def main(): # Create output directory in example directory code_path = Path(__file__) output_dir = code_path.with_name("output").joinpath(code_path.stem) output_dir.mkdir(exist_ok=True, parents=True) # Read JHU dataset jhu_file = "input/covid_19_data.csv" jhu_data = JHUData(jhu_file) # Show the cleaned data as a CSV file ncov_df = jhu_data.cleaned() ncov_df.to_csv(output_dir.joinpath("cleaned.csv"), index=False)
def test_cleaning(self, jhu_data): assert isinstance(jhu_data.raw, pd.DataFrame) with pytest.raises(ValueError): jhu_data.cleaned(population=None) df = jhu_data.cleaned() assert set(df.columns) == set(Term.COLUMNS) assert isinstance(JHUData.from_dataframe(df), JHUData)
def main(): # Create output directory in example directory code_path = Path(__file__) output_dir = code_path.with_name("output").joinpath(code_path.stem) output_dir.mkdir(exist_ok=True, parents=True) # Read JHU dataset jhu_file = "input/covid_19_data.csv" jhu_data = JHUData(jhu_file) ncov_df = jhu_data.cleaned() ncov_df.to_csv(output_dir.joinpath("jhu_cleaned.csv"), index=False) # Read Japan datset jpn_file = "input/covid_jpn_total.csv" jpn_data = CountryData(jpn_file, country="Japan") jpn_data.set_variables(date="Date", confirmed="Positive", fatal="Fatal", recovered="Discharged", province=None) jpn_df = jpn_data.cleaned() jpn_df.to_csv(output_dir.joinpath("jpn_cleaned.csv"), index=False) # Replace data in Japan with Japan-specific dataset jhu_data.replace(jpn_data) ncov_df = jhu_data.cleaned() ncov_df.to_csv(output_dir.joinpath("jhu_cleaned_replaced.csv"), index=False) return ncov_df
def test_from_dataframe(self, jhu_data): df = jhu_data.cleaned() jhu_data2 = JHUData.from_dataframe(df) assert set(df.columns) == set(jhu_data2.cleaned().columns)
def test_from_dataframe(self, japan_data): df = japan_data.cleaned() jhu_data_df = JHUData.from_dataframe(df, directory="input_dir") assert isinstance(jhu_data_df, JHUData) assert jhu_data_df.directory == "input_dir" jhu_data_df.records("Japan")
def test_from_dataframe(self, japan_data): df = japan_data.cleaned() jhu_data_df = JHUData.from_dataframe(df) assert isinstance(jhu_data_df, JHUData) jhu_data_df.records("Japan")