-
Notifications
You must be signed in to change notification settings - Fork 1.7k
/
test_supervised_predict_model.py
135 lines (115 loc) · 4.78 KB
/
test_supervised_predict_model.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
import numpy as np
import pandas as pd
import pycaret.classification
import pycaret.datasets
import pycaret.regression
def test_classification_predict_model():
# loading classification dataset
data = pycaret.datasets.get_data("juice")
assert isinstance(data, pd.DataFrame)
training_data = data.sample(frac=0.90)
unseen_data = data.drop(training_data.index)
# init setup
pycaret.classification.setup(
data,
target="Purchase",
ignore_features=["WeekofPurchase"],
remove_multicollinearity=True,
multicollinearity_threshold=0.95,
html=False,
session_id=123,
n_jobs=1,
)
lr_model = pycaret.classification.create_model("lr")
predictions = pycaret.classification.predict_model(lr_model, data=unseen_data)
metrics = pycaret.classification.pull()
# Check that columns of raw data are contained in columns of returned dataframe
assert all(item in predictions.columns for item in unseen_data.columns)
assert all(metrics[metric][0] for metric in metrics.columns)
predictions = pycaret.classification.predict_model(lr_model)
metrics = pycaret.classification.pull()
assert set(predictions["prediction_label"].unique()) == set(
data["Purchase"].unique()
)
assert all(metrics[metric][0] for metric in metrics.columns)
predictions = pycaret.classification.predict_model(lr_model, raw_score=True)
metrics = pycaret.classification.pull()
assert all(metrics[metric][0] for metric in metrics.columns)
predictions = pycaret.classification.predict_model(lr_model, encoded_labels=True)
metrics = pycaret.classification.pull()
assert set(predictions["prediction_label"].unique()) == {0, 1}
assert all(metrics[metric][0] for metric in metrics.columns)
def test_multiclass_predict_model():
# loading classification dataset
data = pycaret.datasets.get_data("iris")
assert isinstance(data, pd.DataFrame)
training_data = data.sample(frac=0.90)
unseen_data = data.drop(training_data.index)
# init setup
pycaret.classification.setup(
data,
target="species",
remove_multicollinearity=True,
multicollinearity_threshold=0.95,
html=False,
session_id=123,
n_jobs=1,
)
lr_model = pycaret.classification.create_model("lr")
predictions = pycaret.classification.predict_model(lr_model, data=unseen_data)
metrics = pycaret.classification.pull()
# Check that columns of raw data are contained in columns of returned dataframe
assert all(item in predictions.columns for item in unseen_data.columns)
assert all(metrics[metric][0] for metric in metrics.columns)
predictions = pycaret.classification.predict_model(lr_model)
metrics = pycaret.classification.pull()
assert set(predictions["prediction_label"].unique()) == set(
data["species"].unique()
)
assert all(metrics[metric][0] for metric in metrics.columns)
predictions = pycaret.classification.predict_model(lr_model, raw_score=True)
metrics = pycaret.classification.pull()
assert all(metrics[metric][0] for metric in metrics.columns)
predictions = pycaret.classification.predict_model(lr_model, encoded_labels=True)
metrics = pycaret.classification.pull()
assert set(predictions["prediction_label"].unique()) == set(
range(len(data["species"].unique()))
)
assert all(metrics[metric][0] for metric in metrics.columns)
def test_regression_predict_model():
# loading classification dataset
data = pycaret.datasets.get_data("boston")
assert isinstance(data, pd.DataFrame)
training_data = data.sample(frac=0.90)
unseen_data = data.drop(training_data.index)
# init setup
pycaret.regression.setup(
data,
target="medv",
ignore_features=["crim", "zn"],
remove_multicollinearity=True,
multicollinearity_threshold=0.95,
html=False,
session_id=123,
n_jobs=1,
)
lr_model = pycaret.regression.create_model("lr")
predictions = pycaret.regression.predict_model(lr_model, data=unseen_data)
metrics = pycaret.regression.pull()
# Check that columns of raw data are contained in columns of returned dataframe
assert all(item in predictions.columns for item in unseen_data.columns)
pycaret.regression.setup(
data,
target="medv",
ignore_features=["crim", "zn"],
remove_multicollinearity=True,
multicollinearity_threshold=0.95,
transform_target=True,
html=False,
session_id=123,
n_jobs=1,
)
lr_model = pycaret.regression.create_model("lr")
pycaret.regression.predict_model(lr_model, data=unseen_data)
metrics_transformed = pycaret.regression.pull()
assert np.isclose(metrics["R2"], metrics_transformed["R2"], atol=0.15)