Spaces:
Build error
Build error
File size: 13,415 Bytes
b5cf002 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/giorgosnikolaou/Library/Python/3.9/lib/python/site-packages/urllib3/__init__.py:35: NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020\n",
" warnings.warn(\n",
"[nltk_data] Downloading package words to\n",
"[nltk_data] /Users/giorgosnikolaou/nltk_data...\n",
"[nltk_data] Package words is already up-to-date!\n"
]
}
],
"source": [
"import gradio as gr\n",
"import pandas as pd\n",
"import pandas as pd\n",
"from src.utils.io_utils import PROJECT_ROOT\n",
"from run_augmenter import negative_sampler , positive_sampler\n",
"from pathlib import Path\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7860\n",
"Running on public URL: https://85b886469a8c17104c.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
]
},
{
"data": {
"text/html": [
"<div><iframe src=\"https://85b886469a8c17104c.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"random\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Negative Sampling: 100%|██████████| 100/100 [00:11<00:00, 8.43it/s]\n"
]
}
],
"source": [
"\n",
"def augment_interface(factor, type_or_difficulty, use_default, csv_file=None):\n",
" \"\"\"Negative Tool Sampler: Wrapper to handle negative dataset augmentation.\"\"\"\n",
" try:\n",
" if use_default:\n",
" input_csv_path = f\"{PROJECT_ROOT}/data/crossref-preprint-article-relationships-Aug-2023.csv\"\n",
" if not Path(input_csv_path).exists():\n",
" return \"Error: Default CSV file not found!\", None, gr.update(visible=False)\n",
" elif csv_file is not None:\n",
" input_csv_path = csv_file.name\n",
" else:\n",
" return \"Error: Please select default or upload a CSV file.\", None, gr.update(visible=False)\n",
"\n",
" augmented_df = negative_sampler(input_csv_path, factor, type_or_difficulty)\n",
" output_csv_path = \"augmented_dataset.csv\"\n",
" augmented_df.to_csv(output_csv_path, index=False)\n",
"\n",
" return output_csv_path, augmented_df.head(), gr.update(visible=True)\n",
"\n",
" except Exception as e:\n",
" return f\"Error during processing: {str(e)}\", None, gr.update(visible=False)\n",
"\n",
"\n",
"def positive_sampler_interface(use_default, csv_file=None, size=10, random=True, seed=42, full=False):\n",
" \"\"\"Positive Tool Sampler: Wrapper to handle positive dataset augmentation with additional arguments.\"\"\"\n",
" try:\n",
" if use_default:\n",
" input_csv_path = f\"{PROJECT_ROOT}/data/crossref-preprint-article-relationships-Aug-2023.csv\"\n",
" if not Path(input_csv_path).exists():\n",
" return \"Error: Default CSV file not found!\", None, gr.update(visible=False)\n",
" elif csv_file is not None:\n",
" input_csv_path = csv_file.name\n",
" else:\n",
" return \"Error: Please select default or upload a CSV file.\", None, gr.update(visible=False)\n",
"\n",
" # Call the positive sampler function with additional arguments\n",
" augmented_df = positive_sampler(\n",
" optional_path=input_csv_path, \n",
" size=size, \n",
" random=random, \n",
" seed=seed, \n",
" full=full\n",
" )\n",
" output_csv_path = \"positive_augmented_dataset.csv\"\n",
" augmented_df.to_csv(output_csv_path, index=False)\n",
"\n",
" return output_csv_path, augmented_df.head(), gr.update(visible=True)\n",
"\n",
" except Exception as e:\n",
" return f\"Error during processing: {str(e)}\", None, gr.update(visible=False)\n",
"\n",
"\n",
"def reset_output():\n",
" \"\"\"Resets the output fields by returning None and hiding the DataFrame.\"\"\"\n",
" return None, None, gr.update(visible=False)\n",
"\n",
"with gr.Blocks(css=f\"\"\"\n",
" .gradio-container {{\n",
" font-family: Arial, sans-serif;\n",
" max-width: 900px;\n",
" margin: auto;\n",
" }}\n",
" h1 {{\n",
" text-align: center;\n",
" color: white;\n",
" font-size: 60px;\n",
" margin-bottom: 0px;\n",
" }}\n",
" h2 {{\n",
" text-align: center;\n",
" color: #ff0000;\n",
" font-size: 16px;\n",
" font-weight: normal;\n",
" margin-top: 0px;\n",
" }}\n",
" .title {{\n",
" text-align: center;\n",
" font-size: 40px;\n",
" margin-top: 30px;\n",
" margin-bottom: 20px;\n",
" }}\n",
" .title .positive {{\n",
" color: #ff0000;\n",
" }}\n",
" .title .negative {{\n",
" color: #ff0000;\n",
" }}\n",
" .title .tool {{\n",
" color: white;\n",
" }}\n",
" .title .sampler {{\n",
" color: #ff0000;\n",
" }}\n",
" .description {{\n",
" text-align: center;\n",
" margin-bottom: 20px;\n",
" }}\n",
" #submit-button {{\n",
" background-color: #ff0000;\n",
" color: white;\n",
" font-size: 16px;\n",
" border: none;\n",
" border-radius: 5px;\n",
" padding: 10px 20px;\n",
" }}\n",
" #reset-button {{\n",
" background-color: #d3d3d3;\n",
" color: black;\n",
" font-size: 16px;\n",
" border: none;\n",
" border-radius: 5px;\n",
" padding: 10px 20px;\n",
" }}\n",
"\"\"\") as app:\n",
" # Main Title Section\n",
" gr.Markdown(\"\"\"\n",
" <h1>ENTC</h1>\n",
" <h2>Entrepreneurship and Technology Commercialization · EPFL</h2>\n",
" \"\"\")\n",
"\n",
" # Positive Tool Sampler Section\n",
" gr.Markdown(\"\"\"\n",
" <div class=\"title\">\n",
" <span class=\"positive\">Positive</span>\n",
" <span class=\"tool\">Tool</span>\n",
" <span class=\"sampler\">Sampler</span>\n",
" </div>\n",
" \"\"\")\n",
"\n",
" gr.Markdown(\"\"\"\n",
" <p class=\"description\">\n",
" This tool takes a list of DOIs and augments them using the OpenAlex API.\n",
" It is designed to complement the Negative Tool Sampler, enabling the creation of complete datasets.\n",
" </p>\n",
" \"\"\")\n",
"\n",
" with gr.Group():\n",
" with gr.Row():\n",
" pos_use_default_checkbox = gr.Checkbox(label=\"Use Default Dataset\", value=True)\n",
" pos_csv_file_input = gr.File(label=\"Upload CSV (optional)\", file_types=[\".csv\"], visible=False)\n",
"\n",
" with gr.Row():\n",
" size_input = gr.Number(label=\"Number of Samples\", value=10, info=\"Specify the number of samples to generate.\")\n",
" random_input = gr.Checkbox(label=\"Sample Randomly\", value=True, info=\"Whether to sample randomly.\")\n",
" seed_input = gr.Number(label=\"Random Seed\", value=42, info=\"Random seed for reproducibility.\")\n",
" full_input = gr.Checkbox(label=\"Full Dataset Mode\", value=False, info=\"Indicate whether to use the full dataset.\")\n",
"\n",
" with gr.Group():\n",
" pos_output_file = gr.File(label=\"Download Augmented Dataset\")\n",
" pos_dataset_preview = gr.DataFrame(label=\"Dataset Preview\", interactive=False, visible=False)\n",
" with gr.Row():\n",
" pos_submit_button = gr.Button(\"Submit 🚀\", elem_id=\"submit-button\")\n",
" pos_reset_button = gr.Button(\"Reset 🔄\", elem_id=\"reset-button\")\n",
"\n",
" # Button Actions\n",
" pos_submit_button.click(\n",
" positive_sampler_interface,\n",
" inputs=[pos_use_default_checkbox, pos_csv_file_input, size_input, random_input, seed_input, full_input],\n",
" outputs=[pos_output_file, pos_dataset_preview, pos_dataset_preview]\n",
" )\n",
"\n",
" pos_reset_button.click(\n",
" reset_output,\n",
" inputs=[],\n",
" outputs=[pos_output_file, pos_dataset_preview, pos_dataset_preview]\n",
" )\n",
"\n",
" # Toggle File Input\n",
" def toggle_pos_csv_input(use_default):\n",
" return gr.update(visible=not use_default)\n",
"\n",
" pos_use_default_checkbox.change(\n",
" toggle_pos_csv_input,\n",
" inputs=[pos_use_default_checkbox],\n",
" outputs=[pos_csv_file_input]\n",
" )\n",
"\n",
" # Negative Tool Sampler Section\n",
" gr.Markdown(\"\"\"\n",
" <div class=\"title\">\n",
" <span class=\"negative\">Negative</span>\n",
" <span class=\"tool\">Tool</span>\n",
" <span class=\"sampler\">Sampler</span>\n",
" </div>\n",
" \"\"\")\n",
"\n",
" gr.Markdown(\"\"\"\n",
" <p class=\"description\">\n",
" This tool generates datasets by creating negative samples from positive matches between preprints and articles.\n",
" Customize the difficulty and the augmentation factor to meet your needs.\n",
" </p>\n",
" \"\"\")\n",
"\n",
" with gr.Group():\n",
" with gr.Row():\n",
" factor_input = gr.Number(\n",
" label=\"Factor (int)\", value=1, info=\"Specify the number of negative samples per positive sample.\"\n",
" )\n",
" type_dropdown = gr.Dropdown(\n",
" [\"random\", \"similar topics\", \"overlapping authors\", \"random authors\", \"fuzzed title\"],\n",
" label=\"Select Difficulty or Augmentation Type\"\n",
" )\n",
" with gr.Row():\n",
" use_default_checkbox = gr.Checkbox(label=\"Use Default Dataset\", value=True)\n",
" csv_file_input = gr.File(label=\"Upload CSV (optional)\", file_types=[\".csv\"], visible=False)\n",
"\n",
" with gr.Group():\n",
" output_file = gr.File(label=\"Download Augmented Dataset\")\n",
" dataset_preview = gr.DataFrame(label=\"Dataset Preview\", interactive=False, visible=False)\n",
" with gr.Row():\n",
" submit_button = gr.Button(\"Submit 🚀\", elem_id=\"submit-button\")\n",
" reset_button = gr.Button(\"Reset 🔄\", elem_id=\"reset-button\")\n",
"\n",
" # Button Actions\n",
" submit_button.click(\n",
" augment_interface,\n",
" inputs=[factor_input, type_dropdown, use_default_checkbox, csv_file_input],\n",
" outputs=[output_file, dataset_preview, dataset_preview]\n",
" )\n",
"\n",
" reset_button.click(\n",
" reset_output,\n",
" inputs=[],\n",
" outputs=[output_file, dataset_preview, dataset_preview]\n",
" )\n",
"\n",
" # Toggle File Input\n",
" def toggle_csv_input(use_default):\n",
" return gr.update(visible=not use_default)\n",
"\n",
" use_default_checkbox.change(\n",
" toggle_csv_input,\n",
" inputs=[use_default_checkbox],\n",
" outputs=[csv_file_input]\n",
" )\n",
"\n",
"# Launch the app\n",
"if __name__ == \"__main__\":\n",
" app.launch(share=True)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "marple",
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|