예제 #1
0
def testStandardize():
    ctp = CovidTrackingProject()
    df = get_test_data_as_df()
    df = ctp.standardize(df)

    expected_cols = {
        'date', col_std.STATE_POSTAL_COL, col_std.RACE_COL, 'variable_type',
        'value'
    }
    assert set(df.columns) == expected_cols

    expected_race_categories = [r.race for r in col_std.Race]
    assert set(df[col_std.RACE_COL]).issubset(set(expected_race_categories))
예제 #2
0
def testMergeWithMetadata():
    ctp = CovidTrackingProject()
    df = get_test_data_as_df()
    mdf = get_test_metadata_as_df()

    df = ctp.standardize(df)
    df = ctp.merge_with_metadata(df, mdf)

    expected_cols = {
        'date', col_std.STATE_POSTAL_COL, col_std.RACE_COL, 'variable_type',
        'value', 'reports_race', 'race_ethnicity_separately'
    }
    assert set(df.columns) == expected_cols

    expected_race_categories = {
        col_std.Race.AIAN.race, col_std.Race.API.race, col_std.Race.ASIAN.race,
        col_std.Race.BLACK.race, col_std.Race.HISP.race,
        col_std.Race.INDIGENOUS.race, col_std.Race.NHPI.race,
        col_std.Race.MULTI.race, col_std.Race.WHITE.race, col_std.Race.NH.race,
        col_std.Race.ETHNICITY_UNKNOWN.race,
        col_std.Race.OTHER_NONSTANDARD.race, col_std.Race.UNKNOWN.race,
        col_std.Race.TOTAL.race
    }
    assert set(df[col_std.RACE_COL]) == expected_race_categories