def hyperparameter_tuning():
train_x_data = getTrainXData('train_scored.csv')
train_y_data = getTrainYData('train_scored_y.csv')
test_x_data = getTestXData('test_scored.csv')
params = {
'max_features': [8, 16, 32, 'sqrt', 'auto'],
'n_estimators': [2500, 3000, 3500, 4000, 4500, 5000]
}
est = ExtraTreesRegressor()
print est.get_params().keys()
gs_cv = GridSearchCV(est, params)
gs_cv.fit(train_x_data, train_y_data)
print gs_cv.best_params_
print("after shuffling: {}".format(combined_filenames)) # shuffling works ok.
i = 0
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()
getparams_dict = aux_reg_regressor.get_params(deep=True)
print("getparams_dict: ", getparams_dict)
getparams_df = pd.DataFrame.from_dict(data=getparams_dict,orient='index')
getparams_df.to_csv(analysis_path + model_id + str(lstm_model)[:-4] + "getparams.csv")
model_as_pkl_filename = analysis_path + model_id + str(lstm_model)[:-4] + ".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 IF CUT SHORT!!
for files in combined_filenames:
print("filename", files)
i += 1
data_load_path = test_path + '/data/' + files[0]
