Create Sparse Dummies

sparse_dummies.py

# 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")