iris_classification.py

# iris_classification.py

from sklearn import datasets
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, confusion_matrix

# Step 1: Load the iris dataset
iris = datasets.load_iris()
iris_data = pd.DataFrame(data=iris.data, columns=iris.feature_names)
iris_data['species'] = iris.target
iris_data['species'] = iris_data['species'].map({0: 'setosa', 1: 'versicolor', 2: 'virginica'})

# Step 2: Visualize the data
sns.pairplot(iris_data, hue='species')
plt.show()

# Step 3: Split the data into training and testing sets
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Step 4: Train the Decision Tree model
model = DecisionTreeClassifier()
model.fit(X_train, y_train)

# Step 5: Make predictions on the test set
y_pred = model.predict(X_test)

# Step 6: Evaluate the model
print("Accuracy:", accuracy_score(y_test, y_pred))
cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues')
plt.xlabel('Predicted')
plt.ylabel('True')
plt.show()