|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 1, |
| 6 | + "metadata": {}, |
| 7 | + "outputs": [], |
| 8 | + "source": [ |
| 9 | + "import numpy as np\n", |
| 10 | + "import pandas as pd" |
| 11 | + ] |
| 12 | + }, |
| 13 | + { |
| 14 | + "cell_type": "code", |
| 15 | + "execution_count": 2, |
| 16 | + "metadata": {}, |
| 17 | + "outputs": [], |
| 18 | + "source": [ |
| 19 | + "def get_first_cabin(row):\n", |
| 20 | + " try:\n", |
| 21 | + " return row.split()[0]\n", |
| 22 | + " except:\n", |
| 23 | + " return np.nan " |
| 24 | + ] |
| 25 | + }, |
| 26 | + { |
| 27 | + "cell_type": "code", |
| 28 | + "execution_count": 3, |
| 29 | + "metadata": {}, |
| 30 | + "outputs": [], |
| 31 | + "source": [ |
| 32 | + "data = pd.read_csv('https://www.openml.org/data/get_csv/16826755/phpMYEkMl')\n", |
| 33 | + "data = data.replace('?', np.nan)\n", |
| 34 | + "data['cabin'] = data['cabin'].apply(get_first_cabin)\n", |
| 35 | + "data.to_csv('titanic.csv', index=False)" |
| 36 | + ] |
| 37 | + } |
| 38 | + ], |
| 39 | + "metadata": { |
| 40 | + "kernelspec": { |
| 41 | + "display_name": "feml", |
| 42 | + "language": "python", |
| 43 | + "name": "feml" |
| 44 | + }, |
| 45 | + "language_info": { |
| 46 | + "codemirror_mode": { |
| 47 | + "name": "ipython", |
| 48 | + "version": 3 |
| 49 | + }, |
| 50 | + "file_extension": ".py", |
| 51 | + "mimetype": "text/x-python", |
| 52 | + "name": "python", |
| 53 | + "nbconvert_exporter": "python", |
| 54 | + "pygments_lexer": "ipython3", |
| 55 | + "version": "3.7.3" |
| 56 | + }, |
| 57 | + "toc": { |
| 58 | + "nav_menu": {}, |
| 59 | + "number_sections": true, |
| 60 | + "sideBar": true, |
| 61 | + "skip_h1_title": false, |
| 62 | + "toc_cell": false, |
| 63 | + "toc_position": {}, |
| 64 | + "toc_section_display": "block", |
| 65 | + "toc_window_display": false |
| 66 | + } |
| 67 | + }, |
| 68 | + "nbformat": 4, |
| 69 | + "nbformat_minor": 2 |
| 70 | +} |
0 commit comments