sparselr-predict.py

#! /usr/bin/env python

import sys

from sklearn.externals import joblib
from scipy import sparse as sp

MAX_FEATURES=16777216

def predict(sgd, line):
    features = sp.lil_matrix((1,MAX_FEATURES),)
    for f in line.split(','):
       features[0,int(f)] = 1.0
    predicted = sgd.predict_proba(features)
    print predicted[0][1]

def main():
    if len(sys.argv) != 3:
        print >> sys.stderr, \
            "Usage: ./sgd-predict <modelfile> <testfile>"
        exit(-1)

    sgd = joblib.load(sys.argv[1])
    f = open(sys.argv[2])
    line = f.readline()
    while(line):
        predict(sgd, line)
        line = f.readline()

if __name__ == '__main__':
    main()