Machine Learning: التعلم الجماعي

import xgboost as xgb

dtrain = xgb.DMatrix(X_train, label=y_train)
params = {"objective": "reg:squarederror", "max_depth": 6, "learning_rate": 0.1}
model = xgb.train(params, dtrain, num_boost_round=500)

from sklearn.ensemble import GradientBoostingRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_squared_error
import numpy as np

rng = np.random.default_rng(42)
X = rng.uniform(0, 10, (200, 1))
y = np.sin(X.squeeze()) + rng.normal(0, 0.2, 200)

# تصور Boosting خطوة بخطوة
residuals = y.copy()
predictions = np.zeros_like(y, dtype=float)
learning_rate = 0.1

for i in range(1, 51):
    tree = DecisionTreeRegressor(max_depth=3)
    tree.fit(X, residuals)
    update = learning_rate * tree.predict(X)
    predictions += update
    residuals = y - predictions

    if i in [1, 5, 10, 50]:
        mse = mean_squared_error(y, predictions)
        print(f"Round {i:2d}: MSE={mse:.4f}")

# قارن مع sklearn's GradientBoosting
gb = GradientBoostingRegressor(n_estimators=50, max_depth=3, learning_rate=0.1, random_state=42)
gb.fit(X, y)
print(f"\nsklearn GB MSE: {mean_squared_error(y, gb.predict(X)):.4f}")

# Runs successfully

import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error, r2_score
import numpy as np

rng = np.random.default_rng(42)
n = 10000
X = rng.uniform(0, 100, (n, 8))
y = (50 + 0.8 * X[:, 0] + 1.2 * X[:, 1] - 0.5 * X[:, 2]
     + 0.3 * X[:, 3] * X[:, 4]  # مصطلح تفاعل
     + rng.normal(0, 5, n))

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# XGBoost مع واجهة sklearn
model = xgb.XGBRegressor(
    n_estimators=500,
    max_depth=6,
    learning_rate=0.1,
    subsample=0.8,
    colsample_bytree=0.8,
    reg_alpha=0.1,
    reg_lambda=1.0,
    random_state=42,
    early_stopping_rounds=50,
)

model.fit(
    X_train, y_train,
    eval_set=[(X_test, y_test)],
    verbose=False,
)

y_pred = model.predict(X_test)
print(f"R²: {r2_score(y_test, y_pred):.4f}")
print(f"MAE: {mean_absolute_error(y_test, y_pred):.2f}")
print(f"Best iteration: {model.best_iteration}")

# Runs successfully

import lightgbm as lgb
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error, r2_score
import numpy as np

# باستخدام نفس البيانات كمثال XGBoost
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# LightGBM مع واجهة sklearn
model = lgb.LGBMRegressor(
    n_estimators=500,
    max_depth=-1,        # -1 يعني بلا حدود، استخدم num_leaves بدلاً من ذلك
    num_leaves=31,
    learning_rate=0.1,
    subsample=0.8,
    colsample_bytree=0.8,
    reg_alpha=0.1,
    reg_lambda=1.0,
    random_state=42,
    verbose=-1,
)

model.fit(
    X_train, y_train,
    eval_set=[(X_test, y_test)],
    callbacks=[lgb.early_stopping(50, verbose=False)],
)

y_pred = model.predict(X_test)
print(f"R²: {r2_score(y_test, y_pred):.4f}")
print(f"MAE: {mean_absolute_error(y_test, y_pred):.2f}")
print(f"Best iteration: {model.best_iteration_}")

# Runs successfully

import lightgbm as lgb
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score

rng = np.random.default_rng(42)
n = 5000
df = pd.DataFrame({
    "ad_spend_k": rng.uniform(5, 100, n),
    "traffic_k": rng.uniform(10, 500, n),
    "category": rng.choice(["Elec", "Cloth", "Food", "Book", "Home"], n),
    "region": rng.choice(["US", "EU", "CN"], n),
})
df["revenue_k"] = (
    20 + 0.6 * df["ad_spend_k"] + 0.08 * df["traffic_k"]
    + df["category"].map({"Elec": 30, "Cloth": 15, "Food": 5, "Book": 3, "Home": 40})
    + rng.normal(0, 10, n)
)

X = df.drop(columns=["revenue_k"])
y = df["revenue_k"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# دعم LightGBM الأصلي للميزات الفئوية
model = lgb.LGBMRegressor(
    n_estimators=200, learning_rate=0.1,
    categorical_feature=["category", "region"],  # دعم فئوي مباشر
    random_state=42, verbose=-1,
)
model.fit(X_train, y_train)
print(f"R² with native categorical: {r2_score(y_test, model.predict(X_test)):.4f}")

# Runs successfully

import xgboost as xgb
import lightgbm as lgb
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.metrics import mean_absolute_error, r2_score
import time
import numpy as np

rng = np.random.default_rng(42)
n = 100000
X = rng.uniform(0, 100, (n, 20))
y = 50 + X[:, :5] @ [0.8, 1.2, -0.5, 0.3, 0.1] + rng.normal(0, 5, n)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

results = {}

for name, model in [
    ("RandomForest", RandomForestRegressor(n_estimators=100, random_state=42, n_jobs=-1)),
    ("XGBoost", xgb.XGBRegressor(n_estimators=300, max_depth=6, learning_rate=0.1, random_state=42)),
    ("LightGBM", lgb.LGBMRegressor(n_estimators=300, num_leaves=31, learning_rate=0.1, random_state=42, verbose=-1)),
]:
    start = time.time()
    model.fit(X_train, y_train)
    train_time = time.time() - start

    y_pred = model.predict(X_test)
    r2 = r2_score(y_test, y_pred)
    mae = mean_absolute_error(y_test, y_pred)

    results[name] = {"time": train_time, "r2": r2, "mae": mae}
    print(f"{name:15s}: R²={r2:.4f}, MAE={mae:.2f}, Time={train_time:.1f}s")

# Runs successfully