def run_cross_validation(train, train_target, folds):
cv_params = {
'estimator__min_child_weight': [1, 3, 5],
'estimator__subsample': [0.7, 0.8, 0.9],
'estimator__learning_rate': [0.1, 0.01],
'estimator__max_depth': [3, 5, 7],
'estimator__n_estimators': [1000] #try 100
}
ind_params = {
'colsample_bytree': 0.8,
'silent': 1,
'seed': 0,
'objective': 'reg:linear'
}
pipeline = MultiOutputRegressor(xgb.XGBRegressor(**ind_params))
print sorted(pipeline.get_params().keys())
optimized_GBM = GridSearchCV(pipeline,
cv_params,
scoring='r2',
cv=folds,
n_jobs=1,
verbose=4)
optimized_GBM.fit(train, train_target)
print "best scores: " + str(optimized_GBM.grid_scores_)
our_params = ind_params.copy()
our_params.update(optimized_GBM.best_params_)
return our_params
def generate_joint_model(single_model):
model = MultiOutputRegressor(single_model)
model.fit(X_train, Y_train)
score_train = model.score(X_train, Y_train)
print('Score of train', round(score_train * 100, 1), "%")
score = model.score(X_test, Y_test)
print('Score of test', round(score * 100, 1), "%")
model_path = model_folder + r"/" + \
str(round(score, 3)).replace('.', '_') + r"_" + \
str(model.get_params()['estimator']).split('(')[0] + \
'.joblib'
joblib.dump(model, model_path)
print("Save model file", model_path)
return model, model_path
score_rows_list = []
scores_dict = {}
mse_dict = {}
mae_dict = {}
mape_dict = {}
scores_dict_f3 = {}
mse_dict_f3 = {}
mae_dict_f3 = {}
mape_dict_f3 = {}
test_start_time = time.clock()
# try to save the trees attribute
if tree_regressor_check_cond == True:
print("aux_reg_regressor estimator_params", aux_reg_regressor.estimators_)
getparams_dict = aux_reg_regressor.get_params(deep=True)
print(getparams_dict)
getparams_df = pd.DataFrame.from_dict(data=getparams_dict, orient='index')
getparams_df.to_csv(analysis_path + model_id + "getparams.csv")
model_as_pkl_filename = analysis_path + model_id + ".pkl"
joblib.dump(aux_reg_regressor, filename=model_as_pkl_filename)
# np.savetxt(analysis_path + "rf5getparams.txt",fmt='%s',X=str(aux_reg_regressor.get_params(deep=True)))
# np.savetxt(analysis_path + "rf5estimatorparams.txt",fmt='%s',X=aux_reg_regressor.estimator_params) USELESS
# np.savetxt(analysis_path + "rf5classes.txt",fmt='%s',X=aux_reg_regressor.classes_)
# np.savetxt(analysis_path + "rf5baseestim.txt",fmt='%s',X=aux_reg_regressor.base_estimator_)
# TODO: CHANGE THIS BACK!!
for files in combined_filenames:
print("filename", files)
i += 1
data_load_path = test_path + '/data/' + files[0]
