Function create_global_daily_stats_df

sdk/python/feast/driver_test_data.py:281–323

Example df generated by this function: | event_timestamp | num_rides | avg_ride_length | created | |------------------+-------------+-----------------+------------------| | 2021-03-17 19:00 | 99 | 0.889188 | 2021-03-24 19:38 | | 2021-03-18 19:00 | 52

(start_date, end_date)

def create_global_daily_stats_df(start_date, end_date) -> pd.DataFrame:
    """
    Example df generated by this function:

    | event_timestamp  | num_rides   | avg_ride_length | created          |
    |------------------+-------------+-----------------+------------------|
    | 2021-03-17 19:00 | 99          | 0.889188        | 2021-03-24 19:38 |
    | 2021-03-18 19:00 | 52          | 0.979273        | 2021-03-24 19:38 |
    | 2021-03-19 19:00 | 66          | 0.976549        | 2021-03-24 19:38 |
    | 2021-03-20 19:00 | 84          | 0.273697        | 2021-03-24 19:38 |
    | 2021-03-21 19:00 | 89          | 0.438262        | 2021-03-24 19:38 |
    |                  |  ...        |      ...        |                  |
    | 2021-03-24 19:00 | 54          | 0.738860        | 2021-03-24 19:38 |
    | 2021-03-25 19:00 | 58          | 0.848397        | 2021-03-24 19:38 |
    | 2021-03-26 19:00 | 69          | 0.301552        | 2021-03-24 19:38 |
    | 2021-03-27 19:00 | 63          | 0.943030        | 2021-03-24 19:38 |
    | 2021-03-28 19:00 | 79          | 0.354919        | 2021-03-24 19:38 |
    """
    df_daily = pd.DataFrame(
        {
            "event_timestamp": [
                pd.Timestamp(
                    dt,
                    unit="ms",
                ).round("ms")
                for dt in pd.date_range(
                    start=start_date,
                    end=end_date,
                    freq="1D",
                    inclusive="left",
                    tz="UTC",
                )
            ]
        }
    )
    rows = df_daily["event_timestamp"].count()

    df_daily["num_rides"] = np.random.randint(50, 100, size=rows).astype(np.int32)
    df_daily["avg_ride_length"] = np.random.random(size=rows).astype(np.float32)

    # TODO: Remove created timestamp in order to test whether its really optional
    df_daily["created"] = pd.to_datetime(pd.Timestamp.now(tz=None).round("ms"))
    return df_daily


def create_field_mapping_df(start_date, end_date) -> pd.DataFrame: