requirements

Author: omkarxx

Chapter01/DataPrep_Titanic.ipynb

@@ -0,0 +1,70 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_first_cabin(row):\n",
+    "    try:\n",
+    "        return row.split()[0]\n",
+    "    except:\n",
+    "        return np.nan "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv('https://www.openml.org/data/get_csv/16826755/phpMYEkMl')\n",
+    "data = data.replace('?', np.nan)\n",
+    "data['cabin'] = data['cabin'].apply(get_first_cabin)\n",
+    "data.to_csv('titanic.csv', index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "feml",
+   "language": "python",
+   "name": "feml"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  },
+  "toc": {
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": "block",
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}