CW_task4_Decision_trees

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import confusion_matrix, accuracy_score
from sklearn.metrics import make_scorer, f1_score
​
# Load the dataset
data = np.load('C:/Users/print15207/MATLAB Drive/Print HVDC/Smartgrid CW/train_dataset.npy', allow_pickle=True)
​
# Extract features and labels
x = data.item()['feature']
y = data.item()['label']
​
x1=x[:4800] #Only classify between class 0 (normal measurement) and class 1 (FDI attack measurement)
y1=y[:4800]
​
# Split the data into training and testing sets
x_train, x_test, y_train, y_test = train_test_split(x1, y1, test_size=0.325, random_state=42)
​
# Print the shape of training and testing sets
print("Training set size:", x_train.shape)
print("Testing set size:", x_test.shape)
​
# Setting maximum depth and minimum samples per leaf
pruned_model = DecisionTreeClassifier(max_depth=10, min_samples_leaf=4, random_state=42)
pruned_model.fit(x_train, y_train)
# Make predictions on the test set
test_predict = pruned_model.predict(x_test)
​
# Evaluate the model
accuracy = accuracy_score(y_test, test_predict)
# y_test set is the true value and test_predict set is the predicted value
print("accuracy on test set: ", accuracy)
​
# Evaluate the model using TPR and FPR
conf_matrix = confusion_matrix(y_test, test_predict)
print("Confusion Matrix:")
print(conf_matrix)
​
TN, FP, FN, TP = conf_matrix.ravel()
​
# Calculate TPR and FPR
TPR = TP / (TP + FN)
FPR = FP / (FP + TN)
​
# Print or use the metrics
print("True Positive Rate (TPR):", TPR)
print("False Positive Rate (FPR):", FPR)
​
# Define F1 score as the evaluation metric for hyperparameter tuning
scorer = make_scorer(f1_score)
test_f1_score = f1_score(y_test, test_predict)
print("F1 score on test set: ",test_f1_score)
​
​
​#Result with elapsed time: 2 seconds:
#Training set size: (3240, 34)
#Testing set size: (1560, 34)
#accuracy on test set:  0.9846153846153847
#Confusion Matrix:
[[789  12]
 [ 12 747]]
#True Positive Rate (TPR): 0.9841897233201581
#False Positive Rate (FPR): 0.0149812734082397
#F1 score on test set:  0.9841897233201581