import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
# Load the dataset
file_path = "C:/Users/ECE/Desktop/AIML-3RD YEAR/diabetes 3.csv"
df = pd.read_csv(file_path)
# Define features and target
X = df.drop(columns=['label'])
y = df['label']
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Decision Tree Classifier
dt_model = DecisionTreeClassifier(random_state=42)
dt_model.fit(X_train, y_train)
y_pred_dt = dt_model.predict(X_test)
print("Decision Tree Accuracy:", accuracy_score(y_test, y_pred_dt))
print("Decision Tree Classification Report:\n", classification_report(y_test, y_pred_dt))
# Plot the Decision Tree
plt.figure(figsize=(20,10))
plot_tree(dt_model, feature_names=X.columns, class_names=['Non-Diabetic', 'Diabetic'], filled=True,
fontsize=10)
plt.show()
# Random Forest Classifier
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
rf_model.fit(X_train, y_train)
y_pred_rf = rf_model.predict(X_test)
print("Random Forest Accuracy:", accuracy_score(y_test, y_pred_rf))
print("Random Forest Classification Report:\n", classification_report(y_test, y_pred_rf))
