valediction 1.0.0__py3-none-any.whl → 1.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (32) hide show
  1. valediction/__init__.py +8 -8
  2. valediction/convenience.py +45 -50
  3. valediction/data_types/data_type_helpers.py +75 -75
  4. valediction/data_types/data_types.py +58 -58
  5. valediction/data_types/type_inference.py +541 -541
  6. valediction/datasets/datasets.py +870 -870
  7. valediction/datasets/datasets_helpers.py +46 -46
  8. valediction/demo/DEMOGRAPHICS.csv +101 -101
  9. valediction/demo/DIAGNOSES.csv +650 -650
  10. valediction/demo/LAB_TESTS.csv +1001 -1001
  11. valediction/demo/VITALS.csv +1001 -1001
  12. valediction/demo/__init__.py +6 -6
  13. valediction/demo/demo_dictionary.py +129 -129
  14. valediction/dictionary/exporting.py +501 -501
  15. valediction/dictionary/exporting_helpers.py +371 -371
  16. valediction/dictionary/generation.py +357 -357
  17. valediction/dictionary/helpers.py +174 -174
  18. valediction/dictionary/importing.py +494 -494
  19. valediction/dictionary/integrity.py +37 -37
  20. valediction/dictionary/model.py +582 -582
  21. valediction/exceptions.py +22 -22
  22. valediction/integrity.py +97 -97
  23. valediction/io/csv_readers.py +307 -307
  24. valediction/progress.py +206 -206
  25. valediction/support.py +72 -72
  26. valediction/validation/helpers.py +315 -315
  27. valediction/validation/issues.py +280 -280
  28. valediction/validation/validation.py +598 -598
  29. {valediction-1.0.0.dist-info → valediction-1.1.0.dist-info}/METADATA +1 -1
  30. valediction-1.1.0.dist-info/RECORD +38 -0
  31. {valediction-1.0.0.dist-info → valediction-1.1.0.dist-info}/WHEEL +1 -1
  32. valediction-1.0.0.dist-info/RECORD +0 -38
valediction/demo/__init__.py CHANGED
@@ -1,6 +1,6 @@
1
- from pathlib import Path
2
-
3
- from valediction.demo.demo_dictionary import demo_dictionary # noqa
4
-
5
- DEMO_DATA = Path(__file__).resolve().parent
6
- DEMO_DICTIONARY = DEMO_DATA / "DEMO - Data Dictionary.xlsx"
1
+ from pathlib import Path
2
+
3
+ from valediction.demo.demo_dictionary import demo_dictionary # noqa
4
+
5
+ DEMO_DATA = Path(__file__).resolve().parent
6
+ DEMO_DICTIONARY = DEMO_DATA / "DEMO - Data Dictionary.xlsx"
valediction/demo/demo_dictionary.py CHANGED
@@ -1,129 +1,129 @@
1
- from valediction.dictionary.model import Column, Dictionary, Table
2
-
3
-
4
- def demo_dictionary() -> Dictionary:
5
- """Get a Dictionary object equivalent to the demo dataset.
6
-
7
- Returns:
8
- Dictionary: Demo Dictionary
9
- """
10
- demographics = Table(
11
- name="demographics",
12
- columns=[
13
- Column(
14
- name="PATIENT_HASH", order=1, data_type="text", length=12, primary_key=1
15
- ),
16
- Column(name="DATE_OF_BIRTH", order=2, data_type="date"),
17
- Column(name="ETHNICITY", order=3, data_type="text", length=1),
18
- Column(name="SEX", order=4, data_type="text", length=6),
19
- Column(name="DATE_OF_DEATH", order=5, data_type="date"),
20
- ],
21
- description="Demographic information for synthetic patients",
22
- )
23
-
24
- diagnoses = Table(
25
- name="diagnoses",
26
- columns=[
27
- Column(
28
- name="PATIENT_HASH",
29
- order=1,
30
- data_type="text",
31
- length=12,
32
- primary_key=1,
33
- foreign_key="DEMOGRAPHICS.PATIENT_HASH",
34
- ),
35
- Column(name="DATE_OF_RECORDING", order=2, data_type="date", primary_key=2),
36
- Column(
37
- name="DIAGNOSIS_CODE",
38
- order=3,
39
- data_type="text",
40
- length=6,
41
- primary_key=3,
42
- ),
43
- Column(
44
- name="PRIMARY_DIAGNOSIS",
45
- order=4,
46
- data_type="text",
47
- length=1,
48
- enumerations={"Y": "Primary Diagnosis", "N": "Comorbidity"},
49
- ),
50
- ],
51
- description="ICD diagnoses for synthetic patients",
52
- )
53
-
54
- lab_tests = Table(
55
- name="lab_tests",
56
- columns=[
57
- Column(
58
- name="PATIENT_HASH",
59
- order=1,
60
- data_type="text",
61
- length=12,
62
- primary_key=1,
63
- foreign_key="DEMOGRAPHICS.PATIENT_HASH",
64
- ),
65
- Column(name="SAMPLE_DATE", order=2, data_type="date", primary_key=2),
66
- Column(name="RESULT_DATE", order=3, data_type="date", primary_key=3),
67
- Column(name="SAMPLE_TYPE", order=4, data_type="text", length=32),
68
- Column(
69
- name="TEST_TYPE", order=5, data_type="text", length=32, primary_key=4
70
- ),
71
- Column(name="RESULT_RAW", order=6, data_type="text", length=256),
72
- Column(name="UNITS", order=7, data_type="text", length=16),
73
- Column(name="RESULT_NUMERIC", order=8, data_type="float"),
74
- Column(
75
- name="RESULT_PROCESSED",
76
- order=9,
77
- data_type="text",
78
- length=8,
79
- enumerations={"positive": "Positive", "negative": "Negative"},
80
- ),
81
- Column(
82
- name="OPERATOR",
83
- order=10,
84
- data_type="text",
85
- length=1,
86
- enumerations={"-": "Less Than", "+": "Greater Than"},
87
- ),
88
- Column(name="RANGE_LOW", order=11, data_type="float"),
89
- Column(name="RANGE_HIGH", order=12, data_type="float"),
90
- ],
91
- description="Lab test results for synthetic patients",
92
- )
93
-
94
- vitals = Table(
95
- name="vitals",
96
- columns=[
97
- Column(
98
- name="PATIENT_HASH",
99
- order=1,
100
- data_type="text",
101
- length=12,
102
- primary_key=1,
103
- foreign_key="DEMOGRAPHICS.PATIENT_HASH",
104
- ),
105
- Column(
106
- name="OBSERVATION_TIME", order=2, data_type="datetime", primary_key=2
107
- ),
108
- Column(
109
- name="OBSERVATION_TYPE",
110
- order=3,
111
- data_type="text",
112
- length=32,
113
- primary_key=3,
114
- ),
115
- Column(name="RESULT", order=4, data_type="float"),
116
- ],
117
- description="Numeric vital sign obs for synthetic patients",
118
- )
119
-
120
- demo_dictionary = Dictionary(
121
- name="Synthetic Data",
122
- version="v0.1",
123
- version_notes="Synthethic dataset for allowing Wessex SDE onboarding",
124
- inclusion_criteria="* synthetic patients",
125
- exclusion_criteria="* real patients",
126
- tables=[demographics, diagnoses, lab_tests, vitals],
127
- )
128
-
129
- return demo_dictionary
1
+ from valediction.dictionary.model import Column, Dictionary, Table
2
+
3
+
4
+ def demo_dictionary() -> Dictionary:
5
+ """Get a Dictionary object equivalent to the demo dataset.
6
+
7
+ Returns:
8
+ Dictionary: Demo Dictionary
9
+ """
10
+ demographics = Table(
11
+ name="demographics",
12
+ columns=[
13
+ Column(
14
+ name="PATIENT_HASH", order=1, data_type="text", length=12, primary_key=1
15
+ ),
16
+ Column(name="DATE_OF_BIRTH", order=2, data_type="date"),
17
+ Column(name="ETHNICITY", order=3, data_type="text", length=1),
18
+ Column(name="SEX", order=4, data_type="text", length=6),
19
+ Column(name="DATE_OF_DEATH", order=5, data_type="date"),
20
+ ],
21
+ description="Demographic information for synthetic patients",
22
+ )
23
+
24
+ diagnoses = Table(
25
+ name="diagnoses",
26
+ columns=[
27
+ Column(
28
+ name="PATIENT_HASH",
29
+ order=1,
30
+ data_type="text",
31
+ length=12,
32
+ primary_key=1,
33
+ foreign_key="DEMOGRAPHICS.PATIENT_HASH",
34
+ ),
35
+ Column(name="DATE_OF_RECORDING", order=2, data_type="date", primary_key=2),
36
+ Column(
37
+ name="DIAGNOSIS_CODE",
38
+ order=3,
39
+ data_type="text",
40
+ length=6,
41
+ primary_key=3,
42
+ ),
43
+ Column(
44
+ name="PRIMARY_DIAGNOSIS",
45
+ order=4,
46
+ data_type="text",
47
+ length=1,
48
+ enumerations={"Y": "Primary Diagnosis", "N": "Comorbidity"},
49
+ ),
50
+ ],
51
+ description="ICD diagnoses for synthetic patients",
52
+ )
53
+
54
+ lab_tests = Table(
55
+ name="lab_tests",
56
+ columns=[
57
+ Column(
58
+ name="PATIENT_HASH",
59
+ order=1,
60
+ data_type="text",
61
+ length=12,
62
+ primary_key=1,
63
+ foreign_key="DEMOGRAPHICS.PATIENT_HASH",
64
+ ),
65
+ Column(name="SAMPLE_DATE", order=2, data_type="date", primary_key=2),
66
+ Column(name="RESULT_DATE", order=3, data_type="date", primary_key=3),
67
+ Column(name="SAMPLE_TYPE", order=4, data_type="text", length=32),
68
+ Column(
69
+ name="TEST_TYPE", order=5, data_type="text", length=32, primary_key=4
70
+ ),
71
+ Column(name="RESULT_RAW", order=6, data_type="text", length=256),
72
+ Column(name="UNITS", order=7, data_type="text", length=16),
73
+ Column(name="RESULT_NUMERIC", order=8, data_type="float"),
74
+ Column(
75
+ name="RESULT_PROCESSED",
76
+ order=9,
77
+ data_type="text",
78
+ length=8,
79
+ enumerations={"positive": "Positive", "negative": "Negative"},
80
+ ),
81
+ Column(
82
+ name="OPERATOR",
83
+ order=10,
84
+ data_type="text",
85
+ length=1,
86
+ enumerations={"-": "Less Than", "+": "Greater Than"},
87
+ ),
88
+ Column(name="RANGE_LOW", order=11, data_type="float"),
89
+ Column(name="RANGE_HIGH", order=12, data_type="float"),
90
+ ],
91
+ description="Lab test results for synthetic patients",
92
+ )
93
+
94
+ vitals = Table(
95
+ name="vitals",
96
+ columns=[
97
+ Column(
98
+ name="PATIENT_HASH",
99
+ order=1,
100
+ data_type="text",
101
+ length=12,
102
+ primary_key=1,
103
+ foreign_key="DEMOGRAPHICS.PATIENT_HASH",
104
+ ),
105
+ Column(
106
+ name="OBSERVATION_TIME", order=2, data_type="datetime", primary_key=2
107
+ ),
108
+ Column(
109
+ name="OBSERVATION_TYPE",
110
+ order=3,
111
+ data_type="text",
112
+ length=32,
113
+ primary_key=3,
114
+ ),
115
+ Column(name="RESULT", order=4, data_type="float"),
116
+ ],
117
+ description="Numeric vital sign obs for synthetic patients",
118
+ )
119
+
120
+ demo_dictionary = Dictionary(
121
+ name="Synthetic Data",
122
+ version="v0.1",
123
+ version_notes="Synthethic dataset for allowing Wessex SDE onboarding",
124
+ inclusion_criteria="* synthetic patients",
125
+ exclusion_criteria="* real patients",
126
+ tables=[demographics, diagnoses, lab_tests, vitals],
127
+ )
128
+
129
+ return demo_dictionary