enron_outliers.py

#!/usr/bin/python

import pickle
import sys
import matplotlib.pyplot
sys.path.append("../tools/")

from feature_format import featureFormat, targetFeatureSplit


### read in data dictionary, convert to numpy array
data_dict = pickle.load( open("../final_project/final_project_dataset.pkl", "rb") )
data_dict['TOTAL']
data_dict.pop('TOTAL',0)
features = ["salary", "bonus"]

data = featureFormat(data_dict, features)
#find the biggest outlier
temp=sorted(data,key=lambda dat:dat[0], reverse=True)
max_sal= temp[0][0]
#print max_sal
for k in data_dict:
    if (data_dict[k]['bonus'] < 5000000 and data_dict[k]['bonus'] != 'NaN') and \
       (data_dict[k]['salary'] < 1000000 and data_dict[k]['salary'] != 'NaN'):
        print(k)

### your code below
for point in data:
    salary = point[0]
    bonus = point[1]
    matplotlib.pyplot.scatter( salary, bonus )

matplotlib.pyplot.xlabel("salary")
matplotlib.pyplot.ylabel("bonus")
matplotlib.pyplot.show()