#!/home/hadoop/.virtualenvs/env1/bin/python
__author__ = 'chunk'

from common import *

from mdata import MSR, CV
from mmodel import SVM
from mspark import SC


timer = Timer()


def test_spark_io():
    timer.mark()
    dcv = CV.DataCV()
    X, Y = dcv.load_data(mode='spark')
    # X, Y = dcv.load_data()
    timer.report()


def test_spark_ml():
    sparker = SC.Sparker(host='HPC-server', appname='ImageCV', master='spark://HPC-server:7077')
    dcv = CV.DataCV()
    X, Y = dcv.load_data()
    sparker.train_svm(X, Y)
    for path, subdirs, files in os.walk('data/467/'):
        for name in files:
            imgpath = os.path.join(path, name)
            feat = dcv.get_feat(imgpath, 'hog')
            print name, sparker.predict_svm(feat)


if __name__ == '__main__':
    # test_spark_io()
    test_spark_ml()
    print 'helllo'