-
Notifications
You must be signed in to change notification settings - Fork 58
/
test_baselines.py
259 lines (186 loc) · 7.85 KB
/
test_baselines.py
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
import lenskit.algorithms.basic as bl
from lenskit import util as lku
import logging
import pickle
import pandas as pd
import numpy as np
from pytest import approx
import lenskit.util.test as lktu
from lenskit.util.test import ml_test
_log = logging.getLogger(__name__)
simple_df = pd.DataFrame({'item': [1, 1, 2, 3],
'user': [10, 12, 10, 13],
'rating': [4.0, 3.0, 5.0, 2.0]})
def test_bias_full():
algo = bl.Bias()
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is not None
assert algo.item_offsets_.index.name == 'item'
assert set(algo.item_offsets_.index) == set([1, 2, 3])
assert algo.item_offsets_.loc[1:3].values == approx(np.array([0, 1.5, -1.5]))
assert algo.user_offsets_ is not None
assert algo.user_offsets_.index.name == 'user'
assert set(algo.user_offsets_.index) == set([10, 12, 13])
assert algo.user_offsets_.loc[[10, 12, 13]].values == approx(np.array([0.25, -0.5, 0]))
def test_bias_clone():
algo = bl.Bias()
algo.fit(simple_df)
params = algo.get_params()
assert sorted(params.keys()) == ['damping', 'items', 'users']
a2 = lku.clone(algo)
assert a2 is not algo
assert getattr(a2, 'mean_', None) is None
assert getattr(a2, 'item_offsets_', None) is None
assert getattr(a2, 'user_offsets_', None) is None
def test_bias_global_only():
algo = bl.Bias(users=False, items=False)
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is None
assert algo.user_offsets_ is None
def test_bias_no_user():
algo = bl.Bias(users=False)
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is not None
assert algo.item_offsets_.index.name == 'item'
assert set(algo.item_offsets_.index) == set([1, 2, 3])
assert algo.item_offsets_.loc[1:3].values == approx(np.array([0, 1.5, -1.5]))
assert algo.user_offsets_ is None
def test_bias_no_item():
algo = bl.Bias(items=False)
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is None
assert algo.user_offsets_ is not None
assert algo.user_offsets_.index.name == 'user'
assert set(algo.user_offsets_.index) == set([10, 12, 13])
assert algo.user_offsets_.loc[[10, 12, 13]].values == approx(np.array([1.0, -0.5, -1.5]))
def test_bias_global_predict():
algo = bl.Bias(items=False, users=False)
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 2, 3])
assert len(p) == 3
assert (p == algo.mean_).all()
assert p.values == approx(algo.mean_)
def test_bias_item_predict():
algo = bl.Bias(users=False)
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 2, 3])
assert len(p) == 3
assert p.values == approx((algo.item_offsets_ + algo.mean_).values)
def test_bias_user_predict():
algo = bl.Bias(items=False)
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 2, 3])
assert len(p) == 3
assert p.values == approx(algo.mean_ + 1.0)
p = algo.predict_for_user(12, [1, 3])
assert len(p) == 2
assert p.values == approx(algo.mean_ - 0.5)
def test_bias_new_user_predict():
algo = bl.Bias()
algo.fit(simple_df)
ratings = pd.DataFrame({'item': [1, 2, 3], 'rating': [1.5, 2.5, 3.5]})
ratings = ratings.set_index('item').rating
p = algo.predict_for_user(None, [1, 3], ratings=ratings)
offs = ratings - algo.mean_ - algo.item_offsets_
umean = offs.mean()
_log.info('user mean is %f', umean)
assert len(p) == 2
assert p.values == approx((algo.mean_ + algo.item_offsets_ + umean).loc[[1, 3]].values)
def test_bias_predict_unknown_item():
algo = bl.Bias()
algo.fit(simple_df)
p = algo.predict_for_user(10, [1, 3, 4])
assert len(p) == 3
intended = algo.item_offsets_.loc[[1, 3]] + algo.mean_ + 0.25
assert p.loc[[1, 3]].values == approx(intended.values)
assert p.loc[4] == approx(algo.mean_ + 0.25)
def test_bias_predict_unknown_user():
algo = bl.Bias()
algo.fit(simple_df)
p = algo.predict_for_user(15, [1, 3])
assert len(p) == 2
assert p.values == approx((algo.item_offsets_.loc[[1, 3]] + algo.mean_).values)
def test_bias_train_ml_ratings():
algo = bl.Bias()
ratings = ml_test.ratings
algo.fit(ratings)
assert algo.mean_ == approx(ratings.rating.mean())
imeans_data = ratings.groupby('item').rating.mean()
imeans_algo = algo.item_offsets_ + algo.mean_
ares, data = imeans_algo.align(imeans_data)
assert ares.values == approx(data.values)
urates = ratings.set_index('user').loc[2].set_index('item').rating
umean = (urates - imeans_data[urates.index]).mean()
p = algo.predict_for_user(2, [10, 11, -1])
assert len(p) == 3
assert p.iloc[0] == approx(imeans_data.loc[10] + umean)
assert p.iloc[1] == approx(imeans_data.loc[11] + umean)
assert p.iloc[2] == approx(ratings.rating.mean() + umean)
def test_bias_item_damp():
algo = bl.Bias(users=False, damping=5)
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is not None
assert algo.item_offsets_.index.name == 'item'
assert set(algo.item_offsets_.index) == set([1, 2, 3])
assert algo.item_offsets_.loc[1:3].values == approx(np.array([0, 0.25, -0.25]))
assert algo.user_offsets_ is None
def test_bias_user_damp():
algo = bl.Bias(items=False, damping=5)
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is None
assert algo.user_offsets_ is not None
assert algo.user_offsets_.index.name == 'user'
assert set(algo.user_offsets_.index) == set([10, 12, 13])
assert algo.user_offsets_.loc[[10, 12, 13]].values == \
approx(np.array([0.2857, -0.08333, -0.25]), abs=1.0e-4)
def test_bias_damped():
algo = bl.Bias(damping=5)
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is not None
assert algo.item_offsets_.index.name == 'item'
assert set(algo.item_offsets_.index) == set([1, 2, 3])
assert algo.item_offsets_.loc[1:3].values == approx(np.array([0, 0.25, -0.25]))
assert algo.user_offsets_ is not None
assert algo.user_offsets_.index.name == 'user'
assert set(algo.user_offsets_.index) == set([10, 12, 13])
assert algo.user_offsets_.loc[[10, 12, 13]].values == \
approx(np.array([0.25, -00.08333, -0.20833]), abs=1.0e-4)
def test_bias_separate_damping():
algo = bl.Bias(damping=(5, 10))
algo.fit(simple_df)
assert algo.mean_ == approx(3.5)
assert algo.item_offsets_ is not None
assert algo.item_offsets_.index.name == 'item'
assert set(algo.item_offsets_.index) == set([1, 2, 3])
assert algo.item_offsets_.loc[1:3].values == \
approx(np.array([0, 0.136364, -0.13636]), abs=1.0e-4)
assert algo.user_offsets_ is not None
assert algo.user_offsets_.index.name == 'user'
assert set(algo.user_offsets_.index) == set([10, 12, 13])
assert algo.user_offsets_.loc[[10, 12, 13]].values == \
approx(np.array([0.266234, -0.08333, -0.22727]), abs=1.0e-4)
def test_bias_save():
original = bl.Bias(damping=5)
original.fit(simple_df)
assert original.mean_ == approx(3.5)
_log.info('saving baseline model')
mod = pickle.dumps(original)
_log.info('serialized to %d bytes', len(mod))
algo = pickle.loads(mod)
assert algo.mean_ == original.mean_
assert algo.item_offsets_ is not None
assert algo.item_offsets_.index.name == 'item'
assert set(algo.item_offsets_.index) == set([1, 2, 3])
assert algo.item_offsets_.loc[1:3].values == approx(np.array([0, 0.25, -0.25]))
assert algo.user_offsets_ is not None
assert algo.user_offsets_.index.name == 'user'
assert set(algo.user_offsets_.index) == set([10, 12, 13])
assert algo.user_offsets_.loc[[10, 12, 13]].values == \
approx(np.array([0.25, -00.08333, -0.20833]), abs=1.0e-4)