Created
June 22, 2016 16:28
-
-
Save TaylorOshan/ad43047fd242ad81fa9e184e553b0f7f 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": "code", | |
"execution_count": 34, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"from scipy import sparse as sp\n", | |
"import numpy as np\n", | |
"\n", | |
"def spcategorical(n_cat_ids):\n", | |
" '''\n", | |
" Returns a dummy matrix given an array of categorical variables.\n", | |
" Parameters\n", | |
" ----------\n", | |
" n_cat_ids : array\n", | |
" A 1d vector of the categorical labels for n observations.\n", | |
"\n", | |
" Returns\n", | |
" --------\n", | |
" dummy : array\n", | |
" A sparse matrix of dummy (indicator/binary) variables for the\n", | |
" categorical data. \n", | |
"\n", | |
" '''\n", | |
" if np.squeeze(n_cat_ids).ndim == 1:\n", | |
" cat_set = np.unique(n_cat_ids)\n", | |
" n = len(n_cat_ids)\n", | |
" index = [np.where(cat_set == id)[0].tolist()[0] for id in n_cat_ids] #This list comprehension is likely \n", | |
" #the most intense part of the algorithm\n", | |
" indptr = np.arange(n+1, dtype=int) \n", | |
" return sp.csr_matrix((np.ones(n), index, indptr))\n", | |
" else:\n", | |
" raise IndexError(\"The index %s is not understood\" % col)\n", | |
"\n", | |
"#If the variable, n_cat_ids, is already composed of integers and the integers are the n x 1 vector of\n", | |
"#origins or destinations in OD pairs for which w ewant to build fixed effects then there is no need to \n", | |
"#create the index variable, which probably takes the most time within this function. Instead n_cat_ids can\n", | |
"#passed directly to the csr matrix constructor and some speed-ups can be achieved. In the case where the\n", | |
"#origin/destination ids are not integers but are strings a speed-up may be possible by alterign the algorithm\n", | |
"#so that the index is build in chunks (say each origin/destination) rather than for each row of of the n x 1\n", | |
"#n_cat_ids array as is done in creating the index variable." | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 35, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"x = np.random.randint(1,10, 25)\n", | |
"#x = ['a', 'b', 'a', 'c', 'a', 'a', 'b', 'a', 'c', 'a']" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 36, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"10000 loops, best of 3: 124 µs per loop\n" | |
] | |
} | |
], | |
"source": [ | |
"%timeit a = spcategorical(x)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 37, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"<10x3 sparse matrix of type '<type 'numpy.float64'>'\n", | |
"\twith 10 stored elements in Compressed Sparse Row format>" | |
] | |
}, | |
"execution_count": 37, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"a" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"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": "2.7.9" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment