Upload Volumetric.py File

Volumetric.py

+# Importing the libraries
+
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.impute import SimpleImputer
+from sklearn.metrics import accuracy_score
+from sklearn.metrics import f1_score
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import precision_score
+from sklearn.metrics import recall_score
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeClassifier
+
+
+# Importing the dataset
+
+train = pd.read_csv("/Users/ASHEN/Education/SLIIT/Research/Wanheda_Server/MobileBotNet/packet_data.csv",index_col=0,low_memory=False)
+
+train.shape
+
+
+# Feature Scaling
+
+from sklearn import preprocessing 
+for f in train.columns: 
+    if train[f].dtype=='object': 
+        label = preprocessing.LabelEncoder() 
+        label.fit(list(train[f].values)) 
+        train[f] = lbl.transform(list(train[f].values))
+train.fillna((-999), inplace=True) 
+train=np.array(train) 
+train = train.astype(float)
+
+Y = train['Label']
+X = train.drop("Label",axis=1)
+
+print(train.shape)
+print(X.shape)
+print(Y.shape)
+
+
+# Spliting the dataset into the training set and test set
+
+seed = 7
+test_size = 0.33
+X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=test_size, random_state=seed)
+
+print(X_train.shape)
+print(y_train.shape)
+print(X_test.shape)
+print(y_test.shape)
+
+
+# Fitting Decision Tree to the training set
+
+model=DecisionTreeClassifier(max_depth=5,random_state=0)
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+
+print(model)
+
+
+# Plotting the tree, here it should access graph's first element
+
+from sklearn import tree
+from sklearn.externals.six import StringIO  
+import pydot 
+
+dot_data = StringIO() 
+tree.export_graphviz(model, out_file=dot_data) 
+graph = pydot.graph_from_dot_data(dot_data.getvalue()) 
+
+graph[0].write_pdf("tree.pdf")
+
+
+# Predicting the data[round(value) for value in y_pred]
+
+y_pred = model.predict(X_test)
+
+
+# Creating confusion metrics to check the performance of algorithm
+
+cm=confusion_matrix(y_test, y_pred)
+print("confusion matrix:\n",cm)
+
+
+# Accuracy
+
+accuracy = accuracy_score(y_test, y_pred)
+print("accuracy:",accuracy)
+
+
+# F1 Score
+
+f1score=f1_score(y_test, y_pred)
+print("f1_score:",f1score)
+
+
+# Precision Score
+
+pr=precision_score(y_test,y_pred)
+print("Precision:",pr)
+
+
+# Recall Score
+
+rs=recall_score(y_test,y_pred)
+print("Recall_score:",rs)
+
+
+# Misclassified Samples
+
+misclassified_samples = X_test[y_test != y_pred]
+mc=misclassified_samples.shape[0]
+print("Misclassified :",mc)
\ No newline at end of file