For insertion of errors, start with crude errors:
a) Take some variables for only numerical values and randomly insert characters into numbers,
b) take variables that must not have nulls, and insert spaces
c) look into some range values and insert values that are outside of these values.
In [46]:
import pandas as pd
import math
import string
import random
from random import randint
In [47]:
file = pd.read_csv("/Users/michaelbowie/Downloads/INPUTEVENTS_MV.csv")
In [48]:
file = file.iloc[::30, :]
In [60]:
file = file.reset_index(drop=True)
In [61]:
file
Out[61]:
ROW_ID
SUBJECT_ID
HADM_ID
ICUSTAY_ID
STARTTIME
ENDTIME
ITEMID
AMOUNT
AMOUNTUOM
RATE
...
TOTALAMOUNTUOM
ISOPENBAG
CONTINUEINNEXTDEPT
CANCELREASON
STATUSDESCRIPTION
COMMENTS_EDITEDBY
COMMENTS_CANCELEDBY
COMMENTS_DATE
ORIGINALAMOUNT
ORIGINALRATE
0
119199
42367
139932
250305
2147-10-21 23:42:00
2147-10-21 23:43:00
223259
15.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
15.000000
15.000000
1
119080
42367
139932
250305
2147-10-19 16:11:00
2147-10-19 16:12:00
226453
40.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
40.000000
40.000000
2
119227
42367
139932
250305
2147-10-28 19:56:00
2147-10-28 19:57:00
225799
60.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
60.000000
60.000000
3
119110
42367
139932
250305
2147-10-14 11:15:00
2147-10-14 11:16:00
221744
49.999999
mcg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
50.000000
50.000000
4
119244
42367
139932
250305
2147-10-18 16:30:00
2147-10-18 17:30:00
225166
20.000000
mEq
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
20.000000
0.333333
5
118991
42367
139932
250305
2147-10-04 06:00:00
2147-10-04 06:01:00
225158
500.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
500.000000
500.000000
6
119123
42367
139932
250305
2147-10-27 03:35:00
2147-10-28 19:35:00
225158
200.000006
ml
5.000000
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-28 22:13:00
200.000000
5.000000
7
119011
42367
139932
250305
2147-10-07 22:00:00
2147-10-07 22:01:00
223258
4.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
4.000000
4.000000
8
119144
42367
139932
250305
2147-10-05 14:30:00
2147-10-05 16:02:00
222168
32.167836
mg
4.995006
...
ml
0
0
0
Stopped
NaN
NaN
NaN
191.608410
5.000000
9
119336
42367
139932
250305
2147-10-09 21:08:00
2147-10-09 21:09:00
225158
1.000000
ml
60.000000
...
ml
0
0
1
Rewritten
NaN
RN
2147-10-10 00:16:00
632.000000
60.000000
10
119163
42367
139932
250305
2147-10-12 17:00:00
2147-10-12 19:00:00
225158
2.000000
ml
1.000000
...
ml
0
0
0
Changed
NaN
NaN
NaN
100.000000
1.000000
11
119357
42367
139932
250305
2147-10-20 10:00:00
2147-10-20 11:00:00
226089
99.999996
ml
99.999996
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
100.000000
12
119185
42367
139932
250305
2147-10-09 00:07:00
2147-10-09 16:47:00
225158
1000.000000
ml
60.000000
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-09 15:03:00
1000.000000
60.000000
13
119377
42367
139932
250305
2147-10-26 20:00:00
2147-10-26 20:01:00
226453
50.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
50.000000
50.000000
14
119685
42367
139932
250305
2147-10-19 14:32:00
2147-10-19 14:47:00
226089
99.999997
ml
399.999990
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
400.000000
15
119531
42367
139932
250305
2147-10-13 17:31:00
2147-10-13 17:32:00
221794
0.033311
mg
1.998641
...
ml
0
0
0
Rewritten
NaN
NaN
NaN
12.591438
2.000000
16
119725
42367
139932
250305
2147-10-14 05:57:00
2147-10-14 05:58:00
223258
0.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
0.000000
0.000000
17
119735
42367
139932
250305
2147-10-15 17:59:00
2147-10-15 18:14:00
226089
99.999997
ml
399.999990
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
400.000000
18
118930
42367
139932
250305
2147-10-28 19:35:00
2147-10-30 11:35:00
225158
200.000006
ml
5.000000
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-30 16:31:00
200.000000
5.000000
19
119264
42367
139932
250305
2147-10-04 19:14:00
2147-10-05 14:30:00
222168
810.666109
mg
10.018118
...
ml
0
0
0
Changed
NaN
NaN
NaN
1000.000100
10.000000
20
119761
42367
139932
250305
2147-10-22 10:00:00
2147-10-22 10:01:00
226453
50.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
50.000000
50.000000
21
119440
42367
139932
250305
2147-10-14 10:00:00
2147-10-14 10:01:00
223258
5.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
5.000000
5.000000
22
119283
42367
139932
250305
2147-10-09 16:00:00
2147-10-09 16:01:00
223258
4.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
4.000000
4.000000
23
119605
42367
139932
250305
2147-10-06 08:00:00
2147-10-06 08:01:00
225974
5.000000
mg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
5.000000
5.000000
24
119410
42367
139932
250305
2147-10-16 10:00:00
2147-10-16 10:01:00
223258
8.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
8.000000
8.000000
25
119464
42367
139932
250305
2147-10-13 17:22:00
2147-10-18 16:24:00
225156
2500.000035
mg
0.300036
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-13 18:04:00
2500.000000
0.300000
26
119636
42367
139932
250305
2147-10-12 20:16:00
2147-10-12 20:17:00
221794
20.000001
mg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
20.000000
20.000000
27
119672
42367
139932
250305
2147-10-11 05:30:00
2147-10-11 05:31:00
223258
8.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
8.000000
8.000000
28
119438
42367
139932
250305
2147-10-19 11:16:00
2147-10-19 11:17:00
225799
240.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
240.000000
240.000000
29
149189
43881
172454
214180
2104-09-25 20:00:00
2104-09-25 20:01:00
225943
10.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
10.000000
0.000000
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
411
1454659
41976
172082
253931
2200-03-18 20:16:00
2200-03-18 21:48:00
225158
8.719763
ml
5.686802
...
ml
0
0
0
Changed
NaN
NaN
NaN
43.504032
5.681833
412
1454984
41976
172082
253931
2200-03-19 13:51:00
2200-03-19 13:52:00
225893
1.000000
dose
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
1.000000
1.000000
413
1454706
41976
172082
253931
2200-03-20 12:01:00
2200-03-20 13:04:00
225158
113.980261
ml
108.552630
...
ml
0
0
0
Changed
NaN
NaN
NaN
550.000000
108.552630
414
1454609
41976
172082
253931
2200-03-19 02:25:00
2200-03-19 05:10:00
225158
7.824682
ml
2.845339
...
ml
0
0
0
Stopped
NaN
NaN
NaN
15.080296
2.840916
415
1454638
41976
172082
253931
2200-03-22 10:00:00
2200-03-22 10:01:00
221744
74.999996
mcg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
75.000000
75.000000
416
1454965
41976
172082
253931
2200-03-19 16:15:00
2200-03-19 21:47:00
222168
252.086079
mg
10.017090
...
ml
0
0
0
Paused
NaN
NaN
NaN
270.309140
10.000000
417
1454871
41976
172082
253931
2200-03-25 00:00:00
2200-03-25 00:01:00
220949
100.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
0.000000
418
1454784
41976
172082
253931
2200-03-28 06:15:00
2200-03-28 09:33:00
220949
38.594960
ml
11.695442
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
38.594959
11.672711
419
1454749
41976
172082
253931
2200-03-17 22:51:00
2200-03-17 23:15:00
225158
6.825939
ml
17.064847
...
ml
0
0
0
Changed
NaN
NaN
NaN
250.000000
17.045500
420
1454802
41976
172082
253931
2200-03-18 14:54:00
2200-03-20 16:54:00
225942
2.500000
mg
50.000003
...
ml
0
0
1
Rewritten
NaN
RN
2200-03-18 14:58:00
2.500000
50.000000
421
1659771
41976
152032
234541
2200-06-10 09:25:00
2200-06-10 10:25:00
226089
99.999996
ml
99.999996
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
100.000000
422
1659803
41976
152032
234541
2200-06-11 11:17:00
2200-06-11 15:16:00
227979
240.000000
ml
60.251046
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
240.000000
60.251045
423
2027254
41976
130681
265505
2200-11-02 19:42:00
2200-11-02 19:43:00
220949
200.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
200.000000
0.000000
424
2027296
41976
130681
265505
2200-10-30 15:06:00
2200-10-30 15:07:00
225797
125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
125.000000
125.000000
425
2027194
41976
130681
265505
2200-10-30 17:59:00
2200-10-30 18:00:00
223262
8.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
8.000000
8.000000
426
2027239
41976
130681
265505
2200-11-02 08:00:00
2200-11-02 08:01:00
226453
125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
125.000000
125.000000
427
2027292
41976
130681
265505
2200-10-31 02:55:00
2200-10-31 02:56:00
225797
125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
125.000000
125.000000
428
2027324
41976
130681
265505
2200-10-30 07:12:00
2200-10-30 07:13:00
225975
1.000000
dose
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
1.000000
1.000000
429
2027222
41976
130681
265505
2200-10-30 00:58:00
2200-10-30 00:59:00
225828
1000.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
1000.000000
1000.000000
430
2510990
41976
180546
285353
2201-05-13 07:23:00
2201-05-13 07:24:00
220949
100.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
0.000000
431
2847362
41976
125013
213315
2201-10-01 08:00:00
2201-10-01 08:01:00
226452
60.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
60.000000
60.000000
432
2847383
41976
125013
213315
2201-09-28 18:56:00
2201-09-28 21:21:00
221906
3.055802
mg
0.301064
...
ml
0
0
0
Changed
NaN
NaN
NaN
6.764912
0.300000
433
2847429
41976
125013
213315
2201-09-30 13:01:00
2201-09-30 15:38:00
225152
3411.938130
units
1303.925400
...
ml
0
0
0
Rewritten
NaN
NaN
NaN
3411.938000
1300.000000
434
2847390
41976
125013
213315
2201-09-29 06:32:00
2201-09-29 09:58:00
227979
188.414639
ml
54.878050
...
ml
0
0
0
Changed
NaN
NaN
NaN
300.000000
55.000000
435
2847406
41976
125013
213315
2201-09-29 14:16:00
2201-09-29 22:36:00
221906
0.700005
mg
0.020000
...
ml
0
0
0
Stopped
NaN
NaN
NaN
7.537649
0.020000
436
2951796
41976
155297
209797
2201-11-17 19:49:00
2201-11-17 19:50:00
225883
1.000000
dose
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
1.000000
1.000000
437
2951826
41976
155297
209797
2201-11-17 11:07:00
2201-11-17 11:08:00
225799
120.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
120.000000
120.000000
438
2951782
41976
155297
209797
2201-11-17 20:00:00
2201-11-18 02:40:00
225936
500.000000
ml
75.000000
...
ml
0
0
2
Rewritten
RN
NaN
2201-11-18 02:13:00
500.000000
75.000000
439
3173421
41976
151798
280943
2202-02-16 19:37:00
2202-02-16 19:38:00
226453
30.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
30.000000
30.000000
440
3173409
41976
151798
280943
2202-02-15 22:31:00
2202-02-15 23:25:00
220949
30.066814
ml
33.407572
...
ml
0
0
0
Changed
NaN
NaN
NaN
250.000000
33.333302
441 rows × 31 columns
a) Take some variables for only numerical values and randomly insert characters into numbers.
In [74]:
# Sample Percentage
s_percent = .3
iter_times = math.ceil(file.shape[0] * s_percent)
num = 0
num_row = file.shape[0] - 1
file['ITEMID'] = file['ITEMID'].astype(str)
# INSERT RANDOM CHARACTERS INTO NUMERICAL VALUES
while num < iter_times:
row = randint(0, num_row)
col = "ITEMID"
s = file.loc[row][col]
s = str(s)
char = random.choice(string.ascii_letters)
pos = randint(0, len(s) - 1) # pick random position to insert char
change = "".join((s[:pos], char, s[pos:])) # insert char at pos
file = file.set_value(row, col, change)
num = num + 1
b) take variables that must not have nulls, and insert spaces
In [78]:
num = 0
file['SUBJECT_ID'] = file['SUBJECT_ID'].astype(str)
# REPLACES VALUES THAT SHOULD NOT BE NULL WITH SPACES
while num < iter_times:
row = randint(0, num_row)
col = "SUBJECT_ID"
change = " "
file = file.set_value(row, col, change)
num = num + 1
c) look into some range values and insert values that are outside of these values.
In [83]:
num = 0
# INSERT VALUES OUTSIDE THE MIN/MAX RANGE
while num < iter_times:
rand_low = randint(-1000, -1)
rand_high = randint(25000, 50000)
rand = [rand_low, rand_high]
row = randint(0, num_row)
col = "AMOUNT"
change = random.choice(rand)
file = file.set_value(row, col, change)
num = num + 1
In [84]:
file
Out[84]:
ROW_ID
SUBJECT_ID
HADM_ID
ICUSTAY_ID
STARTTIME
ENDTIME
ITEMID
AMOUNT
AMOUNTUOM
RATE
...
TOTALAMOUNTUOM
ISOPENBAG
CONTINUEINNEXTDEPT
CANCELREASON
STATUSDESCRIPTION
COMMENTS_EDITEDBY
COMMENTS_CANCELEDBY
COMMENTS_DATE
ORIGINALAMOUNT
ORIGINALRATE
0
119199
139932
250305
2147-10-21 23:42:00
2147-10-21 23:43:00
223r259
15.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
15.000000
15.000000
1
119080
139932
250305
2147-10-19 16:11:00
2147-10-19 16:12:00
226453
40.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
40.000000
40.000000
2
119227
42367
139932
250305
2147-10-28 19:56:00
2147-10-28 19:57:00
-942
32905.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
60.000000
60.000000
3
119110
42367
139932
250305
2147-10-14 11:15:00
2147-10-14 11:16:00
221744
49.999999
mcg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
50.000000
50.000000
4
119244
42367
139932
250305
2147-10-18 16:30:00
2147-10-18 17:30:00
225166
20.000000
mEq
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
20.000000
0.333333
5
118991
42367
139932
250305
2147-10-04 06:00:00
2147-10-04 06:01:00
225158
500.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
500.000000
500.000000
6
119123
42367
139932
250305
2147-10-27 03:35:00
2147-10-28 19:35:00
22l5158
-874.000000
ml
5.000000
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-28 22:13:00
200.000000
5.000000
7
119011
139932
250305
2147-10-07 22:00:00
2147-10-07 22:01:00
29508
-793.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
4.000000
4.000000
8
119144
42367
139932
250305
2147-10-05 14:30:00
2147-10-05 16:02:00
222M168
32.167836
mg
4.995006
...
ml
0
0
0
Stopped
NaN
NaN
NaN
191.608410
5.000000
9
119336
42367
139932
250305
2147-10-09 21:08:00
2147-10-09 21:09:00
22515W8
1.000000
ml
60.000000
...
ml
0
0
1
Rewritten
NaN
RN
2147-10-10 00:16:00
632.000000
60.000000
10
119163
42367
139932
250305
2147-10-12 17:00:00
2147-10-12 19:00:00
-382
2.000000
ml
1.000000
...
ml
0
0
0
Changed
NaN
NaN
NaN
100.000000
1.000000
11
119357
42367
139932
250305
2147-10-20 10:00:00
2147-10-20 11:00:00
226Z089
27462.000000
ml
99.999996
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
100.000000
12
119185
139932
250305
2147-10-09 00:07:00
2147-10-09 16:47:00
Z225158
1000.000000
ml
60.000000
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-09 15:03:00
1000.000000
60.000000
13
119377
139932
250305
2147-10-26 20:00:00
2147-10-26 20:01:00
226453
50.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
50.000000
50.000000
14
119685
42367
139932
250305
2147-10-19 14:32:00
2147-10-19 14:47:00
226089
99.999997
ml
399.999990
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
400.000000
15
119531
42367
139932
250305
2147-10-13 17:31:00
2147-10-13 17:32:00
-348
0.033311
mg
1.998641
...
ml
0
0
0
Rewritten
NaN
NaN
NaN
12.591438
2.000000
16
119725
42367
139932
250305
2147-10-14 05:57:00
2147-10-14 05:58:00
223258
45257.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
0.000000
0.000000
17
119735
139932
250305
2147-10-15 17:59:00
2147-10-15 18:14:00
226089
99.999997
ml
399.999990
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
400.000000
18
118930
42367
139932
250305
2147-10-28 19:35:00
2147-10-30 11:35:00
225158
200.000006
ml
5.000000
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-30 16:31:00
200.000000
5.000000
19
119264
42367
139932
250305
2147-10-04 19:14:00
2147-10-05 14:30:00
48421
810.666109
mg
10.018118
...
ml
0
0
0
Changed
NaN
NaN
NaN
1000.000100
10.000000
20
119761
42367
139932
250305
2147-10-22 10:00:00
2147-10-22 10:01:00
226453
50.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
50.000000
50.000000
21
119440
42367
139932
250305
2147-10-14 10:00:00
2147-10-14 10:01:00
223258
5.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
5.000000
5.000000
22
119283
139932
250305
2147-10-09 16:00:00
2147-10-09 16:01:00
2W232l58
4.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
4.000000
4.000000
23
119605
42367
139932
250305
2147-10-06 08:00:00
2147-10-06 08:01:00
225974
5.000000
mg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
5.000000
5.000000
24
119410
42367
139932
250305
2147-10-16 10:00:00
2147-10-16 10:01:00
223258
8.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
8.000000
8.000000
25
119464
139932
250305
2147-10-13 17:22:00
2147-10-18 16:24:00
225156
-370.000000
mg
0.300036
...
ml
0
0
2
Rewritten
RN
NaN
2147-10-13 18:04:00
2500.000000
0.300000
26
119636
42367
139932
250305
2147-10-12 20:16:00
2147-10-12 20:17:00
221794
49875.000000
mg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
20.000000
20.000000
27
119672
139932
250305
2147-10-11 05:30:00
2147-10-11 05:31:00
-535
8.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
8.000000
8.000000
28
119438
139932
250305
2147-10-19 11:16:00
2147-10-19 11:17:00
225N799
-125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
240.000000
240.000000
29
149189
172454
214180
2104-09-25 20:00:00
2104-09-25 20:01:00
-897
10.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
10.000000
0.000000
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
411
1454659
41976
172082
253931
2200-03-18 20:16:00
2200-03-18 21:48:00
225158
8.719763
ml
5.686802
...
ml
0
0
0
Changed
NaN
NaN
NaN
43.504032
5.681833
412
1454984
172082
253931
2200-03-19 13:51:00
2200-03-19 13:52:00
-16
33228.000000
dose
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
1.000000
1.000000
413
1454706
41976
172082
253931
2200-03-20 12:01:00
2200-03-20 13:04:00
44445
113.980261
ml
108.552630
...
ml
0
0
0
Changed
NaN
NaN
NaN
550.000000
108.552630
414
1454609
41976
172082
253931
2200-03-19 02:25:00
2200-03-19 05:10:00
225158
7.824682
ml
2.845339
...
ml
0
0
0
Stopped
NaN
NaN
NaN
15.080296
2.840916
415
1454638
172082
253931
2200-03-22 10:00:00
2200-03-22 10:01:00
221744
74.999996
mcg
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
75.000000
75.000000
416
1454965
172082
253931
2200-03-19 16:15:00
2200-03-19 21:47:00
2r22168
252.086079
mg
10.017090
...
ml
0
0
0
Paused
NaN
NaN
NaN
270.309140
10.000000
417
1454871
41976
172082
253931
2200-03-25 00:00:00
2200-03-25 00:01:00
220949
100.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
0.000000
418
1454784
41976
172082
253931
2200-03-28 06:15:00
2200-03-28 09:33:00
220949
29315.000000
ml
11.695442
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
38.594959
11.672711
419
1454749
172082
253931
2200-03-17 22:51:00
2200-03-17 23:15:00
-410
6.825939
ml
17.064847
...
ml
0
0
0
Changed
NaN
NaN
NaN
250.000000
17.045500
420
1454802
41976
172082
253931
2200-03-18 14:54:00
2200-03-20 16:54:00
22y5942
-376.000000
mg
50.000003
...
ml
0
0
1
Rewritten
NaN
RN
2200-03-18 14:58:00
2.500000
50.000000
421
1659771
41976
152032
234541
2200-06-10 09:25:00
2200-06-10 10:25:00
226089
99.999996
ml
99.999996
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
100.000000
422
1659803
41976
152032
234541
2200-06-11 11:17:00
2200-06-11 15:16:00
34802
34918.000000
ml
60.251046
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
240.000000
60.251045
423
2027254
41976
130681
265505
2200-11-02 19:42:00
2200-11-02 19:43:00
29243
200.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
200.000000
0.000000
424
2027296
41976
130681
265505
2200-10-30 15:06:00
2200-10-30 15:07:00
42287
125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
125.000000
125.000000
425
2027194
41976
130681
265505
2200-10-30 17:59:00
2200-10-30 18:00:00
223262
8.000000
units
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
8.000000
8.000000
426
2027239
130681
265505
2200-11-02 08:00:00
2200-11-02 08:01:00
-458
125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
125.000000
125.000000
427
2027292
41976
130681
265505
2200-10-31 02:55:00
2200-10-31 02:56:00
-154
125.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
125.000000
125.000000
428
2027324
41976
130681
265505
2200-10-30 07:12:00
2200-10-30 07:13:00
22M5975
1.000000
dose
NaN
...
NaN
0
0
0
FinishedRunning
NaN
NaN
NaN
1.000000
1.000000
429
2027222
130681
265505
2200-10-30 00:58:00
2200-10-30 00:59:00
-268
1000.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
1000.000000
1000.000000
430
2510990
180546
285353
2201-05-13 07:23:00
2201-05-13 07:24:00
C220949
-582.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
100.000000
0.000000
431
2847362
41976
125013
213315
2201-10-01 08:00:00
2201-10-01 08:01:00
43311
-504.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
60.000000
60.000000
432
2847383
41976
125013
213315
2201-09-28 18:56:00
2201-09-28 21:21:00
221906
3.055802
mg
0.301064
...
ml
0
0
0
Changed
NaN
NaN
NaN
6.764912
0.300000
433
2847429
41976
125013
213315
2201-09-30 13:01:00
2201-09-30 15:38:00
225152
3411.938130
units
1303.925400
...
ml
0
0
0
Rewritten
NaN
NaN
NaN
3411.938000
1300.000000
434
2847390
125013
213315
2201-09-29 06:32:00
2201-09-29 09:58:00
227979
188.414639
ml
54.878050
...
ml
0
0
0
Changed
NaN
NaN
NaN
300.000000
55.000000
435
2847406
125013
213315
2201-09-29 14:16:00
2201-09-29 22:36:00
221PY906
0.700005
mg
0.020000
...
ml
0
0
0
Stopped
NaN
NaN
NaN
7.537649
0.020000
436
2951796
41976
155297
209797
2201-11-17 19:49:00
2201-11-17 19:50:00
-816
1.000000
dose
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
1.000000
1.000000
437
2951826
41976
155297
209797
2201-11-17 11:07:00
2201-11-17 11:08:00
-516
120.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
120.000000
120.000000
438
2951782
41976
155297
209797
2201-11-17 20:00:00
2201-11-18 02:40:00
225936
500.000000
ml
75.000000
...
ml
0
0
2
Rewritten
RN
NaN
2201-11-18 02:13:00
500.000000
75.000000
439
3173421
41976
151798
280943
2202-02-16 19:37:00
2202-02-16 19:38:00
226453
30.000000
ml
NaN
...
ml
0
0
0
FinishedRunning
NaN
NaN
NaN
30.000000
30.000000
440
3173409
41976
151798
280943
2202-02-15 22:31:00
2202-02-15 23:25:00
e220949
30.066814
ml
33.407572
...
ml
0
0
0
Changed
NaN
NaN
NaN
250.000000
33.333302
441 rows × 31 columns
In [80]:
file['AMOUNT'].describe()
Out[80]:
count 441.000000
mean 245.067554
std 1321.189992
min 0.000000
25% 3.055802
50% 30.000000
75% 112.900000
max 24166.666672
Name: AMOUNT, dtype: float64
In [36]:
#change = file.sample(1)
In [85]:
#file.loc[change,'ITEMID'] = 0
In [ ]:
In [ ]:
In [ ]:
Content source: ebegoli/ErrorProne
Similar notebooks: