Your First Machine Learning Model in 30 Minutes

We'll train a classifier on the classic Iris dataset. By the end you'll have predicted flower species from petal measurements — and understood every step.

Step 1 — Load the data

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

X, y = load_iris(return_X_y=True, as_frame=True)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)

We split 80/20 so we can evaluate the model on data it has never seen. random_state=42 makes the split reproducible.

Step 2 — Train

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

A Random Forest is a great default: it works out of the box, handles non-linearities, and rarely overfits with sensible defaults.

Step 3 — Evaluate

from sklearn.metrics import accuracy_score, classification_report

y_pred = model.predict(X_test)
print(f"Accuracy: {accuracy_score(y_test, y_pred):.2%}")
print(classification_report(y_test, y_pred))

You should see ~97% accuracy. The classification report breaks it down per species — precision, recall and F1.

What you just did

• Loaded a real dataset and split it into train/test.
• Trained a tree-based classifier with one line.
• Measured how well it generalizes to new data.

Every supervised ML project follows this exact loop. The hard parts are choosing the right metric, cleaning real-world data, and tuning the model — not the syntax.