From 0b34ba92bc9ccadaf7e16984dd1400ba38b6ee89 Mon Sep 17 00:00:00 2001
From: Dynamo13 <62235947+Dynamo13@users.noreply.github.com>
Date: Sat, 28 Mar 2020 00:40:19 -0400
Subject: [PATCH] Updated naive bayers classifier

Used pandas to import dataset sklearn for preprocessing  and confusion matrix to check accuracy. The classifier is GaussianNB( lines 23-26)
---
 .../modular/classifier_gaussiannaivebayes.txt | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/examples/descriptions/modular/classifier_gaussiannaivebayes.txt b/examples/descriptions/modular/classifier_gaussiannaivebayes.txt
index 3e0f730de5b..9c3e5661a8a 100644
--- a/examples/descriptions/modular/classifier_gaussiannaivebayes.txt
+++ b/examples/descriptions/modular/classifier_gaussiannaivebayes.txt
@@ -1,2 +1,33 @@
 In this example the Gaussian Naive Bayes algorithm is used to classify
 toy data
+#data preprocessing
+
+import pandas as pd
+data=read.csv('\..\filename.csv')
+
+X=data.iloc[:,:-1].values
+Y=data.iloc[:,4].values         #the last cloumn of the data
+
+#splitting the data into training and test set
+
+from sklearn.cross_validation import train_test_split
+X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=0.25,random_state=0)
+
+#feature scaling
+
+from sklearn.preprocessing import StandardScaler
+sc=StandardScaler()
+X_train=sc.fit_transform(X_train)
+X_test=sc.transform(X_test)
+
+#importing and using the classifier
+from sklearn.naive_bayes import GaussianNB
+classifier = GaussianNB()
+classifier.fit(X_train,Y_train)
+
+#predicting the dataset
+Y_pred=classifier.predict(X_test)
+
+#making the confusion matrix to check the accuracy of the data
+from sklearn.metrics import confusion_matrix
+cm=confusion_matrix(Y_test,Y_pred)