From 8e14615c0f22d0676f539e5c2c2155726fd4dda4 Mon Sep 17 00:00:00 2001
From: KameniAlexNea <Kamenialexnea@gmail.com>
Date: Sat, 5 Nov 2022 12:26:34 +0100
Subject: [PATCH] moves normalize funct into filter-cameroon (#15)

---
 etl/filter-cameroon.ipynb | 54 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 47 insertions(+), 7 deletions(-)

diff --git a/etl/filter-cameroon.ipynb b/etl/filter-cameroon.ipynb
index 53bbbd2..9495b50 100644
--- a/etl/filter-cameroon.ipynb
+++ b/etl/filter-cameroon.ipynb
@@ -476,7 +476,7 @@
     "        .pipe(select_relevant_columns) \\\n",
     "        .pipe(add_column_adrs)\n",
     "\n",
-    "df2"
+    "df2.sample(5)"
    ]
   },
   {
@@ -915,7 +915,7 @@
     "\n",
     "# get_info(\"W212001727\")\n",
     "# get_dept_region(30913)\n",
-    "df2"
+    "df2.sample(5)"
    ]
   },
   {
@@ -1368,7 +1368,42 @@
     "\n",
     "df2 = df2.pipe(add_lat_lon) \\\n",
     "         .pipe(format_libelle_for_gogocarto)\n",
-    "df2"
+    "df2.sample(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1de8d9a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def remove_space_at_the_end(x: str):\n",
+    "    if x is not None:\n",
+    "        return x.strip()\n",
+    "\n",
+    "def replace_double_quote(x: str):\n",
+    "    if x is not None:\n",
+    "        return x.replace(\"\\\"\\\"\", \"'\")\n",
+    "\n",
+    "def normalize(data: pd.DataFrame):\n",
+    "    text_columns = [\n",
+    "        \"titre\", \"objet\", \"social_object1_libelle\", \"social_object2_libelle\"\n",
+    "    ]\n",
+    "    data[text_columns] = data[text_columns].apply(\n",
+    "        lambda x: x.apply(remove_space_at_the_end)\n",
+    "    )\n",
+    "    data[text_columns] = data[text_columns].apply(\n",
+    "        lambda x: x.apply(replace_double_quote)\n",
+    "    )\n",
+    "    data[\"titre\"] = data[\"titre\"].apply(lambda x: x.upper())\n",
+    "    data[\"objet\"] = data[\"objet\"].apply(lambda x: x.lower())\n",
+    "\n",
+    "    return data\n",
+    "\n",
+    "df2 = df2.pipe(normalize)\n",
+    "\n",
+    "df2.sample(5)"
    ]
   },
   {
@@ -1389,9 +1424,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "etl",
+   "display_name": "Python 3.9.12 ('base')",
    "language": "python",
-   "name": "etl"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -1403,11 +1438,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.9.12"
   },
   "toc-autonumbering": true,
   "toc-showcode": false,
-  "toc-showmarkdowntxt": false
+  "toc-showmarkdowntxt": false,
+  "vscode": {
+   "interpreter": {
+    "hash": "d9a8acb4f733d3596df9f6fac9daff15e014d11794ebc65488d1c191c94698fd"
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 5