Scikit Learn Machine Learning

pip install scikit-learn numpy pandas matplotlib seaborn

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"]))

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)

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}")

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}")

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")

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)

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}")

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", "income"]
categorical_features = ["gender", "occupation"]

preprocessor = ColumnTransformer([
    ("num", Pipeline([
        ("imputer", SimpleImputer(strategy="median")),
        ("scaler", StandardScaler())
    ]), numeric_features),
    ("cat", Pipeline([
        ("imputer", SimpleImputer(strategy="most_frequent")),
        ("onehot", OneHotEncoder(handle_unknown="ignore"))
    ]), categorical_features),
])

pipe = Pipeline([
    ("preprocessor", preprocessor),
    ("classifier", GradientBoostingClassifier(random_state=42))
])
# pipe.fit(X_train, y_train); pipe.predict(X_test)
print("Pipeline steps:", [name for name, _ in pipe.steps])

import pandas as pd
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report
from sklearn.datasets import load_breast_cancer

# Load data
X, y = load_breast_cancer(return_X_y=True, as_frame=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)

# Build pipeline
pipe = Pipeline([
    ("scaler", StandardScaler()),
    ("clf", RandomForestClassifier(n_estimators=200, random_state=42))
])

# Cross-validate
cv_scores = cross_val_score(pipe, X_train, y_train, cv=5, scoring="f1")
print(f"CV F1: {cv_scores.mean():.3f} ± {cv_scores.std():.3f}")

# Final evaluation
pipe.fit(X_train, y_train)
y_pred = pipe.predict(X_test)
print(classification_report(y_test, y_pred))

from sklearn.datasets import make_blobs
from sklearn.preprocessing import StandardScaler
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.metrics import silhouette_score
import matplotlib.pyplot as plt

# Generate and scale data
X, _ = make_blobs(n_samples=500, centers=4, random_state=42)
X_scaled = StandardScaler().fit_transform(X)

# Cluster
km = KMeans(n_clusters=4, random_state=42, n_init=10)
labels = km.fit_predict(X_scaled)
print(f"Silhouette: {silhouette_score(X_scaled, labels):.3f}")

# Visualize
X_2d = PCA(n_components=2).fit_transform(X_scaled)
plt.scatter(X_2d[:, 0], X_2d[:, 1], c=labels, cmap="viridis", s=20, alpha=0.7)
plt.title("K-Means Clustering (PCA projection)")
plt.savefig("clustering_result.png", dpi=150, bbox_inches="tight")
print("Saved clustering_result.png")

from sklearn.datasets import make_classification
from sklearn.feature_selection import SelectKBest, f_classif
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.model_selection import GridSearchCV

X, y = make_classification(n_samples=500, n_features=50, n_informative=10, random_state=42)

pipe = Pipeline([
    ("scaler", StandardScaler()),
    ("selector", SelectKBest(f_classif)),
    ("svm", SVC(kernel="rbf"))
])

param_grid = {
    "selector__k": [5, 10, 20],
    "svm__C": [0.1, 1, 10],
    "svm__gamma": ["scale", "auto"]
}

grid = GridSearchCV(pipe, param_grid, cv=5, scoring="accuracy", n_jobs=-1)
grid.fit(X, y)
print(f"Best params: {grid.best_params_}")
print(f"Best accuracy: {grid.best_score_:.3f}")