Amendements par année

edf0ff6f · Benoît Courty · 382a71d6 · edf0ff6f · edf0ff6f · edf0ff6f
Commit edf0ff6f authored Feb 26, 2021 by Benoît Courty
--- a/docs/_data/sidebars/home_sidebar.yml
+++ b/docs/_data/sidebars/home_sidebar.yml
@@ -25,7 +25,7 @@ entries:
      title: Etude des sujets des amendements PLFSS - Graph
      url: LDA_show.html
    - output: web,pdf
-      title: Title
+      title: "Etude des r\xE9f\xE9rences des amendements"
      url: eda_ref_amendements.html
    output: web
    title: etudes_amendements

--- a/docs/eda_ref_amendements.html
+++ b/docs/eda_ref_amendements.html
--- a/docs/sidebar.json
+++ b/docs/sidebar.json
@@ -6,6 +6,6 @@
    "Etude des sujets des amendements PLFSS - Nuage de mots": "word_count.html",
    "Etude des sujets des amendements PLFSS (LDA)": "LDA_compute.html",
    "Etude des sujets des amendements PLFSS - Graph": "LDA_show.html",
-    "Title": "eda_ref_amendements.html"
+    "Etude des r\u00e9f\u00e9rences des amendements": "eda_ref_amendements.html"
  }
 }
\ No newline at end of file
--- a/etudes_amendements/_nbdev.py
+++ b/etudes_amendements/_nbdev.py
@@ -2,7 +2,7 @@

 __all__ = ["index", "modules", "custom_doc_links", "git_url"]

-index = {"load_data": "02_word_count.ipynb",
+index = {"load_data": "eda_ref_amendements.ipynb",
         "amdt": "02_word_count.ipynb",
         "build_word_cloud": "02_word_count.ipynb",
         "display_distinct": "eda_ref_amendements.ipynb"}

--- a/etudes_amendements/eda_ref.py
+++ b/etudes_amendements/eda_ref.py
 # AUTOGENERATED! DO NOT EDIT! File to edit: notebook/eda_ref_amendements.ipynb (unless otherwise specified).

-__all__ = ['display_distinct']
+__all__ = ['load_data', 'display_distinct']
+
+# Cell
+def load_data(file):
+    df = pd.read_csv(file)
+    df = df.applymap(lambda s:s.lower() if type(s) == str else s)
+    return df

 # Cell
 def display_distinct(df):
@@ -8,7 +14,7 @@ def display_distinct(df):
    to_be_removed = []
    for column in columns:
        nb_unique_values = eval('df["' + column + '"].nunique()')
-        print("Distinct values in", column, ":", nb_unique_values)
+        print("Nombres de valeurs distinctes pour", column, ":", nb_unique_values)
        if nb_unique_values > 50:
            to_be_removed.append(column)
    print("\nColumn with too many distinct values :\n", to_be_removed)
@@ -17,5 +23,5 @@ def display_distinct(df):
    '''
    columns_redux = [item for item in columns if item not in to_be_removed ]
    for column in columns_redux:
-        print("Distinct values in", column)
+        print("\n\nValeurs distinctes pour", column, ':')
        eval('print(df["' + column + '"].value_counts())')
\ No newline at end of file
--- a/notebook/eda_ref_amendements.ipynb
+++ b/notebook/eda_ref_amendements.ipynb
@@ -2,8 +2,8 @@
 "cells": [
  {
   "cell_type": "code",
-   "execution_count": 28,
-   "id": "human-workstation",
+   "execution_count": null,
+   "id": "macro-heritage",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -12,7 +12,7 @@
  },
  {
   "cell_type": "markdown",
-   "id": "amber-radius",
+   "id": "appropriate-tokyo",
   "metadata": {},
   "source": [
    "# Etude des références des amendements"
@@ -20,8 +20,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 62,
-   "id": "mechanical-pantyhose",
+   "execution_count": null,
+   "id": "hindu-surface",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -31,8 +31,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 63,
-   "id": "addressed-childhood",
+   "execution_count": null,
+   "id": "loaded-inventory",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -42,8 +42,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 64,
-   "id": "metric-spectacular",
+   "execution_count": null,
+   "id": "circular-spanish",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -58,8 +58,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 65,
-   "id": "hispanic-theta",
+   "execution_count": null,
+   "id": "excessive-danish",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -72,15 +72,14 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 66,
-   "id": "affiliated-brooks",
+   "execution_count": null,
+   "id": "seasonal-planner",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "references_amendements_plfss_2020-2021 https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_plfss_2020-2021.csv\n",
      "references_amendements_affaires_sociales https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_affaires_sociales.csv\n"
     ]
    },
@@ -95,7 +94,7 @@
   ],
   "source": [
    "files = {\n",
-    "    \"references_amendements_plfss_2020-2021\" : \"https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_plfss_2020-2021.csv\",\n",
+    "    #\"references_amendements_plfss_2020-2021\" : \"https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_plfss_2020-2021.csv\",\n",
    "    \"references_amendements_affaires_sociales\" : \"https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_affaires_sociales.csv\"\n",
    "}\n",
    "\n",
@@ -108,8 +107,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 76,
-   "id": "greek-parade",
+   "execution_count": null,
+   "id": "spanish-mercury",
   "metadata": {},
   "outputs": [],
   "source": [
@@ -134,8 +133,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 77,
-   "id": "frank-devon",
+   "execution_count": null,
+   "id": "cultural-tourist",
   "metadata": {},
   "outputs": [
    {
@@ -190,27 +189,27 @@
      "5                         6\n",
      "3° order: 3               6\n",
      "a bis order: a            5\n",
-      "10° order: 10             4\n",
      "5° order: 5               4\n",
+      "10° order: 10             4\n",
      "8° order: 8               3\n",
+      "7° order: 7               3\n",
      "9° order: 9               3\n",
-      "6° order: 6               3\n",
      "14° order: 14             3\n",
-      "7° order: 7               3\n",
+      "6° order: 6               3\n",
      "11° order: 11             3\n",
+      "4                         2\n",
+      "a ter order: a            2\n",
+      "c quinquies order: c      2\n",
      "f order: f                2\n",
      "2° order: 2               2\n",
-      "c quinquies order: c      2\n",
-      "a ter order: a            2\n",
-      "4                         2\n",
      "indirect: 1               2\n",
-      "b bis order: b            1\n",
+      "e order: e                1\n",
      "v order: 5                1\n",
+      "7                         1\n",
      "4° order: 4               1\n",
+      "b bis order: b            1\n",
      "15° order: 15             1\n",
-      "e order: e                1\n",
      "j order: j                1\n",
-      "7                         1\n",
      "Name: alinea2, dtype: int64\n",
      "\n",
      "\n",
@@ -244,15 +243,15 @@
      "viii                            11\n",
      "2                                9\n",
      "ii indirect: (relative: 0)       7\n",
-      "ix                               6\n",
      "iii indirect: (relative: 0)      6\n",
+      "ix                               6\n",
      "1er                              5\n",
      "4                                4\n",
-      "8                                3\n",
      "vii indirect: (relative: 0)      3\n",
-      "6                                2\n",
+      "8                                3\n",
      "3                                2\n",
      "7                                2\n",
+      "6                                2\n",
      "5                                1\n",
      "Name: book, dtype: int64\n",
      "\n",
@@ -300,9 +299,9 @@
      "législative                    7\n",
      "indirect: (relative: 0)        6\n",
      "réglementaire                  3\n",
-      "réglementaire indirect: 1      3\n",
      "iv                             3\n",
      "iii                            3\n",
+      "réglementaire indirect: 1      3\n",
      "indirect: -1                   1\n",
      "Name: code-part, dtype: int64\n",
      "\n",
@@ -357,12 +356,12 @@
      "ii                                  4\n",
      "6                                   3\n",
      "indirect: 1                         2\n",
-      "8                                   2\n",
      "indirect: (relative: 0)             2\n",
-      "1er                                 1\n",
-      "iv                                  1\n",
+      "8                                   2\n",
      "7                                   1\n",
+      "iv                                  1\n",
      "iii                                 1\n",
+      "1er                                 1\n",
      "Name: paragraph, dtype: int64\n",
      "\n",
      "\n",
@@ -384,27 +383,27 @@
      "iv                            27\n",
      "vii                           24\n",
      "6                             14\n",
-      "i                             13\n",
      "iii                           13\n",
+      "i                             13\n",
      "12                            12\n",
-      "vi                             6\n",
      "13                             6\n",
+      "vi                             6\n",
      "xx                             6\n",
      "viii                           5\n",
      "11                             4\n",
      "indirect: 1                    4\n",
      "order: 2                       3\n",
      "15                             3\n",
-      "order: 3                       2\n",
-      "16                             2\n",
      "7                              2\n",
      "x                              2\n",
+      "16                             2\n",
      "3 indirect: (relative: 0)      2\n",
-      "01                             1\n",
-      "0                              1\n",
+      "order: 3                       2\n",
+      "xi                             1\n",
      "14                             1\n",
+      "01                             1\n",
      "8                              1\n",
-      "xi                             1\n",
+      "0                              1\n",
      "Name: section, dtype: int64\n",
      "\n",
      "\n",
@@ -429,10 +428,10 @@
      "5                             21\n",
      "indirect: 1                   20\n",
      "10                             3\n",
-      "7                              2\n",
      "indirect: (relative: -1)       2\n",
-      "8                              1\n",
+      "7                              2\n",
      "9                              1\n",
+      "8                              1\n",
      "Name: sentence, dtype: int64\n",
      "\n",
      "\n",
@@ -458,25 +457,25 @@
      "3                               20\n",
      "1er                             18\n",
      "i                               17\n",
-      "ix                              12\n",
      "6                               12\n",
+      "ix                              12\n",
      "viii                            10\n",
-      "xii                             10\n",
      "vii                             10\n",
+      "xii                             10\n",
      "4                                9\n",
      "ii indirect: (relative: 0)       7\n",
-      "xiii                             5\n",
      "7                                5\n",
+      "xiii                             5\n",
      "1                                4\n",
+      "ier indirect: (relative: 0)      2\n",
      "iv indirect: (relative: 0)       2\n",
      "indirect: (relative: -1)         2\n",
-      "ier indirect: (relative: 0)      2\n",
      "2                                1\n",
-      "9                                1\n",
+      "xi                               1\n",
      "xvii                             1\n",
-      "xv                               1\n",
      "5                                1\n",
-      "xi                               1\n",
+      "xv                               1\n",
+      "9                                1\n",
      "Name: title, dtype: int64\n",
      "\n",
      "\n",
@@ -502,8 +501,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 79,
-   "id": "checked-irish",
+   "execution_count": null,
+   "id": "living-aaron",
   "metadata": {},
   "outputs": [
    {
@@ -715,7 +714,7 @@
       "[5 rows x 29 columns]"
      ]
     },
-     "execution_count": 79,
+     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -726,18 +725,496 @@
  },
  {
   "cell_type": "markdown",
-   "id": "average-basics",
+   "id": "weighted-anderson",
   "metadata": {},
   "source": [
+    "TODO :\n",
+    "\n",
    "- Adoptés par parti\n",
    "- Article par année\n",
    "- Adoptés par article"
   ]
  },
+  {
+   "cell_type": "markdown",
+   "id": "rational-anger",
+   "metadata": {},
+   "source": [
+    "## Nombre d'amendements par article, par année"
+   ]
+  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "elect-throat",
+   "id": "waiting-pursuit",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2017\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>law_article</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575</th>\n",
+       "      <td>1286</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575 a</th>\n",
+       "      <td>1286</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code des douanes 265</th>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>indirect: (relative: 0) 1649 quater e</th>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>indirect: (relative: 0) 1649 quater h</th>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1600</th>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1649 quater e</th>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1649 quater h</th>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 199 terdecies-0 a</th>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 154 bis-0 a</th>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                           law_article\n",
+       "code général des impôts 575                       1286\n",
+       "code général des impôts 575 a                     1286\n",
+       "code des douanes 265                                 7\n",
+       "indirect: (relative: 0) 1649 quater e                6\n",
+       "indirect: (relative: 0) 1649 quater h                6\n",
+       "code général des impôts 1600                         6\n",
+       "code général des impôts 1649 quater e                5\n",
+       "code général des impôts 1649 quater h                5\n",
+       "code général des impôts 199 terdecies-0 a            5\n",
+       "code général des impôts 154 bis-0 a                  4"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2018\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>law_article</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575</th>\n",
+       "      <td>3140</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575 a</th>\n",
+       "      <td>3137</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 39 ab</th>\n",
+       "      <td>31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 39 a</th>\n",
+       "      <td>31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 39 ak</th>\n",
+       "      <td>31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 39 ac</th>\n",
+       "      <td>31</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de l’environnement l541-10-6</th>\n",
+       "      <td>25</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>constitution 34</th>\n",
+       "      <td>18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 39 g</th>\n",
+       "      <td>17</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 278-0 bis</th>\n",
+       "      <td>16</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                   law_article\n",
+       "code général des impôts 575               3140\n",
+       "code général des impôts 575 a             3137\n",
+       "code général des impôts 39 ab               31\n",
+       "code général des impôts 39 a                31\n",
+       "code général des impôts 39 ak               31\n",
+       "code général des impôts 39 ac               31\n",
+       "code de l’environnement l541-10-6           25\n",
+       "constitution 34                             18\n",
+       "code général des impôts 39 g                17\n",
+       "code général des impôts 278-0 bis           16"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2019\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>law_article</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575</th>\n",
+       "      <td>2691</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575 a</th>\n",
+       "      <td>2690</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des collectivités territoriales d2224-2</th>\n",
+       "      <td>12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des collectivités territoriales d2224-1</th>\n",
+       "      <td>12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des collectivités territoriales d2224-3</th>\n",
+       "      <td>12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code des transports l1431-3</th>\n",
+       "      <td>12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de l’entrée et du séjour des étrangers et du droit d’asile l311-13</th>\n",
+       "      <td>11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de la construction et de l’habitation l411-2</th>\n",
+       "      <td>9</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1595</th>\n",
+       "      <td>8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1594 a</th>\n",
+       "      <td>8</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                    law_article\n",
+       "code général des impôts 575                                2691\n",
+       "code général des impôts 575 a                              2690\n",
+       "code général des collectivités territoriales d2...           12\n",
+       "code général des collectivités territoriales d2...           12\n",
+       "code général des collectivités territoriales d2...           12\n",
+       "code des transports l1431-3                                  12\n",
+       "code de l’entrée et du séjour des étrangers et ...           11\n",
+       "code de la construction et de l’habitation l411-2             9\n",
+       "code général des impôts 1595                                  8\n",
+       "code général des impôts 1594 a                                8"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2020\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>law_article</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575 a</th>\n",
+       "      <td>3319</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575</th>\n",
+       "      <td>3318</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>indirect: (relative: 0) 4</th>\n",
+       "      <td>18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des collectivités territoriales l1615-2</th>\n",
+       "      <td>18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1519 h</th>\n",
+       "      <td>13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 1594 d</th>\n",
+       "      <td>12</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2011-1977 du 2011-12-28 46</th>\n",
+       "      <td>11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de la construction et de l’habitation l411-2</th>\n",
+       "      <td>11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de la sécurité sociale l162-21-3</th>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code des douanes 265</th>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                    law_article\n",
+       "code général des impôts 575 a                              3319\n",
+       "code général des impôts 575                                3318\n",
+       "indirect: (relative: 0) 4                                    18\n",
+       "code général des collectivités territoriales l1...           18\n",
+       "code général des impôts 1519 h                               13\n",
+       "code général des impôts 1594 d                               12\n",
+       "2011-1977 du 2011-12-28 46                                   11\n",
+       "code de la construction et de l’habitation l411-2            11\n",
+       "code de la sécurité sociale l162-21-3                        10\n",
+       "code des douanes 265                                         10"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2021\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>law_article</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575 a</th>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code général des impôts 575</th>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de la santé publique l1110-12</th>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de la sécurité sociale l215-1</th>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de l’éducation d821-1</th>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>code de la santé publique l1110-4</th>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                    law_article\n",
+       "code général des impôts 575 a                 7\n",
+       "code général des impôts 575                   7\n",
+       "code de la santé publique l1110-12            1\n",
+       "code de la sécurité sociale l215-1            1\n",
+       "code de l’éducation d821-1                    1\n",
+       "code de la santé publique l1110-4             1"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "for y in df.year.unique():\n",
+    "    if np.isnan(y):\n",
+    "        continue\n",
+    "    y = int(y)\n",
+    "    print(y)\n",
+    "    df_tmp = df.query(\"year == @y\")[\"law_article\"]\n",
+    "    df_tmp.value_counts().to_frame().head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "interpreted-trading",
   "metadata": {},
   "outputs": [],
   "source": []
@@ -748,18 +1225,6 @@
   "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": "3.8.5"
  }
 },
 "nbformat": 4,

-%% Cell type:code id:human-workstation tags:
+%% Cell type:code id:macro-heritage tags:

 ``` python
 #default_exp eda_ref
 ```

-%% Cell type:markdown id:amber-radius tags:
+%% Cell type:markdown id:appropriate-tokyo tags:

 # Etude des références des amendements

-%% Cell type:code id:mechanical-pantyhose tags:
+%% Cell type:code id:hindu-surface tags:

 ``` python
 #hide
 #!pip3 install pandas matplotlib
 ```

-%% Cell type:code id:addressed-childhood tags:
+%% Cell type:code id:loaded-inventory tags:

 ``` python
 #hide
 import pandas as pd
 ```

-%% Cell type:code id:metric-spectacular tags:
+%% Cell type:code id:circular-spanish tags:

 ``` python
 #hide
 # Put these at the top of every notebook, to get automatic reloading and inline plotting
 %reload_ext autoreload
 %autoreload 2
 %matplotlib inline
 from IPython.core.interactiveshell import InteractiveShell
 InteractiveShell.ast_node_interactivity = "all"
 ```

-%% Cell type:code id:hispanic-theta tags:
+%% Cell type:code id:excessive-danish tags:

 ``` python
 #export
 def load_data(file):
    df = pd.read_csv(file)
    df = df.applymap(lambda s:s.lower() if type(s) == str else s)
    return df
 ```

-%% Cell type:code id:affiliated-brooks tags:
+%% Cell type:code id:seasonal-planner tags:

 ``` python
 files = {
-    "references_amendements_plfss_2020-2021" : "https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_plfss_2020-2021.csv",
+    #"references_amendements_plfss_2020-2021" : "https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_plfss_2020-2021.csv",
    "references_amendements_affaires_sociales" : "https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_affaires_sociales.csv"
 }

 for k in files.keys():
    print(k, files.get(k))
    df = load_data(files.get(k))
    df["law_article"] = df.law + ' ' + df.article
    df.law_article.value_counts().to_frame().to_csv(k + '-top-article.csv')
 ```

 %% Output

-    references_amendements_plfss_2020-2021 https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_plfss_2020-2021.csv
    references_amendements_affaires_sociales https://github.com/leximpact/donnees-extraites-assemblee/raw/main/references_amendements_affaires_sociales.csv

    /home/ben/.local/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3347: DtypeWarning: Columns (3,8,11,16,25) have mixed types.Specify dtype option on import or set low_memory=False.
      if (await self.run_code(code, result,  async_=asy)):

-%% Cell type:code id:greek-parade tags:
+%% Cell type:code id:spanish-mercury tags:

 ``` python
 #export
 def display_distinct(df):
    columns = df.columns
    to_be_removed = []
    for column in columns:
        nb_unique_values = eval('df["' + column + '"].nunique()')
        print("Nombres de valeurs distinctes pour", column, ":", nb_unique_values)
        if nb_unique_values > 50:
            to_be_removed.append(column)
    print("\nColumn with too many distinct values :\n", to_be_removed)
    '''
    Display distinct values
    '''
    columns_redux = [item for item in columns if item not in to_be_removed ]
    for column in columns_redux:
        print("\n\nValeurs distinctes pour", column, ':')
        eval('print(df["' + column + '"].value_counts())')
 ```

-%% Cell type:code id:frank-devon tags:
+%% Cell type:code id:cultural-tourist tags:

 ``` python
 display_distinct(df)
 ```

 %% Output

    Nombres de valeurs distinctes pour alinea : 203
    Nombres de valeurs distinctes pour alinea1 : 83
    Nombres de valeurs distinctes pour alinea2 : 34
    Nombres de valeurs distinctes pour alinea3 : 4
    Nombres de valeurs distinctes pour article : 1633
    Nombres de valeurs distinctes pour auteur : 551
    Nombres de valeurs distinctes pour auteurType : 3
    Nombres de valeurs distinctes pour book : 24
    Nombres de valeurs distinctes pour book1 : 1
    Nombres de valeurs distinctes pour chapter : 23
    Nombres de valeurs distinctes pour code-part : 14
    Nombres de valeurs distinctes pour code-part1 : 1
    Nombres de valeurs distinctes pour etat : 0
    Nombres de valeurs distinctes pour groupePolitique : 11
    Nombres de valeurs distinctes pour law : 218
    Nombres de valeurs distinctes pour lawType : 9
    Nombres de valeurs distinctes pour paragraph : 18
    Nombres de valeurs distinctes pour paragraph1 : 2
    Nombres de valeurs distinctes pour section : 32
    Nombres de valeurs distinctes pour section1 : 6
    Nombres de valeurs distinctes pour sentence : 14
    Nombres de valeurs distinctes pour sort : 5
    Nombres de valeurs distinctes pour text : 5838
    Nombres de valeurs distinctes pour texteLegislatifUid : 118
    Nombres de valeurs distinctes pour title : 31
    Nombres de valeurs distinctes pour title1 : 2
    Nombres de valeurs distinctes pour uid : 30471
    Nombres de valeurs distinctes pour year : 5
    Nombres de valeurs distinctes pour law_article : 1120
    
    Column with too many distinct values :
     ['alinea', 'alinea1', 'article', 'auteur', 'law', 'text', 'texteLegislatifUid', 'uid', 'law_article']
    
    
    Valeurs distinctes pour alinea2 :
    1                       235
    2                       132
    3                        70
    a order: a               62
    c order: c               47
    b order: b               39
    indirect: -1             26
    1° order: 1              23
    13° order: 13            12
    d order: d                9
    5                         6
    3° order: 3               6
    a bis order: a            5
-    10° order: 10             4
    5° order: 5               4
+    10° order: 10             4
    8° order: 8               3
+    7° order: 7               3
    9° order: 9               3
-    6° order: 6               3
    14° order: 14             3
-    7° order: 7               3
+    6° order: 6               3
    11° order: 11             3
+    4                         2
+    a ter order: a            2
+    c quinquies order: c      2
    f order: f                2
    2° order: 2               2
-    c quinquies order: c      2
-    a ter order: a            2
-    4                         2
    indirect: 1               2
-    b bis order: b            1
+    e order: e                1
    v order: 5                1
+    7                         1
    4° order: 4               1
+    b bis order: b            1
    15° order: 15             1
-    e order: e                1
    j order: j                1
-    7                         1
    Name: alinea2, dtype: int64
    
    
    Valeurs distinctes pour alinea3 :
    2             8
    2.0           3
    5.0           1
    i order: i    1
    Name: alinea3, dtype: int64
    
    
    Valeurs distinctes pour auteurType :
    député          126689
    gouvernement      4441
    rapporteur        3604
    Name: auteurType, dtype: int64
    
    
    Valeurs distinctes pour book :
    ier                            457
    indirect: 1                    372
    ii                             265
    iii                            248
    iv                             143
    indirect: (relative: 0)         84
    vii                             83
    v                               51
    vi                              47
    1                               37
    i                               20
    viii                            11
    2                                9
    ii indirect: (relative: 0)       7
-    ix                               6
    iii indirect: (relative: 0)      6
+    ix                               6
    1er                              5
    4                                4
-    8                                3
    vii indirect: (relative: 0)      3
-    6                                2
+    8                                3
    3                                2
    7                                2
+    6                                2
    5                                1
    Name: book, dtype: int64
    
    
    Valeurs distinctes pour book1 :
    ier    4
    Name: book1, dtype: int64
    
    
    Valeurs distinctes pour chapter :
    ier                            405
    ii                             352
    indirect: 1                    188
    iii                            149
    iv                             139
    indirect: (relative: 0)        132
    v                              119
    1er                             35
    vi                              33
    i                               32
    vii                             29
    2                               27
    7                               16
    viii                             9
    3                                8
    4                                7
    5                                7
    iii indirect: (relative: 0)      3
    x                                2
    ix                               2
    1                                1
    xx                               1
    10                               1
    Name: chapter, dtype: int64
    
    
    Valeurs distinctes pour code-part :
    indirect: 1                  689
    order: 2                     277
    order: 3                     220
    order: 4                     152
    order: 6                      96
    order: 5                      53
    order: 7                      32
    législative                    7
    indirect: (relative: 0)        6
    réglementaire                  3
-    réglementaire indirect: 1      3
    iv                             3
    iii                            3
+    réglementaire indirect: 1      3
    indirect: -1                   1
    Name: code-part, dtype: int64
    
    
    Valeurs distinctes pour code-part1 :
    order: 2    3
    Name: code-part1, dtype: int64
    
    
    Valeurs distinctes pour etat :
    Series([], Name: etat, dtype: int64)
    
    
    Valeurs distinctes pour groupePolitique :
    lr          47932
    larem       18331
    lt          12586
    soc          8532
    dem          6740
    fi           6452
    agir ens     6338
    gdr          4246
    udi-i        3110
    ni           2552
    eds          2087
    Name: groupePolitique, dtype: int64
    
    
    Valeurs distinctes pour lawType :
    code                     54370
    loi                       2748
    constitution              2169
    règlement                  236
    directive                  230
    arrêté                      71
    ordonnance                  24
    décret                      16
    loi constitutionnelle        2
    Name: lawType, dtype: int64
    
    
    Valeurs distinctes pour paragraph :
    indirect: (relative: -1)           34
    2                                  18
    indirect: (relative: undefined)    17
    1                                  14
    3                                  10
    4                                   9
    5                                   9
    indirect: (relative: 1)             8
    i                                   6
    ii                                  4
    6                                   3
    indirect: 1                         2
-    8                                   2
    indirect: (relative: 0)             2
-    1er                                 1
-    iv                                  1
+    8                                   2
    7                                   1
+    iv                                  1
    iii                                 1
+    1er                                 1
    Name: paragraph, dtype: int64
    
    
    Valeurs distinctes pour paragraph1 :
    1.0    2
    4.0    1
    Name: paragraph1, dtype: int64
    
    
    Valeurs distinctes pour section :
    ii                           159
    v                            145
    2                            130
    1                            110
    3                             94
    5                             50
    4                             40
    indirect: (relative: 0)       36
    iv                            27
    vii                           24
    6                             14
-    i                             13
    iii                           13
+    i                             13
    12                            12
-    vi                             6
    13                             6
+    vi                             6
    xx                             6
    viii                           5
    11                             4
    indirect: 1                    4
    order: 2                       3
    15                             3
-    order: 3                       2
-    16                             2
    7                              2
    x                              2
+    16                             2
    3 indirect: (relative: 0)      2
-    01                             1
-    0                              1
+    order: 3                       2
+    xi                             1
    14                             1
+    01                             1
    8                              1
-    xi                             1
+    0                              1
    Name: section, dtype: int64
    
    
    Valeurs distinctes pour section1 :
    indirect: 1    54
    1              20
    2              17
    3              15
    4               9
    5               2
    Name: section1, dtype: int64
    
    
    Valeurs distinctes pour sentence :
    1                           3847
    2                           2333
    indirect: -1                 693
    3                            302
    indirect: (relative: 0)      150
    4                             58
    6                             29
    5                             21
    indirect: 1                   20
    10                             3
-    7                              2
    indirect: (relative: -1)       2
-    8                              1
+    7                              2
    9                              1
+    8                              1
    Name: sentence, dtype: int64
    
    
    Valeurs distinctes pour sort :
    rejeté         67408
    non soutenu    30175
    adopté         18779
    retiré         12930
    tombé           5442
    Name: sort, dtype: int64
    
    
    Valeurs distinctes pour title :
    ii                             438
    ier                            348
    iii                            345
    iv                             230
    indirect: 1                    141
    indirect: (relative: 0)        138
    v                               80
    vi                              65
    x                               47
    3                               20
    1er                             18
    i                               17
-    ix                              12
    6                               12
+    ix                              12
    viii                            10
-    xii                             10
    vii                             10
+    xii                             10
    4                                9
    ii indirect: (relative: 0)       7
-    xiii                             5
    7                                5
+    xiii                             5
    1                                4
+    ier indirect: (relative: 0)      2
    iv indirect: (relative: 0)       2
    indirect: (relative: -1)         2
-    ier indirect: (relative: 0)      2
    2                                1
-    9                                1
+    xi                               1
    xvii                             1
-    xv                               1
    5                                1
-    xi                               1
+    xv                               1
+    9                                1
    Name: title, dtype: int64
    
    
    Valeurs distinctes pour title1 :
    6.0    2
    ier    1
    Name: title1, dtype: int64
    
    
    Valeurs distinctes pour year :
    2018.0    43515
    2019.0    35557
    2020.0    34372
    2017.0    17918
    2021.0      763
    Name: year, dtype: int64

-%% Cell type:code id:checked-irish tags:
+%% Cell type:code id:living-aaron tags:

 ``` python
 df.head()
 ```

 %% Output

            alinea alinea1 alinea2 alinea3 article           auteur auteurType  \
    0  9° order: 9     NaN     NaN     NaN     NaN  elimas nathalie     député
    1          NaN     NaN     NaN     NaN     NaN  elimas nathalie     député
    2          NaN     NaN     NaN     NaN     NaN  elimas nathalie     député
    3   i order: 1     NaN     NaN     NaN     NaN  elimas nathalie     député
    4          NaN     NaN     NaN     NaN     575  elimas nathalie     député
    
      book book1 chapter  ... section1 sentence    sort  \
    0  NaN   NaN     NaN  ...      NaN      NaN  retiré
    1  NaN   NaN     NaN  ...      NaN      NaN  retiré
    2  NaN   NaN     NaN  ...      NaN      NaN  retiré
    3  NaN   NaN     NaN  ...      NaN      NaN  retiré
    4  NaN   NaN     NaN  ...      NaN      NaN  retiré
    
                                                    text texteLegislatifUid title  \
    0                                              le 9°   pionanr5l15b0228   NaN
    1                         du code général des impôts   pionanr5l15b0228   NaN
    2        du code de l’action sociale et des familles   pionanr5l15b0228   NaN
    3                                               du i   pionanr5l15b0228   NaN
    4  aux articles 575 et 575 a du code général des ...   pionanr5l15b0228   NaN
    
      title1                                uid    year  \
    0    NaN  amanr5l15po420120b0228p0d1n000002  2017.0
    1    NaN  amanr5l15po420120b0228p0d1n000002  2017.0
    2    NaN  amanr5l15po420120b0228p0d1n000002  2017.0
    3    NaN  amanr5l15po420120b0228p0d1n000002  2017.0
    4    NaN  amanr5l15po420120b0228p0d1n000002  2017.0
    
                       law_article
    0                          NaN
    1                          NaN
    2                          NaN
    3                          NaN
    4  code général des impôts 575
    
    [5 rows x 29 columns]

-%% Cell type:markdown id:average-basics tags:
+%% Cell type:markdown id:weighted-anderson tags:
+
+TODO :

 - Adoptés par parti
 - Article par année
 - Adoptés par article

-%% Cell type:code id:elect-throat tags:
+%% Cell type:markdown id:rational-anger tags:
+
+## Nombre d'amendements par article, par année
+
+%% Cell type:code id:waiting-pursuit tags:
+
+``` python
+import numpy as np
+for y in df.year.unique():
+    if np.isnan(y):
+        continue
+    y = int(y)
+    print(y)
+    df_tmp = df.query("year == @y")["law_article"]
+    df_tmp.value_counts().to_frame().head(10)
+```
+
+%% Output
+
+    2017
+
+                                               law_article
+    code général des impôts 575                       1286
+    code général des impôts 575 a                     1286
+    code des douanes 265                                 7
+    indirect: (relative: 0) 1649 quater e                6
+    indirect: (relative: 0) 1649 quater h                6
+    code général des impôts 1600                         6
+    code général des impôts 1649 quater e                5
+    code général des impôts 1649 quater h                5
+    code général des impôts 199 terdecies-0 a            5
+    code général des impôts 154 bis-0 a                  4
+
+    2018
+
+                                       law_article
+    code général des impôts 575               3140
+    code général des impôts 575 a             3137
+    code général des impôts 39 ab               31
+    code général des impôts 39 a                31
+    code général des impôts 39 ak               31
+    code général des impôts 39 ac               31
+    code de l’environnement l541-10-6           25
+    constitution 34                             18
+    code général des impôts 39 g                17
+    code général des impôts 278-0 bis           16
+
+    2019
+
+                                                        law_article
+    code général des impôts 575                                2691
+    code général des impôts 575 a                              2690
+    code général des collectivités territoriales d2...           12
+    code général des collectivités territoriales d2...           12
+    code général des collectivités territoriales d2...           12
+    code des transports l1431-3                                  12
+    code de l’entrée et du séjour des étrangers et ...           11
+    code de la construction et de l’habitation l411-2             9
+    code général des impôts 1595                                  8
+    code général des impôts 1594 a                                8
+
+    2020
+
+                                                        law_article
+    code général des impôts 575 a                              3319
+    code général des impôts 575                                3318
+    indirect: (relative: 0) 4                                    18
+    code général des collectivités territoriales l1...           18
+    code général des impôts 1519 h                               13
+    code général des impôts 1594 d                               12
+    2011-1977 du 2011-12-28 46                                   11
+    code de la construction et de l’habitation l411-2            11
+    code de la sécurité sociale l162-21-3                        10
+    code des douanes 265                                         10
+
+    2021
+
+                                        law_article
+    code général des impôts 575 a                 7
+    code général des impôts 575                   7
+    code de la santé publique l1110-12            1
+    code de la sécurité sociale l215-1            1
+    code de l’éducation d821-1                    1
+    code de la santé publique l1110-4             1
+
+%% Cell type:code id:interpreted-trading tags:

 ``` python
 ```