scikit Naive Bayes Jupyter Notebook

In [8]:

import numpy as np
import pandas as pd

import urllib
import sklearn
from sklearn.naive_bayes import BernoulliNB
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB

from sklearn.cross_validation import train_test_split

In [9]:

from sklearn import metrics
from sklearn.metrics import accuracy_score

Naive Bayes
Use Naive Bayes to predict spam

In [12]:

url="https://archive.ics.uci.edu/ml/machine-learning-databases/spambase/spambase.data"
raw_data=urllib.request.urlopen(url)

dataset=np.loadtxt(raw_data,delimiter=",")
print(dataset.shape)
dataset[0]

(4601, 58)

Out[12]:

array([  0.   ,   0.64 ,   0.64 ,   0.   ,   0.32 ,   0.   ,   0.   ,
         0.   ,   0.   ,   0.   ,   0.   ,   0.64 ,   0.   ,   0.   ,
         0.   ,   0.32 ,   0.   ,   1.29 ,   1.93 ,   0.   ,   0.96 ,
         0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,
         0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,
         0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,
         0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,   0.   ,
         0.   ,   0.   ,   0.778,   0.   ,   0.   ,   3.756,  61.   ,
       278.   ,   1.   ])

In [17]:

#predictor dataset
X=dataset[:,0:48]
y=dataset[:,-1]
print(X[0])
print(y[0])

[0.   0.64 0.64 0.   0.32 0.   0.   0.   0.   0.   0.   0.64 0.   0.
 0.   0.32 0.   1.29 1.93 0.   0.96 0.   0.   0.   0.   0.   0.   0.
 0.   0.   0.   0.   0.   0.   0.   0.   0.   0.   0.   0.   0.   0.
 0.   0.   0.   0.   0.   0.  ]
1.0

In [18]:

# Split to train and test
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=.33,random_state=17)

In [19]:

## We first convert few attr to binary and see how it fares with Bernoulli Naive Bayes
BernNB=BernoulliNB(binarize=True)

In [20]:

BernNB.fit(X_train,y_train)
print(BernNB)

BernoulliNB(alpha=1.0, binarize=True, class_prior=None, fit_prior=True)

In [22]:

y_expect=y_test
y_pred=BernNB.predict(X_test)
print(accuracy_score(y_expect,y_pred))

0.8558262014483212

The notebook is  for ease of use. The  video is from The Engineering World. Please visit
https://www.youtube.com/watch?v=99MN-rl8jGY&t=311s