Classifier_Problem

# importing libraries  
import numpy as nm  
import matplotlib.pyplot as plt  
import pandas as pd  
  
#importing datasets  
data_set= pd.read_csv('phone.csv')  
  
#Extracting Independent and dependent Variable  
x= data_set.iloc[:,[1,2]].values  
y= data_set.iloc[:,3].values  
  
# Splitting the dataset into training and test set.  
from sklearn.model_selection import train_test_split  
x_train, x_test, y_train, y_test= train_test_split(x, y, test_size= 0.20, random_state=0)  
  
#feature Scaling  
from sklearn.preprocessing import StandardScaler    
st_x= StandardScaler()    
x_train= st_x.fit_transform(x_train)    
x_test= st_x.transform(x_test)

#Fitting K-NN classifier to the training set  
from sklearn.neighbors import KNeighborsClassifier  
classifier= KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2 )  
classifier.fit(x_train, y_train)

#Predicting the test set result  
y_pred= classifier.predict(x_test)  

#Creating the Confusion matrix  
# Step 7 - Confusion Matrix
from sklearn import metrics
cm = metrics.confusion_matrix(y_test, y_pred) 
print(cm)
accuracy = metrics.accuracy_score(y_test, y_pred) 
print("Accuracy score:",accuracy)
precision = metrics.precision_score(y_test, y_pred) 
print("Precision score:",precision)
recall = metrics.recall_score(y_test, y_pred) 
print("Recall score:",recall)

#Visualizing the training set result  
from matplotlib.colors import ListedColormap  
x_set, y_set = x_train, y_train  
x1, x2 = nm.meshgrid(nm.arange(start = x_set[:, 0].min() - 1, stop = x_set[:, 0].max() + 1, step  =0.01),  
nm.arange(start = x_set[:, 1].min() - 1, stop = x_set[:, 1].max() + 1, step = 0.01))  
plt.contourf(x1, x2, classifier.predict(nm.array([x1.ravel(), x2.ravel()]).T).reshape(x1.shape),  
alpha = 0.75, cmap = ListedColormap(('red','green' )))  
plt.xlim(x1.min(), x1.max())  
plt.ylim(x2.min(), x2.max())  
for i, j in enumerate(nm.unique(y_set)):  
    plt.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],  
        c = ListedColormap(('red', 'green'))(i), label = j)  
plt.title('K-NN Algorithm (Training set)')  
plt.xlabel('Age')  
plt.ylabel('Estimated Salary')  
plt.legend()  
plt.show()  

#Visualizing the test set result  
from matplotlib.colors import ListedColormap  
x_set, y_set = x_test, y_test  
x1, x2 = nm.meshgrid(nm.arange(start = x_set[:, 0].min() - 1, stop = x_set[:, 0].max() + 1, step  =0.01),  
nm.arange(start = x_set[:, 1].min() - 1, stop = x_set[:, 1].max() + 1, step = 0.01))  
plt.contourf(x1, x2, classifier.predict(nm.array([x1.ravel(), x2.ravel()]).T).reshape(x1.shape),  
alpha = 0.75, cmap = ListedColormap(('red','green' )))  
plt.xlim(x1.min(), x1.max())  
plt.ylim(x2.min(), x2.max())  
for i, j in enumerate(nm.unique(y_set)):  
    plt.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],  
        c = ListedColormap(('red', 'green'))(i), label = j)  
plt.title('K-NN algorithm(Test set)')  
plt.xlabel('Age')  
plt.ylabel('Estimated Salary')  
plt.legend()  
plt.show()  

training_accuracy  = []  
test_accuracy = []
for i in range(1, 21):
    knn = KNeighborsClassifier(n_neighbors = i)
    knn.fit(x_train,y_train)
    training_accuracy.append(knn.score(x_train,y_train))
    test_accuracy.append(knn.score(x_test,y_test))

plt.figure()
plt.plot(range(1, 21), training_accuracy, label='Training Accuarcy')
plt.plot(range(1, 21), test_accuracy, label='Testing Accuarcy')
plt.title('Training Accuracy vs Test Accuracy')
plt.xlabel('n_neighbors')
plt.ylabel('Accuracy')
plt.legend(loc='best')
plt.show()