def get_historical_features(features: str, entity_df_path: str,
destination: str):
"""
Get historical features
"""
import pandas
client = Client()
# TODO: clean this up
entity_df = pandas.read_csv(
entity_df_path,
sep=None,
engine="python",
)
entity_df["event_timestamp"] = pandas.to_datetime(
entity_df["event_timestamp"])
uploaded_df = client.stage_dataframe(entity_df, "event_timestamp",
"created_timestamp")
job = client.get_historical_features(
features.split(","),
uploaded_df,
)
print(job.get_output_file_uri())
def get_historical_features(features: str, entity_df_path: str,
entity_df_dtype: str, destination: str):
"""
Get historical features. This CLI command is mostly for testing/easy demos; use the
corresponding API method in production.
The main reason why this command is unlikely to be more broadly useful is that we make quite a
few assumptions about the entity dataframe, namely:
* it has to have `event_timestamp` column
* it has to parse cleanly by `pandas.read_csv()` with no extra tuning of data types
"""
import pandas
client = Client()
if entity_df_dtype:
dtype = json.loads(entity_df_dtype)
entity_df = pandas.read_csv(entity_df_path,
sep=None,
engine="python",
dtype=dtype)
else:
entity_df = pandas.read_csv(entity_df_path, sep=None, engine="python")
entity_df["event_timestamp"] = pandas.to_datetime(
entity_df["event_timestamp"])
uploaded_df = client.stage_dataframe(entity_df, "event_timestamp")
job = client.get_historical_features(
features.split(","),
uploaded_df,
)
print(job.get_output_file_uri())
