Replace IT17106702.py

IT17106702.py

@@ -2,42 +2,50 @@
 import numpy as np
 import matplotlib.pyplot as plt
 import pandas as pd
+from sklearn.impute import SimpleImputer
 
 # Importing the dataset
-dataset = pd.read_csv('packet_data.csv')
-X = dataset.iloc[:, :-1] .values
+dataset = pd.read_csv("/Users/harithachanuka/Documents/SLIIT/Research/Harry/Wanheda_Server/MobileBotNet/packet_data.csv", encoding='latin-1')
+X = dataset.iloc[:, [1,3]].values
 y = dataset.iloc[:, 5].values
 
-#Encoding categorical data
+# datasetnew = pd.read_csv("/Users/harithachanuka/Documents/SLIIT/Research/Implementation/new.csv", encoding='latin-1')
+# Xnw = datasetnew.iloc[:, :5].values
+
+
+#Encoding categorical data-ForX
 from sklearn.preprocessing import LabelEncoder, OneHotEncoder
 from sklearn.compose import ColumnTransformer
-labelencoder_X_T = LabelEncoder()
-X[:, 0] = labelencoder_X_T.fit_transform(X[:, 0])
+
 labelencoder_X_S = LabelEncoder()
-X[:, 1] = labelencoder_X_S.fit_transform(X[:, 1])
-labelencoder_X_D = LabelEncoder()
-X[:, 2] = labelencoder_X_D.fit_transform(X[:, 2])
+X[:, 0] = labelencoder_X_S.fit_transform(X[:, 0])
+#labelencoder_X_D = LabelEncoder()
+# X[:, 2] = labelencoder_X_D.fit_transform(X[:, 2])
 labelencoder_X_P = LabelEncoder()
-X[:, 3] = labelencoder_X_P.fit_transform(X[:, 3])
-ct = ColumnTransformer([("Source", OneHotEncoder(), [1])], remainder='passthrough')
-X = ct.fit_transform(X).toarray()
-ct2 = ColumnTransformer([("Destination", OneHotEncoder(), [72])], remainder='passthrough')
-X = ct2.fit_transform(X)
-ct3 = ColumnTransformer([("Protocol", OneHotEncoder(), [118])], remainder='passthrough')
-X = ct3.fit_transform(X)
+X[:, 1] = labelencoder_X_P.fit_transform(X[:, 1])
+# ct = ColumnTransformer([("Source", OneHotEncoder(), [1])], remainder = 'passthrough')
+# X = ct.fit_transform(X).toarray()
+# ct2 = ColumnTransformer([("Destination", OneHotEncoder(), [72])], remainder = 'passthrough')
+# X = ct2.fit_transform(X)
+# ct3 = ColumnTransformer([("Protocol", OneHotEncoder(), [118])], remainder = 'passthrough')
+# X = ct3.fit_transform(X)
 
 labelencoder_y = LabelEncoder()
 y = labelencoder_y.fit_transform(y)
 
-#Splitting the data set into the training set and test set
+# 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)
+# print(X_test)
+# print(y_train)
+# print(X_train)
 
-#Feature scaling
+# Feature Scaling
 from sklearn.preprocessing import StandardScaler
 sc_X = StandardScaler()
 X_train = sc_X.fit_transform(X_train)
-X_test = sc_X.fit_transform(X_test)
+X_test = sc_X.transform(X_test)
 
 # Fitting classifier to the Training set
 from sklearn.naive_bayes import GaussianNB
@@ -47,42 +55,8 @@ classifier.fit(X_train, y_train)
 # Predicting the Test set results
 y_pred = classifier.predict(X_test)
 
-# Making the Confusion Matrix
+
 from sklearn.metrics import confusion_matrix
 cm = confusion_matrix(y_test, y_pred)
 
-# Visualising the Training set results
-from matplotlib.colors import ListedColormap
+#
\ No newline at end of file
-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('BotNet (Training set)')
-plt.xlabel('Time Source Dest & Protocol')
-plt.ylabel('Malicious Or Not')
-plt.legend()
-plt.show()
-
-# Visualising 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('Naive Bayes (Test set)')
-plt.xlabel('Age')
-plt.ylabel('Estimated Salary')
-plt.legend()
-plt.show()