Upload folder using huggingface_hub
Browse files- app/dataclean_hf.py +1 -0
- hf-space-upload.ipynb +10 -2
app/dataclean_hf.py
CHANGED
@@ -114,6 +114,7 @@ def get_key(df):
|
|
114 |
return df['input__product_name'] + df['input__brand'] + df['input__product_category']
|
115 |
|
116 |
def main(upload_df: pd.DataFrame,
|
|
|
117 |
chunksize: int = 30,
|
118 |
):
|
119 |
category_taxonomy = {
|
|
|
114 |
return df['input__product_name'] + df['input__brand'] + df['input__product_category']
|
115 |
|
116 |
def main(upload_df: pd.DataFrame,
|
117 |
+
output_df: pd.DataFrame=None,
|
118 |
chunksize: int = 30,
|
119 |
):
|
120 |
category_taxonomy = {
|
hf-space-upload.ipynb
CHANGED
@@ -2,16 +2,24 @@
|
|
2 |
"cells": [
|
3 |
{
|
4 |
"cell_type": "code",
|
5 |
-
"execution_count":
|
6 |
"metadata": {},
|
7 |
"outputs": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
{
|
9 |
"data": {
|
10 |
"text/plain": [
|
11 |
"'https://huggingface.co/spaces/kaleidoscope-data/data-cleaning-llm/tree/main/'"
|
12 |
]
|
13 |
},
|
14 |
-
"execution_count":
|
15 |
"metadata": {},
|
16 |
"output_type": "execute_result"
|
17 |
}
|
|
|
2 |
"cells": [
|
3 |
{
|
4 |
"cell_type": "code",
|
5 |
+
"execution_count": 1,
|
6 |
"metadata": {},
|
7 |
"outputs": [
|
8 |
+
{
|
9 |
+
"name": "stderr",
|
10 |
+
"output_type": "stream",
|
11 |
+
"text": [
|
12 |
+
"/Users/christos/opt/miniconda3/envs/kd-llm-dc/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
13 |
+
" from .autonotebook import tqdm as notebook_tqdm\n"
|
14 |
+
]
|
15 |
+
},
|
16 |
{
|
17 |
"data": {
|
18 |
"text/plain": [
|
19 |
"'https://huggingface.co/spaces/kaleidoscope-data/data-cleaning-llm/tree/main/'"
|
20 |
]
|
21 |
},
|
22 |
+
"execution_count": 1,
|
23 |
"metadata": {},
|
24 |
"output_type": "execute_result"
|
25 |
}
|