def test_remove_columns_1():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert list(check.remove_columns(df).columns) == [
'Location', 'population', 'nonwhite', 'density', 'crime'
]
def test_ignore_identifier_1():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert list(check.ignore_identifier(df).columns) == [
'population', 'nonwhite', 'density', 'crime'
]
def test_ignore_identifier_2():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'msleep_ggplot.csv'))
check = Check()
assert list(check.ignore_identifier(df).columns) == [
'genus', 'vore', 'order', 'conservation', 'sleep_total', 'sleep_rem',
'sleep_cycle', 'awake', 'brainwt', 'bodywt'
]
def test_remove_records():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
df1 = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data',
'Freedman_remove_records.csv'))
check = Check()
assert check.remove_records(df).equals(df1) == True
def test_ignore_identifier_2():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'vgsales.csv'))
df1 = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data',
'vgsales_ignore_identifier.csv'))
check = Check()
assert check.ignore_identifier(df).equals(df1) == False
def test_encoding_categorical_2():
check = Check()
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'student.csv'))
assert check.encoding_categorical(df['sex']) == ([0, 0, 0, 0, 0, 1, 1,
0], {
0: 'F',
1: 'F'
})
def test_encoding_categorical_1():
check = Check()
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'cereal.csv'))
assert check.encoding_categorical(df['mfr']) == ([1, 2, 0, 0, 3, 1], {
1: 'Q',
2: 'K',
0: 'N',
3: 'K'
})
def test_encoding_categorical_3():
check = Check()
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'student.csv'))
assert check.encoding_categorical(df['Mjob']) == ([0, 0, 0, 1, 2, 3, 2,
2], {
0: 'at_home',
1: 'at_home',
2: 'at_home',
3: 'health'
})
def test_is_categorical():
"""
Check if the given dataset given a columns
is categorical or not.
:raises AssertionError: { exception_description }
"""
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_categorical(df['Location']) == True
def test_percentage_missing():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'vgsales.csv'))
check = Check()
assert check.percentage_missing(df) == {
'Rank': 0.0,
'Name': 0.0,
'Platform': 0.0,
'Year': 1.63,
'Genre': 0.0,
'Publisher': 0.35,
'NA_Sales': 0.0,
'EU_Sales': 0.0,
'JP_Sales': 0.0,
'Other_Sales': 0.0,
'Global_Sales': 0.0
}
def test_remove_records_1():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert len(check.remove_records(df)) == 110
def test_remove_records_2():
df = pd.read_csv(os.path.join(os.path.dirname(__file__), 'data', 'msleep_ggplot.csv'))
check = Check()
assert len(check.remove_records(df)) == 61
def test_percentage_missing_2():
df = pd.read_csv(os.path.join(os.path.dirname(__file__), 'data', 'msleep_ggplot.csv'))
check=Check()
assert check.percentage_missing(df) == {'name': 0.0, 'genus': 0.0, 'vore': 8.43, 'order': 0.0, 'conservation': 34.94, 'sleep_total': 0.0, 'sleep_rem': 26.51, 'sleep_cycle': 61.45, 'awake': 0.0, 'brainwt': 32.53, 'bodywt': 0.0}
def test_is_discrete_3():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_discrete(df['Location']) == False
def test_is_working():
check = Check()
print(check.is_working())
def test_is_outlier():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
print(check.is_outlier(df['crime'], 3))
def test_ignore_identifier_3():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'msleep_ggplot.csv'))
check = Check()
print(check.ignore_identifier(df))
def test_is_continuous_2():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_continuous(df['population']) == True
def test_is_discrete_1():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_discrete(df['crime']) == True
def test_is_missing_3():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_missing(df['nonwhite']) != True
def test_is_identifier_3():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_identifier(df['nonwhite']) == False
def test_is_categorical_1():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_categorical(df['Location']) == True
def test_is_missing_4():
df = pd.read_csv(
os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check = Check()
assert check.is_missing(df['density']) == True
def test_percentage_missing_1():
df = pd.read_csv(os.path.join(os.path.dirname(__file__), 'data', 'Freedman.csv'))
check=Check()
assert check.percentage_missing(df) == {'Location': 0.0, 'population': 9.09, 'nonwhite': 0.0, 'density': 9.09, 'crime': 0.0}
