k_means_cluster.py

#!/usr/bin/python 

""" 
    Skeleton code for k-means clustering mini-project.
"""

import pickle
import numpy
import matplotlib.pyplot as plt
import sys
import math
sys.path.append("../tools/")
from feature_format import featureFormat, targetFeatureSplit

def Draw(pred, features, poi, mark_poi=False, name="image.png", f1_name="feature 1", f2_name="feature 2"):
    """ some plotting code designed to help you visualize your clusters """

    ### plot each cluster with a different color--add more colors for
    ### drawing more than five clusters
    colors = ["b", "c", "k", "m", "g"]
    for ii, pp in enumerate(pred):
        plt.scatter(features[ii][0], features[ii][1], color = colors[pred[ii]])

    ### if you like, place red stars over points that are POIs (just for funsies)
    if mark_poi:
        for ii, pp in enumerate(pred):
            if poi[ii]:
                plt.scatter(features[ii][0], features[ii][1], color="r", marker="*")
    plt.xlabel(f1_name)
    plt.ylabel(f2_name)
    plt.savefig(name)
    plt.show()



### load in the dict of dicts containing all the data on each person in the dataset
data_dict = pickle.load( open("../final_project/final_project_dataset.pkl", "r") )
### there's an outlier--remove it! 
data_dict.pop("TOTAL", 0)

values = []
for element in data_dict.items():
    values.append(element[1]['salary'])

values = [element for element in values if element != "NaN"]
print "Max, Min: ", max(values), min(values)

### the input features we want to use 
### can be any key in the person-level dictionary (salary, director_fees, etc.) 
feature_1 = "salary"
feature_2 = "exercised_stock_options"

poi  = "poi"
features_list = [poi, feature_1, feature_2]
data = featureFormat(data_dict, features_list )
poi, finance_features = targetFeatureSplit( data )

# feature sclaing
from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler()
finance_features = scaler.fit_transform(finance_features)

print scaler.data_min_, scaler.data_max_

# check for 2000000 salary and 1000000 stock possible scaled values:
for value, number in zip([200000, 1000000], [0, 1]):
    print "Scaled value for: {0} is: {1}"\
        .format(value, (value - scaler.data_min_[number]) / (scaler.data_max_[number] - scaler.data_min_[number]))


minValue, maxValue = 99999999, 0
newList = [feature for feature in finance_features[1] if not math.isnan(feature)]

for each in newList:
    if each > maxValue:
        maxValue = each
    if each < minValue:
        minValue = each

print maxValue, minValue


### in the "clustering with 3 features" part of the mini-project,
### you'll want to change this line to 
### for f1, f2, _ in finance_features:
### (as it's currently written, the line below assumes 2 features)
for f1, f2 in finance_features:
    plt.scatter( f1, f2 )
plt.show()

### cluster here; create predictions of the cluster labels
### for the data and store them to a list called pred
from sklearn.cluster import KMeans

clf = KMeans(n_clusters=2)
clf.fit(data)
pred = clf.predict(data)



### rename the "name" parameter when you change the number of features
### so that the figure gets saved to a different file
try:
    Draw(pred, finance_features, poi, mark_poi=False, name="clusters.pdf", f1_name=feature_1, f2_name=feature_2)
except NameError:
    print "no predictions object named pred found, no clusters to plot"