train_model.py

"""
Train a Random Forest Classifier on the Iris dataset.
Dataset source: UCI Machine Learning Repository
https://archive.ics.uci.edu/dataset/53/iris
"""

import joblib
import numpy as np
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
from sklearn.preprocessing import StandardScaler

# Load dataset
iris = load_iris()
X, y = iris.data, iris.target

# Split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

# Scale
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled  = scaler.transform(X_test)

# Train
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train_scaled, y_train)

# Evaluate
y_pred = model.predict(X_test_scaled)
accuracy = accuracy_score(y_test, y_pred)
print(f"Accuracy: {accuracy * 100:.2f}%")
print(classification_report(y_test, y_pred, target_names=iris.target_names))

# Save
joblib.dump(model,  "model/iris_model.pkl")
joblib.dump(scaler, "model/scaler.pkl")
joblib.dump(iris.target_names.tolist(), "model/class_names.pkl")
print("Model, scaler, and class names saved.")