2026년 Python 데이터 사이언스: NumPy, Pandas, Scikit-Learn 완벽 가이드

# numpy_basics.py
import numpy as np

# Create arrays from different sources
prices = np.array([29.99, 49.99, 19.99, 99.99, 39.99])
quantities = np.arange(1, 6)  # [1, 2, 3, 4, 5]

# Vectorized arithmetic — no loops needed
revenue = prices * quantities
print(revenue)  # [29.99, 99.98, 59.97, 399.96, 199.95]

# Statistical aggregations
print(f"Total revenue: ${revenue.sum():.2f}")   # $789.85
print(f"Mean price: ${prices.mean():.2f}")       # $47.99
print(f"Std deviation: ${prices.std():.2f}")     # $27.64

# Boolean indexing — filter without loops
premium_mask = prices > 40
premium_items = prices[premium_mask]  # [49.99, 99.99]

# numpy_reshape.py
import numpy as np

# Monthly sales data: 4 products x 3 months
sales = np.array([
    [120, 150, 130],  # Product A
    [200, 180, 220],  # Product B
    [90, 110, 95],    # Product C
    [300, 280, 310],  # Product D
])

# Column-wise mean (average per month)
monthly_avg = sales.mean(axis=0)  # [177.5, 180.0, 188.75]

# Row-wise sum (total per product)
product_totals = sales.sum(axis=1)  # [400, 600, 295, 890]

# Normalize each product relative to its own max
normalized = sales / sales.max(axis=1, keepdims=True)
# keepdims=True preserves the shape for broadcasting
print(normalized[0])  # [0.8, 1.0, 0.867] — Product A relative to its peak

# Reshape for Scikit-Learn (requires 2D input)
flat_sales = sales.flatten()  # 1D array of 12 values
reshaped = flat_sales.reshape(-1, 1)  # 12x1 column vector

# pandas_cleaning.py
import pandas as pd
import numpy as np

# Load and inspect raw data
df = pd.read_csv("candidates.csv")
print(df.shape)       # (1500, 8)
print(df.dtypes)      # Check column types
print(df.isna().sum()) # Count missing values per column

# Clean in a reproducible chain
df_clean = (
    df
    .dropna(subset=["salary", "experience_years"])      # Drop rows missing critical fields
    .assign(
        salary=lambda x: x["salary"].clip(lower=20000, upper=500000),  # Cap outliers
        experience_years=lambda x: x["experience_years"].astype(int),
        hired_date=lambda x: pd.to_datetime(x["hired_date"], errors="coerce"),
    )
    .drop_duplicates(subset=["email"])                  # Remove duplicate candidates
    .query("experience_years >= 0")                     # Filter invalid entries
    .reset_index(drop=True)
)

print(f"Cleaned: {len(df)} -> {len(df_clean)} rows")

# pandas_groupby.py
import pandas as pd

# Aggregate candidate stats by department
dept_stats = (
    df_clean
    .groupby("department")
    .agg(
        avg_salary=("salary", "mean"),
        median_experience=("experience_years", "median"),
        headcount=("email", "count"),
        max_salary=("salary", "max"),
    )
    .sort_values("avg_salary", ascending=False)
)
print(dept_stats.head())

# Create features for ML: encode categorical + add aggregated stats
df_features = (
    df_clean
    .assign(
        # Ratio of individual salary to department average
        salary_ratio=lambda x: x["salary"] / x.groupby("department")["salary"].transform("mean"),
        # Time since hire in days
        tenure_days=lambda x: (pd.Timestamp.now() - x["hired_date"]).dt.days,
        # Binary encoding
        is_senior=lambda x: (x["experience_years"] >= 5).astype(int),
    )
)

# sklearn_pipeline.py
from sklearn.model_selection import train_test_split
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import classification_report
import pandas as pd

# Define column groups
numeric_features = ["salary", "experience_years", "salary_ratio", "tenure_days"]
categorical_features = ["department", "role_level"]
target = "promoted"

# Split before any preprocessing
X = df_features[numeric_features + categorical_features]
y = df_features[target]
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

# Build the preprocessing + model pipeline
preprocessor = ColumnTransformer(
    transformers=[
        ("num", StandardScaler(), numeric_features),
        ("cat", OneHotEncoder(handle_unknown="ignore"), categorical_features),
    ]
)

pipeline = Pipeline([
    ("preprocessor", preprocessor),
    ("classifier", GradientBoostingClassifier(
        n_estimators=200,
        learning_rate=0.1,
        max_depth=4,
        random_state=42,
    )),
])

# Train and evaluate
pipeline.fit(X_train, y_train)
y_pred = pipeline.predict(X_test)
print(classification_report(y_test, y_pred))

# sklearn_tuning.py
from sklearn.model_selection import cross_val_score, GridSearchCV
import numpy as np

# 5-fold cross-validation on the full pipeline
scores = cross_val_score(pipeline, X_train, y_train, cv=5, scoring="f1")
print(f"F1 scores: {scores}")
print(f"Mean F1: {scores.mean():.3f} (+/- {scores.std() * 2:.3f})")

# Grid search over hyperparameters
param_grid = {
    "classifier__n_estimators": [100, 200, 300],
    "classifier__max_depth": [3, 4, 5],
    "classifier__learning_rate": [0.05, 0.1, 0.2],
}

grid_search = GridSearchCV(
    pipeline,
    param_grid,
    cv=5,
    scoring="f1",
    n_jobs=-1,
    verbose=1,
)

grid_search.fit(X_train, y_train)
print(f"Best params: {grid_search.best_params_}")
print(f"Best F1: {grid_search.best_score_:.3f}")

# Evaluate the best model on held-out test set
best_model = grid_search.best_estimator_
print(classification_report(y_test, best_model.predict(X_test)))

# sklearn_export.py
import joblib
from pathlib import Path

# Save the complete pipeline (preprocessor + model)
model_dir = Path("models")
model_dir.mkdir(exist_ok=True)
joblib.dump(best_model, model_dir / "promotion_model_v1.joblib")

# Load and predict in a different process
loaded_model = joblib.load(model_dir / "promotion_model_v1.joblib")
new_data = pd.DataFrame({
    "salary": [75000],
    "experience_years": [4],
    "salary_ratio": [1.05],
    "tenure_days": [730],
    "department": ["Engineering"],
    "role_level": ["Mid"],
})

prediction = loaded_model.predict(new_data)
probability = loaded_model.predict_proba(new_data)[:, 1]
print(f"Promoted: {bool(prediction[0])}, Confidence: {probability[0]:.2%}")