दिन 49: Time Series और Forecasting

import pandas as pd
import matplotlib.pyplot as plt
w = pd.read_csv("delhi_weather.csv", parse_dates=["date"]).set_index("date").asfreq("D")
print(w.shape, "| missing days:", w["aqi"].isna().sum())
m = w["aqi"].resample("MS").mean()
fig, ax = plt.subplots(figsize=(10, 3.6))
ax.plot(w.index, w["aqi"], color="#cbd5e1", lw=0.7, label="daily")
ax.plot(m.index, m.values, color="#dc2626", marker="o", lw=2, label="monthly mean")
ax.set_title("Delhi AQI 2022–2024: strong yearly seasonality"); ax.legend(); plt.show()

import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.seasonal import seasonal_decompose
w = pd.read_csv("delhi_weather.csv", parse_dates=["date"]).set_index("date")
weekly = w["aqi"].resample("W").mean()
dec = seasonal_decompose(weekly, model="additive", period=52)
fig = dec.plot(); fig.set_size_inches(10, 6.5); fig.suptitle("Decomposition of weekly AQI", y=1.01)
plt.tight_layout(); plt.show()
print("seasonal swing (max − min):", round(dec.seasonal.max() - dec.seasonal.min()), "AQI points")

import pandas as pd
w = pd.read_csv("delhi_weather.csv", parse_dates=["date"]).set_index("date")
train, test = w.loc[:"2023-12-31", "aqi"], w.loc["2024-01-01":, "aqi"]
print("train:", train.index.min().date(), "→", train.index.max().date(), len(train))
print("test :", test.index.min().date(), "→", test.index.max().date(), len(test))

import numpy as np
import pandas as pd
from sklearn.metrics import mean_absolute_error, mean_absolute_percentage_error
w = pd.read_csv("delhi_weather.csv", parse_dates=["date"]).set_index("date")["aqi"]
test = w.loc["2024"]
preds = {"naive (last value of 2023)": pd.Series(w.loc["2023-12-31"], index=test.index),
         "mean of 2022–23": pd.Series(w.loc[:"2023"].mean(), index=test.index),
         "seasonal naive (same day last year)": w.shift(365).loc["2024"]}
for name, p in preds.items():
    print(f"{name:36s} MAE {mean_absolute_error(test, p):6.1f}   MAPE {mean_absolute_percentage_error(test, p) * 100:5.1f}%")

import numpy as np
import pandas as pd
from sklearn.ensemble import HistGradientBoostingRegressor
from sklearn.metrics import mean_absolute_error
w = pd.read_csv("delhi_weather.csv", parse_dates=["date"]).set_index("date")
f = pd.DataFrame(index=w.index)
f["aqi"] = w["aqi"]
f["lag_365"] = w["aqi"].shift(365)                   # same day last year
f["lag_30"] = w["aqi"].shift(30)                     # a month ago (known 30 days ahead)
f["roll_30_lag_30"] = w["aqi"].shift(30).rolling(30).mean()
f["doy_sin"] = np.sin(2 * np.pi * w.index.dayofyear / 365.25)
f["doy_cos"] = np.cos(2 * np.pi * w.index.dayofyear / 365.25)
f["weekday"] = w.index.dayofweek
f = f.dropna()
tr, te = f.loc[:"2023"], f.loc["2024"]
feats = [c for c in f.columns if c != "aqi"]
model = HistGradientBoostingRegressor(max_iter=300, learning_rate=0.05, random_state=0).fit(tr[feats], tr["aqi"])
pred = pd.Series(model.predict(te[feats]), index=te.index)
print("training rows:", len(tr), "| features:", feats)
print(f"ML forecast MAE {mean_absolute_error(te['aqi'], pred):.1f}")
pred.to_frame("pred").assign(actual=te["aqi"]).to_csv("aqi_forecast_2024.csv")

import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.holtwinters import ExponentialSmoothing
from sklearn.metrics import mean_absolute_error
w = pd.read_csv("delhi_weather.csv", parse_dates=["date"]).set_index("date")["aqi"]
monthly = w.resample("MS").mean()
train, test = monthly.loc[:"2023"], monthly.loc["2024"]
hw = ExponentialSmoothing(train, trend=None, seasonal="additive", seasonal_periods=12).fit()
fc = hw.forecast(12)
snaive = monthly.shift(12).loc["2024"]
print(f"monthly MAE → Holt-Winters {mean_absolute_error(test, fc):.1f} | seasonal naive {mean_absolute_error(test, snaive):.1f}")
plt.figure(figsize=(10, 3.8))
plt.plot(monthly.index, monthly, color="#64748b", marker="o", label="actual")
plt.plot(fc.index, fc, color="#dc2626", marker="o", ls="--", label="Holt-Winters forecast 2024")
plt.axvspan(test.index.min(), test.index.max(), color="#fee2e2", alpha=0.5)
plt.title("Forecasting 2024 monthly AQI from 2022–23 only"); plt.legend(); plt.show()

import numpy as np
from sklearn.model_selection import TimeSeriesSplit
idx = np.arange(12)
for i, (tr, te) in enumerate(TimeSeriesSplit(n_splits=4, test_size=2).split(idx), 1):
    print(f"fold {i}: train months {tr.min()}–{tr.max()}  →  test months {te.tolist()}")