Skip to content

Instantly share code, notes, and snippets.

@satouy

satouy/Take-r-pandas-dataframe

Created October 12, 2014 04:29
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save satouy/6583b0993acf7be90388 to your computer and use it in GitHub Desktop.
Save satouy/6583b0993acf7be90388 to your computer and use it in GitHub Desktop.
Download ZIP
Take-r-pandas-dataframe
Raw
Take-r-pandas-dataframe
{
"metadata": {
"name": "",
"signature": "sha256:fdcdfed4c6430cca0d911e425595a5d8b5cfc60a945170170733883e029ab847"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "heading",
"level": 1,
"metadata": {},
"source": [
"R\u3068Pandas(Sage)\u3067\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306e\u76f8\u4e92\u5909\u63db"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"%pylab inline"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"Populating the interactive namespace from numpy and matplotlib\n"
]
}
],
"prompt_number": 1
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"\u30c7\u30fc\u30bf\u5909\u63db\u3067\u4f7f\u7528\u3059\u308b\u30d1\u30c3\u30b1\u30fc\u30b8\u3068\u30e9\u30a4\u30d6\u30e9\u30ea"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# R\u3068Pandas\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3092\u76f8\u4e92\u306b\u5909\u63db\u3059\u308b\u65b9\u6cd5\n",
"# Sage\u3067\u306f\u3001numpy\u3068pandas\u3092\u30a4\u30f3\u30dd\u30fc\u30c8\n",
"import pandas as pd\n",
"import numpy as np"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"import rpy2.robjects as robjects\n",
"ro = robjects.r"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# \u4f8b\u3068\u3057\u3066R Graphic Cookbook\u306e\u30c7\u30fc\u30bf\u3092\u4f7f\u7528\n",
"#ro(\"install.packages('gcookbook')\")\n",
"ro('library(gcookbook)')"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 4,
"text": [
"<StrVector - Python:0x1131c47e8 / R:0x7fe1fe23eff8>\n",
"['gcoo..., 'tools', 'stats', ..., 'data..., 'meth..., 'base']"
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# R\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3092pandas\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u5909\u63db\u3059\u308b\n",
"import pandas.rpy.common as com\n",
"\n",
"# heightweight = com.load_data('heightweight') \n",
"# R\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3092pandas\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u5909\u63db\u3059\u308b\n",
"# r_dataframe = com.convert_to_r_dataframe(df)\n",
"# pandas\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3092R\u306b\u6e21\u3059"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 9
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"from sage.all import *"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 11
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"R\u304b\u3089Pandas\u3078\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u5909\u63db "
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# print RDf2PandaDf('heightweight').head()"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"heightweight = com.load_data('heightweight')\n",
"heightweight.head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sex</th>\n",
" <th>ageYear</th>\n",
" <th>ageMonth</th>\n",
" <th>heightIn</th>\n",
" <th>weightLb</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> f</td>\n",
" <td> 11.92</td>\n",
" <td> 143</td>\n",
" <td> 56.3</td>\n",
" <td> 85.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> f</td>\n",
" <td> 12.92</td>\n",
" <td> 155</td>\n",
" <td> 62.3</td>\n",
" <td> 105.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> f</td>\n",
" <td> 12.75</td>\n",
" <td> 153</td>\n",
" <td> 63.3</td>\n",
" <td> 108.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> f</td>\n",
" <td> 13.42</td>\n",
" <td> 161</td>\n",
" <td> 59.0</td>\n",
" <td> 92.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td> f</td>\n",
" <td> 15.92</td>\n",
" <td> 191</td>\n",
" <td> 62.5</td>\n",
" <td> 112.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 12,
"text": [
" sex ageYear ageMonth heightIn weightLb\n",
"1 f 11.92 143 56.3 85.0\n",
"2 f 12.92 155 62.3 105.0\n",
"3 f 12.75 153 63.3 108.0\n",
"4 f 13.42 161 59.0 92.0\n",
"5 f 15.92 191 62.5 112.5"
]
}
],
"prompt_number": 12
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"Pandas\u304b\u3089R\u3078\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u5909\u63db "
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# Pandas\u306e\u30c7\u30fc\u30bf\u3092R\u306b\u6e21\u3059\n",
"age = [20, 22, 25, 27, 21, 23, 37, 31, 61, 45, 41, 32]\n",
"sex = ['F', 'M', 'M', 'M', 'F', 'M', 'F', 'M', 'F', 'M', 'F', 'M']\n",
"df = pd.DataFrame({'age': age, 'sex': sex}); df.head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>sex</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 20</td>\n",
" <td> F</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 22</td>\n",
" <td> M</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 25</td>\n",
" <td> M</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 27</td>\n",
" <td> M</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 21</td>\n",
" <td> F</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 13,
"text": [
" age sex\n",
"0 20 F\n",
"1 22 M\n",
"2 25 M\n",
"3 27 M\n",
"4 21 F"
]
}
],
"prompt_number": 13
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# PandaDf2RDf(df, \"a\")\n",
"# r('a')"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"r_dataframe = com.convert_to_r_dataframe(df)\n",
"print(type(r_dataframe))"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"<class 'rpy2.robjects.vectors.DataFrame'>\n"
]
}
],
"prompt_number": 14
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"print(r_dataframe)"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" age sex\n",
"0 20 F\n",
"1 22 M\n",
"2 25 M\n",
"3 27 M\n",
"4 21 F\n",
"5 23 M\n",
"6 37 F\n",
"7 31 M\n",
"8 61 F\n",
"9 45 M\n",
"10 41 F\n",
"11 32 M\n",
"\n"
]
}
],
"prompt_number": 16
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment