scikit-learn-machine-learning

scikit-learn

Overview

scikit-learn is the standard Python library for classical machine learning. It provides consistent APIs for supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, and preprocessing, with seamless integration into NumPy/pandas workflows.

When to Use

• Building classification models for labeled data (spam detection, disease diagnosis, species identification)
• Predicting continuous outcomes with regression (price prediction, dose-response modeling)
• Clustering unlabeled data into groups (patient stratification, gene expression clusters)
• Reducing dimensionality for visualization or feature engineering (PCA, t-SNE on multi-omics data)
• Evaluating and comparing model performance with cross-validation
• Tuning hyperparameters systematically (grid search, random search)
• Building reproducible ML pipelines with preprocessing and modeling steps
• For deep learning tasks (images, NLP), use pytorch or transformers instead
• For large-scale gradient boosting, use xgboost or lightgbm instead

Prerequisites

• Python packages: scikit-learn, numpy, pandas
• Optional: matplotlib, seaborn for visualization
• Data: Tabular data as NumPy arrays or pandas DataFrames

pip install scikit-learn numpy pandas matplotlib seaborn

Quick Start

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report
from sklearn.datasets import load_breast_cancer

# Load dataset, split, train, evaluate in 10 lines
X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

clf = RandomForestClassifier(n_estimators=100, random_state=42)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)

print(f"Accuracy: {accuracy_score(y_test, y_pred):.3f}")
print(classification_report(y_test, y_pred, target_names=["malignant", "benign"]))

Core API

Module 1: Data Preprocessing

Scaling, encoding, imputation, and feature engineering.

from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
import numpy as np

# Scaling: zero mean, unit variance
X = np.array([[1, 2], [3, 4], [5, 6]])
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
print(f"Mean: {X_scaled.mean(axis=0)}, Std: {X_scaled.std(axis=0)}")
# Mean: [0. 0.], Std: [1. 1.]

# Imputation: fill missing values
X_missing = np.array([[1, np.nan], [3, 4], [np.nan, 6]])
imputer = SimpleImputer(strategy="median")
X_filled = imputer.fit_transform(X_missing)
print(f"Filled:\n{X_filled}")

from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder, LabelEncoder

# One-hot encoding for nominal categories
enc = OneHotEncoder(sparse_output=False, handle_unknown="ignore")
X_cat = np.array([["red"], ["blue"], ["green"], ["red"]])
X_encoded = enc.fit_transform(X_cat)
print(f"Categories: {enc.categories_}")
print(f"Encoded shape: {X_encoded.shape}")  # (4, 3)

Module 2: Supervised Learning — Classification

Classifiers for discrete target prediction.

from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

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

# Compare classifiers
classifiers = {
    "LogisticRegression": LogisticRegression(max_iter=200),
    "RandomForest": RandomForestClassifier(n_estimators=100, random_state=42),
    "SVM": SVC(kernel="rbf", C=1.0),
    "GradientBoosting": GradientBoostingClassifier(n_estimators=100, random_state=42),
}
for name, clf in classifiers.items():
    clf.fit(X_train, y_train)
    print(f"{name}: accuracy = {clf.score(X_test, y_test):.3f}")

Module 3: Supervised Learning — Regression

Regressors for continuous target prediction.

from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet
from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets import make_regression
from sklearn.metrics import mean_squared_error, r2_score

X, y = make_regression(n_samples=200, n_features=10, noise=10, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

models = {
    "Linear": LinearRegression(),
    "Ridge": Ridge(alpha=1.0),
    "Lasso": Lasso(alpha=0.1),
    "RandomForest": RandomForestRegressor(n_estimators=100, random_state=42),
}
for name, model in models.items():
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    print(f"{name}: RMSE={mean_squared_error(y_test, y_pred, squared=False):.2f}, R²={r2_score(y_test, y_pred):.3f}")

Module 4: Unsupervised Learning — Clustering

Clustering algorithms for unlabeled data.

from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering
from sklearn.metrics import silhouette_score
from sklearn.datasets import make_blobs

X, y_true = make_blobs(n_samples=300, centers=4, random_state=42)

# K-Means with elbow method
for k in [2, 3, 4, 5, 6]:
    km = KMeans(n_clusters=k, random_state=42, n_init=10)
    labels = km.fit_predict(X)
    sil = silhouette_score(X, labels)
    print(f"k={k}: silhouette={sil:.3f}, inertia={km.inertia_:.1f}")

# DBSCAN — no need to specify k
from sklearn.cluster import DBSCAN

db = DBSCAN(eps=0.5, min_samples=5)
labels = db.fit_predict(X)
n_clusters = len(set(labels)) - (1 if -1 in labels else 0)
n_noise = (labels == -1).sum()
print(f"DBSCAN: {n_clusters} clusters, {n_noise} noise points")

Module 5: Dimensionality Reduction

PCA, t-SNE, and other methods for visualization and feature reduction.

from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.datasets import load_digits

X, y = load_digits(return_X_y=True)
print(f"Original shape: {X.shape}")  # (1797, 64)

# PCA — preserve 95% variance
pca = PCA(n_components=0.95)
X_pca = pca.fit_transform(X)
print(f"PCA: {X_pca.shape[1]} components, explained variance: {pca.explained_variance_ratio_.sum():.3f}")

# t-SNE — 2D visualization
tsne = TSNE(n_components=2, perplexity=30, random_state=42)
X_tsne = tsne.fit_transform(X)
print(f"t-SNE shape: {X_tsne.shape}")  # (1797, 2)

Module 6: Model Evaluation & Selection

Cross-validation, metrics, hyperparameter tuning.

from sklearn.model_selection import cross_val_score, GridSearchCV, StratifiedKFold
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)

# Cross-validation
clf = RandomForestClassifier(n_estimators=100, random_state=42)
scores = cross_val_score(clf, X, y, cv=StratifiedKFold(5), scoring="accuracy")
print(f"CV accuracy: {scores.mean():.3f} ± {scores.std():.3f}")

# Hyperparameter tuning with GridSearchCV
param_grid = {
    "n_estimators": [50, 100, 200],
    "max_depth": [5, 10, None],
    "min_samples_split": [2, 5]
}
grid = GridSearchCV(
    RandomForestClassifier(random_state=42),
    param_grid, cv=5, scoring="accuracy", n_jobs=-1
)
grid.fit(X, y)
print(f"Best params: {grid.best_params_}")
print(f"Best score: {grid.best_score_:.3f}")

Module 7: Pipelines

Chain preprocessing and models; prevent data leakage.

from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.ensemble import GradientBoostingClassifier

# Mixed-type preprocessing
numeric_features = ["age", "i