def test_write_csv():
df = pd.DataFrame({
CommonFields.DATE:
pd.to_datetime(["2020-04-01", "2020-04-02"]),
CommonFields.FIPS: ["06045", "45123"],
CommonFields.CASES: [234, 456],
})
ts = TimeseriesDataset(df)
expected_csv = """,,summary,summary,summary,summary,summary,summary,summary,summary,summary,value,value
date,,has_value,min_date,max_date,max_value,min_value,latest_value,num_observations,largest_delta,largest_delta_date,2020-04-01 00:00:00,2020-04-02 00:00:00
fips,variable,,,,,,,,,,,
06045,cases,True,2020-04-01,2020-04-01,234,234,234,1,,,234,
45123,cases,True,2020-04-02,2020-04-02,456,456,456,1,,,,456
"""
# Call common_df.write_csv with index set to ["fips", "date"], the expected normal index.
with temppathlib.NamedTemporaryFile("w+") as tmp:
wide_dates_df.write_csv(ts.get_date_columns(), tmp.path)
assert expected_csv == tmp.file.read()
def test_wide_dates():
input_df = read_csv_and_index_fips_date(
"fips,county,aggregate_level,date,m1,m2\n"
"97111,Bar County,county,2020-04-01,1,\n"
"97111,Bar County,county,2020-04-02,2,\n"
"97222,Foo County,county,2020-04-01,,10\n"
"97222,Foo County,county,2020-04-03,3,30\n")
provenance = provenance_wide_metrics_to_series(
read_csv_and_index_fips_date("fips,date,m1,m2\n"
"97111,2020-04-01,src11,\n"
"97111,2020-04-02,src11,\n"
"97222,2020-04-01,,src22\n"
"97222,2020-04-03,src21,src22\n"),
structlog.get_logger(),
)
ts = TimeseriesDataset(input_df.reset_index(), provenance=provenance)
date_columns = ts.get_date_columns()
assert to_dict(["fips", "variable"], date_columns["value"]) == {
("97111", "m1"): {
pd.to_datetime("2020-04-01"): 1.0,
pd.to_datetime("2020-04-02"): 2.0
},
("97222", "m1"): {
pd.to_datetime("2020-04-03"): 3.0
},
("97222", "m2"): {
pd.to_datetime("2020-04-01"): 10.0,
pd.to_datetime("2020-04-03"): 30.0
},
}
assert to_dict(["fips", "variable"], date_columns["provenance"]) == {
("97111", "m1"): {
"value": "src11"
},
("97222", "m1"): {
"value": "src21"
},
("97222", "m2"): {
"value": "src22"
},
}