Skip to content

Instantly share code, notes, and snippets.

@satouy

satouy/Take-R-pandas-dataframe-original

Created October 18, 2014 14:05
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/cb1dd4498da9866577aa to your computer and use it in GitHub Desktop.
Save satouy/cb1dd4498da9866577aa to your computer and use it in GitHub Desktop.
Download ZIP
original Take-R-pandas-dataframe
Raw
Take-R-pandas-dataframe-original
{
"metadata": {
"name": "",
"signature": "sha256:b71d98c5ecb07776f4d14e7508277b828a788395e0fc1bba70ebe0a839ae6f78"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "heading",
"level": 1,
"metadata": {},
"source": [
"sage/R\u3068Pandas(Sage)\u3067\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306e\u76f8\u4e92\u5909\u63db (\u7af9\u672c\u6c0f)"
]
},
{
"cell_type": "raw",
"metadata": {},
"source": [
"http://www.pwv.co.jp/~take/TakeWiki/index.php?sage%2FR\u3068Pandas%28Sage%29\u3067\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306e\u76f8\u4e92\u5909\u63db"
]
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"made by Y.Sato Sat 18 Oct, 2014"
]
},
{
"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": "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": [
"%load_ext sage"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 1
},
{
"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\n",
"# R\u3067\u306fjsonlite\u30d1\u30c3\u30b1\u30fc\u30b8\u3092\u4f7f\u7528\n",
"r('library(jsonlite)')\n",
"# \u4f8b\u3068\u3057\u3066R Graphic Cookbook\u306e\u30c7\u30fc\u30bf\u3092\u4f7f\u7528\n",
"#r(\"install.packages('gcookbook')\")\n",
"r('library(gcookbook)')"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 2,
"text": [
"[1] \"gcookbook\" \"jsonlite\" \"stats\" \"graphics\" \"grDevices\" \"utils\" \"datasets\" \"methods\" \n",
"[9] \"base\" "
]
}
],
"prompt_number": 2
},
{
"cell_type": "heading",
"level": 2,
"metadata": {},
"source": [
"R\u304b\u3089Pandas\u3078\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u5909\u63db"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# R\u304b\u3089JSON\u5f62\u5f0f\u3067\u30c7\u30fc\u30bf\u3092\u6301\u3063\u3066\u304f\u308b\u65b9\u6cd5\n",
"# \u4f8b\u3068\u3057\u3066\u3001gcookbook\u306e\u30b5\u30f3\u30d7\u30eb\u30c7\u30fc\u30bf\u3092R\u304b\u3089\u53d6\u5f97\u3059\u308b\n",
"test_json = r('toJSON(heightweight, pretty=FALSE)')\n",
"# heightweight = pd.read_json(sageobj(test_json)); heightweight.head()\n",
"heightweight = pd.read_json(sageobj(test_json)['DATA']); 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>ageMonth</th>\n",
" <th>ageYear</th>\n",
" <th>heightIn</th>\n",
" <th>sex</th>\n",
" <th>weightLb</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td> 143</td>\n",
" <td> 11.92</td>\n",
" <td> 56.3</td>\n",
" <td> f</td>\n",
" <td> 85.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td> 155</td>\n",
" <td> 12.92</td>\n",
" <td> 62.3</td>\n",
" <td> f</td>\n",
" <td> 105.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td> 153</td>\n",
" <td> 12.75</td>\n",
" <td> 63.3</td>\n",
" <td> f</td>\n",
" <td> 108.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td> 161</td>\n",
" <td> 13.42</td>\n",
" <td> 59.0</td>\n",
" <td> f</td>\n",
" <td> 92.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td> 191</td>\n",
" <td> 15.92</td>\n",
" <td> 62.5</td>\n",
" <td> f</td>\n",
" <td> 112.5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"metadata": {},
"output_type": "pyout",
"prompt_number": 3,
"text": [
" ageMonth ageYear heightIn sex weightLb\n",
"0 143 11.92 56.3 f 85.0\n",
"1 155 12.92 62.3 f 105.0\n",
"2 153 12.75 63.3 f 108.0\n",
"3 161 13.42 59.0 f 92.0\n",
"4 191 15.92 62.5 f 112.5"
]
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# sageobj(test_json);"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# sageobj(test_json)['DATA'];"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 5
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"\u95a2\u6570\u306b\u307e\u3068\u3081\u308b"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# \u3053\u308c\u3092\u95a2\u6570\u306b\u307e\u3068\u3081\u308b\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",
"def RDf2PandaDf(name):\n",
" json_str = r('toJSON(%s, pretty=FALSE)' % name)\n",
" return pd.read_json(sageobj(json_str)['DATA'])"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 5
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"RDf2PandasDf\u306e\u4f7f\u7528\u4f8b"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"print RDf2PandaDf('heightweight').head()"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" ageMonth ageYear heightIn sex weightLb\n",
"0 143 11.92 56.3 f 85.0\n",
"1 155 12.92 62.3 f 105.0\n",
"2 153 12.75 63.3 f 108.0\n",
"3 161 13.42 59.0 f 92.0\n",
"4 191 15.92 62.5 f 112.5\n"
]
}
],
"prompt_number": 6
},
{
"cell_type": "heading",
"level": 2,
"metadata": {},
"source": [
"Pandas\u304b\u3089R\u3078\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306b\u5909\u63db"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"# \u540c\u69d8\u306b\u95a2\u6570\u306b\u307e\u3068\u3081\u308b\n",
"# pandas\u306e\u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3092R\u306b\u6e21\u3059\n",
"def PandaDf2RDf(df, name):\n",
" l = [dict(zip(df.columns, x)) for x in df.values.tolist()]\n",
" json_str = str(l)\n",
" json_str = json_str.replace(\"'\", '\\\\\"')\n",
" r('%s <- fromJSON(\"%s\")' % (name, json_str))"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 9
},
{
"cell_type": "heading",
"level": 3,
"metadata": {},
"source": [
"PandaDf2RDf\u306e\u4f7f\u7528\u4f8b"
]
},
{
"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": 10,
"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": 10
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"PandaDf2RDf(df, \"a\")\n",
"r('a')"
],
"language": "python",
"metadata": {},
"outputs": [
{
"metadata": {},
"output_type": "pyout",
"prompt_number": 11,
"text": [
" age sex\n",
"1 20 F\n",
"2 22 M\n",
"3 25 M\n",
"4 27 M\n",
"5 21 F\n",
"6 23 M\n",
"7 37 F\n",
"8 31 M\n",
"9 61 F\n",
"10 45 M\n",
"11 41 F\n",
"12 32 M"
]
}
],
"prompt_number": 11
},
{
"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