def __init__(self,
horizon=1,
dt_col="datetime",
target_col="value",
logs_dir="~/zoo_automl_logs",
extra_features_col=None,
search_alg=None,
search_alg_params=None,
scheduler=None,
scheduler_params=None,
name="automl"
):
"""
Initialize the AutoTS Trainer.
:param horizon: steps to look forward
:param dt_col: the datetime column
:param target_col: the target column to forecast
:param extra_features_col: extra feature columns
"""
target_col_list = target_col
if isinstance(target_col, str):
target_col_list = [target_col]
self.internal = TimeSequencePredictor(
dt_col=dt_col,
target_col=target_col_list,
logs_dir=logs_dir,
future_seq_len=horizon,
extra_features_col=extra_features_col,
search_alg=search_alg,
search_alg_params=search_alg_params,
scheduler=scheduler,
scheduler_params=scheduler_params,
name=name
)
def test_fit_BayesRecipe(self):
from zoo.zouwu.config.recipe import BayesRecipe
train_df, _, future_seq_len = self.create_dataset()
tsp = TimeSequencePredictor(dt_col="datetime",
target_col="value",
future_seq_len=future_seq_len,
extra_features_col=None,
search_alg="BayesOpt",
search_alg_params={
"utility_kwargs": {
"kind": "ucb",
"kappa": 2.5,
"xi": 0.0
}
}
)
pipeline = tsp.fit(
train_df, recipe=BayesRecipe(
num_samples=1,
training_iteration=2,
epochs=1,
look_back=(3, 5)
))
assert isinstance(pipeline, TimeSequencePipeline)
assert isinstance(
pipeline.feature_transformers,
TimeSequenceFeatureTransformer)
assert isinstance(pipeline.model, BaseModel)
assert pipeline.config is not None
assert "epochs" in pipeline.config
assert [config_name for config_name in pipeline.config
if config_name.endswith('float')] == []
assert 'past_seq_len' in pipeline.config
assert 3 <= pipeline.config["past_seq_len"] <= 5
def test_fit_SmokeRecipe(self):
train_df, validation_df, future_seq_len = self.create_dataset()
tsp = TimeSequencePredictor(dt_col="datetime",
target_col="value",
future_seq_len=future_seq_len,
extra_features_col=None, )
pipeline = tsp.fit(train_df, validation_df)
assert isinstance(pipeline, TimeSequencePipeline)
assert isinstance(
pipeline.feature_transformers,
TimeSequenceFeatureTransformer)
assert isinstance(pipeline.model, BaseModel)
assert pipeline.config is not None
def get_input_tsp(self, future_seq_len, target_col):
sample_num = np.random.randint(100, 200)
test_sample_num = np.random.randint(20, 30)
if isinstance(target_col, str):
train_df = pd.DataFrame({
"datetime":
pd.date_range('1/1/2019', periods=sample_num),
target_col:
np.random.randn(sample_num)
})
test_df = pd.DataFrame({
"datetime":
pd.date_range('1/1/2019', periods=test_sample_num),
target_col:
np.random.randn(test_sample_num)
})
else:
train_df = pd.DataFrame(
{t: np.random.randn(sample_num)
for t in target_col})
train_df["datetime"] = pd.date_range('1/1/2019',
periods=sample_num)
test_df = pd.DataFrame(
{t: np.random.randn(test_sample_num)
for t in target_col})
test_df["datetime"] = pd.date_range('1/1/2019',
periods=test_sample_num)
tsp = TimeSequencePredictor(
dt_col="datetime",
target_col=target_col,
future_seq_len=future_seq_len,
extra_features_col=None,
)
return train_df, test_df, tsp, test_sample_num
def test_fit_LSTMGridRandomRecipe(self):
from zoo.zouwu.config.recipe import LSTMGridRandomRecipe
train_df, _, future_seq_len = self.create_dataset()
tsp = TimeSequencePredictor(dt_col="datetime",
target_col="value",
future_seq_len=future_seq_len,
extra_features_col=None, )
pipeline = tsp.fit(train_df,
recipe=LSTMGridRandomRecipe(
lstm_2_units=[4],
batch_size=[1024],
num_rand_samples=5,
look_back=2,
training_iteration=1,
epochs=1))
assert isinstance(pipeline, TimeSequencePipeline)
assert isinstance(
pipeline.feature_transformers,
TimeSequenceFeatureTransformer)
assert isinstance(pipeline.model, BaseModel)
assert pipeline.config is not None
assert 'past_seq_len' in pipeline.config
assert pipeline.config["past_seq_len"] == 2
class AutoTSTrainer:
"""
The Automated Time Series Forecast Trainer
"""
def __init__(self,
horizon=1,
dt_col="datetime",
target_col="value",
logs_dir="~/zoo_automl_logs",
extra_features_col=None,
search_alg=None,
search_alg_params=None,
scheduler=None,
scheduler_params=None,
name="automl"
):
"""
Initialize the AutoTS Trainer.
:param horizon: steps to look forward
:param dt_col: the datetime column
:param target_col: the target column to forecast
:param extra_features_col: extra feature columns
"""
target_col_list = target_col
if isinstance(target_col, str):
target_col_list = [target_col]
self.internal = TimeSequencePredictor(
dt_col=dt_col,
target_col=target_col_list,
logs_dir=logs_dir,
future_seq_len=horizon,
extra_features_col=extra_features_col,
search_alg=search_alg,
search_alg_params=search_alg_params,
scheduler=scheduler,
scheduler_params=scheduler_params,
name=name
)
def fit(self,
train_df,
validation_df=None,
metric="mse",
recipe: Recipe = SmokeRecipe(),
uncertainty: bool = False,
upload_dir=None,
):
"""
Fit a time series forecasting pipeline w/ automl
:param train_df: the input dataframe (as pandas.dataframe)
:param validation_df: the validation dataframe (as pandas.dataframe)
:param recipe: the configuration of searching
:param metric: the evaluation metric to optimize
:param uncertainty: whether to enable uncertainty calculation
(will output an uncertainty sigma)
:param upload_dir: Optional URI to sync training results and checkpoints. We only support
hdfs URI for now.
:return a TSPipeline
"""
zoo_pipeline = self.internal.fit(train_df,
validation_df,
metric,
recipe,
mc=uncertainty,
upload_dir=upload_dir)
ppl = TSPipeline()
ppl.internal = zoo_pipeline
return ppl