머신러닝을 위한 피처 엔지니어링: 핵심 기법과 기술 면접 대비 2026

# encoding_strategies.py
import pandas as pd
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer

df = pd.DataFrame({
    "size": ["small", "medium", "large", "medium", "small"],
    "color": ["red", "blue", "green", "red", "blue"],
    "price": [10, 25, 40, 22, 12]
})

# Label encoding for ordinal feature (size has natural order)
le = LabelEncoder()
df["size_encoded"] = le.fit_transform(df["size"])  # large=0, medium=1, small=2

# One-hot encoding for nominal feature (color has no order)
ct = ColumnTransformer(
    transformers=[
        ("onehot", OneHotEncoder(drop="first", sparse_output=False), ["color"])
    ],
    remainder="passthrough"  # Keep other columns unchanged
)
result = ct.fit_transform(df[["color", "price"]])
# Produces: color_green, color_red columns (blue dropped as reference)

# feature_scaling.py
import numpy as np
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler

# Simulated dataset: salary with outliers
data = np.array([[35000], [42000], [55000], [67000], [450000]])  # 450k is an outlier

# StandardScaler: mean=0, std=1 (sensitive to outliers)
standard = StandardScaler().fit_transform(data)
# Result: [-0.72, -0.68, -0.60, -0.53, 2.53] — outlier distorts the scale

# MinMaxScaler: maps to [0, 1] (very sensitive to outliers)
minmax = MinMaxScaler().fit_transform(data)
# Result: [0.0, 0.017, 0.048, 0.077, 1.0] — most values crushed near zero

# RobustScaler: uses median and IQR (robust to outliers)
robust = RobustScaler().fit_transform(data)
# Result: [-0.77, -0.5, 0.0, 0.46, 15.38] — outlier isolated, core data preserved

# skew_transformations.py
import numpy as np
from sklearn.preprocessing import PowerTransformer

# Right-skewed income data (common in real datasets)
income = np.array([[25000], [32000], [41000], [55000], [72000],
                   [150000], [320000], [890000]])

# Log transform: simple, effective for right-skewed data
log_income = np.log1p(income)  # log1p handles zero values safely

# Box-Cox: finds optimal power parameter automatically
pt = PowerTransformer(method="box-cox")  # Requires strictly positive values
income_boxcox = pt.fit_transform(income)
print(f"Optimal lambda: {pt.lambdas_[0]:.3f}")  # Shows learned parameter

# Yeo-Johnson: works with zero and negative values too
pt_yj = PowerTransformer(method="yeo-johnson")
income_yj = pt_yj.fit_transform(income)

# feature_selection.py
from sklearn.datasets import make_classification
from sklearn.feature_selection import (
    SelectKBest, f_classif,  # Filter method
    SequentialFeatureSelector,  # Wrapper method
    SelectFromModel  # Embedded method
)
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LassoCV

# Dataset: 20 features, only 5 are informative
X, y = make_classification(
    n_samples=1000, n_features=20,
    n_informative=5, n_redundant=3, random_state=42
)

# Filter: ANOVA F-test selects top k features by statistical significance
selector_filter = SelectKBest(f_classif, k=8)
X_filtered = selector_filter.fit_transform(X, y)
print(f"Selected features: {selector_filter.get_support(indices=True)}")

# Embedded: L1 regularization (Lasso) zeros out irrelevant feature weights
lasso = LassoCV(cv=5, random_state=42).fit(X, y)
selector_embedded = SelectFromModel(lasso, prefit=True)
X_lasso = selector_embedded.transform(X)
print(f"Lasso kept {X_lasso.shape[1]} features out of {X.shape[1]}")

# production_pipeline.py
import pandas as pd
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.model_selection import cross_val_score

# Define column groups by type
numeric_features = ["age", "income", "credit_score"]
categorical_features = ["education", "employment_type", "region"]

# Numeric pipeline: impute missing values, then scale
numeric_pipeline = Pipeline([
    ("imputer", SimpleImputer(strategy="median")),  # Median resists outliers
    ("scaler", StandardScaler())
])

# Categorical pipeline: impute missing, then one-hot encode
categorical_pipeline = Pipeline([
    ("imputer", SimpleImputer(strategy="most_frequent")),
    ("encoder", OneHotEncoder(handle_unknown="ignore", sparse_output=False))
])

# Combine into a single preprocessor
preprocessor = ColumnTransformer([
    ("num", numeric_pipeline, numeric_features),
    ("cat", categorical_pipeline, categorical_features)
])

# Full pipeline: preprocessing + model in one object
full_pipeline = Pipeline([
    ("preprocessor", preprocessor),
    ("classifier", GradientBoostingClassifier(n_estimators=200, random_state=42))
])

# Cross-validation applies preprocessing correctly within each fold
scores = cross_val_score(full_pipeline, X, y, cv=5, scoring="roc_auc")
print(f"AUC: {scores.mean():.3f} +/- {scores.std():.3f}")

# automated_feature_engineering.py
import featuretools as ft
import pandas as pd

# Define entities from relational tables
customers = pd.DataFrame({
    "customer_id": [1, 2, 3],
    "signup_date": pd.to_datetime(["2024-01-15", "2024-03-22", "2024-06-01"]),
    "region": ["US", "EU", "APAC"]
})

transactions = pd.DataFrame({
    "txn_id": range(1, 8),
    "customer_id": [1, 1, 1, 2, 2, 3, 3],
    "amount": [50, 120, 30, 200, 85, 340, 15],
    "category": ["food", "tech", "food", "tech", "travel", "food", "tech"]
})

# Create an EntitySet with relationships
es = ft.EntitySet(id="retail")
es = es.add_dataframe(dataframe=customers, dataframe_name="customers",
                      index="customer_id", time_index="signup_date")
es = es.add_dataframe(dataframe=transactions, dataframe_name="transactions",
                      index="txn_id")
es = es.add_relationship("customers", "customer_id",
                         "transactions", "customer_id")

# DFS generates features: COUNT, MEAN, MAX, STD of transactions per customer
feature_matrix, feature_defs = ft.dfs(
    entityset=es, target_dataframe_name="customers",
    max_depth=2,  # Controls complexity of generated features
    trans_primitives=["month", "weekday"],  # Transformation primitives
    agg_primitives=["count", "mean", "std", "max"]  # Aggregation primitives
)
print(f"Generated {len(feature_defs)} features from 2 tables")