-
-
Notifications
You must be signed in to change notification settings - Fork 316
/
Copy pathconftest.py
201 lines (165 loc) · 4.52 KB
/
conftest.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
import numpy as np
import pandas as pd
import pytest
@pytest.fixture(scope="module")
def df_vartypes():
data = {
"Name": ["tom", "nick", "krish", "jack"],
"City": ["London", "Manchester", "Liverpool", "Bristol"],
"Age": [20, 21, 19, 18],
"Marks": [0.9, 0.8, 0.7, 0.6],
"dob": pd.date_range("2020-02-24", periods=4, freq="min"),
}
df = pd.DataFrame(data)
return df
@pytest.fixture(scope="module")
def df_numeric_columns():
data = {
0: ["tom", "nick", "krish", "jack"],
1: ["London", "Manchester", "Liverpool", "Bristol"],
2: [20, 21, 19, 18],
3: [0.9, 0.8, 0.7, 0.6],
4: pd.date_range("2020-02-24", periods=4, freq="min"),
}
df = pd.DataFrame(data)
return df
@pytest.fixture(scope="module")
def df_na():
data = {
"Name": ["tom", "nick", "krish", np.nan, "peter", np.nan, "fred", "sam"],
"City": [
"London",
"Manchester",
np.nan,
np.nan,
"London",
"London",
"Bristol",
"Manchester",
],
"Studies": [
"Bachelor",
"Bachelor",
np.nan,
np.nan,
"Bachelor",
"PhD",
"None",
"Masters",
],
"Age": [20, 21, 19, np.nan, 23, 40, 41, 37],
"Marks": [0.9, 0.8, 0.7, np.nan, 0.3, np.nan, 0.8, 0.6],
"dob": pd.date_range("2020-02-24", periods=8, freq="min"),
}
df = pd.DataFrame(data)
return df
@pytest.fixture(scope="module")
def df_enc():
df = {
"var_A": ["A"] * 6 + ["B"] * 10 + ["C"] * 4,
"var_B": ["A"] * 10 + ["B"] * 6 + ["C"] * 4,
"target": [1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0],
}
df = pd.DataFrame(df)
return df
@pytest.fixture(scope="module")
def df_enc_category_dtypes():
df = {
"var_A": ["A"] * 6 + ["B"] * 10 + ["C"] * 4,
"var_B": ["A"] * 10 + ["B"] * 6 + ["C"] * 4,
"target": [1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0],
}
df = pd.DataFrame(df)
df[["var_A", "var_B"]] = df[["var_A", "var_B"]].astype("category")
return df
@pytest.fixture(scope="module")
def df_enc_numeric():
df = {
"var_A": [1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3],
"var_B": [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3],
"target": [1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0],
}
df = pd.DataFrame(df)
return df
@pytest.fixture(scope="module")
def df_enc_rare():
df = {
"var_A": ["B"] * 9 + ["A"] * 6 + ["C"] * 4 + ["D"] * 1,
"var_B": ["A"] * 10 + ["B"] * 6 + ["C"] * 4,
"target": [1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0],
}
df = pd.DataFrame(df)
return df
@pytest.fixture(scope="module")
def df_enc_na():
df = {
"var_A": ["B"] * 9 + ["A"] * 6 + ["C"] * 4 + ["D"] * 1,
"var_B": ["A"] * 10 + ["B"] * 6 + ["C"] * 4,
"target": [1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0],
}
df = pd.DataFrame(df)
df.loc[0, "var_A"] = np.nan
return df
@pytest.fixture(scope="module")
def df_enc_big():
df = {
"var_A": ["A"] * 6
+ ["B"] * 10
+ ["C"] * 4
+ ["D"] * 10
+ ["E"] * 2
+ ["F"] * 2
+ ["G"] * 6,
"var_B": ["A"] * 10
+ ["B"] * 6
+ ["C"] * 4
+ ["D"] * 10
+ ["E"] * 2
+ ["F"] * 2
+ ["G"] * 6,
"var_C": ["A"] * 4
+ ["B"] * 6
+ ["C"] * 10
+ ["D"] * 10
+ ["E"] * 2
+ ["F"] * 2
+ ["G"] * 6,
}
df = pd.DataFrame(df)
return df
@pytest.fixture(scope="module")
def df_enc_big_na():
df = {
"var_A": ["A"] * 6
+ ["B"] * 10
+ ["C"] * 4
+ ["D"] * 10
+ ["E"] * 2
+ ["F"] * 2
+ ["G"] * 6,
"var_B": ["A"] * 10
+ ["B"] * 6
+ ["C"] * 4
+ ["D"] * 10
+ ["E"] * 2
+ ["F"] * 2
+ ["G"] * 6,
"var_C": ["A"] * 4
+ ["B"] * 6
+ ["C"] * 10
+ ["D"] * 10
+ ["E"] * 2
+ ["F"] * 2
+ ["G"] * 6,
}
df = pd.DataFrame(df)
df.loc[0, "var_A"] = np.nan
return df
@pytest.fixture(scope="module")
def df_normal_dist():
np.random.seed(0)
mu, sigma = 0, 0.1 # mean and standard deviation
s = np.random.normal(mu, sigma, 100)
df = pd.DataFrame(s)
df.columns = ["var"]
return df