Introduction to Machine Learning with Scikit‑learn

Machine Learning Overview

Scikit‑learn (sklearn) is the most popular library for classical machine learning in Python.

Installing scikit‑learn

pip install scikit-learn

Typical ML workflow

1. Define problem (regression, classification, clustering).
2. Load & preprocess data (cleaning, scaling, encoding).
3. Split into training and test sets.
4. Select a model (e.g., LinearRegression).
5. Train (model.fit).
6. Evaluate (metrics).
7. Tune hyperparameters.
8. Deploy.

Example: Simple Linear Regression

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

X = df[['feature1', 'feature2']]
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = LinearRegression()
model.fit(X_train, y_train)

preds = model.predict(X_test)
rmse = mean_squared_error(y_test, preds, squared=False)
print('RMSE:', rmse)

Key concepts

• Estimator: any object with a fit method.
• Transformer: implements fit and transform (e.g., StandardScaler).
• Pipeline: chains transformers and an estimator.