def test_cleanutil_replaceinterpol(self):
int_missing_data = [
[1, 8, 1],
[0, 9394, 2],
[np.nan, np.nan, np.nan],
[2, 4, 3],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[1, 8, 1],
[0, 9394, 2],
[np.nan, np.nan, np.nan],
[2, 4, 3],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5)
clean.replace_missing_interpolate("col1",
"col2",
"col3",
limit_direction="both")
validate = np.any(clean.x_train.isnull()) and np.any(
clean.x_test.isnull())
self.assertFalse(validate)
def test_cleanutil_splitdata(self):
data = np.zeros((5, 5))
columns = ["col1", "col2", "col3", "col4", "col5"]
dataset = pd.DataFrame(data, columns=columns)
clean = Clean(x_train=dataset)
self.assertEqual(clean.x_train.shape[0], 4)
def test_cleanutil_removecolumns(self):
int_missing_data = [[1, 0, 0], [0, None, None], [None, None, None]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.remove_columns(0.5)
validate = clean.x_train.columns.tolist()
self.assertListEqual(validate, ["col1"])
def test_cleanutil_removerows(self):
int_missing_data = np.array([(1, 0, 0), (0, None, None),
(None, None, None)])
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.remove_rows(0.5)
validate = clean.x_train.values.tolist()
self.assertListEqual(validate, np.array([(1, 0, 0)]).tolist())
def test_cleanutil_removeduplicatecolumns(self):
data = [[1, 0, 1], [0, 2, 0], [1, 0, 1]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.remove_duplicate_columns()
validate = clean.x_train.values.tolist()
self.assertListEqual(validate, [[1, 0], [0, 2], [1, 0]])
def test_cleannumeric_median(self):
int_missing_data = [[1, 0, 2], [0, np.nan, 1],
[np.nan, np.nan, np.nan]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_median()
validate = clean.x_train.values.tolist()
self.assertListEqual(validate, [[1, 0, 2], [0, 0, 1], [0.5, 0, 1.5]])
def test_cleancategorical_removerow(self):
int_missing_data = [[1, 0, 2], [1, np.nan, 1],
[np.nan, np.nan, np.nan]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_remove_row("col1", "col2")
validate = clean.x_train.values.tolist()
self.assertListEqual(validate, np.array([(1, 0, 2)]).tolist())
def test_lineplot(self):
np.random.seed(42)
df = pd.DataFrame({
"Google": np.random.randn(1000) + 0.2,
"Apple": np.random.randn(1000) + 0.17,
"date": pd.date_range("1/1/2000", periods=1000),
})
clean = Clean(x_train=df, split=False)
clean.visualize_lineplot("date", "Google", "Apple", show_figure=False)
self.assertTrue(True)
def test_write_data_tocsv(self):
np.random.seed(42)
df = pd.DataFrame({
"Google": np.random.randn(1000) + 0.2,
"Apple": np.random.randn(1000) + 0.17,
"date": pd.date_range("1/1/2000", periods=1000),
})
clean = Clean(x_train=df, split=False)
clean.to_csv("test_write_data")
os.remove("test_write_data_train.csv")
self.assertTrue(True)
def test_cleancategorical_replacemissingnewcategory_noparams(self):
missing_data = [[1.0, "Green", 2], [1.0, "Other", 1],
[np.nan, np.nan, np.nan]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_new_category()
validate = clean.x_train.values.tolist()
self.assertListEqual(
validate, [[1, "Green", 2], [1, "Other", 1], [-1, "Unknown", -1]])
def test_cleannumeric_constant(self):
int_missing_data = np.array([(1, 0, 2), (1, None, 1),
(None, None, None)])
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_constant("col1", "col3", constant=10.5)
validate = clean.x_train.values.tolist()
self.assertListEqual(
validate,
np.array([(1, 0, 2), (1, None, 1), (10.5, None, 10.5)]).tolist())
def test_cleancategorical_replacemissingnewcategory_dict(self):
missing_data = [[1, "Green", 2], [1, np.nan, 1],
[np.nan, np.nan, np.nan]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(missing_data, columns=columns)
category_dict_mapping = {"col1": 2, "col2": "Blue", "col3": 4}
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_new_category(col_mapping=category_dict_mapping)
validate = clean.x_train.values.tolist()
self.assertListEqual(
validate,
[[1.0, "Green", 2.0], [1.0, "Blue", 1.0], [2.0, "Blue", 4.0]])
def test_cleannumeric_mostfrequent(self):
int_missing_data = np.array([(1, 0, 2), (1, np.nan, 1),
(np.nan, np.nan, 1)])
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_mostcommon()
validate = clean.x_train.values.tolist()
self.assertListEqual(
validate,
np.array([(1.0, 0.0, 2.0), (1.0, 0.0, 1.0),
(1.0, 0.0, 1.0)]).tolist(),
)
def test_dropcolumns_keep(self):
int_missing_data = [[1, 0, 0], [0, 2, 3], [0, 3, 4], [1, 2, 3]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data,
report_name="test",
test_split_percentage=0.5)
clean_inst = clean.drop(keep=["col2"],
reason="Columns were unimportant.")
validate = (clean_inst.x_train.columns == ["col2"]
and clean_inst.x_test.columns == ["col2"]
and isinstance(clean_inst, Clean))
self.assertTrue(validate)
def test_cleanutil_replacebfill(self):
int_missing_data = [
[1, 8, 1],
[0, 9394, 2],
[np.nan, np.nan, np.nan],
[2, 4, 3],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5)
clean.replace_missing_backfill("col1", "col2", "col3")
self.assertTrue(True)
def test_gettargetmapping(self):
data = pd.DataFrame({
"A": [1, 1, 2, 2],
"B": [1, 2, 3, 4],
"C": np.random.randn(4),
"D": ["A", "A", "B", "B"],
})
clean = Clean(
x_train=data,
x_test=None,
split=False,
target_field="",
report_name="test",
test_split_percentage=0.5,
)
self.assertIsNone(clean.target_mapping)
def test_search_notequal(self):
data = pd.DataFrame({
"A": [1, 1, 2, 2],
"B": [1, 2, 3, 4],
"C": np.random.randn(4),
"D": ["A", "A", "B", "B"],
})
clean = Clean(
x_train=data,
x_test=None,
split=False,
target_field="",
report_name="test",
test_split_percentage=0.5,
)
clean.search("A", not_equal=True, replace=True)
self.assertTrue(True)
def test_encodelabels(self):
data = pd.DataFrame({
"A": [1, 1, 2, 2],
"B": [1, 2, 3, 4],
"C": np.random.randn(4),
"D": ["B", "A", "B", "B"],
})
clean = Clean(
x_train=data,
x_test=None,
split=False,
target_field="D",
report_name="test",
test_split_percentage=0.5,
)
clean.encode_target()
self.assertDictEqual(clean.target_mapping, {0: "A", 1: "B"})
def test_report_cleaning_technique(self):
int_missing_data = np.array([(1, 0, 0), (0, None, None),
(None, None, None)])
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data,
test_split_percentage=0.5,
split=False,
report_name="test")
clean.remove_columns(0.5)
with open(clean._data_properties.report.filename) as f:
content = f.read()
validate = "col2" in content and "col3" in content
os.remove(clean._data_properties.report.filename)
self.assertTrue(validate)
def test_cleancategorical_replacemissingnewcategory_list_constantnotnone(
self):
missing_data = np.array([(1, "Green", 2), (1, "Other", 1),
(None, None, None)])
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(missing_data, columns=columns)
list_col = ["col1", "col3"]
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_new_category(list_of_cols=list_col,
new_category=0)
validate = clean.x_train.values.tolist()
self.assertListEqual(
validate,
np.array([(1, "Green", 2), (1, "Other", 1),
(0, None, 0)]).tolist(),
)
def test_cleanutil_replaceindicator_removecol(self):
int_missing_data = [
[1, 8, 1],
[0, 9394, 2],
[np.nan, np.nan, np.nan],
[2, 4, 3],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(x_train=data, test_split_percentage=0.5)
clean.replace_missing_indicator("col1", "col2", "col3", keep_col=False)
validate = (clean.x_train.shape[1] == 3) and (clean.x_test.shape[1]
== 3)
self.assertTrue(True)
def test_report_cleaning_new_category(self):
missing_data = [[1.0, "Green", 2], [1.0, "Other", 1],
[np.nan, np.nan, np.nan]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(missing_data, columns=columns)
clean = Clean(x_train=data,
test_split_percentage=0.5,
split=False,
report_name="test")
clean_data = clean.replace_missing_new_category()
with open(clean._data_properties.report.filename) as f:
content = f.read()
validate = "col1" in content and "col2" in content and "col3" in content
os.remove(clean._data_properties.report.filename)
self.assertTrue(validate)
def test_cleancategorical_replacemissingnewcategory_list_constantisnone(
self):
missing_data = [[1.0, "Green", 2], [1.0, "Other", 1],
[np.nan, None, np.nan]]
columns = ["col1", "col2", "col3"]
data = pd.DataFrame(missing_data, columns=columns)
list_col = ["col1", "col2"]
clean = Clean(x_train=data, test_split_percentage=0.5, split=False)
clean.replace_missing_new_category(list_of_cols=list_col)
# Replacing NaNs with strings for validations as regular assert does == and to compare NaNs you need `is`
clean._data_properties.x_train = clean.x_train.fillna("NaN was here")
validate = clean.x_train.values.tolist()
self.assertListEqual(
validate,
[[1, "Green", 2.0], [1, "Other", 1.0],
[-1, "Unknown", "NaN was here"]],
)
def test_dropcolumns_complex(self):
int_missing_data = [[1, 0, 0, 3], [0, 2, 3, 4], [0, 3, 4, 4],
[1, 2, 3, 6]]
columns = ["col1", "col2", "col3", "py"]
data = pd.DataFrame(int_missing_data, columns=columns)
clean = Clean(
x_train=data,
x_test=None,
split=True,
target_field="",
report_name="test",
test_split_percentage=0.5,
)
clean.drop("col1",
keep=["col2"],
regexp=r"col*",
reason="Columns were unimportant.")
validate = list(clean.x_train.columns) == ["col2", "py"] and list(
clean.x_test.columns) == ["col2", "py"]
self.assertTrue(validate)
