def test():
logging.info("creating customers ...")
customers = create_customers(10)
http_cmd_req('{}/customers'.format(BASE_URL), customers)
time.sleep(1)
rsp = request.urlopen('{}/customers'.format(BASE_URL))
customers = get_result(rsp)
logging.info("creating products ...")
products = create_products(100)
http_cmd_req('{}/products'.format(BASE_URL), products)
time.sleep(1)
rsp = request.urlopen('{}/products'.format(BASE_URL))
products = get_result(rsp)
logging.info("creating inventory ...")
inventories = create_inventories(
[product['entity_id'] for product in products], 100)
http_cmd_req('{}/inventories'.format(BASE_URL), inventories)
time.sleep(1)
rsp = request.urlopen('{}/inventories'.format(BASE_URL))
inventories = get_result(rsp)
logging.info("creating carts ...")
carts = create_carts(10, customers, products)
http_cmd_req('{}/carts'.format(BASE_URL), carts)
time.sleep(2)
rsp = request.urlopen('{}/carts'.format(BASE_URL))
carts = get_result(rsp)
while True:
logging.info("updating carts ...")
for cart in carts:
http_cmd_req('{}/cart/{}'.format(BASE_URL, cart['entity_id']),
cart,
_method='PUT')
def run(metal, provider, period, start=None, end=None, evaluate=False):
# Get data
data = get_data(metal, provider, start, end)
dataset = data.values
training_data_len = math.ceil(len(dataset) * 0.8)
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(dataset)
train_data = scaled_data[0:training_data_len, :]
x_train = []
y_train = []
for i in range(60, len(train_data)):
x_train.append(train_data[i - 60:i, 0])
y_train.append(train_data[i, 0])
x_train, y_train = np.array(x_train), np.array(y_train)
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
# Build model
model = Sequential()
model.add(
LSTM(50, return_sequences=True, input_shape=(x_train.shape[1], 1)))
model.add(LSTM(50, return_sequences=False))
model.add(Dense(25))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=['acc'])
model.fit(x_train, y_train, epochs=5, batch_size=32)
if evaluate:
return None, get_evaluate(model, x_train, y_train)
# Get result
test_data = scaled_data[training_data_len - 60:]
x_test = []
for i in range(60, len(test_data)):
x_test.append(test_data[i - 60:i, 0])
x_test = np.array(x_test)
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))
predictions = np.array([])
last = x_test[-1]
for i in range(period):
curr_prediction = model.predict(np.array([last]))
last = np.concatenate([last[1:], curr_prediction])
predictions = np.concatenate([predictions, curr_prediction[0]])
predictions = scaler.inverse_transform([predictions])[0]
dicts = []
curr_date = date.today()
for i in range(period):
curr_date = curr_date + timedelta(days=1)
dicts.append({'Predictions': predictions[i], "Date": curr_date})
new_data = pd.DataFrame(dicts).set_index("Date")
return get_result(data, new_data)