def test_prophet_extract_params():
train = data_generator.generate_test_data(4, 6, 1000, "2020-01-01", 1)
model = GroupedProphet(uncertainty_samples=0).fit(train.df, train.key_columns)
params = model.extract_model_params()
assert len(params) == 6
def grouped_prophet_example(locations, start_dt, artifact_path):
print("Generating data...\n")
data = generate_data(location_data=locations, start_dt=start_dt)
grouping_keys = ["country", "city"]
print("Data Generated.\nBuilding GroupedProphet Model...")
model = GroupedProphet(n_changepoints=96, uncertainty_samples=0).fit(
df=data, group_key_columns=grouping_keys, y_col="watts", datetime_col="datetime"
)
print("GroupedProphet model built.\n")
params = model.extract_model_params()
print(f"Params: \n{params.to_string()}")
print("Running Cross Validation on all groups...\n")
metrics = model.cross_validate_and_score(
horizon="120 hours",
period="480 hours",
initial="960 hours",
parallel="threads",
rolling_window=0.05,
monthly=False,
)
print(f"Cross Validation Metrics: \n{metrics.to_string()}")
mlflow.diviner.log_model(diviner_model=model, artifact_path=artifact_path)
# As an Alternative to saving metrics and params directly with a `log_dict()` function call,
# Serializing the DataFrames to local as a .csv can be done as well, without requiring
# column or object manipulation as shown below this block, utilizing a temporary directory
# with a context wrapper to clean up the files from the local OS after the artifact logging
# is complete:
with tempfile.TemporaryDirectory() as tmpdir:
params.to_csv(f"{tmpdir}/params.csv", index=False, header=True)
metrics.to_csv(f"{tmpdir}/metrics.csv", index=False, header=True)
mlflow.log_artifacts(tmpdir, artifact_path="run_data")
# Saving the parameters and metrics as json without having to serialize to local
# NOTE: this requires casting of fields that cannot be serialized to JSON
# NOTE: Do not use both of these methods. These are shown as an either/or alternative based
# on how you would choose to consume, view, or analyze the per-group metrics and parameters.
# NB: There are object references present in the Prophet model parameters. Coerce to string if
# using a JSON serialization approach with ``mlflow.log_dict()``.
params = params.astype(dtype=str, errors="ignore")
mlflow.log_dict(params.to_dict(), "params.json")
mlflow.log_dict(metrics.to_dict(), "metrics.json")
return mlflow.get_artifact_uri(artifact_path=artifact_path)
def test_prophet_df_naming_overrides():
train = data_generator.generate_test_data(2, 1, 1000, "2020-01-01", 1)
train_df = train.df
train_df.rename(columns={"ds": "datetime", "y": "sales"}, inplace=True)
assert {"datetime", "sales"}.issubset(set(train_df.columns))
model = GroupedProphet().fit(train_df, train.key_columns, "sales", "datetime")
params = model.extract_model_params()
assert len(params) == 1