forked from recommenders-team/recommenders
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_notebooks_python.py
170 lines (146 loc) · 6.21 KB
/
test_notebooks_python.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
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
import pytest
try:
import papermill as pm
import scrapbook as sb
except ImportError:
pass # disable error while collecting tests for non-notebook environments
TOL = 0.05
ABS_TOL = 0.05
@pytest.mark.smoke
@pytest.mark.notebooks
def test_sar_single_node_smoke(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["sar_single_node"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(TOP_K=10, MOVIELENS_DATA_SIZE="100k"),
)
results = sb.read_notebook(output_notebook).scraps.dataframe.set_index("name")[
"data"
]
assert results["map"] == pytest.approx(0.110591, rel=TOL, abs=ABS_TOL)
assert results["ndcg"] == pytest.approx(0.382461, rel=TOL, abs=ABS_TOL)
assert results["precision"] == pytest.approx(0.330753, rel=TOL, abs=ABS_TOL)
assert results["recall"] == pytest.approx(0.176385, rel=TOL, abs=ABS_TOL)
@pytest.mark.smoke
@pytest.mark.notebooks
def test_baseline_deep_dive_smoke(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["baseline_deep_dive"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(TOP_K=10, MOVIELENS_DATA_SIZE="100k"),
)
results = sb.read_notebook(output_notebook).scraps.dataframe.set_index("name")[
"data"
]
assert results["rmse"] == pytest.approx(1.054252, rel=TOL, abs=ABS_TOL)
assert results["mae"] == pytest.approx(0.846033, rel=TOL, abs=ABS_TOL)
assert results["rsquared"] == pytest.approx(0.136435, rel=TOL, abs=ABS_TOL)
assert results["exp_var"] == pytest.approx(0.136446, rel=TOL, abs=ABS_TOL)
assert results["map"] == pytest.approx(0.052850, rel=TOL, abs=ABS_TOL)
assert results["ndcg"] == pytest.approx(0.248061, rel=TOL, abs=ABS_TOL)
assert results["precision"] == pytest.approx(0.223754, rel=TOL, abs=ABS_TOL)
assert results["recall"] == pytest.approx(0.108826, rel=TOL, abs=ABS_TOL)
@pytest.mark.smoke
@pytest.mark.notebooks
def test_surprise_svd_smoke(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["surprise_svd_deep_dive"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(MOVIELENS_DATA_SIZE="100k"),
)
results = sb.read_notebook(output_notebook).scraps.dataframe.set_index("name")[
"data"
]
assert results["rmse"] == pytest.approx(0.96, rel=TOL, abs=ABS_TOL)
assert results["mae"] == pytest.approx(0.75, rel=TOL, abs=ABS_TOL)
assert results["rsquared"] == pytest.approx(0.29, rel=TOL, abs=ABS_TOL)
assert results["exp_var"] == pytest.approx(0.29, rel=TOL, abs=ABS_TOL)
assert results["map"] == pytest.approx(0.013, rel=TOL, abs=ABS_TOL)
assert results["ndcg"] == pytest.approx(0.1, rel=TOL, abs=ABS_TOL)
assert results["precision"] == pytest.approx(0.095, rel=TOL, abs=ABS_TOL)
assert results["recall"] == pytest.approx(0.032, rel=TOL, abs=ABS_TOL)
@pytest.mark.smoke
@pytest.mark.notebooks
@pytest.mark.skip(reason="VW pip package has installation incompatibilities")
def test_vw_deep_dive_smoke(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["vowpal_wabbit_deep_dive"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(MOVIELENS_DATA_SIZE="100k"),
)
results = sb.read_notebook(output_notebook).scraps.dataframe.set_index("name")[
"data"
]
assert results["rmse"] == pytest.approx(0.985920, rel=TOL, abs=ABS_TOL)
assert results["mae"] == pytest.approx(0.71292, rel=TOL, abs=ABS_TOL)
assert results["rsquared"] == pytest.approx(0.231199, rel=TOL, abs=ABS_TOL)
assert results["exp_var"] == pytest.approx(0.231337, rel=TOL, abs=ABS_TOL)
assert results["map"] == pytest.approx(0.012535, rel=TOL, abs=ABS_TOL)
assert results["ndcg"] == pytest.approx(0.096594, rel=TOL, abs=ABS_TOL)
assert results["precision"] == pytest.approx(0.097770, rel=TOL, abs=ABS_TOL)
assert results["recall"] == pytest.approx(0.037612, rel=TOL, abs=ABS_TOL)
@pytest.mark.smoke
@pytest.mark.notebooks
def test_lightgbm_quickstart_smoke(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["lightgbm_quickstart"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(
MAX_LEAF=64,
MIN_DATA=20,
NUM_OF_TREES=100,
TREE_LEARNING_RATE=0.15,
EARLY_STOPPING_ROUNDS=20,
METRIC="auc",
),
)
results = sb.read_notebook(output_notebook).scraps.dataframe.set_index("name")[
"data"
]
assert results["res_basic"]["auc"] == pytest.approx(0.7674, rel=TOL, abs=ABS_TOL)
assert results["res_basic"]["logloss"] == pytest.approx(
0.4669, rel=TOL, abs=ABS_TOL
)
assert results["res_optim"]["auc"] == pytest.approx(0.7757, rel=TOL, abs=ABS_TOL)
assert results["res_optim"]["logloss"] == pytest.approx(
0.4607, rel=TOL, abs=ABS_TOL
)
@pytest.mark.smoke
@pytest.mark.notebooks
def test_cornac_bpr_smoke(notebooks, output_notebook, kernel_name):
notebook_path = notebooks["cornac_bpr_deep_dive"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(MOVIELENS_DATA_SIZE="100k"),
)
results = sb.read_notebook(output_notebook).scraps.dataframe.set_index("name")[
"data"
]
assert results["map"] == pytest.approx(0.1091, rel=TOL, abs=ABS_TOL)
assert results["ndcg"] == pytest.approx(0.4034, rel=TOL, abs=ABS_TOL)
assert results["precision"] == pytest.approx(0.3550, rel=TOL, abs=ABS_TOL)
assert results["recall"] == pytest.approx(0.1802, rel=TOL, abs=ABS_TOL)
@pytest.mark.smoke
@pytest.mark.notebooks
def test_mind_utils(notebooks, output_notebook, kernel_name, tmp):
notebook_path = notebooks["mind_utils"]
pm.execute_notebook(
notebook_path,
output_notebook,
kernel_name=kernel_name,
parameters=dict(mind_type="small", word_embedding_dim=300),
)