Joe_May24
Last Checkpoint: 6 minutes ago
(autosaved)

Logout

Python 2

Trusted
File
Edit
View
Insert
Cell
Kernel
Widgets
Help







Run






In [1]:




1
import sys
2
import pickle
3
import os
4
sys.path.append("../tools/")
5
​
6
final_proj_path = "/Users/jfole/Downloads/ud120-projects-master_joe/ud120-projects-master_joe/final_project"
7
sys.path.append("/Users/jfole/Downloads/ud120-projects-master_joe/ud120-projects-master_joe/tools")
8
sys.path.append(final_proj_path)
9
​
10
​
11
from feature_format import featureFormat, targetFeatureSplit
12
from tester import dump_classifier_and_data
13
#First Section: import dataset
14
data_dict = pickle.load(open(os.path.join(final_proj_path, "final_project_dataset.pkl"), "r") )
15
print 'The total number of data points is',len(data_dict.keys())




The total number of data points is 146

C:\Users\jfole\Anaconda2\lib\site-packages\sklearn\cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
In [2]:




1
### Task 1: Select what features you'll use.
2
feature_list= ['poi','salary',
3
 'to_messages',
4
 'deferral_payments',
5
 'total_payments',
6
 'exercised_stock_options',
7
 'bonus',
8
 'restricted_stock',
9
 'shared_receipt_with_poi',
10
 'restricted_stock_deferred',
11
 'total_stock_value',
12
 'expenses',
13
 'loan_advances',
14
 'from_messages',
15
 'other',
16
 'from_this_person_to_poi',
17
 'poi',
18
 'director_fees',
19
 'deferred_income',
20
 'long_term_incentive',
21
 'email_address',
22
 'from_poi_to_this_person']




In [3]:


1
'''
2
Lets examine our data set before we process it .
3
To examine it ket us convert it to a Pandas DF.
4
'''
5
import pandas as pd
6
df= pd.DataFrame(data_dict)
7
df= df.T  # INCLUDING THE 'T' HERE IS CRITICAL.
8
           #  lATER ROTATING/FLIPPING THE DF IS NOT THE EQUIVALENT
9
df.head()  # LATER ROTAING SEEMS ONLY TO CHANGE THE APPEARANCE TO THE EYE BUT TO THE MACHINE THE ROWS AND COLS ARE
10
            # IN THE ORIGINAL STATE.   I THINK THAT IS WHAT I WENT THROUGH ANYWAY.
11
​
12
​
13
​



Out[3]:

bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
from_this_person_to_poi
...
long_term_incentive
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
ALLEN PHILLIP K
4175000
2869717
-3081055
NaN
phillip.allen@enron.com
1729541
13868
2195
47
65
...
304805
152
False
126027
-126027
201955
1407
2902
4484442
1729541
BADUM JAMES P
NaN
178980
NaN
NaN
NaN
257817
3486
NaN
NaN
NaN
...
NaN
NaN
False
NaN
NaN
NaN
NaN
NaN
182466
257817
BANNANTINE JAMES M
NaN
NaN
-5104
NaN
james.bannantine@enron.com
4046157
56301
29
39
0
...
NaN
864523
False
1757552
-560222
477
465
566
916197
5243487
BAXTER JOHN C
1200000
1295738
-1386055
NaN
NaN
6680544
11200
NaN
NaN
NaN
...
1586055
2660303
False
3942714
NaN
267102
NaN
NaN
5634343
10623258
BAY FRANKLIN R
400000
260455
-201641
NaN
frank.bay@enron.com
NaN
129142
NaN
NaN
NaN
...
NaN
69
False
145796
-82782
239671
NaN
NaN
827696
63014
5 rows × 21 columns
In [4]:


1
## The column of names which is our prime interest is the Index .
2
# Let us re.set the index.
3
df=df.reset_index()
4
df.head()



Out[4]:

index
bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
...
long_term_incentive
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
0
ALLEN PHILLIP K
4175000
2869717
-3081055
NaN
phillip.allen@enron.com
1729541
13868
2195
47
...
304805
152
False
126027
-126027
201955
1407
2902
4484442
1729541
1
BADUM JAMES P
NaN
178980
NaN
NaN
NaN
257817
3486
NaN
NaN
...
NaN
NaN
False
NaN
NaN
NaN
NaN
NaN
182466
257817
2
BANNANTINE JAMES M
NaN
NaN
-5104
NaN
james.bannantine@enron.com
4046157
56301
29
39
...
NaN
864523
False
1757552
-560222
477
465
566
916197
5243487
3
BAXTER JOHN C
1200000
1295738
-1386055
NaN
NaN
6680544
11200
NaN
NaN
...
1586055
2660303
False
3942714
NaN
267102
NaN
NaN
5634343
10623258
4
BAY FRANKLIN R
400000
260455
-201641
NaN
frank.bay@enron.com
NaN
129142
NaN
NaN
...
NaN
69
False
145796
-82782
239671
NaN
NaN
827696
63014
5 rows × 22 columns
In [5]:


1
### Getting closer.  Now we need to rename the index column to employee.
2
df.rename(columns={"index":"employee"},inplace=True)
3
df.head()



Out[5]:

employee
bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
...
long_term_incentive
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
0
ALLEN PHILLIP K
4175000
2869717
-3081055
NaN
phillip.allen@enron.com
1729541
13868
2195
47
...
304805
152
False
126027
-126027
201955
1407
2902
4484442
1729541
1
BADUM JAMES P
NaN
178980
NaN
NaN
NaN
257817
3486
NaN
NaN
...
NaN
NaN
False
NaN
NaN
NaN
NaN
NaN
182466
257817
2
BANNANTINE JAMES M
NaN
NaN
-5104
NaN
james.bannantine@enron.com
4046157
56301
29
39
...
NaN
864523
False
1757552
-560222
477
465
566
916197
5243487
3
BAXTER JOHN C
1200000
1295738
-1386055
NaN
NaN
6680544
11200
NaN
NaN
...
1586055
2660303
False
3942714
NaN
267102
NaN
NaN
5634343
10623258
4
BAY FRANKLIN R
400000
260455
-201641
NaN
frank.bay@enron.com
NaN
129142
NaN
NaN
...
NaN
69
False
145796
-82782
239671
NaN
NaN
827696
63014
5 rows × 22 columns
In [6]:



1
#Lets replace the NaNs with 0s
2
import numpy as np
3
df=df.replace('NaN', 0)
4
#df.replace('NaN',0)
5
df.head()



Out[6]:

employee
bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
...
long_term_incentive
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
0
ALLEN PHILLIP K
4175000
2869717
-3081055
0
phillip.allen@enron.com
1729541
13868
2195
47
...
304805
152
False
126027
-126027
201955
1407
2902
4484442
1729541
1
BADUM JAMES P
0
178980
0
0
0
257817
3486
0
0
...
0
0
False
0
0
0
0
0
182466
257817
2
BANNANTINE JAMES M
0
0
-5104
0
james.bannantine@enron.com
4046157
56301
29
39
...
0
864523
False
1757552
-560222
477
465
566
916197
5243487
3
BAXTER JOHN C
1200000
1295738
-1386055
0
0
6680544
11200
0
0
...
1586055
2660303
False
3942714
0
267102
0
0
5634343
10623258
4
BAY FRANKLIN R
400000
260455
-201641
0
frank.bay@enron.com
0
129142
0
0
...
0
69
False
145796
-82782
239671
0
0
827696
63014
5 rows × 22 columns
In [ ]:


1
df.info()




In [7]:


1
## Before we can do any kind of assesment of the variables we need to make convert them to floats.
2
## There might be a more tedious wauy of accomplishing this but I could not find it.
3
#
4
df['total_payments']= pd.to_numeric(df['total_payments'] , errors='coerce')
5
df['bonus']= pd.to_numeric(df['bonus'] , errors='coerce')
6
df['from_messages']= pd.to_numeric(df['from_messages'] , errors='coerce')
7
df['from_poi_to_this_person']= pd.to_numeric(df['from_poi_to_this_person'] , errors='coerce')
8
df['from_this_person_to_poi']= pd.to_numeric(df['from_this_person_to_poi'] , errors='coerce')
9
df['to_messages']= pd.to_numeric(df['to_messages'] , errors='coerce')
10
df['from_messages']= pd.to_numeric(df['from_messages'] , errors='coerce')
11
df['deferral_payments']= pd.to_numeric(df['deferral_payments'] , errors='coerce')
12
df['exercised_stock_options']= pd.to_numeric(df['exercised_stock_options'] , errors='coerce')
13
df['loan_advances ']= pd.to_numeric(df['loan_advances'] , errors='coerce')
14
df['long_term_incentive']= pd.to_numeric(df['long_term_incentive'] , errors='coerce')
15
df['salary']= pd.to_numeric(df['salary'] , errors='coerce')
16
df['long_term_incentive']= pd.to_numeric(df['long_term_incentive'] , errors='coerce')
17
df['total_stock_value']= pd.to_numeric(df['total_stock_value'] , errors='coerce')




In [ ]:


1
### Task 2: Remove outliers




In [10]:



1
## Lets graph the data to spot the outliers.
2
## It seems that Excercised_Stock_options, total_payments, and total_Stock_value should be investigated before we go further.
3
# I was unable to move the labels to the left .  When I tried they move WAY too much.
4
import matplotlib.pyplot as plt
5
#pd.options.display.mpl_style='default'
6
plt.show(block=True)
7
#matplotlib.style.use('ggplot')
8
#fig.set_size_inches(8,16)
9
plt.figure(figsize=(16,4))
10
df.boxplot(rot=45)
11
plt.title('The Distribution of Each Variable')
12
########
13
#
14
#  For some reason this graph does not run unless called twice.



Out[10]:
Text(0.5,1,u'The Distribution of Each Variable')


In [11]:



1
## pd.set_option('display.max_rows', some_value)  #https://stackoverflow.com/questions/21719063/display-entire-dataset-python
2
pd.set_option('display.max_rows', 200)
3
df
4
​



Out[11]:

employee
bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
...
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
loan_advances
0
ALLEN PHILLIP K
4175000
2869717
-3081055
0
phillip.allen@enron.com
1729541
13868
2195
47
...
152
False
126027
-126027
201955
1407
2902
4484442
1729541
0
1
BADUM JAMES P
0
178980
0
0
0
257817
3486
0
0
...
0
False
0
0
0
0
0
182466
257817
0
2
BANNANTINE JAMES M
0
0
-5104
0
james.bannantine@enron.com
4046157
56301
29
39
...
864523
False
1757552
-560222
477
465
566
916197
5243487
0
3
BAXTER JOHN C
1200000
1295738
-1386055
0
0
6680544
11200
0
0
...
2660303
False
3942714
0
267102
0
0
5634343
10623258
0
4
BAY FRANKLIN R
400000
260455
-201641
0
frank.bay@enron.com
0
129142
0
0
...
69
False
145796
-82782
239671
0
0
827696
63014
0
5
BAZELIDES PHILIP J
0
684694
0
0
0
1599641
0
0
0
...
874
False
0
0
80818
0
0
860136
1599641
0
6
BECK SALLY W
700000
0
0
0
sally.beck@enron.com
0
37172
4343
144
...
566
False
126027
0
231330
2639
7315
969068
126027
0
7
BELDEN TIMOTHY N
5249999
2144013
-2334434
0
tim.belden@enron.com
953136
17355
484
228
...
210698
True
157569
0
213999
5521
7991
5501630
1110705
0
8
BELFER ROBERT
0
-102500
0
3285
0
3285
0
0
0
...
0
False
0
44093
0
0
0
102500
-44093
0
9
BERBERIAN DAVID
0
0
0
0
david.berberian@enron.com
1624396
11892
0
0
...
0
False
869220
0
216582
0
0
228474
2493616
0
10
BERGSIEKER RICHARD P
250000
0
-485813
0
rick.bergsieker@enron.com
0
59175
59
4
...
427316
False
659249
0
187922
233
383
618850
659249
0
11
BHATNAGAR SANJAY
0
0
0
137864
sanjay.bhatnagar@enron.com
2604490
0
29
0
...
137864
False
-2604490
15456290
0
463
523
15456290
0
0
12
BIBI PHILIPPE A
1000000
0
0
0
philippe.bibi@enron.com
1465734
38559
40
23
...
425688
False
378082
0
213625
1336
1607
2047593
1843816
0
13
BLACHMAN JEREMY M
850000
0
0
0
jeremy.blachman@enron.com
765313
84208
14
25
...
272
False
189041
0
248546
2326
2475
2014835
954354
0
14
BLAKE JR. NORMAN P
0
0
-113784
113784
0
0
1279
0
0
...
0
False
0
0
0
0
0
1279
0
0
15
BOWEN JR RAYMOND M
1350000
0
-833
0
raymond.bowen@enron.com
0
65907
27
140
...
1621
True
252055
0
278601
1593
1858
2669589
252055
0
16
BROWN MICHAEL
0
0
0
0
michael.brown@enron.com
0
49288
41
13
...
0
False
0
0
0
761
1486
49288
0
0
17
BUCHANAN HAROLD G
500000
0
0
0
john.buchanan@enron.com
825464
600
125
0
...
1215
False
189041
0
248017
23
1088
1054637
1014505
0
18
BUTTS ROBERT H
750000
0
-75000
0
bob.butts@enron.com
0
9410
0
0
...
150656
False
417619
0
261516
0
0
1271582
417619
0
19
BUY RICHARD B
900000
649584
-694862
0
rick.buy@enron.com
2542813
0
1053
156
...
400572
False
901657
0
330546
2333
3523
2355702
3444470
0
20
CALGER CHRISTOPHER F
1250000
0
-262500
0
christopher.calger@enron.com
0
35818
144
199
...
486
True
126027
0
240189
2188
2598
1639297
126027
0
21
CARTER REBECCA C
300000
0
-159792
0
rebecca.carter@enron.com
0
0
15
29
...
540
False
307301
-307301
261809
196
312
477557
0
0
22
CAUSEY RICHARD A
1000000
0
-235000
0
richard.causey@enron.com
0
30674
49
58
...
307895
True
2502063
0
415189
1585
1892
1868758
2502063
0
23
CHAN RONNIE
0
0
-98784
98784
0
0
0
0
0
...
0
False
32460
-32460
0
0
0
0
0
0
24
CHRISTODOULOU DIOMEDES
0
0
0
0
diomedes.christodoulou@enron.com
5127155
0
0
0
...
0
False
950730
0
0
0
0
0
6077885
0
25
CLINE KENNETH W
0
0
0
0
0
0
0
0
0
...
0
False
662086
-472568
0
0
0
0
189518
0
26
COLWELL WESLEY
1200000
27610
-144062
0
wes.colwell@enron.com
0
16514
40
240
...
101740
True
698242
0
288542
1132
1758
1490344
698242
0
27
CORDES WILLIAM R
0
0
0
0
bill.cordes@enron.com
651850
0
12
10
...
0
False
386335
0
0
58
764
0
1038185
0
28
COX DAVID
800000
0
-41250
0
chip.cox@enron.com
117551
27861
33
0
...
494
False
378082
0
314288
71
102
1101393
495633
0
29
CUMBERLAND MICHAEL S
325000
0
0
0
0
0
22344
0
0
...
713
False
207940
0
184899
0
0
807956
207940
0
30
DEFFNER JOSEPH M
600000
0
0
0
joseph.deffner@enron.com
17378
41626
74
115
...
25553
False
141833
0
206121
552
714
1208649
159211
0
31
DELAINEY DAVID W
3000000
0
0
0
david.delainey@enron.com
2291113
86174
3069
66
...
1661
True
1323148
0
365163
2097
3093
4747979
3614261
0
32
DERRICK JR. JAMES V
800000
0
-1284000
0
james.derrick@enron.com
8831913
51124
909
64
...
7482
False
1787380
-1787380
492375
1401
2181
550981
8831913
0
33
DETMERING TIMOTHY J
425000
875307
-775241
0
timothy.detmering@enron.com
2027865
52255
0
0
...
1105
False
315068
-315068
210500
0
0
1204583
2027865
0
34
DIETRICH JANET R
600000
0
0
0
janet.dietrich@enron.com
1550019
3475
63
305
...
473
False
315068
0
250100
1902
2572
1410464
1865087
0
35
DIMICHELE RICHARD G
1000000
0
0
0
richard.dimichele@enron.com
8191755
35812
0
0
...
374689
False
126027
0
262788
0
0
2368151
8317782
0
36
DODSON KEITH
70000
0
0
0
keith.dodson@enron.com
0
28164
14
10
...
774
False
0
0
221003
114
176
319941
0
0
37
DONAHUE JR JEFFREY M
800000
0
-300000
0
jeff.donahue@enron.com
765920
96268
22
188
...
891
False
315068
0
278601
772
865
875760
1080988
0
38
DUNCAN JOHN H
0
0
-25000
102492
0
371750
0
0
0
...
0
False
0
0
0
0
0
77492
371750
0
39
DURAN WILLIAM D
750000
0
0
0
w.duran@enron.com
1451869
25785
12
106
...
1568
False
189041
0
210692
599
904
2093263
1640910
0
40
ECHOLS JOHN B
200000
0
0
0
john.echols@enron.com
601438
21530
0
0
...
53775
False
407503
0
182245
0
0
2692324
1008941
0
41
ELLIOTT STEVEN
350000
0
-400729
0
steven.elliott@enron.com
4890344
78552
0
0
...
12961
False
1788391
0
170941
0
0
211725
6678735
0
42
FALLON JAMES B
2500000
0
0
0
jim.fallon@enron.com
940257
95924
75
42
...
401481
False
1392142
0
304588
1604
1755
3676340
2332399
0
43
FASTOW ANDREW S
1300000
0
-1386055
0
andrew.fastow@enron.com
0
55921
0
0
...
277464
True
1794412
0
440698
0
0
2424083
1794412
0
44
FITZGERALD JAY L
350000
0
0
0
jay.fitzgerald@enron.com
664461
23870
16
1
...
285414
False
956775
0
199157
723
936
1414857
1621236
0
45
FOWLER PEGGY
0
0
0
0
kulvinder.fowler@enron.com
1324578
0
36
0
...
0
False
560170
0
0
10
517
0
1884748
0
46
FOY JOE
0
181755
0
0
tracy.foy@enron.com
343434
0
13
0
...
0
False
0
0
0
2
57
181755
343434
0
47
FREVERT MARK A
2000000
6426990
-3367011
0
mark.frevert@enron.com
10433518
86987
21
242
...
7427621
False
4188667
0
1060932
2979
3275
17252530
14622185
2000000
48
FUGH JOHN L
0
50591
0
0
0
176378
0
0
0
...
0
False
0
0
0
0
0
50591
176378
0
49
GAHN ROBERT S
509870
73122
-1042
0
0
83237
50080
0
0
...
76547
False
235370
0
192008
0
0
900585
318607
0
50
GARLAND C KEVIN
850000
0
0
0
kevin.garland@enron.com
636246
48405
44
10
...
60814
False
259907
0
231946
178
209
1566469
896153
0
51
GATHMANN WILLIAM D
0
0
0
0
0
1753766
0
0
0
...
0
False
264013
-72419
0
0
0
0
1945360
0
52
GIBBS DANA R
0
504610
0
0
dana.gibbs@enron.com
2218275
0
12
0
...
0
False
0
0
0
23
169
966522
2218275
0
53
GILLIS JOHN
0
0
0
0
0
9803
0
0
0
...
0
False
75838
0
0
0
0
0
85641
0
54
GLISAN JR BEN F
600000
0
0
0
ben.glisan@enron.com
384728
125978
16
52
...
200308
True
393818
0
274975
874
873
1272284
778546
0
55
GOLD JOSEPH
750000
0
0
0
joe.gold@enron.com
436515
0
0
0
...
819288
False
441096
0
272880
0
0
2146973
877611
0
56
GRAMM WENDY L
0
0
0
119292
0
0
0
0
0
...
0
False
0
0
0
0
0
119292
0
0
57
GRAY RODNEY
0
93585
0
0
0
0
0
0
0
...
680833
False
0
0
6615
0
0
1146658
0
0
58
HAEDICKE MARK E
1150000
2157527
-934484
0
mark.haedicke@enron.com
608750
76169
1941
180
...
52382
False
524169
-329825
374125
1847
4009
3859065
803094
0
59
HANNON KEVIN P
1500000
0
-3117011
0
kevin.hannon@enron.com
5538001
34039
32
32
...
11350
True
853064
0
243293
1035
1045
288682
6391065
0
60
HAUG DAVID L
0
0
0
0
david.haug@enron.com
0
475
19
4
...
0
False
2217299
0
0
471
573
475
2217299
0
61
HAYES ROBERT E
0
7961
0
0
robert.hayes@enron.com
0
0
12
16
...
0
False
151418
0
0
50
504
7961
151418
0
62
HAYSLETT RODERICK J
0
0
0
0
rod.hayslett@enron.com
0
0
1061
35
...
0
False
346663
0
0
571
2649
0
346663
0
63
HERMANN ROBERT J
700000
0
-280000
0
robert.hermann@enron.com
187500
48357
0
0
...
416441
False
480632
0
262663
0
0
1297461
668132
0
64
HICKERSON GARY J
1700000
0
0
0
gary.hickerson@enron.com
0
98849
27
40
...
1936
False
441096
0
211788
900
1320
2081796
441096
0
65
HIRKO JOSEPH
0
10259
0
0
joe.hirko@enron.com
30766064
77978
0
0
...
2856
True
0
0
0
0
0
91093
30766064
0
66
HORTON STANLEY C
0
3131860
0
0
stanley.horton@enron.com
5210569
0
1073
44
...
0
False
2046079
0
0
1074
2350
3131860
7256648
0
67
HUGHES JAMES A
0
0
0
0
james.hughes@enron.com
754966
0
34
35
...
0
False
363428
0
0
589
719
0
1118394
0
68
HUMPHREY GENE E
0
2964506
0
0
gene.humphrey@enron.com
2282768
4994
17
10
...
0
False
0
0
130724
119
128
3100224
2282768
0
69
IZZO LAWRENCE L
0
0
0
0
larry.izzo@enron.com
2165172
28093
19
28
...
1553729
False
3654808
0
85274
437
496
1979596
5819980
0
70
JACKSON CHARLENE R
250000
0
0
0
charlene.jackson@enron.com
185063
10181
56
25
...
2435
False
540672
0
288558
117
258
551174
725735
0
71
JAEDICKE ROBERT
0
0
-25000
108750
0
431750
0
0
0
...
0
False
44093
-44093
0
0
0
83750
431750
0
72
KAMINSKI WINCENTY J
400000
0
0
0
vince.kaminski@enron.com
850010
83585
14368
41
...
4669
False
126027
0
275101
583
4607
1086821
976037
0
73
KEAN STEVEN J
1000000
0
0
0
steven.kean@enron.com
2022048
41953
6759
140
...
1231
False
4131594
0
404338
3639
12754
1747522
6153642
0
74
KISHKILL JOSEPH G
0
0
-51042
0
joe.kishkill@enron.com
0
116335
0
0
...
465357
False
1034346
0
174246
0
0
704896
1034346
0
75
KITCHEN LOUISE
3100000
0
0
0
louise.kitchen@enron.com
81042
5774
1728
251
...
93925
False
466101
0
271442
3669
8305
3471141
547143
0
76
KOENIG MARK E
700000
0
0
0
mark.koenig@enron.com
671737
127017
61
53
...
150458
True
1248318
0
309946
2271
2374
1587421
1920055
0
77
KOPPER MICHAEL J
800000
0
0
0
michael.kopper@enron.com
0
118134
0
0
...
907502
True
985032
0
224305
0
0
2652612
985032
0
78
LAVORATO JOHN J
8000000
0
0
0
john.lavorato@enron.com
4158995
49537
2585
528
...
1552
False
1008149
0
339288
3962
7259
10425757
5167144
0
79
LAY KENNETH L
7000000
202911
-300000
0
kenneth.lay@enron.com
34348384
99832
36
123
...
10359729
True
14761694
0
1072321
2411
4273
103559793
49110078
81525000
80
LEFF DANIEL P
1000000
0
0
0
dan.leff@enron.com
0
0
63
67
...
3083
False
360528
0
273746
2672
2822
2664228
360528
0
81
LEMAISTRE CHARLES
0
0
-25000
112492
0
412878
0
0
0
...
0
False
0
0
0
0
0
87492
412878
0
82
LEWIS RICHARD
0
0
0
0
richard.lewis@enron.com
850477
0
26
10
...
0
False
0
0
0
739
952
0
850477
0
83
LINDHOLM TOD A
200000
204075
0
0
tod.lindholm@enron.com
2549361
57727
0
0
...
2630
False
514847
0
236457
0
0
875889
3064208
0
84
LOCKHART EUGENE E
0
0
0
0
0
0
0
0
0
...
0
False
0
0
0
0
0
0
0
0
85
LOWRY CHARLES P
0
0
0
0
0
372205
0
0
0
...
0
False
153686
-153686
0
0
0
0
372205
0
86
MARTIN AMANDA K
0
85430
0
0
a..martin@enron.com
2070306
8211
230
8
...
2818454
False
0
0
349487
477
1522
8407016
2070306
0
87
MCCARTY DANNY J
0
0
0
0
danny.mccarty@enron.com
664375
0
215
25
...
0
False
94556
0
0
508
1433
0
758931
0
88
MCCLELLAN GEORGE
900000
0
-125000
0
george.mcclellan@enron.com
506765
228763
49
52
...
51587
False
441096
0
263413
1469
1744
1318763
947861
0
89
MCCONNELL MICHAEL S
1100000
0
0
0
mike.mcconnell@enron.com
1623010
81364
2742
92
...
540
False
1478269
0
365038
2189
3329
2101364
3101279
0
90
MCDONALD REBECCA
0
0
0
0
rebecca.mcdonald@enron.com
757301
0
13
54
...
0
False
934065
0
0
720
894
0
1691366
0
91
MCMAHON JEFFREY
2600000
0
0
0
jeffrey.mcmahon@enron.com
1104054
137108
48
58
...
297353
False
558801
0
370448
2228
2355
4099771
1662855
0
92
MENDELSOHN JOHN
0
0
-103750
103750
0
0
148
0
0
...
0
False
0
0
0
0
0
148
0
0
93
METTS MARK
600000
0
0
0
mark.metts@enron.com
0
94299
29
38
...
1740
False
585062
0
365788
702
807
1061827
585062
0
94
MEYER JEROME J
0
0
-38346
38346
0
0
2151
0
0
...
0
False
0
0
0
0
0
2151
0
0
95
MEYER ROCKFORD G
0
1848227
0
0
rockford.meyer@enron.com
493489
0
28
0
...
0
False
462384
0
0
22
232
1848227
955873
0
96
MORAN MICHAEL P
0
0
0
0
michael.moran@enron.com
59539
0
19
0
...
0
False
161602
0
0
127
672
0
221141
0
97
MORDAUNT KRISTINA M
325000
0
0
0
kristina.mordaunt@enron.com
0
35018
0
0
...
1411
False
208510
0
267093
0
0
628522
208510
0
98
MULLER MARK S
1100000
842924
-719000
0
s..muller@enron.com
1056320
0
16
12
...
947
False
360528
0
251654
114
136
3202070
1416848
0
99
MURRAY JULIA H
400000
0
0
0
julia.murray@enron.com
400478
57580
45
11
...
330
False
196983
0
229284
395
2192
812194
597461
0
100
NOLES JAMES L
0
774401
0
0
0
0
0
0
0
...
0
False
463261
-94556
0
0
0
774401
368705
0
101
OLSON CINDY K
750000
77716
0
0
cindy.olson@enron.com
1637034
63791
52
20
...
972
False
969729
0
329078
856
1184
1321557
2606763
0
102
OVERDYKE JR JERE C
0
0
0
0
jere.overdyke@enron.com
5266578
18834
0
0
...
176
False
2041016
0
94941
0
0
249787
7307594
0
103
PAI LOU L
1000000
0
0
0
lou.pai@enron.com
15364167
32047
0
0
...
1829457
False
8453763
0
261879
0
0
3123383
23817930
0
104
PEREIRA PAULO V. FERRAZ
0
0
-101250
101250
0
0
27942
0
0
...
0
False
0
0
0
0
0
27942
0
0
105
PICKERING MARK R
300000
0
0
0
mark.pickering@enron.com
28798
31653
67
7
...
0
False
0
0
655037
728
898
1386690
28798
400000
106
PIPER GREGORY F
400000
1130036
-33333
0
greg.piper@enron.com
880290
43057
222
61
...
778
False
409554
-409554
197091
742
1238
1737629
880290
0
107
PIRO JIM
0
0
0
0
jim.piro@enron.com
0
0
16
0
...
0
False
47304
0
0
3
58
0
47304
0
108
POWERS WILLIAM
0
0
-17500
17500
ken.powers@enron.com
0
0
26
0
...
0
False
0
0
0
12
653
0
0
0
109
PRENTICE JAMES
0
564348
0
0
james.prentice@enron.com
886231
0
0
0
...
0
False
208809
0
0
0
0
564348
1095040
0
110
REDMOND BRIAN L
0
0
0
0
brian.redmond@enron.com
7509039
14689
221
204
...
0
False
381285
0
96840
1063
1671
111529
7890324
0
111
REYNOLDS LAWRENCE
100000
51365
-200000
0
0
4160672
8409
0
0
...
202052
False
201483
-140264
76399
0
0
394475
4221891
0
112
RICE KENNETH D
1750000
0
-3504386
0
ken.rice@enron.com
19794175
46950
18
42
...
174839
True
2748364
0
420636
864
905
505050
22542539
0
113
RIEKER PAULA H
700000
214678
-100000
0
paula.rieker@enron.com
1635238
33271
82
35
...
1950
True
283649
0
249201
1258
1328
1099100
1918887
0
114
SAVAGE FRANK
0
0
-121284
125034
0
0
0
0
0
...
0
False
0
0
0
0
0
3750
0
0
115
SCRIMSHAW MATTHEW
0
0
0
0
matthew.scrimshaw@enron.com
759557
0
0
0
...
0
False
0
0
0
0
0
0
759557
0
116
SHANKMAN JEFFREY A
2000000
0
0
0
jeffrey.shankman@enron.com
1441898
178979
2681
94
...
1191
False
630137
0
304110
1730
3221
3038702
2072035
0
117
SHAPIRO RICHARD S
650000
0
0
0
richard.shapiro@enron.com
607837
137767
1215
74
...
705
False
379164
0
269076
4527
15149
1057548
987001
0
118
SHARP VICTORIA T
600000
187469
0
0
vicki.sharp@enron.com
281073
116337
136
24
...
2401
False
213063
0
248146
2477
3136
1576511
494136
0
119
SHELBY REX
200000
0
-4167
0
rex.shelby@enron.com
1624396
22884
39
13
...
1573324
True
869220
0
211844
91
225
2003885
2493616
0
120
SHERRICK JEFFREY B
0
0
0
0
jeffrey.sherrick@enron.com
1426469
0
25
39
...
0
False
405999
0
0
583
613
0
1832468
0
121
SHERRIFF JOHN R
1500000
0
0
0
john.sherriff@enron.com
1835558
0
92
28
...
1852186
False
1293424
0
428780
2103
3187
4335388
3128982
0
122
SKILLING JEFFREY K
5600000
0
0
0
jeff.skilling@enron.com
19250000
29336
108
88
...
22122
True
6843672
0
1111258
2042
3627
8682716
26093672
0
123
STABLER FRANK
500000
0
0
0
frank.stabler@enron.com
0
16514
0
0
...
356071
False
511734
0
239502
0
0
1112087
511734
0
124
SULLIVAN-SHAKLOVITZ COLLEEN
100000
181993
0
0
0
1362375
0
0
0
...
162
False
0
0
162779
0
0
999356
1362375
0
125
SUNDE MARTIN
700000
0
0
0
marty.sunde@enron.com
0
0
38
37
...
111122
False
698920
0
257486
2565
2647
1545059
698920
0
126
TAYLOR MITCHELL S
600000
227449
0
0
mitchell.taylor@enron.com
3181250
0
29
0
...
0
False
563798
0
265214
300
533
1092663
3745048
0
127
THE TRAVEL AGENCY IN THE PARK
0
0
0
0
0
0
0
0
0
...
362096
False
0
0
0
0
0
362096
0
0
128
THORN TERENCE H
0
16586
0
0
terence.thorn@enron.com
4452476
46145
41
0
...
426629
False
365320
0
222093
73
266
911453
4817796
0
129
TILNEY ELIZABETH A
300000
0
-575000
0
elizabeth.tilney@enron.com
591250
0
19
10
...
152055
False
576792
0
247338
379
460
399393
1168042
0
130
TOTAL
97343619
32083396
-27992891
1398517
0
311764000
5235198
0
0
...
42667589
False
130322299
-7576788
26704229
0
0
309886585
434509511
83925000
131
UMANOFF ADAM S
788750
0
0
0
adam.umanoff@enron.com
0
53122
18
12
...
0
False
0
0
288589
41
111
1130461
0
0
132
URQUHART JOHN A
0
0
-36666
36666
0
0
228656
0
0
...
0
False
0
0
0
0
0
228656
0
0
133
WAKEHAM JOHN
0
0
0
109298
0
0
103773
0
0
...
0
False
0
0
0
0
0
213071
0
0
134
WALLS JR ROBERT H
850000
0
0
0
rob.walls@enron.com
4346544
50936
146
17
...
2
False
1552453
0
357091
215
671
1798780
5898997
0
135
WALTERS GARETH W
0
53625
0
0
0
1030329
33785
0
0
...
0
False
0
0
0
0
0
87410
1030329
0
136
WASAFF GEORGE
325000
831299
-583325
0
george.wasaff@enron.com
1668260
0
30
22
...
1425
False
388167
0
259996
337
400
1034395
2056427
0
137
WESTFAHL RICHARD K
0
0
-10800
0
dick.westfahl@enron.com
0
51870
0
0
...
401130
False
384930
0
63744
0
0
762135
384930
0
138
WHALEY DAVID A
0
0
0
0
0
98718
0
0
0
...
0
False
0
0
0
0
0
0
98718
0
139
WHALLEY LAWRENCE G
3000000
0
0
0
greg.whalley@enron.com
3282960
57838
556
186
...
301026
False
2796177
0
510364
3920
6019
4677574
6079137
0
140
WHITE JR THOMAS E
450000
0
0
0
thomas.white@enron.com
1297049
81353
0
0
...
1085463
False
13847074
0
317543
0
0
1934359
15144123
0
141
WINOKUR JR. HERBERT S
0
0
-25000
108579
0
0
1413
0
0
...
0
False
0
0
0
0
0
84992
0
0
142
WODRASKA JOHN
0
0
0
0
john.wodraska@enron.com
0
0
0
0
...
189583
False
0
0
0
0
0
189583
0
0
143
WROBEL BRUCE
0
0
0
0
0
139130
0
0
0
...
0
False
0
0
0
0
0
0
139130
0
144
YEAGER F SCOTT
0
0
0
0
scott.yeager@enron.com
8308552
53947
0
0
...
147950
True
3576206
0
158403
0
0
360300
11884758
0
145
YEAP SOON
0
0
0
0
0
192758
55097
0
0
...
0
False
0
0
0
0
0
55097
192758
0
146 rows × 23 columns
In [12]:


1
#Taking the variables one by one lets look at the outliers.
2
## Now let us examine bonus.
3
## Interstingly Bonuses are a rather confused field.
4
## A number of non-POI had bonuses greater than POIs.
5
​
6
import numpy as np
7
import seaborn as sns
8
import matplotlib.pyplot as plt
9
sns.set_style("whitegrid")
10
fig,ax = plt.subplots()
11
fig.set_size_inches(8,30)
12
ax=sns.barplot(x="bonus",y="employee",data= df)
13
plt.title('Bonuses')



Out[12]:
Text(0.5,1,u'Bonuses')


In [13]:


1
## So who is this guy TOTAL?
2
## Lets get rid of him.
3
## Total is of course some errant data so no harm in deleting it.
4
## A little problem though.
5
# We do not know what index row number TOTAL is.
6
# So we will scrol back up to cell #8 where we re-indexed and look for the index number that
7
# corresponds to TOTAL
8
df.drop(130,axis=0,inplace=True)




In [14]:


1
pd.set_option('display.max_rows', 200)
2
df



Out[14]:

employee
bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
...
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
loan_advances
0
ALLEN PHILLIP K
4175000
2869717
-3081055
0
phillip.allen@enron.com
1729541
13868
2195
47
...
152
False
126027
-126027
201955
1407
2902
4484442
1729541
0
1
BADUM JAMES P
0
178980
0
0
0
257817
3486
0
0
...
0
False
0
0
0
0
0
182466
257817
0
2
BANNANTINE JAMES M
0
0
-5104
0
james.bannantine@enron.com
4046157
56301
29
39
...
864523
False
1757552
-560222
477
465
566
916197
5243487
0
3
BAXTER JOHN C
1200000
1295738
-1386055
0
0
6680544
11200
0
0
...
2660303
False
3942714
0
267102
0
0
5634343
10623258
0
4
BAY FRANKLIN R
400000
260455
-201641
0
frank.bay@enron.com
0
129142
0
0
...
69
False
145796
-82782
239671
0
0
827696
63014
0
5
BAZELIDES PHILIP J
0
684694
0
0
0
1599641
0
0
0
...
874
False
0
0
80818
0
0
860136
1599641
0
6
BECK SALLY W
700000
0
0
0
sally.beck@enron.com
0
37172
4343
144
...
566
False
126027
0
231330
2639
7315
969068
126027
0
7
BELDEN TIMOTHY N
5249999
2144013
-2334434
0
tim.belden@enron.com
953136
17355
484
228
...
210698
True
157569
0
213999
5521
7991
5501630
1110705
0
8
BELFER ROBERT
0
-102500
0
3285
0
3285
0
0
0
...
0
False
0
44093
0
0
0
102500
-44093
0
9
BERBERIAN DAVID
0
0
0
0
david.berberian@enron.com
1624396
11892
0
0
...
0
False
869220
0
216582
0
0
228474
2493616
0
10
BERGSIEKER RICHARD P
250000
0
-485813
0
rick.bergsieker@enron.com
0
59175
59
4
...
427316
False
659249
0
187922
233
383
618850
659249
0
11
BHATNAGAR SANJAY
0
0
0
137864
sanjay.bhatnagar@enron.com
2604490
0
29
0
...
137864
False
-2604490
15456290
0
463
523
15456290
0
0
12
BIBI PHILIPPE A
1000000
0
0
0
philippe.bibi@enron.com
1465734
38559
40
23
...
425688
False
378082
0
213625
1336
1607
2047593
1843816
0
13
BLACHMAN JEREMY M
850000
0
0
0
jeremy.blachman@enron.com
765313
84208
14
25
...
272
False
189041
0
248546
2326
2475
2014835
954354
0
14
BLAKE JR. NORMAN P
0
0
-113784
113784
0
0
1279
0
0
...
0
False
0
0
0
0
0
1279
0
0
15
BOWEN JR RAYMOND M
1350000
0
-833
0
raymond.bowen@enron.com
0
65907
27
140
...
1621
True
252055
0
278601
1593
1858
2669589
252055
0
16
BROWN MICHAEL
0
0
0
0
michael.brown@enron.com
0
49288
41
13
...
0
False
0
0
0
761
1486
49288
0
0
17
BUCHANAN HAROLD G
500000
0
0
0
john.buchanan@enron.com
825464
600
125
0
...
1215
False
189041
0
248017
23
1088
1054637
1014505
0
18
BUTTS ROBERT H
750000
0
-75000
0
bob.butts@enron.com
0
9410
0
0
...
150656
False
417619
0
261516
0
0
1271582
417619
0
19
BUY RICHARD B
900000
649584
-694862
0
rick.buy@enron.com
2542813
0
1053
156
...
400572
False
901657
0
330546
2333
3523
2355702
3444470
0
20
CALGER CHRISTOPHER F
1250000
0
-262500
0
christopher.calger@enron.com
0
35818
144
199
...
486
True
126027
0
240189
2188
2598
1639297
126027
0
21
CARTER REBECCA C
300000
0
-159792
0
rebecca.carter@enron.com
0
0
15
29
...
540
False
307301
-307301
261809
196
312
477557
0
0
22
CAUSEY RICHARD A
1000000
0
-235000
0
richard.causey@enron.com
0
30674
49
58
...
307895
True
2502063
0
415189
1585
1892
1868758
2502063
0
23
CHAN RONNIE
0
0
-98784
98784
0
0
0
0
0
...
0
False
32460
-32460
0
0
0
0
0
0
24
CHRISTODOULOU DIOMEDES
0
0
0
0
diomedes.christodoulou@enron.com
5127155
0
0
0
...
0
False
950730
0
0
0
0
0
6077885
0
25
CLINE KENNETH W
0
0
0
0
0
0
0
0
0
...
0
False
662086
-472568
0
0
0
0
189518
0
26
COLWELL WESLEY
1200000
27610
-144062
0
wes.colwell@enron.com
0
16514
40
240
...
101740
True
698242
0
288542
1132
1758
1490344
698242
0
27
CORDES WILLIAM R
0
0
0
0
bill.cordes@enron.com
651850
0
12
10
...
0
False
386335
0
0
58
764
0
1038185
0
28
COX DAVID
800000
0
-41250
0
chip.cox@enron.com
117551
27861
33
0
...
494
False
378082
0
314288
71
102
1101393
495633
0
29
CUMBERLAND MICHAEL S
325000
0
0
0
0
0
22344
0
0
...
713
False
207940
0
184899
0
0
807956
207940
0
30
DEFFNER JOSEPH M
600000
0
0
0
joseph.deffner@enron.com
17378
41626
74
115
...
25553
False
141833
0
206121
552
714
1208649
159211
0
31
DELAINEY DAVID W
3000000
0
0
0
david.delainey@enron.com
2291113
86174
3069
66
...
1661
True
1323148
0
365163
2097
3093
4747979
3614261
0
32
DERRICK JR. JAMES V
800000
0
-1284000
0
james.derrick@enron.com
8831913
51124
909
64
...
7482
False
1787380
-1787380
492375
1401
2181
550981
8831913
0
33
DETMERING TIMOTHY J
425000
875307
-775241
0
timothy.detmering@enron.com
2027865
52255
0
0
...
1105
False
315068
-315068
210500
0
0
1204583
2027865
0
34
DIETRICH JANET R
600000
0
0
0
janet.dietrich@enron.com
1550019
3475
63
305
...
473
False
315068
0
250100
1902
2572
1410464
1865087
0
35
DIMICHELE RICHARD G
1000000
0
0
0
richard.dimichele@enron.com
8191755
35812
0
0
...
374689
False
126027
0
262788
0
0
2368151
8317782
0
36
DODSON KEITH
70000
0
0
0
keith.dodson@enron.com
0
28164
14
10
...
774
False
0
0
221003
114
176
319941
0
0
37
DONAHUE JR JEFFREY M
800000
0
-300000
0
jeff.donahue@enron.com
765920
96268
22
188
...
891
False
315068
0
278601
772
865
875760
1080988
0
38
DUNCAN JOHN H
0
0
-25000
102492
0
371750
0
0
0
...
0
False
0
0
0
0
0
77492
371750
0
39
DURAN WILLIAM D
750000
0
0
0
w.duran@enron.com
1451869
25785
12
106
...
1568
False
189041
0
210692
599
904
2093263
1640910
0
40
ECHOLS JOHN B
200000
0
0
0
john.echols@enron.com
601438
21530
0
0
...
53775
False
407503
0
182245
0
0
2692324
1008941
0
41
ELLIOTT STEVEN
350000
0
-400729
0
steven.elliott@enron.com
4890344
78552
0
0
...
12961
False
1788391
0
170941
0
0
211725
6678735
0
42
FALLON JAMES B
2500000
0
0
0
jim.fallon@enron.com
940257
95924
75
42
...
401481
False
1392142
0
304588
1604
1755
3676340
2332399
0
43
FASTOW ANDREW S
1300000
0
-1386055
0
andrew.fastow@enron.com
0
55921
0
0
...
277464
True
1794412
0
440698
0
0
2424083
1794412
0
44
FITZGERALD JAY L
350000
0
0
0
jay.fitzgerald@enron.com
664461
23870
16
1
...
285414
False
956775
0
199157
723
936
1414857
1621236
0
45
FOWLER PEGGY
0
0
0
0
kulvinder.fowler@enron.com
1324578
0
36
0
...
0
False
560170
0
0
10
517
0
1884748
0
46
FOY JOE
0
181755
0
0
tracy.foy@enron.com
343434
0
13
0
...
0
False
0
0
0
2
57
181755
343434
0
47
FREVERT MARK A
2000000
6426990
-3367011
0
mark.frevert@enron.com
10433518
86987
21
242
...
7427621
False
4188667
0
1060932
2979
3275
17252530
14622185
2000000
48
FUGH JOHN L
0
50591
0
0
0
176378
0
0
0
...
0
False
0
0
0
0
0
50591
176378
0
49
GAHN ROBERT S
509870
73122
-1042
0
0
83237
50080
0
0
...
76547
False
235370
0
192008
0
0
900585
318607
0
50
GARLAND C KEVIN
850000
0
0
0
kevin.garland@enron.com
636246
48405
44
10
...
60814
False
259907
0
231946
178
209
1566469
896153
0
51
GATHMANN WILLIAM D
0
0
0
0
0
1753766
0
0
0
...
0
False
264013
-72419
0
0
0
0
1945360
0
52
GIBBS DANA R
0
504610
0
0
dana.gibbs@enron.com
2218275
0
12
0
...
0
False
0
0
0
23
169
966522
2218275
0
53
GILLIS JOHN
0
0
0
0
0
9803
0
0
0
...
0
False
75838
0
0
0
0
0
85641
0
54
GLISAN JR BEN F
600000
0
0
0
ben.glisan@enron.com
384728
125978
16
52
...
200308
True
393818
0
274975
874
873
1272284
778546
0
55
GOLD JOSEPH
750000
0
0
0
joe.gold@enron.com
436515
0
0
0
...
819288
False
441096
0
272880
0
0
2146973
877611
0
56
GRAMM WENDY L
0
0
0
119292
0
0
0
0
0
...
0
False
0
0
0
0
0
119292
0
0
57
GRAY RODNEY
0
93585
0
0
0
0
0
0
0
...
680833
False
0
0
6615
0
0
1146658
0
0
58
HAEDICKE MARK E
1150000
2157527
-934484
0
mark.haedicke@enron.com
608750
76169
1941
180
...
52382
False
524169
-329825
374125
1847
4009
3859065
803094
0
59
HANNON KEVIN P
1500000
0
-3117011
0
kevin.hannon@enron.com
5538001
34039
32
32
...
11350
True
853064
0
243293
1035
1045
288682
6391065
0
60
HAUG DAVID L
0
0
0
0
david.haug@enron.com
0
475
19
4
...
0
False
2217299
0
0
471
573
475
2217299
0
61
HAYES ROBERT E
0
7961
0
0
robert.hayes@enron.com
0
0
12
16
...
0
False
151418
0
0
50
504
7961
151418
0
62
HAYSLETT RODERICK J
0
0
0
0
rod.hayslett@enron.com
0
0
1061
35
...
0
False
346663
0
0
571
2649
0
346663
0
63
HERMANN ROBERT J
700000
0
-280000
0
robert.hermann@enron.com
187500
48357
0
0
...
416441
False
480632
0
262663
0
0
1297461
668132
0
64
HICKERSON GARY J
1700000
0
0
0
gary.hickerson@enron.com
0
98849
27
40
...
1936
False
441096
0
211788
900
1320
2081796
441096
0
65
HIRKO JOSEPH
0
10259
0
0
joe.hirko@enron.com
30766064
77978
0
0
...
2856
True
0
0
0
0
0
91093
30766064
0
66
HORTON STANLEY C
0
3131860
0
0
stanley.horton@enron.com
5210569
0
1073
44
...
0
False
2046079
0
0
1074
2350
3131860
7256648
0
67
HUGHES JAMES A
0
0
0
0
james.hughes@enron.com
754966
0
34
35
...
0
False
363428
0
0
589
719
0
1118394
0
68
HUMPHREY GENE E
0
2964506
0
0
gene.humphrey@enron.com
2282768
4994
17
10
...
0
False
0
0
130724
119
128
3100224
2282768
0
69
IZZO LAWRENCE L
0
0
0
0
larry.izzo@enron.com
2165172
28093
19
28
...
1553729
False
3654808
0
85274
437
496
1979596
5819980
0
70
JACKSON CHARLENE R
250000
0
0
0
charlene.jackson@enron.com
185063
10181
56
25
...
2435
False
540672
0
288558
117
258
551174
725735
0
71
JAEDICKE ROBERT
0
0
-25000
108750
0
431750
0
0
0
...
0
False
44093
-44093
0
0
0
83750
431750
0
72
KAMINSKI WINCENTY J
400000
0
0
0
vince.kaminski@enron.com
850010
83585
14368
41
...
4669
False
126027
0
275101
583
4607
1086821
976037
0
73
KEAN STEVEN J
1000000
0
0
0
steven.kean@enron.com
2022048
41953
6759
140
...
1231
False
4131594
0
404338
3639
12754
1747522
6153642
0
74
KISHKILL JOSEPH G
0
0
-51042
0
joe.kishkill@enron.com
0
116335
0
0
...
465357
False
1034346
0
174246
0
0
704896
1034346
0
75
KITCHEN LOUISE
3100000
0
0
0
louise.kitchen@enron.com
81042
5774
1728
251
...
93925
False
466101
0
271442
3669
8305
3471141
547143
0
76
KOENIG MARK E
700000
0
0
0
mark.koenig@enron.com
671737
127017
61
53
...
150458
True
1248318
0
309946
2271
2374
1587421
1920055
0
77
KOPPER MICHAEL J
800000
0
0
0
michael.kopper@enron.com
0
118134
0
0
...
907502
True
985032
0
224305
0
0
2652612
985032
0
78
LAVORATO JOHN J
8000000
0
0
0
john.lavorato@enron.com
4158995
49537
2585
528
...
1552
False
1008149
0
339288
3962
7259
10425757
5167144
0
79
LAY KENNETH L
7000000
202911
-300000
0
kenneth.lay@enron.com
34348384
99832
36
123
...
10359729
True
14761694
0
1072321
2411
4273
103559793
49110078
81525000
80
LEFF DANIEL P
1000000
0
0
0
dan.leff@enron.com
0
0
63
67
...
3083
False
360528
0
273746
2672
2822
2664228
360528
0
81
LEMAISTRE CHARLES
0
0
-25000
112492
0
412878
0
0
0
...
0
False
0
0
0
0
0
87492
412878
0
82
LEWIS RICHARD
0
0
0
0
richard.lewis@enron.com
850477
0
26
10
...
0
False
0
0
0
739
952
0
850477
0
83
LINDHOLM TOD A
200000
204075
0
0
tod.lindholm@enron.com
2549361
57727
0
0
...
2630
False
514847
0
236457
0
0
875889
3064208
0
84
LOCKHART EUGENE E
0
0
0
0
0
0
0
0
0
...
0
False
0
0
0
0
0
0
0
0
85
LOWRY CHARLES P
0
0
0
0
0
372205
0
0
0
...
0
False
153686
-153686
0
0
0
0
372205
0
86
MARTIN AMANDA K
0
85430
0
0
a..martin@enron.com
2070306
8211
230
8
...
2818454
False
0
0
349487
477
1522
8407016
2070306
0
87
MCCARTY DANNY J
0
0
0
0
danny.mccarty@enron.com
664375
0
215
25
...
0
False
94556
0
0
508
1433
0
758931
0
88
MCCLELLAN GEORGE
900000
0
-125000
0
george.mcclellan@enron.com
506765
228763
49
52
...
51587
False
441096
0
263413
1469
1744
1318763
947861
0
89
MCCONNELL MICHAEL S
1100000
0
0
0
mike.mcconnell@enron.com
1623010
81364
2742
92
...
540
False
1478269
0
365038
2189
3329
2101364
3101279
0
90
MCDONALD REBECCA
0
0
0
0
rebecca.mcdonald@enron.com
757301
0
13
54
...
0
False
934065
0
0
720
894
0
1691366
0
91
MCMAHON JEFFREY
2600000
0
0
0
jeffrey.mcmahon@enron.com
1104054
137108
48
58
...
297353
False
558801
0
370448
2228
2355
4099771
1662855
0
92
MENDELSOHN JOHN
0
0
-103750
103750
0
0
148
0
0
...
0
False
0
0
0
0
0
148
0
0
93
METTS MARK
600000
0
0
0
mark.metts@enron.com
0
94299
29
38
...
1740
False
585062
0
365788
702
807
1061827
585062
0
94
MEYER JEROME J
0
0
-38346
38346
0
0
2151
0
0
...
0
False
0
0
0
0
0
2151
0
0
95
MEYER ROCKFORD G
0
1848227
0
0
rockford.meyer@enron.com
493489
0
28
0
...
0
False
462384
0
0
22
232
1848227
955873
0
96
MORAN MICHAEL P
0
0
0
0
michael.moran@enron.com
59539
0
19
0
...
0
False
161602
0
0
127
672
0
221141
0
97
MORDAUNT KRISTINA M
325000
0
0
0
kristina.mordaunt@enron.com
0
35018
0
0
...
1411
False
208510
0
267093
0
0
628522
208510
0
98
MULLER MARK S
1100000
842924
-719000
0
s..muller@enron.com
1056320
0
16
12
...
947
False
360528
0
251654
114
136
3202070
1416848
0
99
MURRAY JULIA H
400000
0
0
0
julia.murray@enron.com
400478
57580
45
11
...
330
False
196983
0
229284
395
2192
812194
597461
0
100
NOLES JAMES L
0
774401
0
0
0
0
0
0
0
...
0
False
463261
-94556
0
0
0
774401
368705
0
101
OLSON CINDY K
750000
77716
0
0
cindy.olson@enron.com
1637034
63791
52
20
...
972
False
969729
0
329078
856
1184
1321557
2606763
0
102
OVERDYKE JR JERE C
0
0
0
0
jere.overdyke@enron.com
5266578
18834
0
0
...
176
False
2041016
0
94941
0
0
249787
7307594
0
103
PAI LOU L
1000000
0
0
0
lou.pai@enron.com
15364167
32047
0
0
...
1829457
False
8453763
0
261879
0
0
3123383
23817930
0
104
PEREIRA PAULO V. FERRAZ
0
0
-101250
101250
0
0
27942
0
0
...
0
False
0
0
0
0
0
27942
0
0
105
PICKERING MARK R
300000
0
0
0
mark.pickering@enron.com
28798
31653
67
7
...
0
False
0
0
655037
728
898
1386690
28798
400000
106
PIPER GREGORY F
400000
1130036
-33333
0
greg.piper@enron.com
880290
43057
222
61
...
778
False
409554
-409554
197091
742
1238
1737629
880290
0
107
PIRO JIM
0
0
0
0
jim.piro@enron.com
0
0
16
0
...
0
False
47304
0
0
3
58
0
47304
0
108
POWERS WILLIAM
0
0
-17500
17500
ken.powers@enron.com
0
0
26
0
...
0
False
0
0
0
12
653
0
0
0
109
PRENTICE JAMES
0
564348
0
0
james.prentice@enron.com
886231
0
0
0
...
0
False
208809
0
0
0
0
564348
1095040
0
110
REDMOND BRIAN L
0
0
0
0
brian.redmond@enron.com
7509039
14689
221
204
...
0
False
381285
0
96840
1063
1671
111529
7890324
0
111
REYNOLDS LAWRENCE
100000
51365
-200000
0
0
4160672
8409
0
0
...
202052
False
201483
-140264
76399
0
0
394475
4221891
0
112
RICE KENNETH D
1750000
0
-3504386
0
ken.rice@enron.com
19794175
46950
18
42
...
174839
True
2748364
0
420636
864
905
505050
22542539
0
113
RIEKER PAULA H
700000
214678
-100000
0
paula.rieker@enron.com
1635238
33271
82
35
...
1950
True
283649
0
249201
1258
1328
1099100
1918887
0
114
SAVAGE FRANK
0
0
-121284
125034
0
0
0
0
0
...
0
False
0
0
0
0
0
3750
0
0
115
SCRIMSHAW MATTHEW
0
0
0
0
matthew.scrimshaw@enron.com
759557
0
0
0
...
0
False
0
0
0
0
0
0
759557
0
116
SHANKMAN JEFFREY A
2000000
0
0
0
jeffrey.shankman@enron.com
1441898
178979
2681
94
...
1191
False
630137
0
304110
1730
3221
3038702
2072035
0
117
SHAPIRO RICHARD S
650000
0
0
0
richard.shapiro@enron.com
607837
137767
1215
74
...
705
False
379164
0
269076
4527
15149
1057548
987001
0
118
SHARP VICTORIA T
600000
187469
0
0
vicki.sharp@enron.com
281073
116337
136
24
...
2401
False
213063
0
248146
2477
3136
1576511
494136
0
119
SHELBY REX
200000
0
-4167
0
rex.shelby@enron.com
1624396
22884
39
13
...
1573324
True
869220
0
211844
91
225
2003885
2493616
0
120
SHERRICK JEFFREY B
0
0
0
0
jeffrey.sherrick@enron.com
1426469
0
25
39
...
0
False
405999
0
0
583
613
0
1832468
0
121
SHERRIFF JOHN R
1500000
0
0
0
john.sherriff@enron.com
1835558
0
92
28
...
1852186
False
1293424
0
428780
2103
3187
4335388
3128982
0
122
SKILLING JEFFREY K
5600000
0
0
0
jeff.skilling@enron.com
19250000
29336
108
88
...
22122
True
6843672
0
1111258
2042
3627
8682716
26093672
0
123
STABLER FRANK
500000
0
0
0
frank.stabler@enron.com
0
16514
0
0
...
356071
False
511734
0
239502
0
0
1112087
511734
0
124
SULLIVAN-SHAKLOVITZ COLLEEN
100000
181993
0
0
0
1362375
0
0
0
...
162
False
0
0
162779
0
0
999356
1362375
0
125
SUNDE MARTIN
700000
0
0
0
marty.sunde@enron.com
0
0
38
37
...
111122
False
698920
0
257486
2565
2647
1545059
698920
0
126
TAYLOR MITCHELL S
600000
227449
0
0
mitchell.taylor@enron.com
3181250
0
29
0
...
0
False
563798
0
265214
300
533
1092663
3745048
0
127
THE TRAVEL AGENCY IN THE PARK
0
0
0
0
0
0
0
0
0
...
362096
False
0
0
0
0
0
362096
0
0
128
THORN TERENCE H
0
16586
0
0
terence.thorn@enron.com
4452476
46145
41
0
...
426629
False
365320
0
222093
73
266
911453
4817796
0
129
TILNEY ELIZABETH A
300000
0
-575000
0
elizabeth.tilney@enron.com
591250
0
19
10
...
152055
False
576792
0
247338
379
460
399393
1168042
0
131
UMANOFF ADAM S
788750
0
0
0
adam.umanoff@enron.com
0
53122
18
12
...
0
False
0
0
288589
41
111
1130461
0
0
132
URQUHART JOHN A
0
0
-36666
36666
0
0
228656
0
0
...
0
False
0
0
0
0
0
228656
0
0
133
WAKEHAM JOHN
0
0
0
109298
0
0
103773
0
0
...
0
False
0
0
0
0
0
213071
0
0
134
WALLS JR ROBERT H
850000
0
0
0
rob.walls@enron.com
4346544
50936
146
17
...
2
False
1552453
0
357091
215
671
1798780
5898997
0
135
WALTERS GARETH W
0
53625
0
0
0
1030329
33785
0
0
...
0
False
0
0
0
0
0
87410
1030329
0
136
WASAFF GEORGE
325000
831299
-583325
0
george.wasaff@enron.com
1668260
0
30
22
...
1425
False
388167
0
259996
337
400
1034395
2056427
0
137
WESTFAHL RICHARD K
0
0
-10800
0
dick.westfahl@enron.com
0
51870
0
0
...
401130
False
384930
0
63744
0
0
762135
384930
0
138
WHALEY DAVID A
0
0
0
0
0
98718
0
0
0
...
0
False
0
0
0
0
0
0
98718
0
139
WHALLEY LAWRENCE G
3000000
0
0
0
greg.whalley@enron.com
3282960
57838
556
186
...
301026
False
2796177
0
510364
3920
6019
4677574
6079137
0
140
WHITE JR THOMAS E
450000
0
0
0
thomas.white@enron.com
1297049
81353
0
0
...
1085463
False
13847074
0
317543
0
0
1934359
15144123
0
141
WINOKUR JR. HERBERT S
0
0
-25000
108579
0
0
1413
0
0
...
0
False
0
0
0
0
0
84992
0
0
142
WODRASKA JOHN
0
0
0
0
john.wodraska@enron.com
0
0
0
0
...
189583
False
0
0
0
0
0
189583
0
0
143
WROBEL BRUCE
0
0
0
0
0
139130
0
0
0
...
0
False
0
0
0
0
0
0
139130
0
144
YEAGER F SCOTT
0
0
0
0
scott.yeager@enron.com
8308552
53947
0
0
...
147950
True
3576206
0
158403
0
0
360300
11884758
0
145
YEAP SOON
0
0
0
0
0
192758
55097
0
0
...
0
False
0
0
0
0
0
55097
192758
0
145 rows × 23 columns
In [16]:


1
#Taking the variables one by one lets look at the outliers.
2
## Now let us examine bonus.
3
## Interstingly Bonuses are a rather confused field.
4
## A number of non-POI had bonuses greater than POIs.
5
#AStonishingly the largest bonus went to a non-poi(Lavorta)
6
## But none stand apart the in the way that TOTAL did so we will not remove any.
7
import numpy as np
8
import seaborn as sns
9
import matplotlib.pyplot as plt
10
sns.set_style("whitegrid")
11
fig,ax = plt.subplots()
12
fig.set_size_inches(8,30)
13
ax=sns.barplot(x="bonus",y="employee",data= df,hue='poi')
14
plt.title('Bonuses')



Out[16]:
Text(0.5,1,u'Bonuses')


In [ ]:


1
​




In [18]:


1
#Next let us look at the outlier in EXCERCISED STOCK OPTIONS
2
# There are outliers but they are POI and there are too few of them to remove any.
3
import numpy as np
4
import seaborn as sns
5
import matplotlib.pyplot as plt
6
sns.set_style("whitegrid")
7
fig,ax = plt.subplots()
8
fig.set_size_inches(8,30)
9
ax=sns.barplot(x="exercised_stock_options",y="employee",data= df,hue="poi")
10
plt.title('Exercised Stock Options')



Out[18]:
Text(0.5,1,u'Exercised Stock Options')


In [19]:


1
## Now let us examine total payments
2
# The winner here is Ken Lay , again a POI, so we will not remove him.
3
## Interestingly a number of non-POI had bonuses greater than POIs.
4
## And the biggest bonus of all went to a non_POI.
5
import numpy as np
6
import seaborn as sns
7
import matplotlib.pyplot as plt
8
sns.set_style("whitegrid")
9
fig,ax = plt.subplots()
10
fig.set_size_inches(8,30)
11
ax=sns.barplot(x="total_payments",y="employee",data= df,  hue = 'poi')
12
plt.title('Total Payments')



Out[19]:
Text(0.5,1,u'Total Payments')


In [20]:


1
## Now let us total stock value.
2
# And the winer is again Ken Lay , a poi, so we will not remove him.
3
import numpy as np
4
import seaborn as sns
5
import matplotlib.pyplot as plt
6
sns.set_style("whitegrid")
7
fig,ax = plt.subplots()
8
fig.set_size_inches(8,30)
9
ax=sns.barplot(x="total_stock_value",y="employee",data= df, hue='poi')
10
plt.title('total_stock_value')



Out[20]:
Text(0.5,1,u'total_stock_value')


In [21]:


1
# Since we are investigating whether criminal behaivor can be detected in emails we will drop any observations
2
# lacking an email address.
3
#df[df.name != 'Tina']  #https://chrisalbon.com/python/data_wrangling/pandas_dropping_column_and_rows/
4
# Besides purging any observation without an email it also rids us of  The Travel Agency
5
# this picked up Eugene Lockart
6
df[df.email_address != 0]



Out[21]:

employee
bonus
deferral_payments
deferred_income
director_fees
email_address
exercised_stock_options
expenses
from_messages
from_poi_to_this_person
...
other
poi
restricted_stock
restricted_stock_deferred
salary
shared_receipt_with_poi
to_messages
total_payments
total_stock_value
loan_advances
0
ALLEN PHILLIP K
4175000
2869717
-3081055
0
phillip.allen@enron.com
1729541
13868
2195
47
...
152
False
126027
-126027
201955
1407
2902
4484442
1729541
0
2
BANNANTINE JAMES M
0
0
-5104
0
james.bannantine@enron.com
4046157
56301
29
39
...
864523
False
1757552
-560222
477
465
566
916197
5243487
0
4
BAY FRANKLIN R
400000
260455
-201641
0
frank.bay@enron.com
0
129142
0
0
...
69
False
145796
-82782
239671
0
0
827696
63014
0
6
BECK SALLY W
700000
0
0
0
sally.beck@enron.com
0
37172
4343
144
...
566
False
126027
0
231330
2639
7315
969068
126027
0
7
BELDEN TIMOTHY N
5249999
2144013
-2334434
0
tim.belden@enron.com
953136
17355
484
228
...
210698
True
157569
0
213999
5521
7991
5501630
1110705
0
9
BERBERIAN DAVID
0
0
0
0
david.berberian@enron.com
1624396
11892
0
0
...
0
False
869220
0
216582
0
0
228474
2493616
0
10
BERGSIEKER RICHARD P
250000
0
-485813
0
rick.bergsieker@enron.com
0
59175
59
4
...
427316
False
659249
0
187922
233
383
618850
659249
0
11
BHATNAGAR SANJAY
0
0
0
137864
sanjay.bhatnagar@enron.com
2604490
0
29
0
...
137864
False
-2604490
15456290
0
463
523
15456290
0
0
12
BIBI PHILIPPE A
1000000
0
0
0
philippe.bibi@enron.com
1465734
38559
40
23
...
425688
False
378082
0
213625
1336
1607
2047593
1843816
0
13
BLACHMAN JEREMY M
850000
0
0
0
jeremy.blachman@enron.com
765313
84208
14
25
...
272
False
189041
0
248546
2326
2475
2014835
954354
0
15
BOWEN JR RAYMOND M
1350000
0
-833
0
raymond.bowen@enron.com
0
65907
27
140
...
1621
True
252055
0
278601
1593
1858
2669589
252055
0
16
BROWN MICHAEL
0
0
0
0
michael.brown@enron.com
0
49288
41
13
...
0
False
0
0
0
761
1486
49288
0
0
17
BUCHANAN HAROLD G
500000
0
0
0
john.buchanan@enron.com
825464
600
125
0
...
1215
False
189041
0
248017
23
1088
1054637
1014505
0
18
BUTTS ROBERT H
750000
0
-75000
0
bob.butts@enron.com
0
9410
0
0
...
150656
False
417619
0
261516
0
0
1271582
417619
0
19
BUY RICHARD B
900000
649584
-694862
0
rick.buy@enron.com
2542813
0
1053
156
...
400572
False
901657
0
330546
2333
3523
2355702
3444470
0
20
CALGER CHRISTOPHER F
1250000
0
-262500
0
christopher.calger@enron.com
0
35818
144
199
...
486
True
126027
0
240189
2188
2598
1639297
126027
0
21
CARTER REBECCA C
300000
0
-159792
0
rebecca.carter@enron.com
0
0
15
29
...
540
False
307301
-307301
261809
196
312
477557
0
0
22
CAUSEY RICHARD A
1000000
0
-235000
0
richard.causey@enron.com
0
30674
49
58
...
307895
True
2502063
0
415189
1585
1892
1868758
2502063
0
24
CHRISTODOULOU DIOMEDES
0
0
0
0
diomedes.christodoulou@enron.com
5127155
0
0
0
...
0
False
950730
0
0
0
0
0
6077885
0
26
COLWELL WESLEY
1200000
27610
-144062
0
wes.colwell@enron.com
0
16514
40
240
...
101740
True
698242
0
288542
1132
1758
1490344
698242
0
27
CORDES WILLIAM R
0
0
0
0
bill.cordes@enron.com
651850
0
12
10
...
0
False
386335
0
0
58
764
0
1038185
0
28
COX DAVID
800000
0
-41250
0
chip.cox@enron.com
117551
27861
33
0
...
494
False
378082
0
314288
71
102
1101393
495633
0
30
DEFFNER JOSEPH M
600000
0
0
0
joseph.deffner@enron.com
17378
41626
74
115
...
25553
False
141833
0
206121
552
714
1208649
159211
0
31
DELAINEY DAVID W
3000000
0
0
0
david.delainey@enron.com
2291113
86174
3069
66
...
1661
True
1323148
0
365163
2097
3093
4747979
3614261
0
32
DERRICK JR. JAMES V
800000
0
-1284000
0
james.derrick@enron.com
8831913
51124
909
64
...
7482
False
1787380
-1787380
492375
1401
2181
550981
8831913
0
33
DETMERING TIMOTHY J
425000
875307
-775241
0
timothy.detmering@enron.com
2027865
52255
0
0
...
1105
False
315068
-315068
210500
0
0
1204583
2027865
0
34
DIETRICH JANET R
600000
0
0
0
janet.dietrich@enron.com
1550019
3475
63
305
...
473
False
315068
0
250100
1902
2572
1410464
1865087
0
35
DIMICHELE RICHARD G
1000000
0
0
0
richard.dimichele@enron.com
8191755
35812
0
0
...
374689
False
126027
0
262788
0
0
2368151
8317782
0
36
DODSON KEITH
70000
0
0
0
keith.dodson@enron.com
0
28164
14
10
...
774
False
0
0
221003
114
176
319941
0
0
37
DONAHUE JR JEFFREY M
800000
0
-300000
0
jeff.donahue@enron.com
765920
96268
22
188
...
891
False
315068
0
278601
772
865
875760
1080988
0
39
DURAN WILLIAM D
750000
0
0
0
w.duran@enron.com
1451869
25785
12
106
...
1568
False
189041
0
210692
599
904
2093263
1640910
0
40
ECHOLS JOHN B
200000
0
0
0
john.echols@enron.com
601438
21530
0
0
...
53775
False
407503
0
182245
0
0
2692324
1008941
0
41
ELLIOTT STEVEN
350000
0
-400729
0
steven.elliott@enron.com
4890344
78552
0
0
...
12961
False
1788391
0
170941
0
0
211725
6678735
0
42
FALLON JAMES B
2500000
0
0
0
jim.fallon@enron.com
940257
95924
75
42
...
401481
False
1392142
0
304588
1604
1755
3676340
2332399
0
43
FASTOW ANDREW S
1300000
0
-1386055
0
andrew.fastow@enron.com
0
55921
0
0
...
277464
True
1794412
0
440698
0
0
2424083
1794412
0
44
FITZGERALD JAY L
350000
0
0
0
jay.fitzgerald@enron.com
664461
23870
16
1
...
285414
False
956775
0
199157
723
936
1414857
1621236
0
45
FOWLER PEGGY
0
0
0
0
kulvinder.fowler@enron.com
1324578
0
36
0
...
0
False
560170
0
0
10
517
0
1884748
0
46
FOY JOE
0
181755
0
0
tracy.foy@enron.com
343434
0
13
0
...
0
False
0
0
0
2
57
181755
343434
0
47
FREVERT MARK A
2000000
6426990
-3367011
0
mark.frevert@enron.com
10433518
86987
21
242
...
7427621
False
4188667
0
1060932
2979
3275
17252530
14622185
2000000
50
GARLAND C KEVIN
850000
0
0
0
kevin.garland@enron.com
636246
48405
44
10
...
60814
False
259907
0
231946
178
209
1566469
896153
0
52
GIBBS DANA R
0
504610
0
0
dana.gibbs@enron.com
2218275
0
12
0
...
0
False
0
0
0
23
169
966522
2218275
0
54
GLISAN JR BEN F
600000
0
0
0
ben.glisan@enron.com
384728
125978
16
52
...
200308
True
393818
0
274975
874
873
1272284
778546
0
55
GOLD JOSEPH
750000
0
0
0
joe.gold@enron.com
436515
0
0
0
...
819288
False
441096
0
272880
0
0
2146973
877611
0
58
HAEDICKE MARK E
1150000
2157527
-934484
0
mark.haedicke@enron.com
608750
76169
1941
180
...
52382
False
524169
-329825
374125
1847
4009
3859065
803094
0
59
HANNON KEVIN P
1500000
0
-3117011
0
kevin.hannon@enron.com
5538001
34039
32
32
...
11350
True
853064
0
243293
1035
1045
288682
6391065
0
60
HAUG DAVID L
0
0
0
0
david.haug@enron.com
0
475
19
4
...
0
False
2217299
0
0
471
573
475
2217299
0
61
HAYES ROBERT E
0
7961
0
0
robert.hayes@enron.com
0
0
12
16
...
0
False
151418
0
0
50
504
7961
151418
0
62
HAYSLETT RODERICK J
0
0
0
0
rod.hayslett@enron.com
0
0
1061
35
...
0
False
346663
0
0
571
2649
0
346663
0
63
HERMANN ROBERT J
700000
0
-280000
0
robert.hermann@enron.com
187500
48357
0
0
...
416441
False
480632
0
262663
0
0
1297461
668132
0
64
HICKERSON GARY J
1700000
0
0
0
gary.hickerson@enron.com
0
98849
27
40
...
1936
False
441096
0
211788
900
1320
2081796
441096
0
65
HIRKO JOSEPH
0
10259
0
0
joe.hirko@enron.com
30766064
77978
0
0
...
2856
True
0
0
0
0
0
91093
30766064
0
66
HORTON STANLEY C
0
3131860
0
0
stanley.horton@enron.com
5210569
0
1073
44
...
0
False
2046079
0
0
1074
2350
3131860
7256648
0
67
HUGHES JAMES A
0
0
0
0
james.hughes@enron.com
754966
0
34
35
...
0
False
363428
0
0
589
719
0
1118394
0
68
HUMPHREY GENE E
0
2964506
0
0
gene.humphrey@enron.com
2282768
4994
17
10
...
0
False
0
0
130724
119
128
3100224
2282768
0
69
IZZO LAWRENCE L
0
0
0
0
larry.izzo@enron.com
2165172
28093
19
28
...
1553729
False
3654808
0
85274
437
496
1979596
5819980
0
70
JACKSON CHARLENE R
250000
0
0
0
charlene.jackson@enron.com
185063
10181
56
25
...
2435
False
540672
0
288558
117
258
551174
725735
0
72
KAMINSKI WINCENTY J
400000
0
0
0
vince.kaminski@enron.com
850010
83585
14368
41
...
4669
False
126027
0
275101
583
4607
1086821
976037
0
73
KEAN STEVEN J
1000000
0
0
0
steven.kean@enron.com
2022048
41953
6759
140
...
1231
False
4131594
0
404338
3639
12754
1747522
6153642
0
74
KISHKILL JOSEPH G
0
0
-51042
0
joe.kishkill@enron.com
0
116335
0
0
...
465357
False
1034346
0
174246
0
0
704896
1034346
0
75
KITCHEN LOUISE
3100000
0
0
0
louise.kitchen@enron.com
81042
5774
1728
251
...
93925
False
466101
0
271442
3669
8305
3471141
547143
0
76
KOENIG MARK E
700000
0
0
0
mark.koenig@enron.com
671737
127017
61
53
...
150458
True
1248318
0
309946
2271
2374
1587421
1920055
0
77
KOPPER MICHAEL J
800000
0
0
0
michael.kopper@enron.com
0
118134
0
0
...
907502
True
985032
0
224305
0
0
2652612
985032
0
78
LAVORATO JOHN J
8000000
0
0
0
john.lavorato@enron.com
4158995
49537
2585
528
...
1552
False
1008149
0
339288
3962
7259
10425757
5167144
0
79
LAY KENNETH L
7000000
202911
-300000
0
kenneth.lay@enron.com
34348384
99832
36
123
...
10359729
True
14761694
0
1072321
2411
4273
103559793
49110078
81525000
80
LEFF DANIEL P
1000000
0
0
0
dan.leff@enron.com
0
0
63
67
...
3083
False
360528
0
273746
2672
2822
2664228
360528
0
82
LEWIS RICHARD
0
0
0
0
richard.lewis@enron.com
850477
0
26
10
...
0
False
0
0
0
739
952
0
850477
0
83
LINDHOLM TOD A
200000
204075
0
0
tod.lindholm@enron.com
2549361
57727
0
0
...
2630
False
514847
0
236457
0
0
875889
3064208
0
86
MARTIN AMANDA K
0
85430
0
0
a..martin@enron.com
2070306
8211
230
8
...
2818454
False
0
0
349487
477
1522
8407016
2070306
0
87
MCCARTY DANNY J
0
0
0
0
danny.mccarty@enron.com
664375
0
215
25
...
0
False
94556
0
0
508
1433
0
758931
0
88
MCCLELLAN GEORGE
900000
0
-125000
0
george.mcclellan@enron.com
506765
228763
49
52
...
51587
False
441096
0
263413
1469
1744
1318763
947861
0
89
MCCONNELL MICHAEL S
1100000
0
0
0
mike.mcconnell@enron.com
1623010
81364
2742
92
...
540
False
1478269
0
365038
2189
3329
2101364
3101279
0
90
MCDONALD REBECCA
0
0
0
0
rebecca.mcdonald@enron.com
757301
0
13
54
...
0
False
934065
0
0
720
894
0
1691366
0
91
MCMAHON JEFFREY
2600000
0
0
0
jeffrey.mcmahon@enron.com
1104054
137108
48
58
...
297353
False
558801
0
370448
2228
2355
4099771
1662855
0
93
METTS MARK
600000
0
0
0
mark.metts@enron.com
0
94299
29
38
...
1740
False
585062
0
365788
702
807
1061827
585062
0
95
MEYER ROCKFORD G
0
1848227
0
0
rockford.meyer@enron.com
493489
0
28
0
...
0
False
462384
0
0
22
232
1848227
955873
0
96
MORAN MICHAEL P
0
0
0
0
michael.moran@enron.com
59539
0
19
0
...
0
False
161602
0
0
127
672
0
221141
0
97
MORDAUNT KRISTINA M
325000
0
0
0
kristina.mordaunt@enron.com
0
35018
0
0
...
1411
False
208510
0
267093
0
0
628522
208510
0
98
MULLER MARK S
1100000
842924
-719000
0
s..muller@enron.com
1056320
0
16
12
...
947
False
360528
0
251654
114
136
3202070
1416848
0
99
MURRAY JULIA H
400000
0
0
0
julia.murray@enron.com
400478
57580
45
11
...
330
False
196983
0
229284
395
2192
812194
597461
0
101
OLSON CINDY K
750000
77716
0
0
cindy.olson@enron.com
1637034
63791
52
20
...
972
False
969729
0
329078
856
1184
1321557
2606763
0
102
OVERDYKE JR JERE C
0
0
0
0
jere.overdyke@enron.com
5266578
18834
0
0
...
176
False
2041016
0
94941
0
0
249787
7307594
0
103
PAI LOU L
1000000
0
0
0
lou.pai@enron.com
15364167
32047
0
0
...
1829457
False
8453763
0
261879
0
0
3123383
23817930
0
105
PICKERING MARK R
300000
0
0
0
mark.pickering@enron.com
28798
31653
67
7
...
0
False
0
0
655037
728
898
1386690
28798
400000
106
PIPER GREGORY F
400000
1130036
-33333
0
greg.piper@enron.com
880290
43057
222
61
...
778
False
409554
-409554
197091
742
1238
1737629
880290
0
107
PIRO JIM
0
0
0
0
jim.piro@enron.com
0
0
16
0
...
0
False
47304
0
0
3
58
0
47304
0
108
POWERS WILLIAM
0
0
-17500
17500
ken.powers@enron.com
0
0
26
0
...
0
False
0
0
0
12
653
0
0
0
109
PRENTICE JAMES
0
564348
0
0
james.prentice@enron.com
886231
0
0
0
...
0
False
208809
0
0
0
0
564348
1095040
0
110
REDMOND BRIAN L
0
0
0
0
brian.redmond@enron.com
7509039
14689
221
204
...
0
False
381285
0
96840
1063
1671
111529
7890324
0
112
RICE KENNETH D
1750000
0
-3504386
0
ken.rice@enron.com
19794175
46950
18
42
...
174839
True
2748364
0
420636
864
905
505050
22542539
0
113
RIEKER PAULA H
700000
214678
-100000
0
paula.rieker@enron.com
1635238
33271
82
35
...
1950
True
283649
0
249201
1258
1328
1099100
1918887
0
115
SCRIMSHAW MATTHEW
0
0
0
0
matthew.scrimshaw@enron.com
759557
0
0
0
...
0
False
0
0
0
0
0
0
759557
0
116
SHANKMAN JEFFREY A
2000000
0
0
0
jeffrey.shankman@enron.com
1441898
178979
2681
94
...
1191
False
630137
0
304110
1730
3221
3038702
2072035
0
117
SHAPIRO RICHARD S
650000
0
0
0
richard.shapiro@enron.com
607837
137767
1215
74
...
705
False
379164
0
269076
4527
15149
1057548
987001
0
118
SHARP VICTORIA T
600000
187469
0
0
vicki.sharp@enron.com
281073
116337
136
24
...
2401
False
213063
0
248146
2477
3136
1576511
494136
0
119
SHELBY REX
200000
0
-4167
0
rex.shelby@enron.com
1624396
22884
39
13
...
1573324
True
869220
0
211844
91
225
2003885
2493616
0
120
SHERRICK JEFFREY B
0
0
0
0
jeffrey.sherrick@enron.com
1426469
0
25
39
...
0
False
405999
0
0
583
613
0
1832468
0
121
SHERRIFF JOHN R
1500000
0
0
0
john.sherriff@enron.com
1835558
0
92
28
...
1852186
False
1293424
0
428780
2103
3187
4335388
3128982
0
122
SKILLING JEFFREY K
5600000
0
0
0
jeff.skilling@enron.com
19250000
29336
108
88
...
22122
True
6843672
0
1111258
2042
3627
8682716
26093672
0
123
STABLER FRANK
500000
0
0
0
frank.stabler@enron.com
0
16514
0
0
...
356071
False
511734
0
239502
0
0
1112087
511734
0
125
SUNDE MARTIN
700000
0
0
0
marty.sunde@enron.com
0
0
38
37
...
111122
False
698920
0
257486
2565
2647
1545059
698920
0
126
TAYLOR MITCHELL S
600000
227449
0
0
mitchell.taylor@enron.com
3181250
0
29
0
...
0
False
563798
0
265214
300
533
1092663
3745048
0
128
THORN TERENCE H
0
16586
0
0
terence.thorn@enron.com
4452476
46145
41
0
...
426629
False
365320
0
222093
73
266
911453
4817796
0
129
TILNEY ELIZABETH A
300000
0
-575000
0
elizabeth.tilney@enron.com
591250
0
19
10
...
152055
False
576792
0
247338
379
460
399393
1168042
0
131
UMANOFF ADAM S
788750
0
0
0
adam.umanoff@enron.com
0
53122
18
12
...
0
False
0
0
288589
41
111
1130461
0
0
134
WALLS JR ROBERT H
850000
0
0
0
rob.walls@enron.com
4346544
50936
146
17
...
2
False
1552453
0
357091
215
671
1798780
5898997
0
136
WASAFF GEORGE
325000
831299
-583325
0
george.wasaff@enron.com
1668260
0
30
22
...
1425
False
388167
0
259996
337
400
1034395
2056427
0
137
WESTFAHL RICHARD K
0
0
-10800
0
dick.westfahl@enron.com
0
51870
0
0
...
401130
False
384930
0
63744
0
0
762135
384930
0
139
WHALLEY LAWRENCE G
3000000
0
0
0
greg.whalley@enron.com
3282960
57838
556
186
...
301026
False
2796177
0
510364
3920
6019
4677574
6079137
0
140
WHITE JR THOMAS E
450000
0
0
0
thomas.white@enron.com
1297049
81353
0
0
...
1085463
False
13847074
0
317543
0
0
1934359
15144123
0
142
WODRASKA JOHN
0
0
0
0
john.wodraska@enron.com
0
0
0
0
...
189583
False
0
0
0
0
0
189583
0
0
144
YEAGER F SCOTT
0
0
0
0
scott.yeager@enron.com
8308552
53947
0
0
...
147950
True
3576206
0
158403
0
0
360300
11884758
0
111 rows × 23 columns
In [ ]:


1
# Create New Features




In [28]:


1
# I then added my new features manually
2
​
3
df['fraction_to_poi_email'] = df.from_this_person_to_poi  / df.to_messages
4
df['fraction_from_poi_email''poi','salary',
2
 'to_messages',
3
 'deferral_payments',
4
 'total_payments',
5
 'exercised_stock_options',
6
 'bonus',
7
 'restricted_stock',
8
 'shared_receipt_with_poi',
9
 'restricted_stock_deferred',
10
 'total_stock_value',
11
 'expenses',
12
 'loan_advances',
13
 'from_messages',
14
 'other',
15
 'from_this_person_to_poi',
16
 'poi',
17
 'director_fees',
18
 'deferred_income',
19
 'long_term_incentive',
20
 'email_address',
21
 'from_poi_to_this_person',
22
  'fraction_from_poi_email',
23
    'fraction_to_poi_email']




In [31]:


1
df=df.set_index('employee')
2
df=df.T
3
df.head()



Out[31]:
employee
ALLEN PHILLIP K
BADUM JAMES P
BANNANTINE JAMES M
BAXTER JOHN C
BAY FRANKLIN R
BAZELIDES PHILIP J
BECK SALLY W
BELDEN TIMOTHY N
BELFER ROBERT
BERBERIAN DAVID
...
WASAFF GEORGE
WESTFAHL RICHARD K
WHALEY DAVID A
WHALLEY LAWRENCE G
WHITE JR THOMAS E
WINOKUR JR. HERBERT S
WODRASKA JOHN
WROBEL BRUCE
YEAGER F SCOTT
YEAP SOON
bonus
4175000
0
0
1200000
400000
0
700000
5249999
0
0
...
325000
0
0
3000000
450000
0
0
0
0
0
deferral_payments
2869717
178980
0
1295738
260455
684694
0
2144013
-102500
0
...
831299
0
0
0
0
0
0
0
0
0
deferred_income
-3081055
0
-5104
-1386055
-201641
0
0
-2334434
0
0
...
-583325
-10800
0
0
0
-25000
0
0
0
0
director_fees
0
0
0
0
0
0
0
0
3285
0
...
0
0
0
0
0
108579
0
0
0
0
email_address
phillip.allen@enron.com
0
james.bannantine@enron.com
0
frank.bay@enron.com
0
sally.beck@enron.com
tim.belden@enron.com
0
david.berberian@enron.com
...
george.wasaff@enron.com
dick.westfahl@enron.com
0
greg.whalley@enron.com
thomas.white@enron.com
0
john.wodraska@enron.com
0
scott.yeager@enron.com
0
5 rows × 145 columns
In [34]:


1
data = df.to_dict()




In [35]:


1
my_dataset =data




In [37]:


1
###Extract featuires and labels from dataset for local testing
2
data = featureFormat(my_dataset, initial_features_list,sort_keys = True)
3
labels , features - targetFeatureSplit(my_dataset)




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-37-f92cb40e6778> in <module>()
      1 ###Extract featuires and labels from dataset for local testing
----> 2 data = featureFormat(my_dataset, initial_features_list,sort_keys = True)
      3 labels , features - targetFeatureSplit(my_dataset)

/Users/jfole/Downloads/ud120-projects-master_joe/ud120-projects-master_joe/tools\feature_format.pyc in featureFormat(dictionary, features, remove_NaN, remove_all_zeroes, remove_any_zeroes, sort_keys)
     67             if value=="NaN" and remove_NaN:
     68                 value = 0
---> 69             tmp_list.append( float(value) )
     70
     71         # Logic for deciding whether or not to add the data point.

ValueError: could not convert string to float: phillip.allen@enron.com

In [38]:


1
type(data)



Out[38]:
dict
In [ ]:


1
​




In [ ]:


1
​




In [ ]:


1
​




In [ ]:


1
​