التنبؤ بالسلاسل الزمنية

import pandas as pd
import numpy as np
import lightgbm as lgb
from sklearn.model_selection import TimeSeriesSplit
from sklearn.metrics import mean_absolute_error

class="tok-comment"># ── Sample daily time-series DataFrame ────────────────────────────────
dates = pd.date_range(class="tok-str">'class="tok-num">2022-class="tok-num">01-class="tok-num">01', periods=class="tok-num">365, freq=class="tok-str">'D')
np.random.seed(class="tok-num">42)
trend = np.linspace(class="tok-num">100, class="tok-num">200, class="tok-num">365)
seasonal = class="tok-num">20 * np.sin(class="tok-num">2 * np.pi * np.arange(class="tok-num">365) / class="tok-num">7)  class="tok-comment"># weekly pattern
noise = np.random.randn(class="tok-num">365) * class="tok-num">5
df = pd.DataFrame({class="tok-str">'sales': trend + seasonal + noise}, index=dates)

def create_features(df, target_col, lags, rolling_windows):
    class="tok-str">"""Create lag and rolling features for supervised time series forecasting."""
    df = df.copy()
    for lag in lags:
        df[fclass="tok-str">'lag_{lag}'] = df[target_col].shift(lag)
    for w in rolling_windows:
        df[fclass="tok-str">'roll_mean_{w}'] = df[target_col].shift(class="tok-num">1).rolling(w).mean()
        df[fclass="tok-str">'roll_std_{w}']  = df[target_col].shift(class="tok-num">1).rolling(w).std()
    class="tok-comment"># Calendar features
    df[class="tok-str">'dayofweek']  = df.index.dayofweek
    df[class="tok-str">'month']      = df.index.month
    df[class="tok-str">'is_weekend'] = df[class="tok-str">'dayofweek'] >= class="tok-num">5
    class="tok-comment"># Fourier seasonality (weekly=class="tok-num">7, yearly=class="tok-num">365)
    for k in range(class="tok-num">1, class="tok-num">3):
        df[fclass="tok-str">'sin_week_{k}'] = np.sin(class="tok-num">2*np.pi*k * df.index.dayofyear / class="tok-num">7)
        df[fclass="tok-str">'cos_week_{k}'] = np.cos(class="tok-num">2*np.pi*k * df.index.dayofyear / class="tok-num">7)
    return df.dropna()

df_feat = create_features(df, class="tok-str">'sales', lags=[class="tok-num">1,class="tok-num">2,class="tok-num">3,class="tok-num">7,class="tok-num">14,class="tok-num">28], rolling_windows=[class="tok-num">7,class="tok-num">14,class="tok-num">28])
X = df_feat.drop(class="tok-str">'sales', axis=class="tok-num">1)
y = df_feat[class="tok-str">'sales']

class="tok-comment"># ── TimeSeriesSplit cross-validation ──────────────────────────────
tscv = TimeSeriesSplit(n_splits=class="tok-num">5, gap=class="tok-num">7)  class="tok-comment"># class="tok-num">7-day gap prevents autocorrelation leakage
maes = []

for train_idx, val_idx in tscv.split(X):
    X_tr, X_val = X.iloc[train_idx], X.iloc[val_idx]
    y_tr, y_val = y.iloc[train_idx], y.iloc[val_idx]

    model = lgb.LGBMRegressor(n_estimators=class="tok-num">500, learning_rate=class="tok-num">0.05,
                               num_leaves=class="tok-num">31, min_child_samples=class="tok-num">20)
    model.fit(X_tr, y_tr,
              eval_set=[(X_val, y_val)],
              callbacks=[lgb.early_stopping(class="tok-num">50, verbose=False)])
    maes.append(mean_absolute_error(y_val, model.predict(X_val)))

print(fclass="tok-str">"CV MAE: {np.mean(maes):.2f} ± {np.std(maes):.2f}")