Machine Learning : Classifier / Logistic Regression Archive - machinelearningtechnilesh

 Machine Learning : Classifier / Logistic Regression ( part 5 )

We were learn all the stuff regrading the Machine learning . 

For Video Lecture on Machine Learning : Decision Go at bottom or google codewithnilesh

Logistic Regression actually is Classifier which is used to classify the data in two part i.e. Binary devision like True and False . One Region Contain the All predicted True Values and other contained the Flase predicted values .The Line which Seprate the region is called Boundary of Logistic Regression.

The Linear Regressor Equation is 

log(Y / Y -1 ) = b0 + b1 * X1 + b2 * X2 + b2 * X2 + b2 * X2

Step 1 : Data Preprocessing :

Initially Import all Libraries like Pandas , numpy , matlibplot pyplot & Sklearn

using the pandas take data and classify in to dependent and independent variable.

Code : 

#it classify the dasts using function who will  through ads suv car

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

#import the data sets

dataset = pd.read_csv('Social_Network_Ads.csv')

X = dataset.iloc[: , [2,3]].values# which coloumwant to use to predict the result

Y = dataset.iloc[: ,:4].values

Code written by @Garry Raut

Step 2 : Split the data in Test and Train Set :

we used the Sklearns model selction Liberaries and Train_test_split class of this  

Split the data in X_train , X_test , Y_train , Y_test 

code :

#split the set to traning and test sets

from sklearn.model_selection import train_test_split

X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.2)

 # test size should be displayed

Step 3: Scaling the data for easy to classify :

For this Scaling we use the StandradScalar class from Library Sklearn . preprocessing.

Creating Object of class , SX object and using the fit method we will fit in the training and test set .Now we Scale the data.

 Step 4: Now we Logistic Regression : 

so for Logistic Regression we need the Logistic Class from the library sklearn . Linear model . we create object name ' Classifier  ' to acces the class and fit to the  model .Now we create an model .

Code:

from sklearn.linear_model import LogisticRegression

classifier = LogisticRegression(random_state=0)

# random state we get same result

classifier.fit(X_train,Y_train)

# fit the regession in train set

#prediction vector

Y_pred = classifier.predict(X_test)

step 5 : Confusion Matrix  :

This matrix is used to differentiate between  test result and Predicted result . so we idea of efficiency of model 

Code :

#Confusion matrix contanied te train set prediction 

from sklearn.metrics import confusion_matrix

cm = confusion_matrix(Y_test,Y_pred)

Step 6 : Visualization of data

Code : 

#visulization data seprate

from matplotlib.colors import ListedColormap  

X_set, Y_set = X_train, Y_train  

X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop =

 X_set[:, 0].max() + 1, step  =0.01),  

np.arange(start = X_set[:, 1].min() - 1, stop =

 X_set[:, 1].max() + 1, step = 0.01))  

plt.contourf(X1, X2, classifier.predict(np.array

([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),  

alpha = 0.75, cmap = ListedColormap(('purple','green' )))

plt.xlim(X1.min(), X1.max())  

plt.ylim(X2.min(), X2.max())  

for i, j in enumerate(np.unique(Y_set)):  

    plt.scatter(X_set[Y_set == j, 0], X_set[Y_set == j, 1],  

        c = ListedColormap(('purple', 'green'))(i), label = j)  

plt.title('Logistic Regression CodeWithNilesh')  

plt.xlabel('CodeWithNilesh-Age')  

plt.ylabel('CodeWithNilesh-Salary')  

plt.legend()  

plt.show() 

Output : 

For Video Lecture on Machine Learning : Decision Go at bottom or google codewithnilesh