Last active
January 16, 2016 22:56
-
-
Save walterreade/1e7dec8682e044ae9ed9 to your computer and use it in GitHub Desktop.
Create Sparse Dummies
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
# http://www.dataiku.com/blog/2015/08/24/xgboost_and_dss.html | |
from pandas.core.categorical import Categorical | |
from scipy.sparse import csr_matrix | |
import numpy as np | |
def sparse_dummies(categorical_values): | |
categories = Categorical.from_array(categorical_values) | |
N = len(categorical_values) | |
row_numbers = np.arange(N, dtype=np.int) | |
ones = np.ones((N,)) | |
return csr_matrix( (ones, (row_numbers, categories.codes)) ) | |
sparse_dummies(df.VAR_0001) | |
# Concatenate with other dummies | |
from scipy.sparse import hstack | |
cat1 = sparse_dummies(df.VAR_0001) | |
cat2 = sparse_dummies(df.VAR_0002) | |
hstack((cat1,cat2), format="csr") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment