-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathtest_pandas_input.py
More file actions
161 lines (133 loc) · 6.29 KB
/
test_pandas_input.py
File metadata and controls
161 lines (133 loc) · 6.29 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
import unittest
import numpy as np
import pandas as pd
from unittest.mock import MagicMock
from sklearn.linear_model import LogisticRegression
from dte_adj import (
SimpleDistributionEstimator,
AdjustedDistributionEstimator,
SimpleStratifiedDistributionEstimator,
AdjustedStratifiedDistributionEstimator,
SimpleLocalDistributionEstimator,
AdjustedLocalDistributionEstimator,
)
class TestPandasInputSimple(unittest.TestCase):
"""Test that Simple/Adjusted DistributionEstimator accept pandas inputs."""
def setUp(self):
np.random.seed(42)
n = 20
self.covariates_df = pd.DataFrame(np.zeros((n, 5)), columns=[f"x{i}" for i in range(5)])
self.treatment_arms_series = pd.Series(np.hstack([np.zeros(10), np.ones(10)]))
self.outcomes_series = pd.Series(np.arange(n, dtype=float))
def test_simple_estimator_with_dataframe_and_series(self):
estimator = SimpleDistributionEstimator()
result = estimator.fit(
self.covariates_df, self.treatment_arms_series, self.outcomes_series
)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)
def test_simple_estimator_predict_after_pandas_fit(self):
estimator = SimpleDistributionEstimator()
estimator.fit(self.covariates_df, self.treatment_arms_series, self.outcomes_series)
output = estimator.predict(0, np.array([3, 6]))
expected = np.array([0.4, 0.7])
np.testing.assert_array_almost_equal(output, expected, decimal=2)
def test_adjusted_estimator_with_dataframe_and_series(self):
base_model = MagicMock()
base_model.predict_proba.side_effect = lambda x, y: x
estimator = AdjustedDistributionEstimator(base_model, folds=2)
result = estimator.fit(
self.covariates_df, self.treatment_arms_series, self.outcomes_series
)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)
class TestPandasInputStratified(unittest.TestCase):
"""Test that Stratified estimators accept pandas inputs."""
def setUp(self):
np.random.seed(42)
n = 100
self.covariates_df = pd.DataFrame(
np.random.randn(n, 5), columns=[f"x{i}" for i in range(5)]
)
self.treatment_arms_series = pd.Series(np.random.choice([0, 1], size=n))
self.outcomes_series = pd.Series(np.random.randn(n))
self.strata_series = pd.Series(np.random.choice([0, 1, 2], size=n))
def test_simple_stratified_with_pandas(self):
estimator = SimpleStratifiedDistributionEstimator()
result = estimator.fit(
self.covariates_df,
self.treatment_arms_series,
self.outcomes_series,
self.strata_series,
)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)
self.assertIsInstance(result.strata, np.ndarray)
def test_adjusted_stratified_with_pandas(self):
base_model = LogisticRegression(random_state=42)
estimator = AdjustedStratifiedDistributionEstimator(base_model, folds=2)
result = estimator.fit(
self.covariates_df,
self.treatment_arms_series,
self.outcomes_series,
self.strata_series,
)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)
self.assertIsInstance(result.strata, np.ndarray)
class TestPandasInputLocal(unittest.TestCase):
"""Test that Local estimators accept pandas inputs."""
def setUp(self):
np.random.seed(42)
n = 100
self.covariates_df = pd.DataFrame(
np.random.randn(n, 3), columns=[f"x{i}" for i in range(3)]
)
self.treatment_arms_series = pd.Series(np.random.choice([0, 1], size=n))
self.treatment_indicator_series = pd.Series(np.random.choice([0, 1], size=n))
self.outcomes_series = pd.Series(np.random.randn(n))
self.strata_series = pd.Series(np.random.choice([0, 1], size=n))
def test_simple_local_with_pandas(self):
estimator = SimpleLocalDistributionEstimator()
result = estimator.fit(
self.covariates_df,
self.treatment_arms_series,
self.treatment_indicator_series,
self.outcomes_series,
self.strata_series,
)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.treatment_indicator, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)
self.assertIsInstance(result.strata, np.ndarray)
def test_adjusted_local_with_pandas(self):
base_model = LogisticRegression(random_state=42)
estimator = AdjustedLocalDistributionEstimator(base_model=base_model)
result = estimator.fit(
self.covariates_df,
self.treatment_arms_series,
self.treatment_indicator_series,
self.outcomes_series,
self.strata_series,
)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.treatment_indicator, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)
self.assertIsInstance(result.strata, np.ndarray)
class TestNumpyInputStillWorks(unittest.TestCase):
"""Verify that np.ndarray inputs continue to work as before."""
def test_simple_estimator_with_numpy(self):
estimator = SimpleDistributionEstimator()
covariates = np.zeros((20, 5))
treatment_arms = np.hstack([np.zeros(10), np.ones(10)])
outcomes = np.arange(20, dtype=float)
result = estimator.fit(covariates, treatment_arms, outcomes)
self.assertIsInstance(result.covariates, np.ndarray)
self.assertIsInstance(result.treatment_arms, np.ndarray)
self.assertIsInstance(result.outcomes, np.ndarray)