-
Notifications
You must be signed in to change notification settings - Fork 7
Expand file tree
/
Copy pathtest_target_encoder.py
More file actions
392 lines (293 loc) · 17.5 KB
/
Copy pathtest_target_encoder.py
File metadata and controls
392 lines (293 loc) · 17.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
import pytest
import pandas as pd
from sklearn.exceptions import NotFittedError
from cobra.preprocessing.target_encoder import TargetEncoder
class TestTargetEncoder:
def test_target_encoder_constructor_weight_value_error(self):
with pytest.raises(ValueError):
TargetEncoder(weight=-1)
def test_target_encoder_constructor_imputation_value_error(self):
with pytest.raises(ValueError):
TargetEncoder(imputation_strategy="something")
# Tests for attributes_attributes_to_dict and set_attributes_from_dict
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
@pytest.mark.parametrize("attribute",
["weight", "mapping"],
ids=["test_weight", "test_mapping"])
def test_target_encoder_set_attributes_from_dict_unfitted(self, attribute):
encoder = TargetEncoder()
data = {"weight": 1.0}
encoder.set_attributes_from_dict(data)
if attribute == "weight":
actual = encoder.weight
expected = 1.0
assert expected == actual
elif attribute == "mapping":
actual = encoder._mapping
expected = {}
assert expected == actual
def test_target_encoder_set_attributes_from_dict(self):
encoder = TargetEncoder()
data = {"weight": 0.0,
"_global_mean": 0.5,
"_mapping": {"variable": {
"negative": 0.333333,
"neutral": 0.50000,
"positive": 0.666667
}}}
encoder.set_attributes_from_dict(data)
expected = pd.Series(data=[0.333333, 0.50000, 0.666667],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
actual = encoder._mapping["variable"]
pd.testing.assert_series_equal(actual, expected)
# Tests for _fit_column:
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_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(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)
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)
# Tests for fit method
def test_target_encoder_fit_binary_classification(self):
# test_target_encoder_fit_column_linear_regression() tested on one
# column input as a numpy series; this test runs on a dataframe input.
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.fit(data=df, column_names=["variable"], target_column="target")
expected = pd.Series(data=[0.333333, 0.50000, 0.666667],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
actual = encoder._mapping["variable"]
pd.testing.assert_series_equal(actual, expected)
def test_target_encoder_fit_linear_regression(self):
# test_target_encoder_fit_column_linear_regression() tested on one
# column input as a numpy series; this test runs on a dataframe input.
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.fit(data=df, column_names=["variable"], target_column="target")
expected = pd.Series(data=[-4.666667, 0.250000, 4.500000],
index=["negative", "neutral", "positive"])
expected.index.name = "variable"
actual = encoder._mapping["variable"]
pd.testing.assert_series_equal(actual, expected)
# Tests for transform method
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_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)
def test_target_encoder_transform_new_category_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]})
df_appended = pd.concat([df, pd.DataFrame({"variable": "new", "target": 1}, index=[len(df)])], 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 = pd.concat([df, pd.DataFrame({"variable": "new", "target": 10}, index=[len(df)])], 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_new_category_linear_regression_median(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]})
new_row = pd.DataFrame({"variable": ["new"], "target": [10]})
df_appended = pd.concat([df, new_row], 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,
0.250000] # median imputation for new value
encoder = TargetEncoder(imputation_strategy="median")
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_binary_classification_median(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]})
new_row = pd.DataFrame({"variable": ["new"], "target": [1]})
df_appended = pd.concat([df, new_row], 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, 0.50000]
encoder = TargetEncoder(imputation_strategy="median")
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)
# Tests for _clean_column_name:
def test_target_encoder_clean_column_name_binned_column(self):
column_name = "test_column_bin"
expected = "test_column_enc"
encoder = TargetEncoder()
actual = encoder._clean_column_name(column_name)
assert actual == expected
def test_target_encoder_clean_column_name_processed_column(self):
column_name = "test_column_processed"
expected = "test_column_enc"
encoder = TargetEncoder()
actual = encoder._clean_column_name(column_name)
assert actual == expected
def test_target_encoder_clean_column_name_cleaned_column(self):
column_name = "test_column_cleaned"
expected = "test_column_enc"
encoder = TargetEncoder()
actual = encoder._clean_column_name(column_name)
assert actual == expected
def test_target_encoder_clean_column_other_name(self):
column_name = "test_column"
expected = "test_column_enc"
encoder = TargetEncoder()
actual = encoder._clean_column_name(column_name)
assert actual == expected