Pipelines و preprocessing في scikit-learn

[Step 1: تنظيف]  →  [Step 2: تحضير]  →  [Step 3: نموذج]

from sklearn.pipeline import Pipeline

pipe = Pipeline([
    ('scaler', StandardScaler()),       # Step 1
    ('model', LogisticRegression())     # Step 3
])

from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

# ❌ خطأ كلاسيكي
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)   # ← يقرأ كل البيانات، بما فيها test!
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y)

# ✅ صح
X_train, X_test, y_train, y_test = train_test_split(X, y)

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)   # ← يتعلّم من train فقط
X_test = scaler.transform(X_test)          # ← يطبّق ما تعلّمه على test

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 1. تحضير
X, y = ...  # بياناتك
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

# 2. بناء Pipeline
pipe = Pipeline([
    ('scaler', StandardScaler()),
    ('model', LogisticRegression(max_iter=1000))
])

# 3. fit على train
pipe.fit(X_train, y_train)

# 4. تنبّؤ على test
y_pred = pipe.predict(X_test)

# 5. تقييم
print(f"Accuracy: {accuracy_score(y_test, y_pred):.3f}")

from sklearn.model_selection import cross_val_score

scores = cross_val_score(pipe, X, y, cv=5, scoring='accuracy')
print(f"CV accuracy: {scores.mean():.3f} ± {scores.std():.3f}")

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder

preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), ['age', 'income']),
        ('cat', OneHotEncoder(), ['city', 'gender']),
    ]
)

pipe = Pipeline([
    ('preprocess', preprocessor),
    ('model', LogisticRegression(max_iter=1000))
])

pipe.fit(X_train, y_train)

import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split, cross_val_score

# بيانات وهمية: عملاء
df = pd.DataFrame({
    'age': [25, 40, 35, 50, 23, 38, 60, 28],
    'income': [3000, 5000, 4500, 7000, 2500, 4800, 8000, 3500],
    'city': ['A', 'B', 'A', 'C', 'A', 'B', 'C', 'A'],
    'churned': [1, 0, 0, 0, 1, 0, 0, 1]   # هل ترك الخدمة؟
})

X = df[['age', 'income', 'city']]
y = df['churned']

# تقسيم
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25, random_state=42, stratify=y
)

# Pipeline
preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), ['age', 'income']),
        ('cat', OneHotEncoder(handle_unknown='ignore'), ['city'])
    ]
)

pipe = Pipeline([
    ('preprocess', preprocessor),
    ('model', LogisticRegression(max_iter=1000))
])

# تدريب
pipe.fit(X_train, y_train)

# تقييم على test
print(f"Test accuracy: {pipe.score(X_test, y_test):.3f}")

# تقييم آمن عبر CV
scores = cross_val_score(pipe, X, y, cv=3, scoring='accuracy')
print(f"CV accuracy: {scores.mean():.3f} ± {scores.std():.3f}")