import pandas as pd 
# Load the dataset 
df = pd.read_csv('Iris.csv') 
# Display the first few rows and basic information 
print(df.head()) 
print(df.describe()) 
print(df.info()) 
from sklearn.model_selection import train_test_split 
from sklearn.preprocessing import LabelEncoder 
# Encode the target variable 
label_encoder = LabelEncoder() 
df['Species'] = label_encoder.fit_transform(df['Species']) 
# Separate features and target variable 
X = df.drop(columns=['Species']) 
y = df['Species'] 
# Split the data 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) 
from sklearn.tree import DecisionTreeClassifier 
from sklearn.metrics import accuracy_score 
# Initialize the Decision Tree Classifier 
model = DecisionTreeClassifier(random_state=42) 
model.fit(X_train, y_train) 
# Predict on the test set 
y_pred = model.predict(X_test) 
# Estimate the accuracy of the model 
accuracy = accuracy_score(y_test, y_pred) 
print("Accuracy of Decision Tree Classifier:", accuracy) 
from sklearn.tree import plot_tree 
import matplotlib.pyplot as plt 
# Plot the decision tree 
plt.figure(figsize=(12, 8)) 
plot_tree(model, feature_names=X.columns, class_names=label_encoder.classes_, filled=True) 
plt.title("Decision Tree Structure") 
plt.show() 
importances = model.feature_importances_ 
feature_names = X.columns 
# Plot feature importances 
plt.figure(figsize=(8, 6)) 
plt.barh(feature_names, importances, color='skyblue') 
plt.xlabel("Feature Importance") 
plt.ylabel("Feature") 
plt.title("Feature Importances in Decision Tree Model") 
plt.show() 
import numpy as np 
from matplotlib.colors import ListedColormap 
# Define a function to plot decision boundaries 
def plot_decision_boundary(model, X, y): 
# Set up the grid for plotting decision boundaries 
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1 
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1 
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02), 
np.arange(y_min, y_max, 0.02)) 
# Predict over the grid 
Z = model.predict(np.c_[xx.ravel(), yy.ravel()]) 
Z = Z.reshape(xx.shape) 
# Plot the contour and training examples 
plt.figure(figsize=(10, 6)) 
plt.contourf(xx, yy, Z, alpha=0.3, cmap=ListedColormap(('red', 'green', 'blue'))) 
scatter = plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=ListedColormap(('red', 'green', 'blue'))) 
plt.xlabel("Petal Length") 
plt.ylabel("Petal Width") 
plt.title("Decision Boundary (Petal Length vs Petal Width)") 
plt.legend(handles=scatter.legend_elements()[0], labels=label_encoder.classes_) 
plt.show() 
# Extract PetalLength and PetalWidth for visualization 
X_2d_train = X_train[['PetalLengthCm', 'PetalWidthCm']].values 
y_train_2d = y_train.values 
# Train a new model on these two features for simplicity 
model_2d = DecisionTreeClassifier(random_state=42) 
model_2d.fit(X_2d_train, y_train_2d) 
# Plot the decision boundary 
plot_decision_boundary(model_2d, X_2d_train, y_train_2d)