def AB_random_search(X_train, y_train):
model = AdaBoostRegressor(random_state=0)
params = {
'n_estimators': np.arange(10, 500, 10),
'learning_rate': np.arange(0.005, 0.5, 0.001),
}
cv_inner = KFold(n_splits=3, shuffle=True, random_state=1)
search = RandomizedSearchCV(model,
params,
cv=cv_inner,
scoring='neg_mean_absolute_error',
verbose=0,
n_jobs=-1,
n_iter=100,
refit=False,
random_state=999)
search.fit(X_train, y_train)
model.set_params(**search.best_params_)
print(search.best_params_)
return model
def ab_cv(cv_outer, data):
MAE_results = []
RMSE_results = []
MedAE_results = []
r2_results = []
model_params = []
for train_index, test_index in cv_outer:
X_train, y_train = data.iloc[train_index,
6:].values, data.iloc[train_index,
3].values
X_test, y_test = data.iloc[test_index,
6:].values, data.iloc[test_index, 3].values
cv_inner = KFold(n_splits=3, shuffle=True, random_state=1)
model = AdaBoostRegressor(random_state=0)
params = {
'n_estimators': np.arange(10, 500, 10),
'learning_rate': np.arange(0.005, 0.5, 0.001),
}
search = RandomizedSearchCV(model,
params,
cv=cv_inner,
scoring='neg_mean_absolute_error',
verbose=0,
n_jobs=-1,
n_iter=100,
refit=False,
random_state=999)
search.fit(X_train, y_train)
model_params.append(search.best_params_)
model.set_params(**search.best_params_)
model.fit(X_train, y_train)
print(search.best_params_)
y_pred = model.predict(X_test)
mae = MAE(y_test, y_pred)
MAE_results.append(mae)
rmse = mean_squared_error(y_test, y_pred, squared=False)
RMSE_results.append(rmse)
med = median_absolute_error(y_test, y_pred)
MedAE_results.append(med)
r2 = r2_score(y_test, y_pred)
r2_results.append(r2)
return MAE_results, RMSE_results, MedAE_results, r2_results, model_params
def train_and_save_final_model(X, y, X_train, y_train, params,
save_model_file_path, test_data):
adbr = AdaBoostRegressor(random_state=0)
adbr.set_params(**params)
if test_data == None:
adbr.fit(X_train, y_train)
else:
adbr.fit(X, y)
#save model
model_file_path = save_model_file_path + 'adbr.sav'
pickle.dump(adbr, open(model_file_path, 'wb'))
def predict_validation(model_params, X_train, y_train, X_valid, y_valid):
predictions = []
for param in model_params:
model = AdaBoostRegressor(random_state=0)
model.set_params(**param)
model.fit(X_train, y_train)
y_pred = model.predict(X_valid)
predictions.append(y_pred)
y_hat = list(map(lambda x: sum(x) / len(x), np.array(predictions).T))
return y_hat
