Scikit-Learn in Practice

pip install scikit-learn numpy pandas matplotlib

# Verify installation
python -c "import sklearn; print(sklearn.__version__)"
# → 1.4.0

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

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, random_state=42)

model = KNeighborsClassifier(n_neighbors=3)
model.fit(X_train, y_train)
print(f"Accuracy: {model.score(X_test, y_test):.2%}")

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.pipeline import Pipeline

# 1. Load data
from sklearn.datasets import load_breast_cancer
X, y = load_breast_cancer(return_X_y=True)

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

# 3. Build pipeline (prevents data leakage)
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('classifier', RandomForestClassifier(n_estimators=100, random_state=42))
])

# 4. Train
pipeline.fit(X_train, y_train)

# 5. Evaluate
y_pred = pipeline.predict(X_test)
print(classification_report(y_test, y_pred))
print("Confusion Matrix:")
print(confusion_matrix(y_test, y_pred))

from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestClassifier

param_grid = {
    'n_estimators': [50, 100, 200],
    'max_depth': [None, 5, 10],
    'min_samples_split': [2, 5]
}

grid_search = GridSearchCV(
    RandomForestClassifier(random_state=42),
    param_grid,
    cv=5,
    scoring='f1',
    n_jobs=-1  # use all CPU cores
)

grid_search.fit(X_train, y_train)
print(f"Best params: {grid_search.best_params_}")
print(f"Best CV F1: {grid_search.best_score_:.3f}")
best_model = grid_search.best_estimator_

import joblib

# Save model to disk
joblib.dump(pipeline, 'my_model.pkl')

# Load model later (in production)
loaded_model = joblib.load('my_model.pkl')
predictions = loaded_model.predict(new_data)