def test_regression_line_housing_no_libs():
"""
Testing 2 variable solution for HW1 prob 2
"""
print('Testing linear regression with 2 columns')
test, train = utils.load_and_normalize_housing_set()
print str(len(train)) + " # in training set <--> # in test " + str(len(test))
columns = train.columns[:-1]
Y_fit = mystats.linear_regression_points(train[columns[0]], train['MEDV'])
#for i, col in enumerate(columns):
print 'Y_fit'
print Y_fit
for i in range(0, len(Y_fit)):
print str(Y_fit[i]) + ' -- ' + str(train['MEDV'][i])
print train[columns[0]]
#myplot.points([train[columns[0]], train['MEDV']])
#myplot.points([train[columns[0]], list(Y_fit[0])])
myplot.fit_v_point([train[columns[0]], train['MEDV'], list(Y_fit[0] + Y_fit[-1])])
col_MSE = {}
print columns[0]
i = 0
col = 'CRIM'
col_fit = Y_fit[i] + Y_fit[-1]
col_MSE[col] = mystats.compute_MSE_arrays(col_fit, train['MEDV'])
print col_MSE
def testScale():
test, train = utils.load_and_normalize_housing_set()
df_full = pd.DataFrame(train)
df = utils.train_subset(df_full, ['CRIM', 'TAX', 'B', 'MEDV'], n=10)
w = []
for i in range(0,len(df['TAX'])):
w.append(random.random())
scaled = utils.scale(w, min(df['TAX']), max(df['TAX']))
plot.fit_v_point([w, df['MEDV'], scaled])