knn_mine.py

import numpy as np
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn import metrics
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt

# Importing the dataset
dataset = pd.read_csv('printing.csv')
X = dataset.iloc[:, [0, 1]].values
y = dataset.iloc[:, 2].values

# Splitting the dataset into the Training set and Test set and scaling it
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.30, random_state=10)
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#Create a knn Classifier with a defined number of neighbors
classifier = KNeighborsClassifier(n_neighbors=2)

#Train the model using the training sets
classifier.fit(X_train, y_train)

#Predict the response for test dataset
y_pred = classifier.predict(X_test)

# Model Precision: what percentage of positive tuples are labeled as such?
#print("Precision:", metrics.precision_score(y_test, y_pred))

# Model Recall: what percentage of positive tuples are labelled as such?
#print("Recall:", metrics.recall_score(y_test, y_pred))

# Making the Confusion Matrix
print(confusion_matrix(y_test, y_pred))
print(classification_report(y_test, y_pred))

# Visualising the Training set results
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(('red', '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],
                color=ListedColormap(('red', 'green'))(i), label=j)
plt.title('Classifier (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

# Visualising the Test set results
X_set, y_set = X_test, y_test
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(('red', '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],
                color=ListedColormap(('red', 'green'))(i), label=j)
plt.title('Classifier (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()


error = []
# Calculating error for K values between 1 and 40
for i in range(1, 6):
    knn = KNeighborsClassifier(n_neighbors=i)
    knn.fit(X_train, y_train)
    pred_i = knn.predict(X_test)
    error.append(np.mean(pred_i != y_test))
plt.figure(figsize=(12, 6))
plt.plot(range(1, 6), error, color='red', linestyle='dashed', marker='o',
         markerfacecolor='blue', markersize=10)
plt.title('Error Rate K Value')
plt.xlabel('K Value')
plt.ylabel('Mean Error')
plt.show()