Created
July 31, 2015 22:29
-
-
Save anonymous/872f9431de3e37b65682 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# Question: How should I transform multiple key/value columns in a scikit-learn pipeline?\n", | |
"\n", | |
"See http://stackoverflow.com/questions/31749812/how-should-i-transform-multiple-key-value-columns-in-a-scikit-learn-pipeline/" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Input data:" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 1, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
" k1 v1 k2 v2\n", | |
"0 a 1 b 2\n", | |
"1 b 2 c 3\n" | |
] | |
} | |
], | |
"source": [ | |
"import pandas as pd\n", | |
"\n", | |
"D = pd.DataFrame([ ['a', 1, 'b', 2], ['b', 2, 'c', 3]], columns = ['k1', 'v1', 'k2', 'v2'])\n", | |
"print(D)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"This is the type of output data that is required:" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[{'a': 1, 'b': 2}, {'c': 3, 'b': 2}]\n" | |
] | |
}, | |
{ | |
"data": { | |
"text/plain": [ | |
"array([[ 1., 2., 0.],\n", | |
" [ 0., 2., 3.]])" | |
] | |
}, | |
"execution_count": 2, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"from sklearn.feature_extraction import DictVectorizer\n", | |
"\n", | |
"row1 = {'a':1, 'b':2}\n", | |
"row2 = {'b':2, 'c':3}\n", | |
"data = [row1, row2]\n", | |
"print(data)\n", | |
"\n", | |
"DictVectorizer( sparse=False ).fit_transform(data)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"collapsed": true | |
}, | |
"source": [ | |
"# Solution\n", | |
"\n", | |
"Courtesy of [Mike](http://stackoverflow.com/users/2055368/mike): http://stackoverflow.com/a/31752733/1185562 and extended into a general pipeline transformer.\n", | |
"\n", | |
"Here is the transformer:" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"from sklearn.base import TransformerMixin\n", | |
"from sklearn.pipeline import Pipeline, FeatureUnion\n", | |
"\n", | |
"class KVExtractor(TransformerMixin):\n", | |
" def __init__(self, kvpairs):\n", | |
" self.kpairs = kvpairs\n", | |
" \n", | |
" def transform(self, X, *_):\n", | |
" result = []\n", | |
" for index, rowdata in X.iterrows():\n", | |
" rowdict = {}\n", | |
" for kvp in self.kpairs:\n", | |
" rowdict.update( { rowdata[ kvp[0] ]: rowdata[ kvp[1] ] } )\n", | |
" result.append(rowdict)\n", | |
" return result\n", | |
"\n", | |
" def fit(self, *_):\n", | |
" return self" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Lets try it out:" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[{'a': 1, 'b': 2}, {'b': 2, 'c': 3}]" | |
] | |
}, | |
"execution_count": 4, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"kvpairs = [ ['k1', 'v1'], ['k2', 'v2'] ]\n", | |
"KVExtractor( kvpairs ).transform(D)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Now try it out in a pipeline with `DictVectorizer`:" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
" k1 v1 k2 v2\n", | |
"0 a 1 b 2\n", | |
"1 b 2 c 3\n", | |
"(2, 3)\n", | |
"[[ 1. 2. 0.]\n", | |
" [ 0. 2. 3.]]\n" | |
] | |
} | |
], | |
"source": [ | |
"pipeline = Pipeline(\n", | |
" [( 'kv', KVExtractor( kvpairs ) )] +\n", | |
" [( 'dv', DictVectorizer(sparse=False) )] +\n", | |
" []\n", | |
")\n", | |
"print(D)\n", | |
"A=pipeline.fit_transform(D)\n", | |
"print A.shape\n", | |
"print A" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"Perfect!" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 2", | |
"language": "python", | |
"name": "python2" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 2 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython2", | |
"version": "2.7.10" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment