Machine Learning: البدء مع MLOps و MLflow

import mlflow

mlflow.set_experiment("SalesPredict-Revenue")
with mlflow.start_run(run_name="xgboost_v1"):
    mlflow.log_params({"n_estimators": 300, "max_depth": 6, "learning_rate": 0.1})
    mlflow.log_metrics({"r2": 0.89, "mae": 8.5})
    mlflow.sklearn.log_model(model, "model")

import mlflow
import mlflow.sklearn
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score, mean_absolute_error
from sklearn.model_selection import train_test_split
import numpy as np

mlflow.set_tracking_uri("sqlite:///mlflow.db")
mlflow.set_experiment("SalesPredict-Revenue")

rng = np.random.default_rng(42)
n = 1000
X = rng.uniform(0, 100, (n, 5))
y = 50 + 0.8 * X[:, 0] + 1.2 * X[:, 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)

# التجربة 1: Random Forest
with mlflow.start_run(run_name="rf_baseline"):
    params = {"n_estimators": 100, "max_depth": 10}
    mlflow.log_params(params)

    model = RandomForestRegressor(**params, random_state=42)
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)

    r2 = r2_score(y_test, y_pred)
    mae = mean_absolute_error(y_test, y_pred)
    mlflow.log_metrics({"r2": r2, "mae": mae})
    mlflow.sklearn.log_model(model, "model")

    print(f"RF: R²={r2:.4f}, MAE={mae:.2f}")

# التجربة 2: XGBoost
import xgboost as xgb

with mlflow.start_run(run_name="xgboost_v1"):
    params = {"n_estimators": 300, "max_depth": 6, "learning_rate": 0.1}
    mlflow.log_params(params)

    model = xgb.XGBRegressor(**params, random_state=42)
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)

    r2 = r2_score(y_test, y_pred)
    mae = mean_absolute_error(y_test, y_pred)
    mlflow.log_metrics({"r2": r2, "mae": mae})
    mlflow.xgboost.log_model(model, "model")

    print(f"XGB: R²={r2:.4f}, MAE={mae:.2f}")

# Execution successful

import mlflow

# الاستعلام عن التجارب
experiment = mlflow.get_experiment_by_name("SalesPredict-Revenue")
runs = mlflow.search_runs(experiment_ids=[experiment.experiment_id])

# فرز حسب R² (الأفضل أولًا)
best_runs = runs.sort_values("metrics.r2", ascending=False)
print("Top 3 runs by R²:")
print(best_runs[["run_name", "metrics.r2", "metrics.mae",
                   "params.n_estimators", "params.max_depth"]].head(3))

Top 3 runs by R²:

import mlflow

# تسجيل نموذج
model_uri = f"runs:/{run_id}/model"
mlflow.register_model(model_uri, "SalesPredict-Revenue-Model")

# نقل مرحلة النموذج
client = mlflow.tracking.MlflowClient()
client.transition_model_version_stage(
    name="SalesPredict-Revenue-Model",
    version=1,
    stage="Staging",
)

# ترقية إلى الإنتاج
client.transition_model_version_stage(
    name="SalesPredict-Revenue-Model",
    version=1,
    stage="Production",
)

# تحميل نموذج الإنتاج
model = mlflow.sklearn.load_model("models:/SalesPredict-Revenue-Model/Production")

# Execution successful

import mlflow
import mlflow.sklearn
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.model_selection import train_test_split
import numpy as np

# تسجيل تلقائي: تسجيل جميع المعاملات والمقاييس والنموذج تلقائيًا
mlflow.sklearn.autolog()

rng = np.random.default_rng(42)
X = rng.uniform(0, 100, (1000, 5))
y = 50 + 0.8 * X[:, 0] + 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)

with mlflow.start_run(run_name="gb_autolog"):
    model = GradientBoostingRegressor(n_estimators=100, max_depth=5, learning_rate=0.1, random_state=42)
    model.fit(X_train, y_train)
    # autolog يلتقط كل شيء تلقائيًا!

# Execution successful

import mlflow
import matplotlib.pyplot as plt
import numpy as np

with mlflow.start_run(run_name="feature_analysis"):
    # إنشاء وتسجيل رسم بياني
    fig, ax = plt.subplots()
    ax.barh(["feat_1", "feat_2", "feat_3", "feat_4", "feat_5"],
            [0.35, 0.25, 0.15, 0.10, 0.05])
    ax.set_xlabel("Importance")
    ax.set_title("Feature Importance")
    plt.tight_layout()

    mlflow.log_figure(fig, "feature_importance.png")
    plt.close()

    # تسجيل القطع الأثرية (أي ملف)
    # mlflow.log_artifact("local_file.csv")

# Execution successful

import mlflow
import mlflow.sklearn
import xgboost as xgb
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression, Ridge
from sklearn.model_selection import cross_val_score
from sklearn.metrics import r2_score, mean_absolute_error
import numpy as np

mlflow.set_experiment("SalesPredict-Benchmark")

# بيانات محاكاة
rng = np.random.default_rng(42)
X = rng.uniform(0, 100, (2000, 10))
y = 50 + X[:, :5] @ [0.8, 1.2, -0.5, 0.3, 0.1] + rng.normal(0, 5, 2000)

# تتبع التجارب المنهجي
experiments = [
    {"name": "linear_baseline", "model": LinearRegression(), "params": {}},
    {"name": "ridge_alpha1", "model": Ridge(alpha=1), "params": {"alpha": 1}},
    {"name": "rf_100", "model": RandomForestRegressor(n_estimators=100, random_state=42),
     "params": {"n_estimators": 100}},
    {"name": "rf_300", "model": RandomForestRegressor(n_estimators=300, random_state=42),
     "params": {"n_estimators": 300}},
    {"name": "xgb_d6_lr01", "model": xgb.XGBRegressor(max_depth=6, learning_rate=0.1, random_state=42),
     "params": {"max_depth": 6, "learning_rate": 0.1}},
]

for exp in experiments:
    with mlflow.start_run(run_name=exp["name"]):
        mlflow.log_params(exp["params"])
        cv_scores = cross_val_score(exp["model"], X, y, cv=5, scoring="r2")
        mlflow.log_metrics({
            "cv_r2_mean": cv_scores.mean(),
            "cv_r2_std": cv_scores.std(),
        })

# إيجاد أفضل تجربة
runs = mlflow.search_runs(
    experiment_ids=[mlflow.get_experiment_by_name("SalesPredict-Benchmark").experiment_id],
    order_by=["metrics.cv_r2_mean DESC"],
)
print("Best experiments:")
print(runs[["run_name", "metrics.cv_r2_mean", "metrics.cv_r2_std"]].head(5))

Best experiments: