output_filename = os.path.join(self.HOME_DIR, "output",
"conciseness_valid.predict")
else:
output_filename = os.path.join(self.HOME_DIR, "output",
"clarity_valid.predict")
np.savetxt(output_filename,
df_test["predictions_proba"],
fmt='%1.10f',
delimiter="\n")
#=======================================================================================
if __name__ == '__main__':
dp = DataPreparation()
dp.build_combination(processing_mode=1,
out_filename="data_all_conciseness.csv")
dp.clean_data(target_column="conciseness")
feature_man = FeatureManagement()
phase = 1
flags = [True, False]
if flags[0]:
features = feature_man.get_basic_features() + \
feature_man.get_text_features(mode=0, type=0) + \
feature_man.get_text_features(mode=0, type=1)
print("Total number of training features {}".format(len(features)))
print(feature_man.get_basic_features())
no_models = 20
no_rounds = 500
both_predictions = both_predictions / num_of_models
both_filename = os.path.join(self.HOME_DIR, "output",
"both_test.predict")
np.savetxt(both_filename,
both_predictions,
fmt='%1.10f',
delimiter="\n")
#=======================================================================================
if __name__ == '__main__':
dp = DataPreparation()
dp.build_combination(processing_mode=0,
out_filename="data_all_clarity.csv")
dp.clean_data(target_column="clarity")
feature_man = FeatureManagement()
phase = 2
flags = [False, True]
if flags[0]:
features = feature_man.get_basic_features(is_clarity=True) + \
feature_man.get_text_features(mode=0, type=0) + \
feature_man.get_text_features(mode=0, type=1)
print("Total number of training features {}".format(len(features)))
no_models = 20
no_rounds = 500