K-Nearest Neighbors (K-NN)

Importing the libraries

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

Importing the dataset

df = pd.read_csv('Social_Network_Ads.csv')
df.head(10)

	Age	EstimatedSalary	Purchased
0	19	19000	0
1	35	20000	0
2	26	43000	0
3	27	57000	0
4	19	76000	0
5	27	58000	0
6	27	84000	0
7	32	150000	1
8	25	33000	0
9	35	65000	0

X = df.iloc[:, :-1].values
y = df.iloc[:, -1].values

Splitting the dataset into the Training set 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 = 0.25, random_state = 0)

print(X_train[0:3])

[[    44  39000]
 [    32 120000]
 [    38  50000]]

print(y_train[0:3])

[0 1 0]

Feature Scaling

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

print(X_train[0:3])

[[ 0.58164944 -0.88670699]
 [-0.60673761  1.46173768]
 [-0.01254409 -0.5677824 ]]

Training the K-NN model on the Training set

from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
classifier.fit(X_train, y_train)

KNeighborsClassifier()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Predicting a new result

Predict whether a person of age 30 and salary 87000 will purchase a product

print(classifier.predict(sc.transform([[30,87000]])))

[0]

Predicting the Test set results

y_pred = classifier.predict(X_test)
print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.reshape(len(y_test),1)),1))

Making the Confusion Matrix

from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)

[[64  4]
 [ 3 29]]

#Compute Accuracy
accuracy_score(y_test, y_pred)

0.93

Visualising the Training set results

colors = ['#FA8072', '#1E90FF']

from matplotlib.colors import ListedColormap
X_set, y_set = sc.inverse_transform(X_train), y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 10, stop = X_set[:, 0].max() + 10, step = 0.5),
                     np.arange(start = X_set[:, 1].min() - 1000, stop = X_set[:, 1].max() + 1000, step = 0.5))
plt.contourf(X1, X2, classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(colors))
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], 
            color = ListedColormap(colors)(i), label = j)
plt.title('K-NN (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

Visualising the Test set results

from matplotlib.colors import ListedColormap
X_set, y_set = sc.inverse_transform(X_test), y_test
# Create a grid of points
X1, X2 = np.meshgrid(
    np.arange(start=X_set[:, 0].min() - 1, stop=X_set[:, 0].max() + 1, step=0.5),
    np.arange(start=X_set[:, 1].min() - 1, stop=X_set[:, 1].max() + 1, step=0.5)
)
# Predict for each point on the grid
Z = classifier.predict(sc.transform(np.array([X1.ravel(), X2.ravel()]).T)).reshape(X1.shape)
# Plot the decision boundary
plt.contourf(X1, X2, Z, alpha=0.75, cmap = ListedColormap(colors) )
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
# Define colors for scatter plot
colors = colors
# Plot the test set points
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], 
            color = ListedColormap(colors)(i), label = j)
# Add titles and labels
plt.title('K-NN (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()