|
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194 |
- {
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 66,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Import des librairies\n",
- "import pandas as pd\n",
- "import os\n",
- "\n",
- "# Repertoire des donnés\n",
- "data_path = '../../data/LAYER1/MO/MO/'"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 68,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Data saved to ../../data/LAYER1/MO/dataset.csv\n"
- ]
- },
- {
- "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>species_id</th>\n",
- " <th>imgs_files</th>\n",
- " </tr>\n",
- " </thead>\n",
- " <tbody>\n",
- " <tr>\n",
- " <th>0</th>\n",
- " <td>2749</td>\n",
- " <td>51775.jpg,48607.jpg,7283.jpg,56752.jpg,19683.j...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>1</th>\n",
- " <td>15162</td>\n",
- " <td>1340401.jpg,489065.jpg,635182.jpg,464456.jpg,5...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>2</th>\n",
- " <td>50164</td>\n",
- " <td>1483369.jpg,161806.jpg,541519.jpg,644907.jpg,8...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>3</th>\n",
- " <td>1540</td>\n",
- " <td>905357.jpg,1376931.jpg,1573947.jpg,897180.jpg,...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>4</th>\n",
- " <td>1174</td>\n",
- " <td>1565785.jpg,1196459.jpg,619643.jpg,888195.jpg,...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>5</th>\n",
- " <td>373</td>\n",
- " <td>735385.jpg,1029205.jpg,58108.jpg,400760.jpg,57...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>6</th>\n",
- " <td>362</td>\n",
- " <td>1022083.jpg,864049.jpg,1553692.jpg,727623.jpg,...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>7</th>\n",
- " <td>42</td>\n",
- " <td>377481.jpg,353396.jpg,17237.jpg,304456.jpg,280...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>8</th>\n",
- " <td>344</td>\n",
- " <td>57062.jpg,284982.jpg,497195.jpg,497192.jpg,517...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>9</th>\n",
- " <td>39842</td>\n",
- " <td>366700.jpg,56994.jpg,28073.jpg,370092.jpg,3037...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>10</th>\n",
- " <td>330</td>\n",
- " <td>262051.jpg,575138.jpg,97947.jpg,575143.jpg,554...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>11</th>\n",
- " <td>63454</td>\n",
- " <td>319811.jpg,43831.jpg,1467353.jpg,1467354.jpg,4...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>12</th>\n",
- " <td>382</td>\n",
- " <td>1368137.jpg,554254.jpg,1497568.jpg,248852.jpg,...</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th>13</th>\n",
- " <td>29997</td>\n",
- " <td>1322991.jpg,1453819.jpg,316370.jpg,609577.jpg,...</td>\n",
- " </tr>\n",
- " </tbody>\n",
- "</table>\n",
- "</div>"
- ],
- "text/plain": [
- " species_id imgs_files\n",
- "0 2749 51775.jpg,48607.jpg,7283.jpg,56752.jpg,19683.j...\n",
- "1 15162 1340401.jpg,489065.jpg,635182.jpg,464456.jpg,5...\n",
- "2 50164 1483369.jpg,161806.jpg,541519.jpg,644907.jpg,8...\n",
- "3 1540 905357.jpg,1376931.jpg,1573947.jpg,897180.jpg,...\n",
- "4 1174 1565785.jpg,1196459.jpg,619643.jpg,888195.jpg,...\n",
- "5 373 735385.jpg,1029205.jpg,58108.jpg,400760.jpg,57...\n",
- "6 362 1022083.jpg,864049.jpg,1553692.jpg,727623.jpg,...\n",
- "7 42 377481.jpg,353396.jpg,17237.jpg,304456.jpg,280...\n",
- "8 344 57062.jpg,284982.jpg,497195.jpg,497192.jpg,517...\n",
- "9 39842 366700.jpg,56994.jpg,28073.jpg,370092.jpg,3037...\n",
- "10 330 262051.jpg,575138.jpg,97947.jpg,575143.jpg,554...\n",
- "11 63454 319811.jpg,43831.jpg,1467353.jpg,1467354.jpg,4...\n",
- "12 382 1368137.jpg,554254.jpg,1497568.jpg,248852.jpg,...\n",
- "13 29997 1322991.jpg,1453819.jpg,316370.jpg,609577.jpg,..."
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
- "source": [
- "# Genere le nouveau fichier CSV qui n'incluent que les images processés avec succè\n",
- "data = []\n",
- "\n",
- "for species_folder in os.listdir(data_path):\n",
- " folder_path = os.path.join(data_path, species_folder)\n",
- " files = os.listdir(folder_path)\n",
- " data.append({'species_id': species_folder, 'imgs_files': files})\n",
- "\n",
- "df = pd.DataFrame(data)\n",
- "df['imgs_files'] = df['imgs_files'].apply(','.join) # Convertir les array en chaîne de caractères, avec les éléments séparés par des virgules.\n",
- "\n",
- "\n",
- "output_path = '../../data/LAYER1/MO/dataset.csv'\n",
- "df.to_csv(output_path, index=False)\n",
- "\n",
- "print(f'Data saved to {output_path}')\n",
- "\n",
- "display(df)"
- ]
- }
- ],
- "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": "3.11.9"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 2
- }
|
