هندسة الميزات والخطوط

from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import (StandardScaler, OneHotEncoder,
                                   RobustScaler, PolynomialFeatures)
from sklearn.impute import SimpleImputer
from sklearn.feature_selection import SelectFromModel
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.model_selection import cross_val_score, train_test_split
import pandas as pd
import numpy as np

class="tok-comment"># ── Sample DataFrame ───────────────────────────────────────────────────
np.random.seed(class="tok-num">42)
n = class="tok-num">300
df = pd.DataFrame({
    class="tok-str">'age':        np.random.randint(class="tok-num">18, class="tok-num">70, n).astype(float),
    class="tok-str">'income':     np.random.exponential(class="tok-num">40000, n),
    class="tok-str">'score':      np.random.uniform(class="tok-num">300, class="tok-num">850, n),
    class="tok-str">'city':       np.random.choice([class="tok-str">'Paris', class="tok-str">'Lyon', class="tok-str">'Toulouse'], n),
    class="tok-str">'occupation': np.random.choice([class="tok-str">'engineer', class="tok-str">'teacher', class="tok-str">'doctor'], n),
    class="tok-str">'target':     np.random.randint(class="tok-num">0, class="tok-num">2, n),
})
class="tok-comment"># Add some missing values
df.loc[np.random.choice(n, class="tok-num">20, replace=False), class="tok-str">'age'] = np.nan
df.loc[np.random.choice(n, class="tok-num">15, replace=False), class="tok-str">'city'] = np.nan

X_train = df.drop(class="tok-str">'target', axis=class="tok-num">1)
y_train = df[class="tok-str">'target']

class="tok-comment"># ── Define column groups ───────────────────────────────────────────
num_features = [class="tok-str">'age', class="tok-str">'income', class="tok-str">'score']
cat_features = [class="tok-str">'city', class="tok-str">'occupation']

class="tok-comment"># ── Preprocessing for numeric columns ─────────────────────────────
numeric_transformer = Pipeline([
    (class="tok-str">'imputer', SimpleImputer(strategy=class="tok-str">'median')),
    (class="tok-str">'scaler', RobustScaler()),
])

class="tok-comment"># ── Preprocessing for categorical columns ─────────────────────────
categorical_transformer = Pipeline([
    (class="tok-str">'imputer', SimpleImputer(strategy=class="tok-str">'most_frequent')),
    (class="tok-str">'encoder', OneHotEncoder(handle_unknown=class="tok-str">'ignore', drop=class="tok-str">'first')),
])

class="tok-comment"># ── Combine with ColumnTransformer ─────────────────────────────────
preprocessor = ColumnTransformer([
    (class="tok-str">'num', numeric_transformer, num_features),
    (class="tok-str">'cat', categorical_transformer, cat_features),
])

class="tok-comment"># ── Full pipeline: preprocess → feature select → model ────────────
pipe = Pipeline([
    (class="tok-str">'prep', preprocessor),
    (class="tok-str">'poly', PolynomialFeatures(degree=class="tok-num">2, interaction_only=True, include_bias=False)),
    (class="tok-str">'select', SelectFromModel(RandomForestClassifier(n_estimators=class="tok-num">50), threshold=class="tok-str">'median')),
    (class="tok-str">'clf', GradientBoostingClassifier(n_estimators=class="tok-num">200, learning_rate=class="tok-num">0.05)),
])

class="tok-comment"># Train / evaluate — preprocessing is always fitted on train only
pipe.fit(X_train, y_train)
scores = cross_val_score(pipe, X_train, y_train, cv=class="tok-num">5, scoring=class="tok-str">'roc_auc')
print(fclass="tok-str">"CV AUC: {scores.mean():.3f} ± {scores.std():.3f}")