def save_dataframes_unique(file):
df = get_dataframe(file, worksheet=0, usecols=("A:O"))
branches = find_branches(df)
branches = find_duplicates(branches)
headquartes = find_headquarters(df)
headquartes = find_duplicates(headquartes)
worksheets = {'filiais': branches, 'matrizes': headquartes}
writer = create_excel_file(worksheets, filename='petroleo_empresas')
writer.save()
def test_unique_headquarters():
df = get_dataframe(FILE, worksheet=0, usecols=USECOLS)
headquarters = find_headquarters(df)
headquarters = find_duplicates(headquarters)
assert headquarters.shape == (782, 15)
def test_get_headquarters():
df = get_dataframe(FILE, worksheet=0, usecols=USECOLS)
headquarters = find_headquarters(df)
branches = headquarters[headquarters['CNPJ'].str.contains(
'^(?!.*/0001).*$', regex=True)]
assert len(branches) == 0
def test_get_branches(worksheet, result):
df = get_dataframe(FILE, worksheet=worksheet, usecols=USECOLS)
df = find_branches(df)
assert df.shape == (result, 15)
def test_read_file(file=FILE, usecols=USECOLS):
df = get_dataframe(file, worksheet=0, usecols=usecols)
assert isinstance(df, pd.core.frame.DataFrame)
assert df.iloc[0]['Categoria'] == 'Produtos'
assert df.shape[1] == 15