N Days_With_Machine_Learning (Part2 )

In This Blog , I will write About How to Learn and Master Machine Learning , It will takes from me N-1 Days , and it will be divided into 6 Parts (Data Preprocessing , Classification , Regression , Clustering , Artificial Neural networks , Reinforcement learning )

Day 2 : Classification

In This part I will explain for you what is Classification in Machine learning ?

What is Classification ?

Classification is one of the most widely used techniques in machine learning, with a broad array of applications, including sentiment analysis, ad targeting, Spam detection, risk assessment, medical diagnosis and image classification.

Spam Classification

Ads targeting

The core goal of classification is to predict a category or class y from some inputs x.

Let’s start Building our Model

Our Problem is To Predict if the Customer will purchase our Product or Not ?

We Have the dataset of the customers with all the necessary data (Age , Estimated_Salary , Gender ,User_Id, and Purchased or not )

Our Mission is Train Machine learning Model with Logistic_Regression to predict the action of the customers (To Buy or not To Buy .. )

What is Logistic Regression ?

. A Logistic regression maps a continuous x to a “binary” y

. We can use Logistic regression to make “category” or “true/false” decisions from data.

Example of application :

Logistic Regression: Given a set of medical inputs, does a patient have cancer? (Yes/No)

Don’t’ Worry if you don’t like Maths , you are not supposed to know the Mathematics equations

All What we have to do it to know how to implement the Logistic_Regression Classifier with scikit-learn

Let’ start Coding

Import the necessary Libraries

# Imporitng the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

Load the Dataset (Social_Network_Ads.csv)

dataset = pd.read_csv('Social_Network_Ads.csv');
X = dataset.iloc[:,[2,3]].values
Y = dataset.iloc[:,4].values

We need to Provide 2 Features for our Model : Age && Estimated_Salary

# Splitting the Data into Training Set and Testing Set
from sklearn.model_selection import train_test_split
X_Train ,X_Test , Y_Train,Y_Test= train_test_split(X,Y, test_size=0.25,random_state=0)

Now let’s Scale our Data

# Scaling the data *************
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train = scaler.fit_transform(X_Train)
X_Test  =scaler.transform(X_Test)

Now let’s Prepare our Classifier :sklearn.linear_model.LogisticRegression

and Train it with Our Data (X_Train Y_Train )

from sklearn import linear_model
#Prepare our Classifier*********
classifier = linear_model.LogisticRegression(C=1e5)
#Train our classifier 
classifier.fit(X_Train,Y_Train);

Now let’s Make Our Prediction with Classifier.predict

y_predicted = classifier.predict(X_Test)

I tried in This Blog to Explain for You How To make a Machine Learning Model , Train it with Data , and make your Prediction

I have used Logistic_Regression as a Classifier , there is other Classifier we can use them for the classification Task like (SVM, Naive-Bayes , Decision_Tree , K-Nearest-Neighbor and Random Forest )

Making mistakes is a lot better than not doing anything

You Can fin the Full code source Here :

Follow me in Twitter for code Updates

Thanks For Your Feed Back