def test_generalize_names_duplcheck():
df = pd.read_csv(StringIO(csv))
# duplicates before
dupl = any(df['Name'].apply(generalize_names).duplicated())
assert dupl is True
# no duplicates
df_new = generalize_names_duplcheck(df=df, col_name='Name')
no_dupl = any(df_new['Name'].duplicated())
assert no_dupl is False
def test_generalize_names_duplcheck():
path = os.path.join(os.getcwd(),'tests','data', 'csv', 'DKSalaries.csv')
df = pd.read_csv(path)
# duplicates before
dupl = any(df['Name'].apply(generalize_names).duplicated())
assert(dupl==True)
# no duplicates
df_new = generalize_names_duplcheck(df=df, col_name='Name')
no_dupl = any(df_new['Name'].duplicated())
assert(no_dupl==False)
def test_generalize_names_duplcheck():
path = os.path.join(os.getcwd(), 'tests', 'data', 'csv', 'DKSalaries.csv')
df = pd.read_csv(path)
# duplicates before
dupl = any(df['Name'].apply(generalize_names).duplicated())
assert (dupl == True)
# no duplicates
df_new = generalize_names_duplcheck(df=df, col_name='Name')
no_dupl = any(df_new['Name'].duplicated())
assert (no_dupl == False)
