2024-06-26

PRODUCTION/2024_JADT/2024-06-25/Pour_Mathilde.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "06d1d892-453c-475a-9b26-6e552a80427e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fragment : 358\n",
+      "Words : 20973\n",
+      "Characters : 122282\n",
+      "Average words per fragment : 58.58379888268156\n",
+      "Average character per word (including punctuation) : 5.830448672102227\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "path = r\"C:\\Users\\audin\\gitlab\\anthalgo\\PRODUCTION\\2024_JADT\\2024-06-25\\corpus_fra.csv\"\n",
+    "df = pd.read_csv(path)\n",
+    "characters = 0\n",
+    "words = 0\n",
+    "fragments = 0\n",
+    "for index, row in df.iterrows():\n",
+    "    if row[\"book\"] == 6:\n",
+    "        fragments = fragments + 1\n",
+    "        words = words + len(row[\"text\"].split())\n",
+    "        characters = characters + len(row[\"text\"])\n",
+    "\n",
+    "print(\"Fragment : \" + str(fragments))\n",
+    "print(\"Words : \" + str(words))\n",
+    "print(\"Characters : \" + str(characters))\n",
+    "print(\"Average words per fragment : \" + str(words/fragments))\n",
+    "print(\"Average character per word (including punctuation) : \" + str(characters/words))"
+   ]
+  }
+ ],
+ "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": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

PRODUCTION/2024_JADT/2024-06-25/Pour_Mathilde.md

+```python
+import pandas as pd
+path = r"C:\Users\audin\gitlab\anthalgo\PRODUCTION\2024_JADT\2024-06-25\corpus_fra.csv"
+df = pd.read_csv(path)
+characters = 0
+words = 0
+fragments = 0
+for index, row in df.iterrows():
+    if row["book"] == 6:
+        fragments = fragments + 1
+        words = words + len(row["text"].split())
+        characters = characters + len(row["text"])
+
+print("Fragment : " + str(fragments))
+print("Words : " + str(words))
+print("Characters : " + str(characters))
+print("Average words per fragment : " + str(words/fragments))
+print("Average character per word (including punctuation) : " + str(characters/words))
+```
+
+    Fragment : 358
+    Words : 20973
+    Characters : 122282
+    Average words per fragment : 58.58379888268156
+    Average character per word (including punctuation) : 5.830448672102227
+