def test_tweedie_score(regression_data, power, link):
"""Test that GLM score equals d2_tweedie_score for Tweedie losses."""
X, y = regression_data
# make y positive
y = np.abs(y) + 1.0
glm = TweedieRegressor(power=power, link=link).fit(X, y)
assert glm.score(X, y) == pytest.approx(
d2_tweedie_score(y, glm.predict(X), power=power))
def sk_tweedie_regression(X_train,
X_test,
y_train,
y_test,
set_model='linear'):
if set_model == 'Poisson':
reg = TweedieRegressor(
alpha=0,
power=1, # Poisson distribution
link='log',
fit_intercept=False,
max_iter=300)
elif set_model == 'linear':
reg = TweedieRegressor(
alpha=0,
power=0, # Normal distribution
link='identity',
fit_intercept=False,
max_iter=300)
else:
print('Set the correct name.')
return
reg.fit(X_train, y_train)
print('score: ', reg.score(X_test, y_test))
y_hat = reg.predict(X)
fig = plt.figure(figsize=(6.0, 6.0))
plt.plot(X, y, 'o')
plt.plot(X, y_hat, '*', color='r')
plt.xlabel('x (total_bill)')
plt.ylabel('y (tips)')
plt.xlim(0, 60)
plt.ylim(0, 12)
plt.show()
#%% from sklearn.linear_model import TweedieRegressor X = np.array(x).reshape(-1,1) Y = np.array(y) pr = TweedieRegressor(power = 1, alpha=0, fit_intercept=True) y_pred_pr = pr.fit(X, Y).predict(X) fig, axes = utils.plot_make(size_length=5) sns.scatterplot(data = sc_vs_quickness_group_fill, x = "sc_LR_mean", y= "inverse_quickness", linewidth=0, s=100) sns.lineplot(x = X.flatten(), y = y_pred_pr) pr.score(X, Y) #% X2 = sm.add_constant(X) glm = sm.GLM(Y, X2, family=sm.families.Tweedie()) glm_fit = glm.fit() print(glm_fit.summary()) Y2 = glm.predict(glm_fit.params) fig, axes = utils.plot_make(size_length=5) sns.scatterplot(data = sc_vs_quickness_group_fill, x = "sc_LR_mean", y= "inverse_quickness", linewidth=0, s=100) sns.lineplot(x = X.flatten(), y = Y2)