train_model.py

import pickle
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

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

# Split the dataset (80% training, 20% testing)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Build a pipeline: scaler + classifier (this ensures any future input is processed in the same way)
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', RandomForestClassifier(random_state=42))
])

# Train the model
pipeline.fit(X_train, y_train)

# Evaluate the model
y_pred = pipeline.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f"Test Accuracy: {accuracy:.2f}")

# Save the entire pipeline to disk
with open("iris_pipeline.pkl", "wb") as f:
    pickle.dump(pipeline, f)