{
"metadata": {
"name": "",
"signature": "sha256:ce0f6141b311238afce988530e0c8920ffd7854a937e1a54040717a37ecce3da"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Make New Columns Using Functions\n",
"\n",
"- **Author:** [Chris Albon](http://www.chrisalbon.com/), [@ChrisAlbon](https://twitter.com/chrisalbon)\n",
"- **Date:** -\n",
"- **Repo:** [Python 3 code snippets for data science](https://github.com/chrisalbon/code_py)\n",
"- **Note:** Credit: http://manishamde.github.io/blog/2013/03/07/pandas-and-python-top-10/"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Import modules\n",
"import pandas as pd"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 5
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Example dataframe\n",
"raw_data = {'regiment': ['Nighthawks', 'Nighthawks', 'Nighthawks', 'Nighthawks', 'Dragoons', 'Dragoons', 'Dragoons', 'Dragoons', 'Scouts', 'Scouts', 'Scouts', 'Scouts'], \n",
" 'company': ['1st', '1st', '2nd', '2nd', '1st', '1st', '2nd', '2nd','1st', '1st', '2nd', '2nd'], \n",
" 'name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze', 'Jacon', 'Ryaner', 'Sone', 'Sloan', 'Piger', 'Riani', 'Ali'], \n",
" 'preTestScore': [4, 24, 31, 2, 3, 4, 24, 31, 2, 3, 2, 3],\n",
" 'postTestScore': [25, 94, 57, 62, 70, 25, 94, 57, 62, 70, 62, 70]}\n",
"df = pd.DataFrame(raw_data, columns = ['regiment', 'company', 'name', 'preTestScore', 'postTestScore'])\n",
"df"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"
\n",
"
\n",
" \n",
" \n",
" | \n",
" regiment | \n",
" company | \n",
" name | \n",
" preTestScore | \n",
" postTestScore | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" Nighthawks | \n",
" 1st | \n",
" Miller | \n",
" 4 | \n",
" 25 | \n",
"
\n",
" \n",
" 1 | \n",
" Nighthawks | \n",
" 1st | \n",
" Jacobson | \n",
" 24 | \n",
" 94 | \n",
"
\n",
" \n",
" 2 | \n",
" Nighthawks | \n",
" 2nd | \n",
" Ali | \n",
" 31 | \n",
" 57 | \n",
"
\n",
" \n",
" 3 | \n",
" Nighthawks | \n",
" 2nd | \n",
" Milner | \n",
" 2 | \n",
" 62 | \n",
"
\n",
" \n",
" 4 | \n",
" Dragoons | \n",
" 1st | \n",
" Cooze | \n",
" 3 | \n",
" 70 | \n",
"
\n",
" \n",
" 5 | \n",
" Dragoons | \n",
" 1st | \n",
" Jacon | \n",
" 4 | \n",
" 25 | \n",
"
\n",
" \n",
" 6 | \n",
" Dragoons | \n",
" 2nd | \n",
" Ryaner | \n",
" 24 | \n",
" 94 | \n",
"
\n",
" \n",
" 7 | \n",
" Dragoons | \n",
" 2nd | \n",
" Sone | \n",
" 31 | \n",
" 57 | \n",
"
\n",
" \n",
" 8 | \n",
" Scouts | \n",
" 1st | \n",
" Sloan | \n",
" 2 | \n",
" 62 | \n",
"
\n",
" \n",
" 9 | \n",
" Scouts | \n",
" 1st | \n",
" Piger | \n",
" 3 | \n",
" 70 | \n",
"
\n",
" \n",
" 10 | \n",
" Scouts | \n",
" 2nd | \n",
" Riani | \n",
" 2 | \n",
" 62 | \n",
"
\n",
" \n",
" 11 | \n",
" Scouts | \n",
" 2nd | \n",
" Ali | \n",
" 3 | \n",
" 70 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 6,
"text": [
" regiment company name preTestScore postTestScore\n",
"0 Nighthawks 1st Miller 4 25\n",
"1 Nighthawks 1st Jacobson 24 94\n",
"2 Nighthawks 2nd Ali 31 57\n",
"3 Nighthawks 2nd Milner 2 62\n",
"4 Dragoons 1st Cooze 3 70\n",
"5 Dragoons 1st Jacon 4 25\n",
"6 Dragoons 2nd Ryaner 24 94\n",
"7 Dragoons 2nd Sone 31 57\n",
"8 Scouts 1st Sloan 2 62\n",
"9 Scouts 1st Piger 3 70\n",
"10 Scouts 2nd Riani 2 62\n",
"11 Scouts 2nd Ali 3 70"
]
}
],
"prompt_number": 6
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create one column as a function of two columns"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Create a function that takes two inputs, pre and post\n",
"def pre_post_difference(pre, post):\n",
" # returns the difference between post and pre\n",
" return post - pre"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 7
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Create a variable that is the output of the function\n",
"df['score_change'] = pre_post_difference(df['preTestScore'], df['postTestScore'])\n",
"\n",
"# View the dataframe\n",
"df"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" regiment | \n",
" company | \n",
" name | \n",
" preTestScore | \n",
" postTestScore | \n",
" score_change | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" Nighthawks | \n",
" 1st | \n",
" Miller | \n",
" 4 | \n",
" 25 | \n",
" 21 | \n",
"
\n",
" \n",
" 1 | \n",
" Nighthawks | \n",
" 1st | \n",
" Jacobson | \n",
" 24 | \n",
" 94 | \n",
" 70 | \n",
"
\n",
" \n",
" 2 | \n",
" Nighthawks | \n",
" 2nd | \n",
" Ali | \n",
" 31 | \n",
" 57 | \n",
" 26 | \n",
"
\n",
" \n",
" 3 | \n",
" Nighthawks | \n",
" 2nd | \n",
" Milner | \n",
" 2 | \n",
" 62 | \n",
" 60 | \n",
"
\n",
" \n",
" 4 | \n",
" Dragoons | \n",
" 1st | \n",
" Cooze | \n",
" 3 | \n",
" 70 | \n",
" 67 | \n",
"
\n",
" \n",
" 5 | \n",
" Dragoons | \n",
" 1st | \n",
" Jacon | \n",
" 4 | \n",
" 25 | \n",
" 21 | \n",
"
\n",
" \n",
" 6 | \n",
" Dragoons | \n",
" 2nd | \n",
" Ryaner | \n",
" 24 | \n",
" 94 | \n",
" 70 | \n",
"
\n",
" \n",
" 7 | \n",
" Dragoons | \n",
" 2nd | \n",
" Sone | \n",
" 31 | \n",
" 57 | \n",
" 26 | \n",
"
\n",
" \n",
" 8 | \n",
" Scouts | \n",
" 1st | \n",
" Sloan | \n",
" 2 | \n",
" 62 | \n",
" 60 | \n",
"
\n",
" \n",
" 9 | \n",
" Scouts | \n",
" 1st | \n",
" Piger | \n",
" 3 | \n",
" 70 | \n",
" 67 | \n",
"
\n",
" \n",
" 10 | \n",
" Scouts | \n",
" 2nd | \n",
" Riani | \n",
" 2 | \n",
" 62 | \n",
" 60 | \n",
"
\n",
" \n",
" 11 | \n",
" Scouts | \n",
" 2nd | \n",
" Ali | \n",
" 3 | \n",
" 70 | \n",
" 67 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 10,
"text": [
" regiment company name preTestScore postTestScore score_change\n",
"0 Nighthawks 1st Miller 4 25 21\n",
"1 Nighthawks 1st Jacobson 24 94 70\n",
"2 Nighthawks 2nd Ali 31 57 26\n",
"3 Nighthawks 2nd Milner 2 62 60\n",
"4 Dragoons 1st Cooze 3 70 67\n",
"5 Dragoons 1st Jacon 4 25 21\n",
"6 Dragoons 2nd Ryaner 24 94 70\n",
"7 Dragoons 2nd Sone 31 57 26\n",
"8 Scouts 1st Sloan 2 62 60\n",
"9 Scouts 1st Piger 3 70 67\n",
"10 Scouts 2nd Riani 2 62 60\n",
"11 Scouts 2nd Ali 3 70 67"
]
}
],
"prompt_number": 10
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create two columns as a function of one column"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Create a function that takes one input, x\n",
"def score_multipler_2x_and_3x(x):\n",
" # returns two things, x multiplied by 2 and x multiplied by 3\n",
" return x*2, x*3"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 21
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Create two new variables that take the two outputs of the function\n",
"df['post_score_x2'], df['post_score_x3'] = zip(*df['postTestScore'].map(score_multipler_2x_and_3x))\n",
"df"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"\n",
"
\n",
" \n",
" \n",
" | \n",
" regiment | \n",
" company | \n",
" name | \n",
" preTestScore | \n",
" postTestScore | \n",
" score_change | \n",
" post_score_x2 | \n",
" post_score_x3 | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" Nighthawks | \n",
" 1st | \n",
" Miller | \n",
" 4 | \n",
" 25 | \n",
" 21 | \n",
" 50 | \n",
" 75 | \n",
"
\n",
" \n",
" 1 | \n",
" Nighthawks | \n",
" 1st | \n",
" Jacobson | \n",
" 24 | \n",
" 94 | \n",
" 70 | \n",
" 188 | \n",
" 282 | \n",
"
\n",
" \n",
" 2 | \n",
" Nighthawks | \n",
" 2nd | \n",
" Ali | \n",
" 31 | \n",
" 57 | \n",
" 26 | \n",
" 114 | \n",
" 171 | \n",
"
\n",
" \n",
" 3 | \n",
" Nighthawks | \n",
" 2nd | \n",
" Milner | \n",
" 2 | \n",
" 62 | \n",
" 60 | \n",
" 124 | \n",
" 186 | \n",
"
\n",
" \n",
" 4 | \n",
" Dragoons | \n",
" 1st | \n",
" Cooze | \n",
" 3 | \n",
" 70 | \n",
" 67 | \n",
" 140 | \n",
" 210 | \n",
"
\n",
" \n",
" 5 | \n",
" Dragoons | \n",
" 1st | \n",
" Jacon | \n",
" 4 | \n",
" 25 | \n",
" 21 | \n",
" 50 | \n",
" 75 | \n",
"
\n",
" \n",
" 6 | \n",
" Dragoons | \n",
" 2nd | \n",
" Ryaner | \n",
" 24 | \n",
" 94 | \n",
" 70 | \n",
" 188 | \n",
" 282 | \n",
"
\n",
" \n",
" 7 | \n",
" Dragoons | \n",
" 2nd | \n",
" Sone | \n",
" 31 | \n",
" 57 | \n",
" 26 | \n",
" 114 | \n",
" 171 | \n",
"
\n",
" \n",
" 8 | \n",
" Scouts | \n",
" 1st | \n",
" Sloan | \n",
" 2 | \n",
" 62 | \n",
" 60 | \n",
" 124 | \n",
" 186 | \n",
"
\n",
" \n",
" 9 | \n",
" Scouts | \n",
" 1st | \n",
" Piger | \n",
" 3 | \n",
" 70 | \n",
" 67 | \n",
" 140 | \n",
" 210 | \n",
"
\n",
" \n",
" 10 | \n",
" Scouts | \n",
" 2nd | \n",
" Riani | \n",
" 2 | \n",
" 62 | \n",
" 60 | \n",
" 124 | \n",
" 186 | \n",
"
\n",
" \n",
" 11 | \n",
" Scouts | \n",
" 2nd | \n",
" Ali | \n",
" 3 | \n",
" 70 | \n",
" 67 | \n",
" 140 | \n",
" 210 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 20,
"text": [
" regiment company name preTestScore postTestScore score_change \\\n",
"0 Nighthawks 1st Miller 4 25 21 \n",
"1 Nighthawks 1st Jacobson 24 94 70 \n",
"2 Nighthawks 2nd Ali 31 57 26 \n",
"3 Nighthawks 2nd Milner 2 62 60 \n",
"4 Dragoons 1st Cooze 3 70 67 \n",
"5 Dragoons 1st Jacon 4 25 21 \n",
"6 Dragoons 2nd Ryaner 24 94 70 \n",
"7 Dragoons 2nd Sone 31 57 26 \n",
"8 Scouts 1st Sloan 2 62 60 \n",
"9 Scouts 1st Piger 3 70 67 \n",
"10 Scouts 2nd Riani 2 62 60 \n",
"11 Scouts 2nd Ali 3 70 67 \n",
"\n",
" post_score_x2 post_score_x3 \n",
"0 50 75 \n",
"1 188 282 \n",
"2 114 171 \n",
"3 124 186 \n",
"4 140 210 \n",
"5 50 75 \n",
"6 188 282 \n",
"7 114 171 \n",
"8 124 186 \n",
"9 140 210 \n",
"10 124 186 \n",
"11 140 210 "
]
}
],
"prompt_number": 20
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}