def test_target_encoder_transform_when_not_fitted(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]
})
# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
encoder = TargetEncoder()
with pytest.raises(NotFittedError):
encoder.transform(data=df, column_names=["variable"])
def test_target_encoder_transform_new_category(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]
})
df_appended = df.append({
"variable": "new",
"target": 1
},
ignore_index=True)
# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
df_appended["variable"] = df_appended["variable"].astype("category")
expected = df_appended.copy()
expected["variable_enc"] = [
0.666667, 0.666667, 0.333333, 0.50000, 0.333333, 0.666667,
0.333333, 0.50000, 0.50000, 0.50000, 0.333333
]
encoder = TargetEncoder(imputation_strategy="min")
encoder.fit(data=df, column_names=["variable"], target_column="target")
actual = encoder.transform(data=df_appended, column_names=["variable"])
pd.testing.assert_frame_equal(actual, expected)
def test_target_encoder_transform_new_category_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]
})
df_appended = df.append({
"variable": "new",
"target": 10
},
ignore_index=True)
# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
df_appended["variable"] = df_appended["variable"].astype("category")
expected = df_appended.copy()
expected["variable_enc"] = [
4.500000, 4.500000, -4.666667, 0.250000, -4.666667, 4.500000,
-4.666667, 0.250000, 0.250000, 0.250000, 4.500000, -4.666667
] # min imputation for new value
encoder = TargetEncoder(imputation_strategy="min")
encoder.fit(data=df, column_names=["variable"], target_column="target")
actual = encoder.transform(data=df_appended, column_names=["variable"])
pd.testing.assert_frame_equal(actual, expected)
def test_target_encoder_transform_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]
})
# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
expected = df.copy()
expected["variable_enc"] = [
0.666667, 0.666667, 0.333333, 0.50000, 0.333333, 0.666667,
0.333333, 0.50000, 0.50000, 0.50000
]
encoder = TargetEncoder()
encoder.fit(data=df, column_names=["variable"], target_column="target")
actual = encoder.transform(data=df, column_names=["variable"])
pd.testing.assert_frame_equal(actual, expected)
def test_target_encoder_transform_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]
})
# inputs of TargetEncoder will be of dtype category
df["variable"] = df["variable"].astype("category")
expected = df.copy()
expected["variable_enc"] = [
4.500000, 4.500000, -4.666667, 0.250000, -4.666667, 4.500000,
-4.666667, 0.250000, 0.250000, 0.250000, 4.500000
]
encoder = TargetEncoder()
encoder.fit(data=df, column_names=["variable"], target_column="target")
actual = encoder.transform(data=df, column_names=["variable"])
pd.testing.assert_frame_equal(actual, expected)