|
1
|
|
|
import pytest |
|
2
|
|
|
|
|
3
|
|
|
|
|
4
|
|
|
@pytest.fixture |
|
5
|
|
|
def test_datapoints_full_file_path(): |
|
6
|
|
|
import os |
|
7
|
|
|
return lambda file_name: os.path.join(os.path.dirname(os.path.realpath(__file__)), '..', 'dts', file_name) |
|
8
|
|
|
|
|
9
|
|
|
|
|
10
|
|
|
@pytest.fixture |
|
11
|
|
|
def sample_json(test_datapoints_full_file_path): |
|
12
|
|
|
return test_datapoints_full_file_path('sample-data.jsonlines') |
|
13
|
|
|
|
|
14
|
|
|
@pytest.fixture |
|
15
|
|
|
def sample_collaped_json(test_datapoints_full_file_path): |
|
16
|
|
|
return test_datapoints_full_file_path('sample-data-collapsed.jsonlines') |
|
17
|
|
|
|
|
18
|
|
|
|
|
19
|
|
|
@pytest.fixture |
|
20
|
|
|
def datapoint_files_to_test(sample_collaped_json, sample_json): |
|
21
|
|
|
import pandas as pd |
|
22
|
|
|
import numpy as np |
|
23
|
|
|
return { |
|
24
|
|
|
'data_1': { |
|
25
|
|
|
'data_path': sample_collaped_json, |
|
26
|
|
|
'nb_rows': 100, |
|
27
|
|
|
'nb_columns': 46, |
|
28
|
|
|
'type_distros': { |
|
29
|
|
|
'type': {str: 100}, |
|
30
|
|
|
'flavors': {list: 98, type(None): 2}, |
|
31
|
|
|
}, |
|
32
|
|
|
'value_distros': { |
|
33
|
|
|
'type': {'hybrid': 48, 'sativa': 19, 'indica': 33}, |
|
34
|
|
|
}, |
|
35
|
|
|
'row': { |
|
36
|
|
|
0: { |
|
37
|
|
|
'flavors': [lambda v: v == ["Chemical", "Pine", "Diesel"], |
|
38
|
|
|
lambda v: type(v) == list, |
|
39
|
|
|
], |
|
40
|
|
|
'type': [lambda v: v == 'hybrid', |
|
41
|
|
|
lambda v: type(v) == str, |
|
42
|
|
|
], |
|
43
|
|
|
}, |
|
44
|
|
|
7: { |
|
45
|
|
|
'flavors': [lambda v: v == ["Earthy", "Pungent", "Sweet"], |
|
46
|
|
|
lambda v: type(v) == list, |
|
47
|
|
|
], |
|
48
|
|
|
'type': [lambda v: v == 'hybrid', |
|
49
|
|
|
lambda v: type(v) == str, |
|
50
|
|
|
], |
|
51
|
|
|
}, |
|
52
|
|
|
76: { |
|
53
|
|
|
'flavors': [lambda v: v is None, |
|
54
|
|
|
lambda v: pd.isnull(v), |
|
55
|
|
|
lambda v: isinstance(v, type(None)), |
|
56
|
|
|
], |
|
57
|
|
|
}, |
|
58
|
|
|
87: { |
|
59
|
|
|
'flavors': [lambda v: v is None, |
|
60
|
|
|
lambda v: type(v) == type(None), |
|
61
|
|
|
], |
|
62
|
|
|
}, |
|
63
|
|
|
}, |
|
64
|
|
|
'column_names': ( |
|
65
|
|
|
'flavors', |
|
66
|
|
|
'name', |
|
67
|
|
|
'description', |
|
68
|
|
|
'image_urls', |
|
69
|
|
|
'parents', |
|
70
|
|
|
'_id', |
|
71
|
|
|
'type', |
|
72
|
|
|
'image_paths', |
|
73
|
|
|
'Aroused', |
|
74
|
|
|
'Creative', |
|
75
|
|
|
'Energetic', |
|
76
|
|
|
'Euphoric', |
|
77
|
|
|
'Focused', |
|
78
|
|
|
'Giggly', |
|
79
|
|
|
'Happy', |
|
80
|
|
|
'Hungry', |
|
81
|
|
|
'Relaxed', |
|
82
|
|
|
'Sleepy', |
|
83
|
|
|
'Talkative', |
|
84
|
|
|
'Tingly', |
|
85
|
|
|
'Uplifted', |
|
86
|
|
|
'Cramps', |
|
87
|
|
|
'Depression', |
|
88
|
|
|
'Eye Pressure', |
|
89
|
|
|
'Fatigue', |
|
90
|
|
|
'Headaches', |
|
91
|
|
|
'Inflammation', |
|
92
|
|
|
'Insomnia', |
|
93
|
|
|
'Lack of Appetite', |
|
94
|
|
|
'Muscle Spasms', |
|
95
|
|
|
'Nausea', |
|
96
|
|
|
'Pain', |
|
97
|
|
|
'Seizures', |
|
98
|
|
|
'Spasticity', |
|
99
|
|
|
'Stress', |
|
100
|
|
|
'Anxious', |
|
101
|
|
|
'Dizzy', |
|
102
|
|
|
'Dry Eyes', |
|
103
|
|
|
'Dry Mouth', |
|
104
|
|
|
'Headache', |
|
105
|
|
|
'Paranoid', |
|
106
|
|
|
'difficulty', |
|
107
|
|
|
'flowering', |
|
108
|
|
|
'height', |
|
109
|
|
|
'stretch', |
|
110
|
|
|
'yield', |
|
111
|
|
|
), |
|
112
|
|
|
}, |
|
113
|
|
|
'data_2': { |
|
114
|
|
|
'data_path': sample_json, |
|
115
|
|
|
'nb_rows': 100, |
|
116
|
|
|
'nb_columns': 12, |
|
117
|
|
|
'type_distros': { |
|
118
|
|
|
'type': {str: 100}, |
|
119
|
|
|
'flavors': {list: 98, float: 2}, |
|
120
|
|
|
}, |
|
121
|
|
|
'value_distros': { |
|
122
|
|
|
'type': {'hybrid': 48, 'sativa': 19, 'indica': 33}, |
|
123
|
|
|
}, |
|
124
|
|
|
'row': { |
|
125
|
|
|
0: { |
|
126
|
|
|
'flavors': [lambda v: v == ["Chemical", "Pine", "Diesel"], |
|
127
|
|
|
lambda v: type(v) == list, |
|
128
|
|
|
], |
|
129
|
|
|
'type': [lambda v: v == 'hybrid', |
|
130
|
|
|
lambda v: type(v) == str |
|
131
|
|
|
], |
|
132
|
|
|
}, |
|
133
|
|
|
7: { |
|
134
|
|
|
'flavors': [lambda v: v == ["Earthy", "Pungent", "Sweet"], |
|
135
|
|
|
lambda v: type(v) == list, |
|
136
|
|
|
], |
|
137
|
|
|
'type': [lambda v: v == 'hybrid', |
|
138
|
|
|
lambda v: type(v) == str |
|
139
|
|
|
], |
|
140
|
|
|
}, |
|
141
|
|
|
76: { |
|
142
|
|
|
'flavors': [lambda v: np.isnan(v), |
|
143
|
|
|
lambda v: pd.isnull(v), |
|
144
|
|
|
lambda v: type(v) == float, |
|
145
|
|
|
], |
|
146
|
|
|
}, |
|
147
|
|
|
87: { |
|
148
|
|
|
'flavors': [lambda v: np.isnan(v), |
|
149
|
|
|
lambda v: pd.isnull(v), |
|
150
|
|
|
lambda v: type(v) == float, |
|
151
|
|
|
], |
|
152
|
|
|
}, |
|
153
|
|
|
}, |
|
154
|
|
|
'column_names': ( |
|
155
|
|
|
'flavors', |
|
156
|
|
|
'name', |
|
157
|
|
|
'medical', |
|
158
|
|
|
'description', |
|
159
|
|
|
'image_urls', |
|
160
|
|
|
'parents', |
|
161
|
|
|
'negatives', |
|
162
|
|
|
'grow_info', |
|
163
|
|
|
'_id', |
|
164
|
|
|
'type', |
|
165
|
|
|
'image_paths', |
|
166
|
|
|
'effects', |
|
167
|
|
|
), |
|
168
|
|
|
}, |
|
169
|
|
|
} |
|
170
|
|
|
|