forked from OHDSI/Broadsea-Spark-SQL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathload_eunomia_demo_cdm_data.sql
1629 lines (1421 loc) · 59.8 KB
/
load_eunomia_demo_cdm_data.sql
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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
-- note. database and schema are synonymous in Spark SQL
create database if not exists eunomia;
use eunomia;
-- note. OpenCSVSerde ignores hive tblproperties 'serialization.null.format'=''
-- so we have to convert empty string to null for each nullable column in the later DELTA table insert select
-- note. can only use 'CREATE OR REPLACE' for v2 (DELTA) tables so explicit drops are needed for v1 tables
-----------------------------------------------
-- PERSON
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.person_temp;
CREATE TABLE eunomia.person_temp (
person_id INT,
gender_concept_id INT,
year_of_birth INT,
month_of_birth INT, -- NULL
day_of_birth INT, -- NULL
birth_datetime TIMESTAMP, -- NULL
race_concept_id INT,
ethnicity_concept_id INT,
location_id INT, -- NULL
provider_id INT, -- NULL
care_site_id INT, -- NULL
person_source_value VARCHAR(50), -- NULL
gender_source_value VARCHAR(50), -- NULL
gender_source_concept_id INT, -- NULL
race_source_value VARCHAR(50), -- NULL
race_source_concept_id INT, -- NULL
ethnicity_source_value VARCHAR(50), -- NULL
ethnicity_source_concept_id INT -- NULL
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/person.csv' OVERWRITE INTO TABLE eunomia.person_temp;
CREATE OR REPLACE TABLE eunomia.person USING DELTA AS SELECT * from eunomia.person_temp where 1 <> 1;
INSERT INTO eunomia.person
SELECT
person_id,
gender_concept_id,
year_of_birth,
nullif(month_of_birth, '') as month_of_birth,
nullif(day_of_birth, '') as day_of_birth,
nullif(birth_datetime, '') as birth_datetime,
race_concept_id,
ethnicity_concept_id,
nullif(location_id, '') as location_id,
nullif(provider_id, '') as provider_id,
nullif(care_site_id, '') as care_site_id,
nullif(person_source_value, '') as person_source_value,
nullif(gender_source_value, '') as gender_source_value,
nullif(gender_source_concept_id, '') as gender_source_concept_id,
nullif(race_source_value, '') as race_source_value,
nullif(race_source_concept_id, '') as race_source_concept_id,
nullif(ethnicity_source_value, '') as ethnicity_source_value,
nullif(ethnicity_source_concept_id, '') as ethnicity_source_concept_id
FROM eunomia.person_temp WHERE upper(person_id) <> 'PERSON_ID';
DROP TABLE IF EXISTS eunomia.person_temp;
-----------------------------------------------
-- OBSERVATION_PERIOD
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.observation_period_temp;
CREATE TABLE eunomia.observation_period_temp (
observation_period_id INT,
person_id INT,
observation_period_start_date DATE,
observation_period_end_date DATE,
period_type_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/observation_period.csv' OVERWRITE INTO TABLE eunomia.observation_period_temp;
CREATE OR REPLACE TABLE eunomia.observation_period USING DELTA AS SELECT * from eunomia.observation_period_temp where 1 <> 1;
INSERT INTO eunomia.observation_period
SELECT
observation_period_id,
person_id,
observation_period_start_date,
observation_period_end_date,
period_type_concept_id
FROM eunomia.observation_period_temp
where upper(observation_period_id) <> 'OBSERVATION_PERIOD_ID';
DROP TABLE IF EXISTS eunomia.observation_period_temp;
-----------------------------------------------
-- VISIT_OCCURRENCE
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.visit_occurrence_temp;
CREATE TABLE eunomia.visit_occurrence_temp (
visit_occurrence_id INT,
person_id INT,
visit_concept_id INT,
visit_start_date DATE,
visit_start_datetime TIMESTAMP,
visit_end_date DATE,
visit_end_datetime TIMESTAMP,
visit_type_concept_id INT,
provider_id INT,
care_site_id INT,
visit_source_value VARCHAR(50),
visit_source_concept_id INT,
admitted_from_concept_id INT,
admitted_from_source_value VARCHAR(50),
discharged_to_concept_id INT,
discharged_to_source_value VARCHAR(50),
preceding_visit_occurrence_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/visit_occurrence.csv' OVERWRITE INTO TABLE eunomia.visit_occurrence_temp;
CREATE OR REPLACE TABLE eunomia.visit_occurrence USING DELTA AS SELECT * from eunomia.visit_occurrence_temp where 1 <> 1;
INSERT INTO eunomia.visit_occurrence
SELECT
visit_occurrence_id,
person_id,
visit_concept_id,
nullif(visit_start_date, '') as visit_start_date,
nullif(visit_start_datetime, '') as visit_start_datetime,
nullif(visit_end_date, '') as visit_end_date,
nullif(visit_end_datetime, '') as visit_end_datetime,
nullif(visit_type_concept_id, '') as visit_type_concept_id,
nullif(provider_id, '') as provider_id,
nullif(care_site_id, '') as care_site_id,
nullif(visit_source_value, '') as visit_source_value,
nullif(visit_source_concept_id, '') as visit_source_concept_id,
nullif(admitted_from_concept_id, '') as admitted_from_concept_id,
nullif(admitted_from_source_value, '') as admitted_from_source_value,
nullif(discharged_to_concept_id, '') as discharged_to_concept_id,
nullif(discharged_to_source_value, '') as discharged_to_source_value,
nullif(preceding_visit_occurrence_id, '') as preceding_visit_occurrence_id
FROM eunomia.visit_occurrence_temp WHERE upper(visit_occurrence_id) <> 'VISIT_OCCURRENCE_ID';
DROP TABLE IF EXISTS eunomia.visit_occurrence_temp;
-----------------------------------------------
-- VISIT_DETAIL
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.visit_detail_temp;
CREATE TABLE eunomia.visit_detail_temp (
visit_detail_id INT,
person_id INT,
visit_detail_concept_id INT,
visit_detail_start_date DATE,
visit_detail_start_datetime TIMESTAMP,
visit_detail_end_date DATE,
visit_detail_end_datetime TIMESTAMP,
visit_detail_type_concept_id INT,
provider_id INT,
care_site_id INT,
visit_detail_source_value VARCHAR(50),
visit_detail_source_concept_id INT,
admitted_from_concept_id INT,
admitted_from_source_value VARCHAR(50),
discharged_to_source_value VARCHAR(50),
discharged_to_concept_id INT,
preceding_visit_detail_id INT,
parent_visit_detail_id INT,
visit_occurrence_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/visit_detail.csv' OVERWRITE INTO TABLE eunomia.visit_detail_temp;
CREATE OR REPLACE TABLE eunomia.visit_detail USING DELTA AS SELECT * from eunomia.visit_detail_temp where 1 <> 1;
INSERT INTO eunomia.visit_detail
SELECT
visit_detail_id,
person_id,
visit_detail_concept_id,
visit_detail_start_date,
nullif(visit_detail_start_datetime, '') as visit_detail_start_datetime,
visit_detail_end_date,
nullif(visit_detail_end_datetime, '') as visit_detail_end_datetime,
visit_detail_type_concept_id,
nullif(provider_id, '') as provider_id,
nullif(care_site_id, '') as care_site_id,
nullif(visit_detail_source_value, '') as visit_detail_source_value,
nullif(visit_detail_source_concept_id, '') as visit_detail_source_concept_id,
nullif(admitted_from_concept_id, '') as admitted_from_concept_id,
nullif(admitted_from_source_value, '') as admitted_from_source_value,
nullif(discharged_to_source_value, '') as discharged_to_source_value,
nullif(discharged_to_concept_id, '') as discharged_to_concept_id,
nullif(preceding_visit_detail_id, '') as preceding_visit_detail_id,
nullif(parent_visit_detail_id, '') as parent_visit_detail_id,
visit_occurrence_id
FROM eunomia.visit_detail_temp WHERE upper(visit_detail_id) <> 'VISIT_DETAIL_ID';
DROP TABLE IF EXISTS eunomia.visit_detail_temp;
-----------------------------------------------
-- CONDITION_OCCURRENCE
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.condition_occurrence_temp;
CREATE TABLE eunomia.condition_occurrence_temp (
condition_occurrence_id INT,
person_id INT,
condition_concept_id INT,
condition_start_date DATE,
condition_start_datetime TIMESTAMP,
condition_end_date DATE,
condition_end_datetime TIMESTAMP,
condition_type_concept_id INT,
condition_status_concept_id INT,
stop_reason VARCHAR(20),
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
condition_source_value VARCHAR(50),
condition_source_concept_id INT,
condition_status_source_value VARCHAR(50)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/condition_occurrence.csv' OVERWRITE INTO TABLE eunomia.condition_occurrence_temp;
CREATE OR REPLACE TABLE eunomia.condition_occurrence USING DELTA AS SELECT * from eunomia.condition_occurrence_temp where 1 <> 1;
INSERT INTO eunomia.condition_occurrence
SELECT
condition_occurrence_id,
person_id,
condition_concept_id,
condition_start_date,
nullif(condition_start_datetime, '') as condition_start_datetime,
nullif(condition_end_date, '') as condition_end_date,
nullif(condition_end_datetime, '') as condition_end_datetime,
condition_type_concept_id,
nullif(condition_status_concept_id, '') as condition_status_concept_id,
nullif(stop_reason, '') as stop_reason,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(condition_source_value, '') as condition_source_value,
nullif(condition_source_concept_id, '') as condition_source_concept_id,
nullif(condition_status_source_value, '') as condition_status_source_value
FROM eunomia.condition_occurrence_temp WHERE upper(condition_occurrence_id) <> 'CONDITION_OCCURRENCE_ID';
DROP TABLE IF EXISTS eunomia.condition_occurrence_temp;
-----------------------------------------------
-- DRUG_EXPOSURE
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.drug_exposure_temp;
CREATE TABLE eunomia.drug_exposure_temp (
drug_exposure_id INT,
person_id INT,
drug_concept_id INT,
drug_exposure_start_date DATE,
drug_exposure_start_datetime TIMESTAMP,
drug_exposure_end_date DATE,
drug_exposure_end_datetime TIMESTAMP,
verbatim_end_date DATE,
drug_type_concept_id INT,
stop_reason VARCHAR(20),
refills INT,
quantity NUMERIC,
days_supply INT,
sig STRING,
route_concept_id INT,
lot_number VARCHAR(50),
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
drug_source_value VARCHAR(50),
drug_source_concept_id INT,
route_source_value VARCHAR(50),
dose_unit_source_value VARCHAR(50)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/drug_exposure.csv' OVERWRITE INTO TABLE eunomia.drug_exposure_temp;
CREATE OR REPLACE TABLE eunomia.drug_exposure USING DELTA AS SELECT * from eunomia.drug_exposure_temp where 1 <> 1;
INSERT INTO eunomia.drug_exposure
SELECT
drug_exposure_id,
person_id,
drug_concept_id,
drug_exposure_start_date,
nullif(drug_exposure_start_datetime, '') as drug_exposure_start_datetime,
drug_exposure_end_date,
nullif(drug_exposure_end_datetime, '') as drug_exposure_end_datetime,
nullif(verbatim_end_date, '') as verbatim_end_date,
drug_type_concept_id,
nullif(stop_reason, '') as stop_reason,
nullif(refills, '') as refills,
nullif(quantity, '') as quantity,
nullif(days_supply, '') as days_supply,
nullif(sig, '') as sig,
nullif(route_concept_id, '') as route_concept_id,
nullif(lot_number, '') as lot_number,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(drug_source_value, '') as drug_source_value,
nullif(drug_source_concept_id, '') as drug_source_concept_id,
nullif(route_source_value, '') as route_source_value,
nullif(dose_unit_source_value, '') as dose_unit_source_value
FROM eunomia.drug_exposure_temp WHERE upper(drug_exposure_id) <> 'DRUG_EXPOSURE_ID';
DROP TABLE IF EXISTS eunomia.drug_exposure_temp;
-----------------------------------------------
-- PROCEDURE_OCCURRENCE
-----------------------------------------------
drop table if exists eunomia.procedure_occurrence_temp;
create table eunomia.procedure_occurrence_temp (
procedure_occurrence_id INT,
person_id INT,
procedure_concept_id INT,
procedure_date DATE,
procedure_datetime TIMESTAMP,
procedure_end_date DATE,
procedure_end_datetime TIMESTAMP,
procedure_type_concept_id INT,
modifier_concept_id INT,
quantity INT,
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
procedure_source_value VARCHAR(50),
procedure_source_concept_id INT,
modifier_source_value VARCHAR(50)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/procedure_occurrence.csv' OVERWRITE INTO TABLE eunomia.procedure_occurrence_temp;
CREATE OR REPLACE TABLE eunomia.procedure_occurrence USING DELTA AS SELECT * from eunomia.procedure_occurrence_temp where 1 <> 1;
INSERT INTO eunomia.procedure_occurrence
SELECT
procedure_occurrence_id,
person_id,
procedure_concept_id,
procedure_date,
nullif(procedure_datetime, '') as procedure_datetime,
nullif(procedure_end_date, '') as procedure_end_date,
nullif(procedure_end_datetime, '') as procedure_end_datetime,
procedure_type_concept_id,
nullif(modifier_concept_id, '') as modifier_concept_id,
nullif(quantity, '') as quantity,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(procedure_source_value, '') as procedure_source_value,
nullif(procedure_source_concept_id, '') as procedure_source_concept_id,
nullif(modifier_source_value, '') as modifier_source_value
FROM eunomia.procedure_occurrence_temp WHERE upper(procedure_occurrence_id) <> 'PROCEDURE_OCCURRENCE_ID';
DROP TABLE IF EXISTS eunomia.procedure_occurrence_temp;
-----------------------------------------------
-- DEVICE_EXPOSURE
-----------------------------------------------
drop table if exists eunomia.device_exposure_temp;
create table eunomia.device_exposure_temp (
device_exposure_id INT,
person_id INT,
device_concept_id INT,
device_exposure_start_date DATE,
device_exposure_start_datetime TIMESTAMP,
device_exposure_end_date DATE,
device_exposure_end_datetime TIMESTAMP,
device_type_concept_id INT,
unique_device_id VARCHAR(255),
production_id VARCHAR(255),
quantity INT,
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
device_source_value VARCHAR(50),
device_source_concept_id INT,
unit_concept_id INT,
unit_source_value VARCHAR(50),
unit_source_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/device_exposure.csv' OVERWRITE INTO TABLE eunomia.device_exposure_temp;
CREATE OR REPLACE TABLE eunomia.device_exposure USING DELTA AS SELECT * from eunomia.device_exposure_temp where 1 <> 1;
INSERT INTO eunomia.device_exposure
SELECT
device_exposure_id,
person_id,
device_concept_id,
device_exposure_start_date,
nullif(device_exposure_start_datetime, '') as device_exposure_start_datetime,
nullif(device_exposure_end_date, '') as device_exposure_end_date,
nullif(device_exposure_end_datetime, '') as device_exposure_end_datetime,
device_type_concept_id,
nullif(unique_device_id, '') as unique_device_id,
nullif(production_id, '') as production_id,
nullif(quantity, '') as quantity,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(device_source_value, '') as device_source_value,
nullif(device_source_concept_id, '') as device_source_concept_id,
nullif(unit_concept_id, '') as unit_concept_id,
nullif(unit_source_value, '') as unit_source_value,
nullif(unit_source_concept_id, '') as unit_source_concept_id
FROM eunomia.device_exposure_temp WHERE upper(device_exposure_id) <> 'DEVICE_EXPOSURE_ID';
DROP TABLE IF EXISTS eunomia.device_exposure_temp;
-----------------------------------------------
-- MEASUREMENT
-----------------------------------------------
drop table if exists eunomia.measurement_temp;
create table eunomia.measurement_temp (
measurement_id INT,
person_id INT,
measurement_concept_id INT,
measurement_date DATE,
measurement_datetime TIMESTAMP,
measurement_time VARCHAR(10),
measurement_type_concept_id INT,
operator_concept_id INT,
value_as_number NUMERIC,
value_as_concept_id INT,
unit_concept_id INT,
range_low NUMERIC,
range_high NUMERIC,
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
measurement_source_value VARCHAR(50),
measurement_source_concept_id INT,
unit_source_value VARCHAR(50),
unit_source_concept_id INT,
value_source_value VARCHAR(50),
measurement_event_id BIGINT,
meas_event_field_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/measurement.csv' OVERWRITE INTO TABLE eunomia.measurement_temp;
CREATE OR REPLACE TABLE eunomia.measurement USING DELTA AS SELECT * from eunomia.measurement_temp where 1 <> 1;
INSERT INTO eunomia.measurement
SELECT
measurement_id,
person_id,
measurement_concept_id,
measurement_date,
nullif(measurement_datetime, '') as measurement_datetime,
nullif(measurement_time, '') as measurement_time,
measurement_type_concept_id,
nullif(operator_concept_id, '') as operator_concept_id,
nullif(value_as_number, '') as value_as_number,
nullif(value_as_concept_id, '') as value_as_concept_id,
nullif(unit_concept_id, '') as unit_concept_id,
nullif(range_low, '') as range_low,
nullif(range_high, '') as range_high,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(measurement_source_value, '') as measurement_source_value,
nullif(measurement_source_concept_id, '') as measurement_source_concept_id,
nullif(unit_source_value, '') as unit_source_value,
nullif(unit_source_concept_id, '') as unit_source_concept_id,
nullif(value_source_value, '') as value_source_value,
nullif(measurement_event_id, '') as measurement_event_id,
nullif(meas_event_field_concept_id, '') as meas_event_field_concept_id
FROM eunomia.measurement_temp WHERE upper(measurement_id) <> 'MEASUREMENT_ID';
DROP TABLE IF EXISTS eunomia.measurement_temp;
-----------------------------------------------
-- OBSERVATION
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.observation_temp;
CREATE TABLE eunomia.observation_temp (
observation_id INT,
person_id INT,
observation_concept_id INT,
observation_date DATE,
observation_datetime TIMESTAMP,
observation_type_concept_id INT,
value_as_number NUMERIC,
value_as_string VARCHAR(60),
value_as_concept_id INT,
qualifier_concept_id INT,
unit_concept_id INT,
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
observation_source_value VARCHAR(50),
observation_source_concept_id INT,
unit_source_value VARCHAR(50),
qualifier_source_value VARCHAR(50),
value_source_value VARCHAR(50),
observation_event_id BIGINT,
obs_event_field_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/observation.csv' OVERWRITE INTO TABLE eunomia.observation_temp;
CREATE OR REPLACE TABLE eunomia.observation USING DELTA AS SELECT * from eunomia.observation_temp where 1 <> 1;
INSERT INTO eunomia.observation
SELECT
observation_id,
person_id,
observation_concept_id,
observation_date,
nullif(observation_datetime, '') as observation_datetime,
observation_type_concept_id,
nullif(value_as_number, '') as value_as_number,
nullif(value_as_string, '') as value_as_string,
nullif(value_as_concept_id, '') as value_as_concept_id,
nullif(qualifier_concept_id, '') as qualifier_concept_id,
nullif(unit_concept_id, '') as unit_concept_id,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(observation_source_value, '') as observation_source_value,
nullif(observation_source_concept_id, '') as observation_source_concept_id,
nullif(unit_source_value, '') as unit_source_value,
nullif(qualifier_source_value, '') as qualifier_source_value,
nullif(value_source_value, '') as value_source_value,
nullif(observation_event_id, '') as observation_event_id,
nullif(obs_event_field_concept_id, '') as obs_event_field_concept_id
FROM eunomia.observation_temp WHERE upper(observation_id) <> 'OBSERVATION_ID';
DROP TABLE IF EXISTS eunomia.observation_temp;
-----------------------------------------------
-- DEATH
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.death_temp;
CREATE TABLE eunomia.death_temp (
person_id INT,
death_date DATE,
death_datetime TIMESTAMP,
death_type_concept_id INT,
cause_concept_id INT,
cause_source_value VARCHAR(50),
cause_source_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/death.csv' OVERWRITE INTO TABLE eunomia.death_temp;
CREATE OR REPLACE TABLE eunomia.death USING DELTA AS SELECT * from eunomia.death_temp where 1 <> 1;
INSERT INTO eunomia.death
SELECT
person_id,
death_date,
nullif(death_datetime, '') as death_datetime,
nullif(death_type_concept_id, '') as death_type_concept_id,
nullif(cause_concept_id, '') as cause_concept_id,
nullif(cause_source_value, '') as cause_source_value,
nullif(cause_source_concept_id, '') as cause_source_concept_id
FROM eunomia.death_temp WHERE person_id <> 'PERSON_ID';
DROP TABLE IF EXISTS eunomia.death_temp;
-----------------------------------------------
-- NOTE
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.note_temp;
CREATE TABLE eunomia.note_temp (
note_id INT,
person_id INT,
note_date DATE,
note_datetime TIMESTAMP,
note_type_concept_id INT,
note_class_concept_id INT,
note_title VARCHAR(250),
note_text STRING,
encoding_concept_id INT,
language_concept_id INT,
provider_id INT,
visit_occurrence_id INT,
visit_detail_id INT,
note_source_value VARCHAR(50),
note_event_id BIGINT,
note_event_field_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/note.csv' OVERWRITE INTO TABLE eunomia.note_temp;
CREATE OR REPLACE TABLE eunomia.note USING DELTA AS SELECT * from eunomia.note_temp where 1 <> 1;
INSERT INTO eunomia.note
SELECT
note_id,
person_id,
note_date,
nullif(note_datetime, '') as note_datetime,
note_type_concept_id,
note_class_concept_id,
nullif(note_title, '') as note_title,
note_text,
encoding_concept_id,
language_concept_id,
nullif(provider_id, '') as provider_id,
nullif(visit_occurrence_id, '') as visit_occurrence_id,
nullif(visit_detail_id, '') as visit_detail_id,
nullif(note_source_value, '') as note_source_value,
nullif(note_event_id, '') as note_event_id,
nullif(note_event_field_concept_id, '') as note_event_field_concept_id
FROM eunomia.note_temp WHERE upper(note_id) <> 'NOTE_ID';
DROP TABLE IF EXISTS eunomia.note_temp;
-----------------------------------------------
-- NOTE_NLP
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.note_nlp_temp;
CREATE TABLE eunomia.note_nlp_temp (
note_nlp_id INT,
note_id INT,
section_concept_id INT,
snippet VARCHAR(250),
offset VARCHAR(50),
lexical_variant VARCHAR(250),
note_nlp_concept_id INT,
note_nlp_source_concept_id INT,
nlp_system VARCHAR(250),
nlp_date DATE,
nlp_datetime TIMESTAMP,
term_exists VARCHAR(1),
term_temporal VARCHAR(50),
term_modifiers VARCHAR(2000)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/note_nlp.csv' OVERWRITE INTO TABLE eunomia.note_nlp_temp;
CREATE OR REPLACE TABLE eunomia.note_nlp USING DELTA AS SELECT * from eunomia.note_nlp_temp where 1 <> 1;
INSERT INTO eunomia.note_nlp
SELECT
note_nlp_id,
note_id,
nullif(section_concept_id, '') as section_concept_id,
nullif(snippet, '') as snippet,
nullif(offset, '') as offset,
lexical_variant,
nullif(note_nlp_concept_id, '') as note_nlp_concept_id,
nullif(note_nlp_source_concept_id, '') as note_nlp_source_concept_id,
nullif(nlp_system, '') as nlp_system,
nlp_date,
nullif(nlp_datetime, '') as nlp_datetime,
nullif(term_exists, '') as term_exists,
nullif(term_temporal, '') as term_temporal,
nullif(term_modifiers, '') as term_modifiers
FROM eunomia.note_nlp_temp WHERE upper(note_nlp_id) <> 'NOTE_NLP_ID';
DROP TABLE IF EXISTS eunomia.note_nlp_temp;
-----------------------------------------------
-- SPECIMEN
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.specimen_temp;
CREATE TABLE eunomia.specimen_temp (
specimen_id INT,
person_id INT,
specimen_concept_id INT,
specimen_type_concept_id INT,
specimen_date DATE,
specimen_datetime TIMESTAMP,
quantity NUMERIC,
unit_concept_id INT,
anatomic_site_concept_id INT,
disease_status_concept_id INT,
specimen_source_id VARCHAR(50),
specimen_source_value VARCHAR(50),
unit_source_value VARCHAR(50),
anatomic_site_source_value VARCHAR(50),
disease_status_source_value VARCHAR(50)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/specimen.csv' OVERWRITE INTO TABLE eunomia.specimen_temp;
CREATE OR REPLACE TABLE eunomia.specimen USING DELTA AS SELECT * from eunomia.specimen_temp where 1 <> 1;
INSERT INTO eunomia.specimen
SELECT
specimen_id,
person_id,
specimen_concept_id,
specimen_type_concept_id,
specimen_date,
nullif(specimen_datetime, '') as specimen_datetime,
nullif(quantity, '') as quantity,
nullif(unit_concept_id, '') as unit_concept_id,
nullif(anatomic_site_concept_id, '') as anatomic_site_concept_id,
nullif(disease_status_concept_id, '') as disease_status_concept_id,
nullif(specimen_source_id, '') as specimen_source_id,
nullif(specimen_source_value, '') as specimen_source_value,
nullif(unit_source_value, '') as unit_source_value,
nullif(anatomic_site_source_value, '') as anatomic_site_source_value,
nullif(disease_status_source_value, '') as disease_status_source_value
FROM eunomia.specimen_temp WHERE upper(specimen_id) <> 'SPECIMEN_ID';
DROP TABLE IF EXISTS eunomia.specimen_temp;
-----------------------------------------------
-- FACT_RELATIONSHIP
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.fact_relationship_temp;
CREATE TABLE eunomia.fact_relationship_temp (
domain_concept_id_1 INT,
fact_id_1 INT,
domain_concept_id_2 INT,
fact_id_2 INT,
relationship_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/fact_relationship.csv' OVERWRITE INTO TABLE eunomia.fact_relationship_temp;
CREATE OR REPLACE TABLE eunomia.fact_relationship USING DELTA AS SELECT * from eunomia.fact_relationship_temp where 1 <> 1;
INSERT INTO eunomia.fact_relationship
SELECT
domain_concept_id_1,
fact_id_1,
domain_concept_id_2,
fact_id_2,
relationship_concept_id
FROM eunomia.fact_relationship_temp WHERE upper(domain_concept_id_1) <> 'DOMAIN_CONCEPT_ID_1';
DROP TABLE IF EXISTS eunomia.fact_relationship_temp;
-----------------------------------------------
-- LOCATION
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.location_temp;
CREATE TABLE eunomia.location_temp (
location_id INT,
address_1 VARCHAR(50),
address_2 VARCHAR(50),
city VARCHAR(50),
state VARCHAR(2),
zip VARCHAR(9),
county VARCHAR(20),
location_source_value VARCHAR(50),
country_concept_id INT,
country_source_value VARCHAR(80),
latitude NUMERIC,
longitude NUMERIC
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/location.csv' OVERWRITE INTO TABLE eunomia.location_temp;
CREATE OR REPLACE TABLE eunomia.location USING DELTA AS SELECT * from eunomia.location_temp where 1 <> 1;
INSERT INTO eunomia.location
SELECT
location_id,
nullif(address_1, '') as address_1,
nullif(address_2, '') as address_2,
nullif(city, '') as city,
nullif(state, '') as state,
nullif(zip, '') as zip,
nullif(county, '') as county,
nullif(location_source_value, '') as location_source_value,
nullif(country_concept_id, '') as country_concept_id,
nullif(country_source_value, '') as country_source_value,
nullif(latitude, '') as latitude,
nullif(longitude, '') as longitude
FROM eunomia.location_temp WHERE upper(location_id) <> 'LOCATION_ID';
DROP TABLE IF EXISTS eunomia.location_temp;
-----------------------------------------------
-- CARE_SITE
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.care_site_temp;
CREATE TABLE eunomia.care_site_temp (
care_site_id INT,
care_site_name VARCHAR(255),
place_of_service_concept_id INT,
location_id INT,
care_site_source_value VARCHAR(50),
place_of_service_source_value VARCHAR(50)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/care_site.csv' OVERWRITE INTO TABLE eunomia.care_site_temp;
CREATE OR REPLACE TABLE eunomia.care_site USING DELTA AS SELECT * from eunomia.care_site_temp where 1 <> 1;
INSERT INTO eunomia.care_site
SELECT
care_site_id,
nullif(care_site_name, '') as care_site_name,
nullif(place_of_service_concept_id, '') as place_of_service_concept_id,
nullif(location_id, '') as location_id,
nullif(care_site_source_value, '') as care_site_source_value,
nullif(place_of_service_source_value, '') as place_of_service_source_value
FROM eunomia.care_site_temp WHERE upper(care_site_id) <> 'CARE_SITE_ID';
DROP TABLE IF EXISTS eunomia.care_site_temp;
-----------------------------------------------
-- PROVIDER
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.provider_temp;
CREATE TABLE eunomia.provider_temp (
provider_id INT,
provider_name VARCHAR(255),
npi VARCHAR(20),
dea VARCHAR(20),
specialty_concept_id INT,
care_site_id INT,
year_of_birth INT,
gender_concept_id INT,
provider_source_value VARCHAR(50),
specialty_source_value VARCHAR(50),
specialty_source_concept_id INT,
gender_source_concept_id INT,
gender_source_value VARCHAR(50)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/provider.csv' OVERWRITE INTO TABLE eunomia.provider_temp;
CREATE OR REPLACE TABLE eunomia.provider USING DELTA AS SELECT * from eunomia.provider_temp where 1 <> 1;
INSERT INTO eunomia.provider
SELECT
provider_id,
nullif(provider_name, '') as provider_name,
nullif(npi, '') as npi,
nullif(dea, '') as dea,
nullif(specialty_concept_id, '') as specialty_concept_id,
nullif(care_site_id, '') as care_site_id,
nullif(year_of_birth, '') as year_of_birth,
nullif(gender_concept_id, '') as gender_concept_id,
nullif(provider_source_value, '') as provider_source_value,
nullif(specialty_source_value, '') as specialty_source_value,
nullif(specialty_source_concept_id, '') as specialty_source_concept_id,
nullif(gender_source_value, '') as gender_source_value,
nullif(gender_source_concept_id, '') as gender_source_concept_id
FROM eunomia.provider_temp WHERE upper(provider_id) <> 'PROVIDER_ID';
DROP TABLE IF EXISTS eunomia.provider_temp;
-----------------------------------------------
-- PAYER_PLAN_PERIOD
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.payer_plan_period_temp;
CREATE TABLE eunomia.payer_plan_period_temp (
payer_plan_period_id INT,
person_id INT,
payer_plan_period_start_date DATE,
payer_plan_period_end_date DATE,
payer_concept_id INT,
payer_source_value VARCHAR(50),
payer_source_concept_id INT,
plan_concept_id INT,
plan_source_value VARCHAR(50),
plan_source_concept_id INT,
sponsor_concept_id INT,
sponsor_source_value VARCHAR(50),
sponsor_source_concept_id INT,
family_source_value VARCHAR(50),
stop_reason_concept_id INT,
stop_reason_source_value VARCHAR(50),
stop_reason_source_concept_id INT
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/payer_plan_period.csv' OVERWRITE INTO TABLE eunomia.payer_plan_period_temp;
CREATE OR REPLACE TABLE eunomia.payer_plan_period USING DELTA AS SELECT * from eunomia.payer_plan_period_temp where 1 <> 1;
INSERT INTO eunomia.payer_plan_period
SELECT
payer_plan_period_id,
person_id,
payer_plan_period_start_date,
payer_plan_period_end_date,
nullif(payer_concept_id, '') as payer_concept_id,
nullif(payer_source_value, '') as payer_source_value,
nullif(payer_source_concept_id, '') as payer_source_concept_id,
nullif(plan_concept_id, '') as plan_concept_id,
nullif(plan_source_value, '') as plan_source_value,
nullif(plan_source_concept_id, '') as plan_source_concept_id,
nullif(sponsor_concept_id, '') as sponsor_concept_id,
nullif(sponsor_source_value, '') as sponsor_source_value,
nullif(sponsor_source_concept_id, '') as sponsor_source_concept_id,
nullif(family_source_value, '') as family_source_value,
nullif(stop_reason_concept_id, '') as stop_reason_concept_id,
nullif(stop_reason_source_value, '') as stop_reason_source_value,
nullif(stop_reason_source_concept_id, '') as stop_reason_source_concept_id
FROM eunomia.payer_plan_period_temp WHERE upper(payer_plan_period_id) <> 'PAYER_PLAN_PERIOD_ID';
DROP TABLE IF EXISTS eunomia.payer_plan_period_temp;
-----------------------------------------------
-- COST
-----------------------------------------------
DROP TABLE IF EXISTS eunomia.cost_temp;
CREATE TABLE eunomia.cost_temp (
cost_id INT,
cost_event_id INT,
cost_domain_id VARCHAR(20),
cost_type_concept_id INT,
currency_concept_id INT,
total_charge NUMERIC,
total_cost NUMERIC,
total_paid NUMERIC,
paid_by_payer NUMERIC,
paid_by_patient NUMERIC,
paid_patient_copay NUMERIC,
paid_patient_coinsurance NUMERIC,
paid_patient_deductible NUMERIC,
paid_by_primary NUMERIC,
paid_ingredient_cost NUMERIC,
paid_dispensing_fee NUMERIC,
payer_plan_period_id INT,
amount_allowed NUMERIC,
revenue_code_concept_id INT,
revenue_code_source_value VARCHAR(50),
drg_concept_id INT,
drg_source_value VARCHAR(3)
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
TBLPROPERTIES('dateFormat'='yyyy-MM-dd');
LOAD DATA LOCAL INPATH '/demo_cdm_csv_files/cost.csv' OVERWRITE INTO TABLE eunomia.cost_temp;
CREATE OR REPLACE TABLE eunomia.cost USING DELTA AS SELECT * from eunomia.cost_temp where 1 <> 1;
INSERT INTO eunomia.cost
SELECT
cost_id,
cost_event_id,
cost_domain_id,
cost_type_concept_id,
nullif(currency_concept_id, '') as currency_concept_id,
nullif(total_charge, '') as total_charge,
nullif(total_cost, '') as total_cost,
nullif(total_paid, '') as total_paid,
nullif(paid_by_payer, '') as paid_by_payer,
nullif(paid_by_patient, '') as paid_by_patient,
nullif(paid_patient_copay, '') as paid_patient_copay,
nullif(paid_patient_coinsurance, '') as paid_patient_coinsurance,
nullif(paid_patient_deductible, '') as paid_patient_deductible,
nullif(paid_by_primary, '') as paid_by_primary,
nullif(paid_ingredient_cost, '') as paid_ingredient_cost,
nullif(paid_dispensing_fee, '') as paid_dispensing_fee,
nullif(payer_plan_period_id, '') as payer_plan_period_id,
nullif(amount_allowed, '') as amount_allowed,
nullif(revenue_code_concept_id, '') as revenue_code_concept_id,
nullif(revenue_code_source_value, '') as revenue_code_source_value,
nullif(drg_concept_id, '') as drg_concept_id,
nullif(drg_source_value, '') as drg_source_value