def linear_model(x_train, x_test, y_train, y_test):
G = linear_regression(x_train, y_train)
y_pred, rmse, mae, r2 = regression_predictor(G, x_test, y_test)
val = cross_validation_regressor(model, x_train, y_train)
stats = pd.DataFrame([(val, mae, rmse, r2)],
columns=['cross_val', 'rmse', 'mae', 'r2'])
return G, y_pred, stats
def linear_model(x_train, x_test, y_train, y_test):
model = linear_regression(x_train, y_train)
val = cross_validation_regressor(model, x_train, y_train)
y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
rmse = (mse)
d = {'0': val, '1': mae, '2': rmse, '3': r2}
stats = pd.DataFrame(d, index=d.keys())
stats.reset_index(drop=True, inplace=True)
return model, y_pred, stats
def linear_model(x_train, x_test, y_train, y_test):
model = linear_regression(x_train, y_train)
val = cross_validation_regressor(model, x_train, y_train)
y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
stats = pd.DataFrame(np.array([val, mae, mse, r2]).reshape(1, 4),
columns=['v', 'm', 's', 'r'],
index=[0])
return model, y_pred, stats
def linear_model(x_train, x_test, y_train, y_test):
model = linear_regression(x_train, y_train)
val = cross_validation_regressor(model, x_train, y_train)
y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
stats = pd.DataFrame()
stats['CV_score'] = val, val
stats['MAE'] = mae
stats['MSE'] = mse
stats['r2'] = r2
#stats.set_index('Name',inplace=True)
return model, y_pred, stats
def linear_model(x_train, x_test, y_train, y_test):
model = linear_regression(x_train, y_train)
val = cross_validation_regressor(model, x_train, y_train)
y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
d = {
'cross_validation': [val],
'rmse': [mse],
'mae': [mae],
'rsquared': [r2]
}
stats = pd.DataFrame(data=d)
return model, y_pred, stats
def linear_model(x_train, x_test, y_train, y_test):
G = linear_regression(x_train, y_train)
c_val = cross_validation_regressor(G, x_train, y_train)
y_pred, mse, mae, r2 = regression_predictor(G, x_test, y_test)
my_dict = {'c_val': c_val, 'mse': mse, 'mae': mae, 'r2': r2}
stats = pd.DataFrame(my_dict, index=[0])
return G, y_pred, stats
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
from greyatomlib.multivariate_regression_project.q05_linear_regression_model.build import linear_regression
from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor
df = load_data('data/student-mat.csv')
x_train, x_test, y_train, y_test = split_dataset(df)
x_train, x_test = label_encode(x_train, x_test)
model = linear_regression(x_train, y_train)
val = cross_validation_regressor(model, x_train, y_train)
y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
class Test_regression_predictor(TestCase):
def test_args(self): # Input parameters tests
args = getfullargspec(regression_predictor)
self.assertEqual(len(args[0]), 3,
"Expected arguments %d, Given %d" % (2, len(args[0])))
def test_y_pred_type(self):
self.assertIsInstance(
y_pred, np.ndarray,
"Expected data type for 'return value' is float you are returning\
def linear_model(x_train, x_test, y_train, y_test):
G = linear_regression(x_train, y_train)
stats = pd.DataFrame([(val,mae,mse,r2)], columns = ['cross_val','rmse','mae','r2'])
return G, y_pred, stats
import matplotlib.pyplot as plt
import pylab
import scipy.stats as stats
from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
from greyatomlib.multivariate_regression_project.q05_linear_regression_model.build import linear_regression
from greyatomlib.multivariate_regression_project.q07_regression_pred.build import regression_predictor
#from greyatomlib.linear_regression.q05_residuals.build import residuals
#from greyatomlib.multivariate_regression_project.q06_cross_validation import cross_validation_regressor
from sklearn.linear_model import LinearRegression
from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
df = load_data('data/student-mat.csv')
x_train, x_test, y_train, y_test = split_dataset(df)
x_train, x_test = label_encode(x_train, x_test)
lin_reg = linear_regression(x_train, y_train)
y_pred, _, __, ___ = regression_predictor(lin_reg, x_test, y_test)
def plot_residuals(y_test, y_pred, name):
error_residuals = y_test - y_pred
stats.probplot(error_residuals, dist="norm", plot=pylab)
return pylab.show()
#plot_residuals(y_test,y_pred,'name')
