def test_no_data_specified(
self, coords_cols, coords_defaults, coords_terminologies, coords_value_mapping
):
file_input_long = DATA_PATH / "long.csv"
del coords_cols["sec_cats__Class"]
del coords_defaults["sec_cats__Type"]
del coords_terminologies["sec_cats__Class"]
del coords_terminologies["sec_cats__Type"]
coords_cols["time"] = "year"
with pytest.raises(
ValueError,
match="No data column in the CSV specified in coords_cols, so nothing to"
" read.",
):
pm2io.read_long_csv_file_if(
file_input_long,
coords_cols=coords_cols,
coords_defaults=coords_defaults,
coords_terminologies=coords_terminologies,
coords_value_mapping=coords_value_mapping,
time_format="%Y",
)
def test_compare_wide(
self,
coords_cols,
coords_defaults,
coords_terminologies,
coords_value_mapping,
):
file_input_wide = DATA_PATH / "test_csv_data.csv"
file_input_long = DATA_PATH / "long.csv"
del coords_cols["sec_cats__Class"]
del coords_defaults["sec_cats__Type"]
del coords_terminologies["sec_cats__Class"]
del coords_terminologies["sec_cats__Type"]
meta_data = {"references": "Just ask around"}
df_result_wide = pm2io.read_wide_csv_file_if(
file_input_wide,
coords_cols=coords_cols,
coords_defaults=coords_defaults,
coords_terminologies=coords_terminologies,
coords_value_mapping=coords_value_mapping,
meta_data=meta_data,
)
coords_cols["time"] = "year"
coords_cols["data"] = "emissions"
df_result_long = pm2io.read_long_csv_file_if(
file_input_long,
coords_cols=coords_cols,
coords_defaults=coords_defaults,
coords_terminologies=coords_terminologies,
coords_value_mapping=coords_value_mapping,
meta_data=meta_data,
time_format="%Y",
)
pd.testing.assert_frame_equal(df_result_wide, df_result_long)
assert df_result_wide.attrs == df_result_long.attrs
def test_compare_wide_add_cols(
self,
coords_cols,
add_coords_cols,
coords_defaults,
coords_terminologies,
coords_value_mapping,
):
file_input_wide = DATA_PATH / "test_csv_data_category_name.csv"
file_input_long = DATA_PATH / "test_csv_data_category_name_long.csv"
del coords_cols["sec_cats__Class"]
del coords_defaults["sec_cats__Type"]
del coords_terminologies["sec_cats__Class"]
del coords_terminologies["sec_cats__Type"]
df_result_wide = pm2io.read_wide_csv_file_if(
file_input_wide,
coords_cols=coords_cols,
add_coords_cols=add_coords_cols,
coords_defaults=coords_defaults,
coords_terminologies=coords_terminologies,
coords_value_mapping=coords_value_mapping,
)
coords_cols["time"] = "year"
coords_cols["data"] = "emissions"
df_result_long = pm2io.read_long_csv_file_if(
file_input_long,
coords_cols=coords_cols,
add_coords_cols=add_coords_cols,
coords_defaults=coords_defaults,
coords_terminologies=coords_terminologies,
coords_value_mapping=coords_value_mapping,
time_format="%Y",
)
pd.testing.assert_frame_equal(df_result_wide, df_result_long)
assert df_result_wide.attrs == df_result_long.attrs
def test_no_time(
self, coords_cols, coords_defaults, coords_terminologies, coords_value_mapping
):
file_input_long = DATA_PATH / "long_no_time.csv"
del coords_cols["sec_cats__Class"]
del coords_defaults["sec_cats__Type"]
del coords_terminologies["sec_cats__Class"]
del coords_terminologies["sec_cats__Type"]
coords_cols["data"] = "emissions"
coords_defaults["time"] = datetime.datetime(2020, 1, 1)
df = pm2io.read_long_csv_file_if(
file_input_long,
coords_cols=coords_cols,
coords_defaults=coords_defaults,
coords_terminologies=coords_terminologies,
coords_value_mapping=coords_value_mapping,
time_format="%Y",
)
df_expected = pd.DataFrame(
[
("TESTcsv2021", "HISTORY", "AUS", "CO2", "Gg CO2 / yr", "1", 4.1),
("TESTcsv2021", "HISTORY", "ZAM", "CH4", "Mt CH4 / yr", "2", 7.0),
],
columns=[
"source",
"scenario (general)",
"area (ISO3)",
"entity",
"unit",
"category (IPCC2006)",
"2020",
],
)
pd.testing.assert_frame_equal(df, df_expected)