historique messages cumulés

recap.ipynb

@@ -2,13 +2,15 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
     "import numpy as np\n",
     "import json\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.linear_model import LinearRegression \n",
     "\n",
     "pd.options.display.max_columns = 2000\n",
     "pd.options.display.max_rows = 2000\n",
@@ -34,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -46,7 +48,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -58,24 +60,67 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "text    220\n",
-       "Name: 1337, dtype: int64"
-      ]
-     },
-     "execution_count": 34,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "words_freq.loc['1337']"
    ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Messages cumulés sur la durée par membre."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "hist_data = data[['date','from', 'type']]\n",
+    "hist_data['date'] =  pd.to_datetime(hist_data['date'], yearfirst=True).dt.date"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(data['from'].unique())\n",
+    "btz_core = ['Nathan Spaeter', 'Luyzon', 'Clément Krebs', 't o', 'Leous', 'Arnaud']\n",
+    "btz_ext = [*btz_core, *['Senkei', 'Éléonore', 'Tozpa', 'Léo', 'XxX_MatthieuXPlume_XxX', 'poline', 'Sarah Guillemant']]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "list_scores = {}\n",
+    "for name in btz_core:\n",
+    "    idx = hist_data['from']==name\n",
+    "    time_range = pd.to_datetime(hist_data[idx]['date'], yearfirst=True).dt.date\n",
+    "    cumulative_count = np.arange(time_range.shape[0])\n",
+    "    plt.plot(time_range, cumulative_count, label=name)\n",
+    "plt.legend()\n",
+    "plt.show()\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "hist_data.groupby(['date','from']).size()"
+   ]
   }
  ],
  "metadata": {
@@ -94,7 +139,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.10.9 (main, Dec 19 2022, 17:35:49) [GCC 12.2.0]"
   },
   "orig_nbformat": 4,
   "vscode": {