def save_model(model):
try:
if sys.argv[1] == 'save':
save_data(model, MODEL_FILE_NAME)
else:
pass
except IndexError:
pass
def save_model(model, model_name):
try:
if sys.argv[1] == 'save':
save_data(model, model_file_dict[model_name])
else:
pass
except IndexError:
pass
except KeyError:
print('Save error! Specified model name is invalid')
def save_model(model, model_name=None, file_path=None):
if model_name is None and file_path is None:
print('Please specify either model_name or file_path')
print('file_path argument should have .pkl extension')
print('Valid model_name arguments: ')
print(list(model_file_dict.keys()))
return
try:
if file_path is not None: # if file_path specified, save to file_path if valid
if file_path[-4:] != '.pkl':
print('file_path argument should have .pkl extension')
else:
save_data(model, file_path)
return
save_data(model, model_file_dict[model_name])
except KeyError: # model_name alias specified not supported as per in model_file_dict
print(
'Error! Saving this model to file not supported by ai_cloud_model module'
)
print('Model aliases supported:')
print(model_list)
def main():
# Data Extraction
df = data_extract_e('e_20190609_15.pkl')
# Data Transformation and Engineering
df = feature_eng(df)
df = extract_queues(df)
dept_encoder, queue_encoder = load_labels('dept_encoder.pkl',
'queue_encoder.pkl',
df=df)
df = feature_transform(df,
dept_encoder=dept_encoder,
queue_encoder=queue_encoder)
# Training/Test Split
x, y = data_filter(df)
x_train, x_test, y_train, y_test = train_test_split(
x, y, test_size=0.2,
random_state=1357) # 2468 to use same shuffle as individual models
# Load models from persistent files
models = load_models()
print(models)
# Stacking
# Produces a new set of features based on the predictions of base models
x_train_s, x_test_s = stacking(models,
x_train,
y_train,
x_test,
n_folds=10,
shuffle=True,
verbose=0,
regression=True)
save_data(x_train_s, 'x_train_s.pkl')
save_data(y_train, 'y_train.pkl')
save_data(x_test_s, 'x_test_s.pkl')
save_data(y_test, 'y_test.pkl')