>: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</assistant>\n",
+ "<output>: [ ]: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</output>\n",
+ "<assistant>: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</assistant>\n",
+ "<output>: [ ]: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</output>\n",
+ "<assistant>: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</assistant>\n",
+ "<output>\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "data = pd.DataFrame({'ID': ['01', '01', '01', '02', '02'],\n",
+ "'TIME': ['2018-07-11 11:12:20', '2018-07-12 12:00:23', '2018-07-13 12:00:00', '2019-09-11 11:00:00', '2019-09-12 12:00:00']})\n",
+ "\n",
+ "data['TIME'] = pd.to_datetime(data['TIME'])\n",
+ "\n",
+ "</output>\n",
+ "BEGIN SOLUTION\n",
+ "<output>\n",
+ "[insert]\n",
+ "</output>\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Test-mgc-Copy1.ipynb

@@ -0,0 +1,1177 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so\n",
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 121\n",
+ "CUDA SETUP: Loading binary /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so...\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib64'), PosixPath('/usr/local/nvidia/lib')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('ssh-rsa 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 shanjay@LAPTOP-Q1PG3AE7')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//g.notebooksg.jarvislabs.net'), PosixPath('https')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
+ " warn(msg)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3edf6ee054e9464eb510d3aff9d1dc5f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2be27a54d3e14399a41c46cd9c423399",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/6 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at ise-uiuc/Magicoder-S-DS-6.7B and are newly initialized: ['model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/mgc-ds\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 400\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "CPU times: user 26.5 s, sys: 177 ms, total: 26.7 s\n",
+ "Wall time: 26.7 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': ['A', 'B', 'C', 'D'],\n",
+ " 'B': [1, 2, 3, 4]})\n",
+ "df2 = pd.DataFrame({'A': ['A', 'B', 'C', 'E'],\n",
+ " 'B': [1, 2, 3, 5]})\n",
+ "# merge df1 and df2 on column 'A'\n",
+ "# SOLUTION START\n",
+ "\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': ['A', 'B', 'C', 'D'],\n",
+ " 'B': [1, 2, 3, 4]})\n",
+ "df2 = pd.DataFrame({'A': ['A', 'B', 'C', 'E'],\n",
+ " 'B': [1, 2, 3, 5]})\n",
+ "# merge df1 and df2 on column 'A'\n",
+ "result = pd.merge(df1, df2, on='A')\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "name = ['joy', 'shan']\n",
+ "roll_no = [1, 2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n",
+ "y = [1, 2, 3, 4, 5]\n",
+ "\n",
+ "# plot all types of plots in matplotlib\n",
+ "# SOLUTION START\n",
+ "\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n",
+ "y = [1, 2, 3, 4, 5]\n",
+ "\n",
+ "# plot all types of plots in matplotlib\n",
+ "plt.plot(x, y, label=\"plot\")\n",
+ "plt.scatter(x, y, label=\"scatter\")\n",
+ "plt.bar(x, y, label=\"bar\")\n",
+ "plt.hist(x, y, label=\"hist\")\n",
+ "plt.boxplot(x, y, label=\"boxplot\")\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n",
+ "y = [1, 2, 3, 4, 5]\n",
+ "\n",
+ "# plot all types of plots in matplotlib\n",
+ "plt.plot(x, y, label=\"plot\")\n",
+ "plt.scatter(x, y, label=\"scatter\")\n",
+ "plt.bar(x, y, label=\"bar\")\n",
+ "plt.hist(x, y, label=\"hist\")\n",
+ "plt.boxplot(x, y, label=\"boxplot\")\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = [1, 2, 3, 4, 5]\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'ID': ['01', '01', '01', '02', '02'],\n",
+ " 'TIME': ['2018-07-11 11:12:20', '2018-07-12 12:00:23', '2018-07-13 12:00:00', '2019-09-11 11:00:00', '2019-09-12 12:00:00']})\n",
+ "def g(df):\n",
+ " df['TIME'] = pd.to_datetime(df['TIME'])\n",
+ " df['RANK'] = df.groupby('ID')['TIME'].rank(ascending=True)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'ID': ['01', '01', '01', '02', '02'],\n",
+ " 'TIME': ['2018-07-11 11:12:20', '2018-07-12 12:00:23', '2018-07-13 12:00:00', '2019-09-11 11:00:00', '2019-09-12 12:00:00']})\n",
+ "def g(df):\n",
+ " df['TIME'] = pd.to_datetime(df['TIME'])\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "def g(df):\n",
+ " df['A'] = df['A'].replace(0, np.nan)\n",
+ " df['A'] = df['A'].fillna(method='ffill')\n",
+ " df['A'] = df['A'].fillna(method='bfill')\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n",
+ "<output>: import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "def g(df):\n",
+ " df['A'] = df['A'].replace(0, np.nan)\n",
+ " df['A'] = df['A'].fillna(method='ffill')\n",
+ " df['A'] = df['A'].fillna(method='bfill')\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n",
+ "<output>: import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Problem:\n",
+ "My sample df has four columns with NaN values. The goal is to concatenate all the keywords rows while excluding the NaN values.\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3\n",
+ "0 Hu Tao a d NaN f\n",
+ "1 Zhongli NaN e NaN NaN\n",
+ "2 Xingqiu c NaN b g\n",
+ "\n",
+ "\n",
+ "Want to accomplish the following:\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3 keywords_all\n",
+ "0 Hu Tao a d NaN f a-d-f\n",
+ "1 Zhongli NaN e NaN NaN e\n",
+ "2 Xingqiu c NaN b g c-b-g\n",
+ "\n",
+ "\n",
+ "Pseudo code:\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "df[\"keywords_all\"] = df[\"keywords_all\"].apply(lambda cols: \"-\".join(cols), axis=1)\n",
+ "\n",
+ "\n",
+ "I know I can use \"-\".join() to get the exact result, but I am unsure how to pass the column names into the function.\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['question'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "id": "1c5841e9-4331-4185-a7ad-7dd00d4e13b1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "import numpy as np\n",
+ "def g(df):\n",
+ " df[\"keywords_all\"] = df.filter(like='keyword').apply(lambda x: '-'.join(x.dropna()), axis=1)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['answer'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "id": "090e98c3-78db-4e33-af4b-01c6e1fc23d0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "def f(cols):\n",
+ " return \"-\".join(cols)\n",
+ "\n",
+ "\n",
+ "df[\"keywords_all\"] = df.apply(lambda row: f(row[cols]), axis=1)\n",
+ "\n",
+ "\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "def f(cols):\n",
+ " return \"-\".join(cols)\n",
+ "\n",
+ "\n",
+ "df[\"keywords_all\"] = df.apply(lambda\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = data[5]['question']\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "id": "29609669-1ac7-4f6a-b0e3-64a3bf7a6545",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None, 4, 5],\n",
+ " 'B': [None, 2, 3, 4, 5],\n",
+ " 'C': [1, 2, 3, 4, 5]})\n",
+ "df = df.dropna()\n",
+ "print(df)\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, None,\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to remove null valued rows?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 39,
+ "id": "5ca085f6-30fc-4e50-a436-673f3baa75af",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import sklearn\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "\n",
+ "X, y = load_data()\n",
+ "\n",
+ "# Split the data into training and test sets\n",
+ "# Split the data into training and test sets\n",
+ "# Split the data into training and test sets\n",
+ "# Train a Logistic Regression model on the training data\n",
+ "# Print the accuracy of the model on the test data\n",
+ "# SOLUTION START\n",
+ "\n",
+ "<output>: import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import sklearn\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "\n",
+ "X, y = load_data()\n",
+ "\n",
+ "# Split the data into training and test sets\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
+ "# Train a Logistic Regression model on the training data\n",
+ "model = LogisticRegression()\n",
+ "model.fit(X_train, y_train)\n",
+ "# Print the accuracy of the model on the test data\n",
+ "print(model.score(X_test, y_test))\n",
+ "<output>: import numpy as np\n",
+ "import pandas as pd\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import sklearn\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.model_selection import train_test_split\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to train a Logistic Regression model?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "146527ff-5d37-42c7-b06b-45c1aa224d17",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "84f671f3-7bd6-4a7c-81e9-758052b424cf",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Test.ipynb

@@ -0,0 +1,725 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b92bb6f7a2784be8bf5cab2ee87292ff",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3d6c5533e9ea48e295b7fdfd96da6d47",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at deepseek-ai/deepseek-coder-6.7b-instruct and are newly initialized: ['model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/ds-dsc\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 200\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n",
+ " \"B\": np.array([4, 5, 6]),\n",
+ " \"C\": np.array([7, 8, 9]),\n",
+ " }\n",
+ ")\n",
+ "</output>\n",
+ "BEGIN SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "# Your code here\n",
+ "</code>\n",
+ "</output>\n",
+ "END SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "print(df)\n",
+ "</code>\n",
+ "</output>\n",
+ "\n",
+ "<assistant>: df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n",
+ "CPU times: user 27.4 s, sys: 372 ms, total: 27.8 s\n",
+ "Wall time: 27.9 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n",
+ " \"B\": np.array([4, 5, 6]),\n",
+ " \"C\": np.array([7, 8, 9]),\n",
+ " }\n",
+ ")\n",
+ "</output>\n",
+ "BEGIN SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "# Your code here\n",
+ "</code>\n",
+ "</output>\n",
+ "END SOLUTION\n",
+ "<output>\n",
+ "[1]\n",
+ "<code>\n",
+ "[python]\n",
+ "print(df)\n",
+ "</code>\n",
+ "</output>\n",
+ "\n",
+ "<assistant>: df = pd.DataFrame(\n",
+ " {\n",
+ " \"A\": np.array([1, 2, 3]),\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'A': [4, 5, 6], 'B': [7, 8, 9]})\n",
+ "</output>\n",
+ "<assistant>: df = pd.concat([df1, df2])\n",
+ "</assistant>\n",
+ "<output>: df\n",
+ "</output>\n",
+ "<code>\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'A': [4, 5, 6],\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<code>\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "name=np.array(['joy','shan'])\n",
+ "roll_no=np.array([1,2])\n",
+ "</code>\n",
+ "BEGIN SOLUTION\n",
+ "<code>\n",
+ "[insert]\n",
+ "</code>\n",
+ "END SOLUTION\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "<assistant>: df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "</assistant>\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "\n",
+ "<assistant>: df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "</assistant>\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "<assistant>: df = pd.\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "[ ]: import matplotlib.pyplot as plt\n",
+ "import numpy as np\n",
+ "\n",
+ "x = np.linspace(0, 10, 100)\n",
+ "y = np.sin(x)\n",
+ "\n",
+ "# your code here\n",
+ "</output>\n",
+ "<assistant>: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</assistant>\n",
+ "<output>: [ ]: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</output>\n",
+ "<assistant>: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</assistant>\n",
+ "<output>: [ ]: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</output>\n",
+ "<assistant>: plt.plot(x, y)\n",
+ "plt.show()\n",
+ "</assistant>\n",
+ "<output>\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "data = pd.DataFrame({'ID': ['01', '01', '01', '02', '02'],\n",
+ "'TIME': ['2018-07-11 11:12:20', '2018-07-12 12:00:23', '2018-07-13 12:00:00', '2019-09-11 11:00:00', '2019-09-12 12:00:00']})\n",
+ "\n",
+ "data['TIME'] = pd.to_datetime(data['TIME'])\n",
+ "\n",
+ "</output>\n",
+ "BEGIN SOLUTION\n",
+ "<output>\n",
+ "[insert]\n",
+ "</output>\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<code>\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "</code>\n",
+ "BEGIN SOLUTION\n",
+ "<code>\n",
+ "[insert]\n",
+ "</code>\n",
+ "END SOLUTION\n",
+ "<code>\n",
+ "print(df)\n",
+ "</code>\n",
+ "\n",
+ "<assistant>: df['A'] = df['A'].replace(0, np.nan)\n",
+ "df['A'] = df['A'].fillna(method='ffill')\n",
+ "df['A'] = df['A'].fillna(method='bfill')\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Testv3.ipynb

@@ -0,0 +1,831 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so\n",
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 121\n",
+ "CUDA SETUP: Loading binary /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so...\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib'), PosixPath('/usr/local/nvidia/lib64')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('ssh-rsa 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 shanjay@LAPTOP-Q1PG3AE7')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('https'), PosixPath('//g.notebooksg.jarvislabs.net')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
+ " warn(msg)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2316598db91e443f8c4e1cc615a9507f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7e1406ca2f5f4c0dbf0a581edebc9a6b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at deepseek-ai/deepseek-coder-6.7b-instruct and are newly initialized: ['model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2b9911223be04aeabbc44875a5929afa",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "adapter_model.bin: 0%| | 0.00/33.6M [00:00<?, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/ds-dsc-v4\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 200\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n",
+ "CPU times: user 26.8 s, sys: 346 ms, total: 27.1 s\n",
+ "Wall time: 27.2 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'C': [7, 8, 9], 'D': [10, 11, 12]})\n",
+ "\n",
+ "# merge df1 and df2\n",
+ "result = ...\n",
+ "\n",
+ "print(result)\n",
+ "\n",
+ "# Expected output\n",
+ "# A B C D\n",
+ "# 0 1 4 7 10\n",
+ "# 1 2 5 8 11\n",
+ "# 2 3 6 9 12\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "plt.legend()\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "pl\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Problem:\n",
+ "My sample df has four columns with NaN values. The goal is to concatenate all the keywords rows while excluding the NaN values.\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3\n",
+ "0 Hu Tao a d NaN f\n",
+ "1 Zhongli NaN e NaN NaN\n",
+ "2 Xingqiu c NaN b g\n",
+ "\n",
+ "\n",
+ "Want to accomplish the following:\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3 keywords_all\n",
+ "0 Hu Tao a d NaN f a-d-f\n",
+ "1 Zhongli NaN e NaN NaN e\n",
+ "2 Xingqiu c NaN b g c-b-g\n",
+ "\n",
+ "\n",
+ "Pseudo code:\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "df[\"keywords_all\"] = df[\"keywords_all\"].apply(lambda cols: \"-\".join(cols), axis=1)\n",
+ "\n",
+ "\n",
+ "I know I can use \"-\".join() to get the exact result, but I am unsure how to pass the column names into the function.\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['question'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "1c5841e9-4331-4185-a7ad-7dd00d4e13b1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "import numpy as np\n",
+ "def g(df):\n",
+ " df[\"keywords_all\"] = df.filter(like='keyword').apply(lambda x: '-'.join(x.dropna()), axis=1)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['answer'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "090e98c3-78db-4e33-af4b-01c6e1fc23d0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = data[5]['question']\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "29609669-1ac7-4f6a-b0e3-64a3bf7a6545",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Testv4.ipynb

@@ -0,0 +1,866 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "addd199c-097c-419d-a0f2-c3d73efb8d5d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so\n",
+ "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+ "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 121\n",
+ "CUDA SETUP: Loading binary /opt/conda/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda121.so...\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib'), PosixPath('/usr/local/nvidia/lib64')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('ssh-rsa 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 shanjay@LAPTOP-Q1PG3AE7')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('https'), PosixPath('//g.notebooksg.jarvislabs.net')}\n",
+ " warn(msg)\n",
+ "/opt/conda/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//matplotlib_inline.backend_inline')}\n",
+ " warn(msg)\n"
+ ]
+ }
+ ],
+ "source": [
+ "import json\n",
+ "import os\n",
+ "from pprint import pprint\n",
+ "\n",
+ "import bitsandbytes as bnb\n",
+ "import pandas as pd\n",
+ "import torch\n",
+ "import torch.nn as nn\n",
+ "\n",
+ "import transformers\n",
+ "from datasets import load_dataset\n",
+ "from huggingface_hub import notebook_login\n",
+ "from peft import (\n",
+ " LoraConfig,\n",
+ " PeftConfig,\n",
+ " PeftModel,\n",
+ " get_peft_model,\n",
+ " prepare_model_for_kbit_training,\n",
+ ")\n",
+ "from transformers import (\n",
+ " AutoConfig,\n",
+ " AutoModelForCausalLM,\n",
+ " AutoTokenizer,\n",
+ " BitsAndBytesConfig,\n",
+ ")\n",
+ "import warnings\n",
+ "warnings.filterwarnings(\"ignore\")\n",
+ "\n",
+ "os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "acfb1578-a66f-44f0-8df9-1c6bcf7530ea",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2316598db91e443f8c4e1cc615a9507f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d2f13cac-1536-4da0-8ff7-0a0454fd0b4a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\") as json_file:\n",
+ " data = json.load(json_file)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "6706e68b-d525-4392-ab2c-1dff356da52d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'answer': 'import pandas as pd\\n'\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " 'def g(df):\\n'\n",
+ " \" l = df['A'].replace(to_replace=0, method='ffill')\\n\"\n",
+ " \" r = df['A'].replace(to_replace=0, method='bfill')\\n\"\n",
+ " ' for i in range(len(df)):\\n'\n",
+ " \" df['A'].iloc[i] = max(l[i], r[i])\\n\"\n",
+ " ' return df\\n'\n",
+ " '\\n'\n",
+ " 'df = g(df.copy())\\n'\n",
+ " 'result = df\\n'\n",
+ " 'print(result)',\n",
+ " 'question': 'Problem:\\n'\n",
+ " 'I have the following dataframe:\\n'\n",
+ " 'index = range(14)\\n'\n",
+ " 'data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\\n'\n",
+ " \"df = pd.DataFrame(data=data, index=index, columns = ['A'])\\n\"\n",
+ " '\\n'\n",
+ " '\\n'\n",
+ " 'How can I fill the zeros with the maximun between previous and '\n",
+ " 'posterior non-zero value using pandas? Is there a fillna that is '\n",
+ " 'not just for \"NaN\"?. \\n'\n",
+ " 'The output should look like:\\n'\n",
+ " ' A\\n'\n",
+ " '0 1\\n'\n",
+ " '1 2\\n'\n",
+ " '2 2\\n'\n",
+ " '3 2\\n'\n",
+ " '4 4\\n'\n",
+ " '5 4\\n'\n",
+ " '6 6\\n'\n",
+ " '7 8\\n'\n",
+ " '8 8\\n'\n",
+ " '9 8\\n'\n",
+ " '10 8\\n'\n",
+ " '11 8\\n'\n",
+ " '12 2\\n'\n",
+ " '13 1'}\n"
+ ]
+ }
+ ],
+ "source": [
+ "pprint(data[0])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "9cc4983a-9a3f-485f-983f-efe2f10ce516",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "with open(\"ds1000-test-cleaned.json\", \"w\") as f:\n",
+ " json.dump(data, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "f45c3674-4eed-4ca5-8343-2184ff1e4da1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>question</th>\n",
+ " <th>answer</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>Problem:\\nI have the following dataframe:\\nind...</td>\n",
+ " <td>import pandas as pd\\n\\n\\nindex = range(14)\\nda...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>Problem:\\ni got an issue over ranking of date ...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>Problem:\\nI have a DataFrame like :\\n 0 ...</td>\n",
+ " <td>import pandas as pd\\nimport numpy as np\\n\\ndf ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>Problem:\\nI have this Pandas dataframe (df):\\n...</td>\n",
+ " <td>import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic...</td>\n",
+ " <td>import pandas as pd\\n\\ndf = pd.DataFrame.from_...</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " question \\\n",
+ "0 Problem:\\nI have the following dataframe:\\nind... \n",
+ "1 Problem:\\ni got an issue over ranking of date ... \n",
+ "2 Problem:\\nI have a DataFrame like :\\n 0 ... \n",
+ "3 Problem:\\nI have this Pandas dataframe (df):\\n... \n",
+ "4 Problem:\\nI have\\n\\ndf = pd.DataFrame.from_dic... \n",
+ "\n",
+ " answer \n",
+ "0 import pandas as pd\\n\\n\\nindex = range(14)\\nda... \n",
+ "1 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'I... \n",
+ "2 import pandas as pd\\nimport numpy as np\\n\\ndf ... \n",
+ "3 import pandas as pd\\n\\n\\ndf = pd.DataFrame({'A... \n",
+ "4 import pandas as pd\\n\\ndf = pd.DataFrame.from_... "
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.DataFrame(data).head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "6fbdd3ad-062f-4744-bb8e-1c19950adfd5",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "bnb_config = BitsAndBytesConfig(\n",
+ " load_in_4bit=True,\n",
+ " bnb_4bit_use_double_quant=True,\n",
+ " bnb_4bit_quant_type=\"nf4\",\n",
+ " bnb_4bit_compute_dtype=torch.bfloat16,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "2b5ae38c-b0d2-4b9a-acde-3370130ca6e7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7e1406ca2f5f4c0dbf0a581edebc9a6b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at deepseek-ai/deepseek-coder-6.7b-instruct and are newly initialized: ['model.layers.17.self_attn.rotary_emb.inv_freq', 'model.layers.4.self_attn.rotary_emb.inv_freq', 'model.layers.12.self_attn.rotary_emb.inv_freq', 'model.layers.29.self_attn.rotary_emb.inv_freq', 'model.layers.20.self_attn.rotary_emb.inv_freq', 'model.layers.15.self_attn.rotary_emb.inv_freq', 'model.layers.21.self_attn.rotary_emb.inv_freq', 'model.layers.19.self_attn.rotary_emb.inv_freq', 'model.layers.23.self_attn.rotary_emb.inv_freq', 'model.layers.30.self_attn.rotary_emb.inv_freq', 'model.layers.3.self_attn.rotary_emb.inv_freq', 'model.layers.18.self_attn.rotary_emb.inv_freq', 'model.layers.6.self_attn.rotary_emb.inv_freq', 'model.layers.1.self_attn.rotary_emb.inv_freq', 'model.layers.31.self_attn.rotary_emb.inv_freq', 'model.layers.28.self_attn.rotary_emb.inv_freq', 'model.layers.14.self_attn.rotary_emb.inv_freq', 'model.layers.0.self_attn.rotary_emb.inv_freq', 'model.layers.22.self_attn.rotary_emb.inv_freq', 'model.layers.11.self_attn.rotary_emb.inv_freq', 'model.layers.7.self_attn.rotary_emb.inv_freq', 'model.layers.5.self_attn.rotary_emb.inv_freq', 'model.layers.9.self_attn.rotary_emb.inv_freq', 'model.layers.27.self_attn.rotary_emb.inv_freq', 'model.layers.24.self_attn.rotary_emb.inv_freq', 'model.layers.13.self_attn.rotary_emb.inv_freq', 'model.layers.16.self_attn.rotary_emb.inv_freq', 'model.layers.26.self_attn.rotary_emb.inv_freq', 'model.layers.25.self_attn.rotary_emb.inv_freq', 'model.layers.8.self_attn.rotary_emb.inv_freq', 'model.layers.2.self_attn.rotary_emb.inv_freq', 'model.layers.10.self_attn.rotary_emb.inv_freq']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2b9911223be04aeabbc44875a5929afa",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "adapter_model.bin: 0%| | 0.00/33.6M [00:00<?, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "PEFT_MODEL = \"shanjay/ds-dsc-v4\"\n",
+ "\n",
+ "config = PeftConfig.from_pretrained(PEFT_MODEL)\n",
+ "model = AutoModelForCausalLM.from_pretrained(\n",
+ " config.base_model_name_or_path,\n",
+ " return_dict=True,\n",
+ " quantization_config=bnb_config,\n",
+ " device_map=\"auto\",\n",
+ " trust_remote_code=True,\n",
+ ")\n",
+ "tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
+ "tokenizer.pad_token = tokenizer.eos_token\n",
+ "\n",
+ "model = PeftModel.from_pretrained(model, PEFT_MODEL)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "7c3e35e0-f77c-4d63-8e2b-e72027341e31",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "generation_config = model.generation_config\n",
+ "generation_config.max_new_tokens = 200\n",
+ "generation_config.temperature = 0.7\n",
+ "generation_config.top_p = 0.7\n",
+ "generation_config.num_return_sequences = 1\n",
+ "generation_config.pad_token_id = tokenizer.eos_token_id\n",
+ "generation_config.eos_token_id = tokenizer.eos_token_id"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "aee4385b-d855-4225-9532-4e9002322579",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "DEVICE = \"cuda:0\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "7b14a1c6-ac62-4a9c-9df9-0db50facfd7e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n",
+ "CPU times: user 26.8 s, sys: 346 ms, total: 27.1 s\n",
+ "Wall time: 27.2 s\n"
+ ]
+ }
+ ],
+ "source": [
+ "%%time\n",
+ "prompt = f\"\"\"\n",
+ "<instruction>: How can I create a dataframe?\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ "\n",
+ "encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ "with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "93c95988-c563-4871-974d-004bf73fbce8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def generate_response(question: str) -> str:\n",
+ " prompt = f\"\"\"\n",
+ "<instruction>: {question}\n",
+ "<output>:\n",
+ "\"\"\".strip()\n",
+ " encoding = tokenizer(prompt, return_tensors=\"pt\").to(DEVICE)\n",
+ " with torch.inference_mode():\n",
+ " outputs = model.generate(\n",
+ " input_ids=encoding.input_ids,\n",
+ " attention_mask=encoding.attention_mask,\n",
+ " generation_config=generation_config,\n",
+ " )\n",
+ " response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+ "\n",
+ " assistant_start = \"<output>:\"\n",
+ " response_start = response.find(assistant_start)\n",
+ " return response[response_start + len(assistant_start) :].strip()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "8a9a9b87-193b-4bed-8ef1-57944d931958",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A B\n",
+ "0 1 4\n",
+ "1 2 5\n",
+ "2 3 6\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "print(df)\n",
+ " A\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How can I create a dataframe?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "4658f305-b7c6-432c-ac0c-f62bd79e9ad5",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})\n",
+ "df2 = pd.DataFrame({'C': [7, 8, 9], 'D': [10, 11, 12]})\n",
+ "\n",
+ "# merge df1 and df2\n",
+ "result = ...\n",
+ "\n",
+ "print(result)\n",
+ "\n",
+ "# Expected output\n",
+ "# A B C D\n",
+ "# 0 1 4 7 10\n",
+ "# 1 2 5 8 11\n",
+ "# 2 3 6 9 12\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "df1 = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to merge two dataframes?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "0e9ed231-4a62-4331-94df-f3bcd601f138",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({'name': name, 'roll_no': roll_no})\n",
+ "print(df)\n",
+ "\n",
+ "\n",
+ " name roll_no\n",
+ "0 joy 1\n",
+ "1 shan 2\n",
+ "<output>: import pandas as pd\n",
+ "\n",
+ "\n",
+ "name=['joy','shan']\n",
+ "roll_no=[1,2]\n",
+ "df = pd.DataFrame({\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"given two arrays name=['joy','shan'], roll_no=[1,2]. put these array in a dataframe ?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "381ba5c0-276d-411e-a8d5-9f010528433d",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "plt.legend()\n",
+ "plt.show()\n",
+ "<output>: import matplotlib.pyplot as plt\n",
+ "\n",
+ "x = range(10)\n",
+ "y = range(10)\n",
+ "\n",
+ "plt.plot(x, y, label='line')\n",
+ "plt.scatter(x, y, label='scatter')\n",
+ "plt.bar(x, y, label='bar')\n",
+ "plt.hist(x, y, label='hist')\n",
+ "pl\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"can you plot all types of plots in matplotlib?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "6864c3c7-b721-48ca-8943-dcff9838f7d2",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "i got an issue over ranking of date times. Lets say i have following table.\n",
+ "ID TIME\n",
+ "01 2018-07-11 11:12:20\n",
+ "01 2018-07-12 12:00:23\n",
+ "01 2018-07-13 12:00:00\n",
+ "02 2019-09-11 11:00:00\n",
+ "02 2019-09-12 12:00:00\n",
+ "\n",
+ "\n",
+ "and i want to add another column to rank the table by time for each id and group. I used \n",
+ "df['RANK'] = data.groupby('ID')['TIME'].rank(ascending=True)\n",
+ "\n",
+ "\n",
+ "but get an error:\n",
+ "'NoneType' object is not callable\n",
+ "\n",
+ "\n",
+ "If i replace datetime to numbers, it works.... any solutions?\n",
+ "\"\"\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "7fa02929-5c65-4aa6-81ce-9c51879e7535",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"\"\"Problem:\n",
+ "I have the following dataframe:\n",
+ "index = range(14)\n",
+ "data = [1, 0, 0, 2, 0, 4, 6, 8, 0, 0, 0, 0, 2, 1]\n",
+ "df = pd.DataFrame(data=data, index=index, columns = ['A'])\n",
+ "\n",
+ "\n",
+ "How can I fill the zeros with the maximun between previous and posterior non-zero value using pandas? Is there a fillna that is not just for \"NaN\"?. \n",
+ "The output should look like:\n",
+ " A\n",
+ "0 1\n",
+ "1 2\n",
+ "2 2\n",
+ "3 2\n",
+ "4 4\n",
+ "5 4\n",
+ "6 6\n",
+ "7 8\n",
+ "8 8\n",
+ "9 8\n",
+ "10 8\n",
+ "11 8\n",
+ "12 2\n",
+ "13 1\n",
+ "\"\"\"\n",
+ "\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "id": "255cc021-5f5e-46af-a75e-a435b9629cdf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Problem:\n",
+ "My sample df has four columns with NaN values. The goal is to concatenate all the keywords rows while excluding the NaN values.\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "\n",
+ "\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3\n",
+ "0 Hu Tao a d NaN f\n",
+ "1 Zhongli NaN e NaN NaN\n",
+ "2 Xingqiu c NaN b g\n",
+ "\n",
+ "\n",
+ "Want to accomplish the following:\n",
+ " users keywords_0 keywords_1 keywords_2 keywords_3 keywords_all\n",
+ "0 Hu Tao a d NaN f a-d-f\n",
+ "1 Zhongli NaN e NaN NaN e\n",
+ "2 Xingqiu c NaN b g c-b-g\n",
+ "\n",
+ "\n",
+ "Pseudo code:\n",
+ "cols = [df.keywords_0, df.keywords_1, df.keywords_2, df.keywords_3]\n",
+ "df[\"keywords_all\"] = df[\"keywords_all\"].apply(lambda cols: \"-\".join(cols), axis=1)\n",
+ "\n",
+ "\n",
+ "I know I can use \"-\".join() to get the exact result, but I am unsure how to pass the column names into the function.\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['question'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "1c5841e9-4331-4185-a7ad-7dd00d4e13b1",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'users': ['Hu Tao', 'Zhongli', 'Xingqiu'],\n",
+ " 'keywords_0': [\"a\", np.nan, \"c\"],\n",
+ " 'keywords_1': [\"d\", \"e\", np.nan],\n",
+ " 'keywords_2': [np.nan, np.nan, \"b\"],\n",
+ " 'keywords_3': [\"f\", np.nan, \"g\"]})\n",
+ "import numpy as np\n",
+ "def g(df):\n",
+ " df[\"keywords_all\"] = df.filter(like='keyword').apply(lambda x: '-'.join(x.dropna()), axis=1)\n",
+ " return df\n",
+ "\n",
+ "df = g(df.copy())\n",
+ "result = df\n",
+ "print(result)\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(data[5]['answer'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "id": "090e98c3-78db-4e33-af4b-01c6e1fc23d0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = data[5]['question']\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "id": "29609669-1ac7-4f6a-b0e3-64a3bf7a6545",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "import pandas as pd\n",
+ "\n",
+ "\n",
+ "df = pd.DataFrame({'A': [1, 2, 3, None, 5],\n",
+ " 'B': [1, 2, 3, None, 5],\n",
+ " 'C': [1, 2, 3, None, 5],\n",
+ " 'D': [1, 2, 3, None, 5],\n",
+ " 'E': [1, 2, 3, None, 5]})\n",
+ "\n",
+ "df = df.dropna(how='all')\n",
+ "print(df)\n",
+ "<output>: A B C D E\n",
+ "0 1 1 1 1 1\n",
+ "1 2 2 2 2 2\n",
+ "2 3 3 3 3 3\n",
+ "4 5 5 5 5 5\n",
+ "<output>: import pand\n"
+ ]
+ }
+ ],
+ "source": [
+ "prompt = \"How to remove null valued rows?\"\n",
+ "print(generate_response(prompt))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "5ca085f6-30fc-4e50-a436-673f3baa75af",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.13"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

experiments/runs/Dec11_06-38-12_114d9a2e28a3/1702276693.5141723/events.out.tfevents.1702276693.114d9a2e28a3.6724.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25e1807afb8c8257bbc7fff824e498df2917d3fbdfabce9311e29dbfd64ee4c
+size 5900

experiments/runs/Dec11_06-38-12_114d9a2e28a3/events.out.tfevents.1702276693.114d9a2e28a3.6724.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef523b5bf07e40277c221485f9b694b435700bf700f4ca2b72b91f038ac6441
+size 4470

experiments/runs/Dec11_06-44-21_114d9a2e28a3/1702277061.7964196/events.out.tfevents.1702277061.114d9a2e28a3.9175.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5cd2abb0dfdfd8ae2ef03e0800fb3b0cab4628d98832ac59083f3cca2cdaab
+size 5900

experiments/runs/Dec11_06-44-21_114d9a2e28a3/events.out.tfevents.1702277061.114d9a2e28a3.9175.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b100927e05f3d0ef5550a60df85903496fa0bebf24ec51116d6dea4ccc9b78b
+size 6625

experiments/runs/Dec11_06-47-03_114d9a2e28a3/1702277223.9722266/events.out.tfevents.1702277223.114d9a2e28a3.10257.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d68e699976be729ef5e3439a979beeb843b9ca534f2669b7e7b10e84bdc8fe
+size 5900

experiments/runs/Dec11_06-47-03_114d9a2e28a3/events.out.tfevents.1702277223.114d9a2e28a3.10257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d63259dbe437e29c5dce266f395061f0037d1046552b861267b8208fb6bf426
+size 74778

trained-model/adapter_config.json

@@ -0,0 +1,20 @@
+{
+ "base_model_name_or_path": "ise-uiuc/Magicoder-S-DS-6.7B",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 32,
+ "lora_dropout": 0.05,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "revision": null,
+ "target_modules": [
+ "q_proj",
+ "v_proj"
+ ],
+ "task_type": "CAUSAL_LM"
+}

trained-model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c57b8002f6685aa7fcf0ea30c8cf2d1c37454e7dede5b034baf2ebd984c72a
+size 33600906