Scikit-Learn Pipeline 2026: Hướng Dẫn Feature Engineering và Câu Hỏi Phỏng Vấn

# pipeline_basics.py
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score

# Create a pipeline that scales features and trains a classifier
pipeline = Pipeline([
    ('scaler', StandardScaler()),  # Step 1: Normalize features
    ('classifier', LogisticRegression(max_iter=1000))  # Step 2: Train model
])

# cross_val_score fits the scaler separately for each fold
# No data leakage: test fold is never seen during scaler.fit()
scores = cross_val_score(pipeline, X, y, cv=5, scoring='accuracy')
print(f"Mean accuracy: {scores.mean():.3f} (+/- {scores.std():.3f})")

# column_transformer_example.py
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
import pandas as pd

# Sample dataset with mixed types
df = pd.DataFrame({
    'age': [25, 30, None, 45],
    'salary': [50000, 60000, 75000, None],
    'country': ['US', 'UK', 'DE', 'US'],
    'education': ['Bachelor', 'Master', 'PhD', 'Bachelor']
})

# Define numeric preprocessing: impute missing values, then scale
numeric_transformer = Pipeline([
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler())
])

# Define categorical preprocessing: impute with mode, then one-hot encode
categorical_transformer = Pipeline([
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('encoder', OneHotEncoder(handle_unknown='ignore', sparse_output=False))
])

# Combine transformers with ColumnTransformer
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numeric_transformer, ['age', 'salary']),
        ('cat', categorical_transformer, ['country', 'education'])
    ],
    verbose_feature_names_out=True  # Prefix output names with transformer name
)

# Fit and inspect output shape
X_transformed = preprocessor.fit_transform(df)
print(f"Transformed shape: {X_transformed.shape}")
print(f"Feature names: {preprocessor.get_feature_names_out()}")

# automatic_column_selection.py
from sklearn.compose import ColumnTransformer, make_column_selector
from sklearn.preprocessing import StandardScaler, OneHotEncoder

# Select columns by dtype: no hardcoded column names
preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), make_column_selector(dtype_include='number')),
        ('cat', OneHotEncoder(handle_unknown='ignore'),
         make_column_selector(dtype_include='object'))
    ],
    remainder='passthrough'  # Keep unprocessed columns as-is
)

# Works with any DataFrame that has numeric and object columns
X_processed = preprocessor.fit_transform(df)

# custom_transformer.py
from sklearn.base import BaseEstimator, TransformerMixin
import numpy as np

class DateFeatureExtractor(BaseEstimator, TransformerMixin):
    """Extract year, month, day, and weekday from datetime columns."""
    
    def __init__(self, date_column='date'):
        self.date_column = date_column
    
    def fit(self, X, y=None):
        # No fitting required for date extraction
        return self
    
    def transform(self, X):
        X = X.copy()
        dates = pd.to_datetime(X[self.date_column])
        
        # Extract temporal features
        X['year'] = dates.dt.year
        X['month'] = dates.dt.month
        X['day'] = dates.dt.day
        X['weekday'] = dates.dt.weekday
        X['is_weekend'] = (dates.dt.weekday >= 5).astype(int)
        
        # Drop original date column
        return X.drop(columns=[self.date_column])
    
    def get_feature_names_out(self, input_features=None):
        # Required for Pipeline.get_feature_names_out() to work
        return ['year', 'month', 'day', 'weekday', 'is_weekend']

# Integrate into a full pipeline
full_pipeline = Pipeline([
    ('date_features', DateFeatureExtractor(date_column='signup_date')),
    ('preprocessor', preprocessor),
    ('model', LogisticRegression())
])

# pipeline_gridsearch.py
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestClassifier

# Build pipeline with tunable components
pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('classifier', RandomForestClassifier(random_state=42))
])

# Define parameter grid: note the double underscore syntax
param_grid = {
    'preprocessor__num__imputer__strategy': ['mean', 'median'],
    'classifier__n_estimators': [100, 200],
    'classifier__max_depth': [10, 20, None]
}

# GridSearchCV handles all combinations automatically
grid_search = GridSearchCV(
    pipeline,
    param_grid,
    cv=5,
    scoring='f1_weighted',
    n_jobs=-1
)

grid_search.fit(X_train, y_train)
print(f"Best params: {grid_search.best_params_}")
print(f"Best score: {grid_search.best_score_:.3f}")

# cached_pipeline.py
from sklearn.pipeline import Pipeline
from tempfile import mkdtemp
import joblib

# Create a cache directory
cachedir = mkdtemp()

# Pipeline caches intermediate steps
cached_pipeline = Pipeline(
    [
        ('preprocessor', preprocessor),  # Cached after first fit
        ('classifier', RandomForestClassifier())
    ],
    memory=cachedir  # Or use joblib.Memory for more control
)

# First fit: slow (computes all transformations)
cached_pipeline.fit(X_train, y_train)

# Second fit with same X_train: fast (loads cached transformers)
cached_pipeline.fit(X_train, y_train)  # Skips preprocessor fitting

# callback_monitoring.py
from sklearn.callback import ProgressBar, ScoringMonitor
from sklearn.linear_model import LogisticRegression

# Display progress during GridSearchCV
with ProgressBar():
    grid_search = GridSearchCV(
        pipeline,
        param_grid,
        cv=5,
        n_jobs=1  # Progress bars require single-threaded execution
    )
    grid_search.fit(X_train, y_train)

# Monitor scoring metrics per iteration
with ScoringMonitor(X_val, y_val, scoring='accuracy') as monitor:
    logreg = LogisticRegression(solver='lbfgs', max_iter=500)
    logreg.fit(X_train, y_train)
    print(f"Scores per iteration: {monitor.scores_}")

# feature_union_example.py
from sklearn.pipeline import FeatureUnion, Pipeline
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest, f_classif

# Combine PCA and univariate selection
feature_union = FeatureUnion([
    ('pca', PCA(n_components=5)),
    ('select', SelectKBest(f_classif, k=10))
])

# Pipeline: preprocess, combine features, classify
pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('features', feature_union),
    ('classifier', LogisticRegression())
])

# Output contains 5 PCA components + 10 selected features = 15 features
pipeline.fit(X_train, y_train)

# model_deployment.py
import joblib

# Save the entire pipeline (preprocessing + model)
joblib.dump(pipeline, 'churn_predictor.pkl')

# Load in production
loaded_pipeline = joblib.load('churn_predictor.pkl')

# Predict on new data (same preprocessing automatically applied)
new_data = pd.DataFrame({'age': [32], 'salary': [65000], ...})
predictions = loaded_pipeline.predict(new_data)