def test_target_encoder_attributes_to_dict(self):
encoder = TargetEncoder()
mapping_data = pd.Series(data=[0.333333, 0.50000, 0.666667],
index=["negative", "neutral", "positive"])
mapping_data.index.name = "variable"
encoder._mapping["variable"] = mapping_data
encoder._global_mean = 0.5
actual = encoder.attributes_to_dict()
expected = {
"weight": 0.0,
"imputation_strategy": "mean",
"_global_mean": 0.5,
"_mapping": {
"variable": {
"negative": 0.333333,
"neutral": 0.50000,
"positive": 0.666667
}
}
}
assert actual == expected
def test_target_encoder_fit_column_global_mean_linear_regression(self):
df = pd.DataFrame({
'variable': [
'positive', 'positive', 'negative', 'neutral', 'negative',
'positive', 'negative', 'neutral', 'neutral', 'neutral',
'positive'
],
'target': [5, 4, -5, 0, -4, 5, -5, 0, 1, 0, 4]
})
encoder = TargetEncoder(weight=1)
encoder._global_mean = 0.454545
actual = encoder._fit_column(X=df.variable, y=df.target)
# expected new value:
# [count of the value * its mean encoding + weight (= 1) * global mean]
# / [count of the value + weight (=1)].
expected = pd.Series(data=[(3 * -4.666667 + 1 * 0.454545) / (3 + 1),
(4 * 0.250000 + 1 * 0.454545) / (4 + 1),
(4 * 4.500000 + 1 * 0.454545) / (4 + 1)],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
pd.testing.assert_series_equal(actual, expected)
def test_target_encoder_fit_column_binary_classification(self):
df = pd.DataFrame({
'variable': [
'positive', 'positive', 'negative', 'neutral', 'negative',
'positive', 'negative', 'neutral', 'neutral', 'neutral'
],
'target': [1, 1, 0, 0, 1, 0, 0, 0, 1, 1]
})
encoder = TargetEncoder()
encoder._global_mean = 0.5
actual = encoder._fit_column(X=df.variable, y=df.target)
expected = pd.Series(data=[0.333333, 0.50000, 0.666667],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
pd.testing.assert_series_equal(actual, expected)
def test_target_encoder_fit_column_linear_regression(self):
df = pd.DataFrame({
'variable': [
'positive', 'positive', 'negative', 'neutral', 'negative',
'positive', 'negative', 'neutral', 'neutral', 'neutral',
'positive'
],
'target': [5, 4, -5, 0, -4, 5, -5, 0, 1, 0, 4]
})
encoder = TargetEncoder()
encoder._global_mean = 0.454545
actual = encoder._fit_column(X=df.variable, y=df.target)
expected = pd.Series(data=[-4.666667, 0.250000, 4.500000],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
pd.testing.assert_series_equal(actual, expected)
def test_target_encoder_fit_column_global_mean(self):
df = pd.DataFrame({
'variable': [
'positive', 'positive', 'negative', 'neutral', 'negative',
'positive', 'negative', 'neutral', 'neutral', 'neutral'
],
'target': [1, 1, 0, 0, 1, 0, 0, 0, 1, 1]
})
encoder = TargetEncoder(weight=1)
encoder._global_mean = df.target.sum() / df.target.count() # is 0.5
actual = encoder._fit_column(X=df.variable, y=df.target)
expected = pd.Series(data=[0.375, 0.500, 0.625],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
pd.testing.assert_series_equal(actual, expected)