{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "a64f4c1c",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import os\n",
"import sys\n",
"from pathlib import Path\n",
"\n",
"workding_dir = str(Path.cwd().parent)\n",
"os.chdir(workding_dir)\n",
"sys.path.append(workding_dir)\n",
"print(\"workding dir:\", workding_dir)\n",
"\n",
"from dotenv import find_dotenv, load_dotenv\n",
"\n",
"found_dotenv = find_dotenv(\".env\")\n",
"\n",
"if len(found_dotenv) == 0:\n",
" found_dotenv = find_dotenv(\".env.example\")\n",
"print(f\"loading env vars from: {found_dotenv}\")\n",
"load_dotenv(found_dotenv, override=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "52701550-0bda-4fa4-959f-2b42eb42e140",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8cb2dd41-79e1-45bf-a0eb-ff9abc0baa8b",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"df = pd.read_csv(\"cleaned_data_with_categories.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c4e79890-de47-4774-9445-142cff46cf86",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "df3cdbd0-a8b4-4b6e-b5bf-5fdbb7ce93a3",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"df_sorted = df.groupby(\"Category\").count().sort_values(by='id', ascending = False)\n",
"df_sorted"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d3ddee2c-946c-4ee5-b0ba-31ac6d201261",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"# Function to determine the value for the new column\n",
"def categorize(value):\n",
" if '/' in str(value) or ',' in str(value):\n",
" return 'Miscellaneous Events'\n",
" else:\n",
" return value"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b470266e-00c1-4d4c-8738-28b4fde2dcc6",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"df['GPT Generated Result'] = df['Category'].apply(categorize)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4d5d7300-a663-4394-979e-cf7c5d4f88d5",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"df_sorted1 = df.groupby(\"GPT Generated Result\").count().sort_values(by='id', ascending = False)\n",
"df_sorted1"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6dbe0ac2-4ac6-4d75-9fa7-c856b9370269",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"df.to_csv('result.csv')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5dfe7870-c29c-4942-8301-f5e8b1bd9994",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "dc6007d3-c6bd-4bc3-8ccc-099440354ce8",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"eva = pd.read_csv('evaluation_result.csv')\n",
"eva"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a98d47b7-7ab1-4947-a10a-a36fa303dcc1",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"eva['Result_GPT_True_Count'] = eva['Result_GPT'].astype(int) # Convert boolean values to integers\n",
"result = eva.groupby(\"GPT Generated Result\")['Result_GPT_True_Count'].sum()\n",
"\n",
"result_gpt = result.sort_values(ascending=False)\n",
"result_gpt"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ec0defea-c4ad-4f97-9704-23ef83f73ff7",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"test = eva.groupby(\"Category_GoldenResult\").count().sort_values(by='id', ascending = False)\n",
"test"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6bc57f6b-c554-4634-8a98-45d82546d6f8",
"metadata": {},
"outputs": [
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mFailed to start the Kernel. \n",
"\u001b[1;31mUnable to start Kernel 'maritime (Python 3.12.4)' due to a timeout waiting for the ports to get used. \n",
"\u001b[1;31mView Jupyter log for further details."
]
}
],
"source": [
"eva['Result_Golden_True_Count'] = eva['Result_Golden'].astype(int) # Convert boolean values to integers\n",
"result = eva.groupby(\"Category_GoldenResult\")['Result_Golden_True_Count'].sum()\n",
"\n",
"# If you want to sort the result by the count in descending order:\n",
"result_golden = result.sort_values(ascending=False)\n",
"\n",
"result_golden"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}