def testGradient(): # Great success with subset
test, train = utils.load_and_normalize_housing_set()
df_full = pd.DataFrame(train)
subset_size = 100
df = utils.train_subset(df_full, ['CRIM', 'TAX', 'B', 'MEDV'], n=subset_size)
dfX = pd.DataFrame([df['CRIM'], df['TAX']]).transpose()
print len(dfX)
print dfX
#raw_input()
fit = gd.gradient(dfX, df['MEDV'].head(subset_size), .5, max_iterations=300)
print 'read v fit'
print len(dfX)
print df['MEDV'].head(10)
print fit
data = gd.add_col(gd.pandas_to_data(dfX), 1)
print np.dot(data, fit)
def k_folds_linear_gd(df_test, df_train, Y):
k = 10
df_test = gd.pandas_to_data(df_test)
k_folds = partition_folds(df_test, k)
model = Model_w()
theta = None
for ki in range(k - 1):
print "k fold is {}".format(k)
data, truth = get_data_and_truth(k_folds[ki])
binary = True
model.update(gd.gradient(data, np.array(truth), 0.00001, max_iterations=5, binary=binary))
print model.w
if theta is None:
theta, max_acc = get_best_theta(data, truth, model.w, binary, False)
predict = gd.predict_data(data, model.w, binary, False, theta)
error = mystats.get_error(predict, truth, binary)
print "Error for fold {} is {} with theta = {}".format(k, error, theta)
test, truth = get_data_and_truth(k_folds[k - 1])
predict = gd.predict_data(test, model.w, binary, False, theta)
test_error = mystats.get_error(predict, truth, binary)
return [error, test_error]
