"""
import numpy as np
from util import read_file
import ffs
import tags
from logistic_regression import LogisticRegression
"""Import a small sample dataset and run calcgis. Export the output to a csv."""
data_sample, labels_sample = read_file('sample')
lr = LogisticRegression(method="collins", max_iters=1)
labels_proc = lr.preproclabels(labels_sample)
i = int(np.random.rand() * len(data_sample))
n = len(data_sample[i])
ws = np.random.rand(ffs.numJ)
x = data_sample[i]
y = labels_proc[i]
#lr.calcgis(ws, x, n)
print data_sample[i]
print labels_sample[i],y
print ws
lr.calcAs(x, n)
print "As",lr.As
# read data and split training data into training and validation sets
data_train, labels_train = read_file('training')
#assert len(data_train[0]) == len(labels_train[0])
#assert len(data_train[200]) == len(labels_train[200])
data_test, labels_test = read_file('test')
#assert len(data_test[0]) == len(data_test[0])
#assert len(data_test[200]) == len(data_test[200])
return data_train, data_test, labels_train, labels_test
def runML(meth, itrs, data_train, data_test, labels_train, labels_test):
print meth,datetime.now().time()
model = LogisticRegression(method=meth,max_iters=itrs)
model.fit(data_train, labels_train)
print datetime.now().time()
prediction = model.predict(data_test)
tagscores = LogisticRegression.tagAccuracy(labels_test, prediction)
score = np.mean(tagscores)
print " score tags: mean: {}, max: {}, min: {}".format(score,max(tagscores),min(tagscores))
print " error rate: {}".format(1 - score)
print datetime.now().time()
if __name__ == "__main__":
data_train, data_test, labels_train, labels_test = importData()
labels_test=LogisticRegression.preproclabels(labels_test)
runML("collins",10,data_train, data_test, labels_train, labels_test)
runML("cd",10,data_train, data_test, labels_train, labels_test)
