def run_lasso_model(X,y):
X_train, X_test, y_train, y_test = train_test_split(X, y)
standardizer = utils.XyScaler()
standardizer.fit(X_train,y_train)
X_train_std, y_train_std = standardizer.transform(X_train, y_train)
X_test_std, y_test_std = standardizer.transform(X_test, y_test)
lasso = LassoCV(alphas = np.logspace(-2,4,num=250),cv=10)
lasso.fit(X_train_std,y_train_std)
y_hats_std = lasso.predict(X_test_std)
X_test, y_hats = standardizer.inverse_transform(X_test_std,y_hats_std)
lasso_score = r2_score(y_test_std,y_hats_std)
return lasso, lasso_score, y_hats, y_test, X_test
def run_ridge_model(X,y):
X_train, X_test, y_train, y_test = train_test_split(X, y)
standardizer = utils.XyScaler()
standardizer.fit(X_train,y_train)
X_train_std, y_train_std = standardizer.transform(X_train, y_train)
X_test_std, y_test_std = standardizer.transform(X_test, y_test)
ridge = RidgeCV(alphas = np.logspace(-2,4,num=250),cv=10)
ridge.fit(X_train_std,y_train_std)
y_hats_std = ridge.predict(X_test_std)
X_test, y_hats = standardizer.inverse_transform(X_test_std,y_hats_std)
ridge_score = r2_score(y_test_std,y_hats_std)
return ridge, ridge_score, y_hats, y_test, X_test
def make_qqplot_route():
boulders, routes = grade_model.import_data()
route = grade_model.drop_columns_grades(routes)
X_train1, y_train1, X_hold, y_hold = grade_model.split_data_grades(
route, 'usa_routes')
X_train2, X_test, y_train2, y_test = train_test_split(X_train1, y_train1)
standardizer = utils.XyScaler()
standardizer.fit(X_train2, y_train2)
X_train_std, y_train_std = standardizer.transform(X_train2, y_train2)
X_test_std, y_test_std = standardizer.transform(X_test, y_test)
X_hold_std, y_hold_std = standardizer.transform(X_hold, y_hold)
ridge = RidgeCV(alphas=np.logspace(-2, 4, num=250), cv=10)
ridge.fit(X_train_std, y_train_std)
residuals = y_hold_std - ridge.predict(X_hold_std)
sm.graphics.qqplot(residuals)
plt.savefig('images/routes_qqplot.png', fit=True, line='45')
plt.show()
def test_model_on_hold(X_train,y_train,X_hold,y_hold,model,alpha,title,filename):
standardizer = utils.XyScaler()
standardizer.fit(X_train,y_train)
X_train_std, y_train_std = standardizer.transform(X_train, y_train)
X_hold_std, y_hold_std = standardizer.transform(X_hold, y_hold)
final_model = model(alpha)
final_model.fit(X_train_std,y_train_std)
y_pred_std = final_model.predict(X_hold_std)
X_hold, y_pred = standardizer.inverse_transform(X_hold_std,y_pred_std)
plot_model_predictions(y_hold, y_pred, title, filename)
final_score = final_model.score(X_hold_std,y_hold_std)
final_mse_std = mse(y_hold_std,y_pred_std)
final_mse = mse(y_hold,y_pred)
print('Final R2 score: {}'.format(final_score))
print('Final standardized RMSE: {}'.format(np.sqrt(final_mse_std)))
print('Final RMSE: {}'.format(np.sqrt(final_mse)))
return final_score, final_mse
def __init__(self, X, y):
self.X = X
self.y = y
self.scaler = ut.XyScaler()