KNN done

Part 3 - Classification/Section 15 - K-Nearest Neighbors (K-NN)/KNN.py

@@ -0,0 +1,69 @@
+#Simple Linear Regression
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importing the dataset
+dataset = pd.read_csv('Social_Network_Ads.csv')
+X = dataset.iloc[:, [2,3]].values
+y = dataset.iloc[:, 4].values
+
+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)
+
+#Feature Scaling
+from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.transform(X_test)
+
+#Fitting Logistic Regression
+from sklearn.neighbors import KNeighborsClassifier
+classifier = KNeighborsClassifier(n_neighbors = 5,metric = 'minkowski', p=2)
+classifier.fit(X_train, y_train)
+
+#Predicting the results
+y_pred = classifier.predict(X_test)
+
+#Making the confusion matrix
+from sklearn.metrics import confusion_matrix
+cm = confusion_matrix(y_test, y_pred)
+print(cm)
+
+
+#Visualizing the training set results
+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(('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],
+                c = ListedColormap(('red','green'))(i), label = j)
+plt.title('Logistic Regression (Training Set)')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+plt.show()
+
+
+#Visualizing the test set results
+from matplotlib.colors import ListedColormap
+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],
+                c = ListedColormap(('red','green'))(i), label = j)
+plt.title('Logistic Regression (Training Set)')
+plt.xlabel('Age')
+plt.ylabel('Estimated Salary')
+plt.legend()
+plt.show()