Naive Bayes Classifier

Complete the code in ClassifyNB.py with the sklearn Naive Bayes classifier to classify the terrain data. The objective of this exercise is to recreate the decision boundary found in the lesson video, and make a plot that visually shows the decision boundary



In [3]:

    
import sys
sys.path.append("../naive bayes/")
from prep_terrain_data import makeTerrainData
from class_vis import prettyPicture, output_image

import numpy as np
import pylab as pl

%matplotlib inline



In [4]:

    
import matplotlib as pl
font_cache_path = pl.get_cachedir() + '/fontList.cache'
%rm $font_cache_path









    



rm: /Users/omojumiller/.matplotlib/fontList.cache: No such file or directory



In [5]:

    
features_train, labels_train, features_test, labels_test = makeTerrainData()

### the training data (features_train, labels_train) have both "fast" and "slow" points mixed
### in together--separate them so we can give them different colors in the scatterplot,
### and visually identify them
grade_fast = [features_train[ii][0] for ii in range(0, len(features_train)) if labels_train[ii]==0]
bumpy_fast = [features_train[ii][1] for ii in range(0, len(features_train)) if labels_train[ii]==0]
grade_slow = [features_train[ii][0] for ii in range(0, len(features_train)) if labels_train[ii]==1]
bumpy_slow = [features_train[ii][1] for ii in range(0, len(features_train)) if labels_train[ii]==1]



In [31]:

    
def classify(features_train, labels_train):
    ### import the sklearn module for GaussianNB
    ### create classifier
    ### fit the classifier on the training features and labels
    ### return the fit classifier


    ### your code goes here!

    from sklearn.naive_bayes import GaussianNB
    clf = GaussianNB()


    return clf.fit(features_train, labels_train)



In [32]:

    
clf = classify(features_train, labels_train)
pred = clf.predict(features_test)



In [33]:

    
### draw the decision boundary with the text points overlaid
prettyPicture(clf, features_test, labels_test)
#output_image("test.png", "png", open("test.png", "rb").read())



In [37]:

    
def NBAccuracy(features_train, labels_train, features_test, labels_test):
    """ compute the accuracy of your Naive Bayes classifier """
    ### import the sklearn module for GaussianNB
    from sklearn.naive_bayes import GaussianNB
    

    ### create classifier
    clf = GaussianNB()

    ### fit the classifier on the training features and labels
    clf.fit(features_train, labels_train)

    ### use the trained classifier to predict labels for the test features
    pred = clf.predict(features_test)


    ### calculate and return the accuracy on the test data
    ### this is slightly different than the example, 
    ### where we just print the accuracy
    ### you might need to import an sklearn module
    
    accuracy = clf.score(features_test, labels_test)
    
    return accuracy



In [38]:

    
NBAccuracy(features_train, labels_train, features_test, labels_test)









    Out[38]:





0.88400000000000001

Another way I could have found the accuracy is as follows:

from sklearn.metrics import accuracy_score
print accuracy_score(pred, labels_test)



In [41]:

    
""" 
    This is the code to accompany the Lesson 1 (Naive Bayes) mini-project. 
    Use a Naive Bayes Classifier to identify emails by their authors
    
    authors and labels:
    Sara has label 0
    Chris has label 1
"""
    
import sys
from time import time
sys.path.append("../tools/")
from email_preprocess import preprocess


### features_train and features_test are the features for the training
### and testing datasets, respectively
### labels_train and labels_test are the corresponding item labels
features_train, features_test, labels_train, labels_test = preprocess()




#########################################################
### your code goes here ###

from sklearn.naive_bayes import GaussianNB

### create classifier
clf = GaussianNB()

### fit the classifier on the training features and labels

# lets capture how long it took to train the classifier
t0 = time()
clf.fit(features_train, labels_train)
print "training time:", round(time()-t0, 3), "s"

### use the trained classifier to predict labels for the test features
t0 = time()
pred = clf.predict(features_test)
print "testing time:", round(time()-t0, 3), "s"

### calculate and return the accuracy on the test data
### this is slightly different than the example, 
### where we just print the accuracy
### you might need to import an sklearn module
    
accuracy = clf.score(features_test, labels_test)

#########################################################









    



no. of Chris training emails: 7936
no. of Sara training emails: 7884
training time: 1.461 s



In [40]:

    
accuracy









    Out[40]:





0.97326507394766781



In [ ]: