def test_variables_cast_as_category(df_enc_category_dtypes):
encoder = CountFrequencyEncoder(encoding_method="count", variables=["var_A"])
X = encoder.fit_transform(df_enc_category_dtypes)
# expected result
transf_df = df_enc_category_dtypes.copy()
transf_df["var_A"] = [
6,
6,
6,
6,
6,
6,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
4,
4,
4,
4,
]
# transform params
pd.testing.assert_frame_equal(X, transf_df, check_dtype=False)
assert X["var_A"].dtypes == int
encoder = CountFrequencyEncoder(encoding_method="frequency", variables=["var_A"])
X = encoder.fit_transform(df_enc_category_dtypes)
assert X["var_A"].dtypes == float
def test_column_names_are_numbers(df_numeric_columns):
encoder = CountFrequencyEncoder(encoding_method="frequency",
variables=[0, 1, 2, 3],
ignore_format=True)
X = encoder.fit_transform(df_numeric_columns)
# expected output
transf_df = {
0: [0.25, 0.25, 0.25, 0.25],
1: [0.25, 0.25, 0.25, 0.25],
2: [0.25, 0.25, 0.25, 0.25],
3: [0.25, 0.25, 0.25, 0.25],
4: pd.date_range("2020-02-24", periods=4, freq="T"),
}
transf_df = pd.DataFrame(transf_df)
# init params
assert encoder.encoding_method == "frequency"
assert encoder.variables == [0, 1, 2, 3]
# fit params
assert encoder.variables_ == [0, 1, 2, 3]
assert encoder.n_features_in_ == 5
# transform params
pd.testing.assert_frame_equal(X, transf_df)
def test_ignore_variable_format_with_frequency(df_vartypes):
encoder = CountFrequencyEncoder(encoding_method="frequency",
variables=None,
ignore_format=True)
X = encoder.fit_transform(df_vartypes)
# expected output
transf_df = {
"Name": [0.25, 0.25, 0.25, 0.25],
"City": [0.25, 0.25, 0.25, 0.25],
"Age": [0.25, 0.25, 0.25, 0.25],
"Marks": [0.25, 0.25, 0.25, 0.25],
"dob": [0.25, 0.25, 0.25, 0.25],
}
transf_df = pd.DataFrame(transf_df)
# init params
assert encoder.encoding_method == "frequency"
assert encoder.variables is None
# fit params
assert encoder.variables_ == ["Name", "City", "Age", "Marks", "dob"]
assert encoder.n_features_in_ == 5
# transform params
pd.testing.assert_frame_equal(X, transf_df)
def clean_data(X):
X.dropna(subset=['target'], inplace=True)
y = X.pop('target')
X.drop(columns='ID', inplace=True)
X['v22'] = X['v22'].apply(az_to_int)
cat_cols = X.select_dtypes(include=['object']).columns.tolist()
con_cols = X.select_dtypes(include=['number']).columns.tolist()
num_missing_imputer = SimpleImputer(strategy='median')
cat_missing_imputer = CategoricalImputer(fill_value='__MISS__')
rare_label_encoder = RareLabelEncoder(tol=0.01, n_categories=10, replace_with='__OTHER__')
cat_freq_encoder = CountFrequencyEncoder(encoding_method="frequency")
X[con_cols] = num_missing_imputer.fit_transform(X[con_cols])
X[cat_cols] = cat_missing_imputer.fit_transform(X[cat_cols])
X[cat_cols] = rare_label_encoder.fit_transform(X[cat_cols])
X[cat_cols] = cat_freq_encoder.fit_transform(X[cat_cols])
# more cleaning
trimmer = Winsorizer(capping_method='quantiles', tail='both', fold=0.005)
X = trimmer.fit_transform(X)
undersampler = RandomUnderSampler(sampling_strategy=0.7, random_state=1234)
X, Y = undersampler.fit_resample(X, y)
quasi_constant = DropConstantFeatures(tol=0.998)
X = quasi_constant.fit_transform(X)
print(f"Quasi Features to drop {quasi_constant.features_to_drop_}")
# Remove duplicated features¶
duplicates = DropDuplicateFeatures()
X = duplicates.fit_transform(X)
print(f"Duplicate feature sets {duplicates.duplicated_feature_sets_}")
print(f"Dropping duplicate features {duplicates.features_to_drop_}")
drop_corr = DropCorrelatedFeatures(method="pearson", threshold=0.95, missing_values="ignore")
X = drop_corr.fit_transform(X)
print(f"Drop correlated feature sets {drop_corr.correlated_feature_sets_}")
print(f"Dropping correlared features {drop_corr.features_to_drop_}")
X['target'] = Y
return X
def test_encode_1_variable_with_counts(df_enc):
# test case 1: 1 variable, counts
encoder = CountFrequencyEncoder(encoding_method="count",
variables=["var_A"])
X = encoder.fit_transform(df_enc)
# expected result
transf_df = df_enc.copy()
transf_df["var_A"] = [
6,
6,
6,
6,
6,
6,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
4,
4,
4,
4,
]
# init params
assert encoder.encoding_method == "count"
assert encoder.variables == ["var_A"]
# fit params
assert encoder.variables_ == ["var_A"]
assert encoder.encoder_dict_ == {"var_A": {"A": 6, "B": 10, "C": 4}}
assert encoder.n_features_in_ == 3
# transform params
pd.testing.assert_frame_equal(X, transf_df)
def test_automatically_select_variables_encode_with_frequency(df_enc):
# test case 2: automatically select variables, frequency
encoder = CountFrequencyEncoder(encoding_method="frequency",
variables=None)
X = encoder.fit_transform(df_enc)
# expected output
transf_df = df_enc.copy()
transf_df["var_A"] = [
0.3,
0.3,
0.3,
0.3,
0.3,
0.3,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.2,
0.2,
0.2,
0.2,
]
transf_df["var_B"] = [
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.5,
0.3,
0.3,
0.3,
0.3,
0.3,
0.3,
0.2,
0.2,
0.2,
0.2,
]
# init params
assert encoder.encoding_method == "frequency"
assert encoder.variables == ["var_A", "var_B"]
# fit params
assert encoder.encoder_dict_ == {
"var_A": {
"A": 0.3,
"B": 0.5,
"C": 0.2
},
"var_B": {
"A": 0.5,
"B": 0.3,
"C": 0.2
},
}
assert encoder.input_shape_ == (20, 3)
# transform params
pd.testing.assert_frame_equal(X, transf_df)