def test_num_created_batches_is_0(self, len_array, input_seq_length,
output_seq_length, batch_size):
"""Tests for the ValueError raised if num_created_batches == 0
"""
with pytest.raises(ValueError):
make_tf_dataset(
np.arange(len_array).reshape(-1, 1),
input_seq_length,
output_seq_length,
batch_size,
)
def make_predictions(input_model_path):
check_all_needed_files_exist(input_model_path)
num_days = 9
bitcoin = get_last_num_days_hourly_bitcoin_data(num_days)
bitcoin = bitcoin.price.values.reshape(-1, 1)
bitcoin = np.log(bitcoin)
with open(f"{input_model_path}_scaler.pkl", "rb") as f:
min_max = pickle.load(f)
bitcoin_preprocessed = min_max.transform(bitcoin)
bitcoin_ds = make_tf_dataset(
bitcoin_preprocessed,
input_seq_length=INPUT_SEQ_LENGTH,
output_seq_length=0,
# Only feed in single batches for inference for flexibility
batch_size=1,
)
inference_model = build_LSTM_training(batch_size=1,
timesteps=INPUT_SEQ_LENGTH)
inference_model.load_weights(f"{input_model_path}_weights.h5")
preds = inference_model.predict(bitcoin_ds)
preds = pd.Series(preds.reshape(-1, ), name="preds")
return preds
def test_num_created_batches_is_not_0(self, len_array, input_seq_length,
output_seq_length, batch_size):
ds = make_tf_dataset(
np.arange(len_array).reshape(-1, 1),
input_seq_length,
output_seq_length,
batch_size,
)
num_created_batches = len(list(ds.as_numpy_iterator()))
assert num_created_batches > 0
def compare_feature_and_target_shapes(self, array, input_seq_length,
output_seq_length, batch_size):
expected_feature_shape = (batch_size, input_seq_length, 1)
expected_target_shape = (batch_size, output_seq_length, 1)
ds = make_tf_dataset(array, input_seq_length, output_seq_length,
batch_size)
for x in ds.take(1):
feature, target = x
assert expected_feature_shape == feature.shape
assert expected_target_shape == target.shape
def test_array_less_than_2D(self):
array_1D = np.arange(DATASET_SIZE)
with pytest.raises(ValueError) as exec_info:
make_tf_dataset(array_1D, 5, 5, 5)
def test_array_greater_than_2D(self):
array_3D = np.arange(DATASET_SIZE)
array_3D = array_3D.reshape(-1, 10, 5)
with pytest.raises(ValueError) as exec_info:
make_tf_dataset(array_3D, 5, 5, 5)
def test_input_is_numpy(self, input_array_2D):
not_a_numpy_array = list(input_array_2D)
with pytest.raises(TypeError) as exec_info:
assert make_tf_dataset(not_a_numpy_array)
def train_model(output_model_name):
if not output_model_name.endswith(".h5"):
raise ValueError(
f"You must pass a model name with a .h5 extension at the end. "
f"Received: {output_model_name}")
output_dir = Path("models")
if not output_dir.exists():
output_dir.mkdir()
# Remove .h5 at the end
output_model_name = output_model_name[:-3]
bitcoin = load_raw_bitcoin_df()
# In total we have: ~70% training, 20% val, 10% test
train, test = temporal_train_test_split(bitcoin, train_size=0.05)
train, val = temporal_train_test_split(train, train_size=0.77)
train = np.log(train)
val = np.log(val)
test = np.log(test)
min_max = MinMaxScaler()
train = min_max.fit_transform(train)
val = min_max.transform(val)
test = min_max.transform(test)
with open(output_dir / f"{output_model_name}_scaler.pkl", "wb") as f:
pickle.dump(min_max, f)
train_ds = make_tf_dataset(
train,
input_seq_length=INPUT_SEQ_LENGTH,
output_seq_length=OUTPUT_SEQ_LENGTH,
batch_size=BATCH_SIZE_TRAINING,
)
val_ds = make_tf_dataset(
val,
input_seq_length=INPUT_SEQ_LENGTH,
output_seq_length=OUTPUT_SEQ_LENGTH,
batch_size=BATCH_SIZE_TRAINING,
)
test_ds = make_tf_dataset(
test,
input_seq_length=INPUT_SEQ_LENGTH,
output_seq_length=OUTPUT_SEQ_LENGTH,
batch_size=1,
)
model = build_LSTM_training(batch_size=BATCH_SIZE_TRAINING,
timesteps=INPUT_SEQ_LENGTH)
early_stop_cb = EarlyStopping(patience=10,
restore_best_weights=True,
baseline=None)
callbacks = [early_stop_cb]
history = model.fit(
train_ds,
epochs=10,
shuffle=False,
validation_data=val_ds,
callbacks=callbacks,
batch_size=BATCH_SIZE_TRAINING,
)
model.save(output_dir / f"{output_model_name}")
model.save_weights(output_dir / f"{output_model_name}_weights.h5")