In [1]:
import pandas as pd
import numpy as np
In [6]:
df = pd.read_csv("tr.csv")
In [7]:
df.head()
Out[7]:
ACTION
RESOURCE
MGR_ID
ROLE_ROLLUP_1
ROLE_ROLLUP_2
ROLE_DEPTNAME
ROLE_TITLE
ROLE_FAMILY_DESC
ROLE_FAMILY
ROLE_CODE
0
1
39353
85475
117961
118300
123472
117905
117906
290919
117908
1
1
17183
1540
117961
118343
123125
118536
118536
308574
118539
2
1
36724
14457
118219
118220
117884
117879
267952
19721
117880
3
1
36135
5396
117961
118343
119993
118321
240983
290919
118322
4
1
42680
5905
117929
117930
119569
119323
123932
19793
119325
In [8]:
lengh = len(df)
for i in df.columns.values :
print(df[i].value_counts())
1 30872
0 1897
Name: ACTION, dtype: int64
4675 839
79092 484
25993 409
75078 409
3853 404
6977 299
75834 299
32270 295
42085 247
17308 239
1020 236
13878 220
42093 204
18418 192
7543 186
23921 167
278393 163
34924 161
79121 157
28149 137
18072 136
20364 135
39262 129
14354 127
23096 126
75901 115
15064 113
33054 108
20897 104
33642 99
...
35046 1
92378 1
100413 1
79728 1
79792 1
36894 1
28635 1
59370 1
45057 1
30629 1
18462 1
38809 1
77905 1
42879 1
75631 1
39012 1
30565 1
18275 1
79693 1
97530 1
28793 1
18243 1
20290 1
26407 1
43202 1
35014 1
75535 1
30936 1
89856 1
16376 1
Name: RESOURCE, dtype: int64
770 152
2270 99
2594 82
1350 71
2014 67
16850 66
3966 64
7807 64
5244 62
5396 62
3526 62
4659 61
7411 61
54618 61
18686 60
7578 58
7389 58
3281 57
70062 57
18213 57
6982 56
1475 56
71189 55
85475 55
1334 54
3838 54
46254 54
1903 53
1755 53
7553 53
...
50605 1
93720 1
55662 1
53519 1
28225 1
6358 1
20421 1
3285 1
17628 1
64779 1
6030 1
5542 1
311597 1
8047 1
5526 1
5966 1
50604 1
142801 1
7639 1
15651 1
97915 1
58648 1
44633 1
1908 1
73591 1
1940 1
8087 1
22526 1
34948 1
58677 1
Name: MGR_ID, dtype: int64
117961 21407
117902 742
91261 721
118315 498
118212 400
118290 398
119062 375
118887 334
117916 295
118169 291
118752 282
117929 276
118256 275
117926 269
119596 239
117890 234
118079 221
118006 197
118573 190
5110 186
118219 184
117876 171
120864 160
117910 149
119134 149
119280 144
118595 140
117983 129
118602 129
118084 119
...
247952 12
120883 12
132839 12
118976 12
130684 11
119178 10
216705 10
121518 9
119740 8
119370 7
127044 7
192441 5
183723 5
119828 5
120268 4
127616 4
119615 4
119027 3
311178 2
118358 2
147236 1
118774 1
120354 1
143008 1
133430 1
203209 1
209434 1
141221 1
119343 1
121411 1
Name: ROLE_ROLLUP_1, dtype: int64
118300 4424
118343 3945
118327 2641
118225 2547
118386 1796
118052 1665
117962 1567
118413 1295
118446 971
118026 721
117903 489
117969 397
118291 396
118888 334
119091 321
118213 295
118170 291
118463 267
118257 257
118041 253
119597 239
118316 231
118080 221
119070 209
118007 197
118574 190
117954 186
118178 185
118220 184
119256 181
...
119762 5
141176 5
119829 5
119616 4
120269 4
123999 4
121019 3
119715 3
119028 3
120862 3
132564 2
124157 2
118359 2
119344 1
176316 1
118907 1
286791 1
131390 1
143009 1
132840 1
185842 1
140550 1
125018 1
147237 1
121602 1
141222 1
32137 1
120355 1
118775 1
120018 1
Name: ROLE_ROLLUP_2, dtype: int64
117878 1135
117941 763
117945 659
118514 601
117920 597
117884 546
119598 543
118403 532
119181 525
120722 501
118320 435
117895 431
118746 415
118783 366
120663 335
118910 325
118437 317
118352 305
118631 304
120551 304
118458 300
118042 296
118202 296
118395 292
118623 284
120370 278
122007 267
118507 267
118522 251
118391 231
...
118433 2
148436 2
126574 2
120142 2
122001 2
125101 2
119496 1
121097 1
122587 1
120201 1
139001 1
138789 1
147019 1
184402 1
132647 1
286792 1
122722 1
118035 1
121030 1
223958 1
255696 1
29113 1
127155 1
134848 1
122358 1
123175 1
122963 1
123675 1
119565 1
272283 1
Name: ROLE_DEPTNAME, dtype: int64
118321 4649
117905 3583
118784 1772
117879 1256
118568 1043
117885 806
118054 774
118685 597
118777 566
118451 521
120344 473
307024 467
280788 394
179731 384
118422 376
118890 347
118636 344
118396 342
119849 337
118834 335
117946 329
120773 289
118641 288
118259 274
117899 240
118043 238
119093 224
118747 218
120690 217
120006 216
...
149916 1
157300 1
130633 1
166800 1
122188 1
137370 1
124486 1
126502 1
310825 1
130284 1
126418 1
240103 1
268608 1
270690 1
157359 1
152268 1
123131 1
297560 1
157799 1
153248 1
117906 1
208565 1
266862 1
155110 1
126547 1
126931 1
239003 1
130362 1
157347 1
125405 1
Name: ROLE_TITLE, dtype: int64
117906 6896
240983 1244
117913 670
279443 665
117886 530
130134 419
117897 351
117879 333
168365 324
133686 321
118054 311
118448 282
118959 246
280788 244
118785 233
302830 225
300136 222
311622 219
269406 211
306399 205
310608 202
118260 199
311441 194
305057 181
120324 179
118806 174
281735 161
310997 160
123107 155
301534 154
...
150320 1
222005 1
216064 1
120034 1
192106 1
146655 1
203113 1
250160 1
194805 1
124811 1
137275 1
126932 1
194455 1
147792 1
220962 1
145167 1
135770 1
266874 1
136811 1
126548 1
127782 1
153123 1
151040 1
214497 1
122130 1
125925 1
130023 1
160903 1
128102 1
157709 1
Name: ROLE_FAMILY_DESC, dtype: int64
290919 10980
118424 2690
19721 2636
117887 2400
292795 1318
118398 1294
308574 1287
118453 941
118331 892
118638 783
118643 783
270488 689
118295 493
118960 465
118205 449
119095 412
4673 384
19793 362
120518 294
119184 293
118704 241
249618 224
118363 190
118474 181
121916 176
118131 160
118467 150
118762 150
3130 146
119221 128
...
119788 58
124136 53
119006 49
120134 39
119772 35
122032 30
121069 27
121620 23
118372 20
118736 20
118347 19
120302 16
124487 15
118478 9
151277 7
131999 7
124145 7
123689 6
123611 5
155173 5
125407 4
143398 4
254395 3
127957 3
136398 3
130364 3
159679 3
161100 2
149353 2
132725 2
Name: ROLE_FAMILY, dtype: int64
118322 4649
117908 3583
118786 1772
117880 1256
118570 1043
117888 806
118055 774
118687 597
118779 566
118454 521
120346 473
118332 467
119082 394
117973 384
118425 376
118892 347
118639 344
118399 342
119851 337
118836 335
117948 329
120774 289
118644 288
118261 274
117900 240
118046 238
119096 224
118749 218
120692 217
120008 216
...
123133 1
155111 1
126420 1
209875 1
123657 1
166801 1
130285 1
208567 1
157361 1
126933 1
268610 1
121395 1
122190 1
157348 1
125408 1
240105 1
137371 1
152270 1
149918 1
124488 1
157801 1
130635 1
119817 1
270691 1
130365 1
266863 1
126504 1
239004 1
126549 1
188048 1
Name: ROLE_CODE, dtype: int64
In [ ]:
Content source: DataAnalysts/MachineLearning
Similar notebooks: