تحليل البيانات المتقدم بلغتي Python وR للمؤسسات والجهات الحكومية

import numpy as np
import statsmodels.api as sm
from statsmodels.tsa.statespace.sarimax import SARIMAX

# Built-in weekly CO2 series aggregated to monthly
y = (sm.datasets.co2.load_pandas().data["co2"]
     .resample("MS").mean().ffill())
train, test = y[:-24], y[-24:]

# Backtest: fit on training window, score last 24 months
fit = SARIMAX(train, order=(1, 1, 1),
              seasonal_order=(0, 1, 1, 12)).fit(disp=False)
pred = fit.forecast(len(test))
naive = y.shift(12)[-24:]  # seasonal naive benchmark
mae = lambda f: np.mean(np.abs(test - f))
print(f"MAE  sarima={mae(pred):.3f}  naive={mae(naive):.3f}")

# Same parameters on full data: 12 months, 95% interval
fc = fit.apply(y).get_forecast(12).summary_frame(alpha=0.05)
print(fc[["mean", "mean_ci_lower", "mean_ci_upper"]].round(2))

import numpy as np
import pandas as pd
import statsmodels.formula.api as smf

# Synthetic panel: 100 districts x 8 years, half treated
rng = np.random.default_rng(1)
df = pd.DataFrame(
    [(i, t) for i in range(100) for t in range(8)],
    columns=["unit", "year"])
df["treated"] = (df.unit < 50).astype(int)
df["post"] = (df.year >= 4).astype(int)
u = rng.normal(0, 1, 100)[df.unit]  # unit heterogeneity
df["y"] = (u + 0.3 * df.year + 2.0 * df.treated * df.post
           + rng.normal(0, 1, len(df)))

# Two-way fixed effects DiD, SEs clustered by district
m = smf.ols("y ~ treated:post + C(unit) + C(year)",
            data=df).fit(cov_type="cluster",
                         cov_kwds={"groups": df["unit"]})
print("ATT:", round(m.params["treated:post"], 3),
      "SE:", round(m.bse["treated:post"], 3))
print(m.conf_int().loc["treated:post"].round(3).tolist())

from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import HistGradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import cross_validate
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler

X, y = load_breast_cancer(return_X_y=True)
cv = StratifiedKFold(5, shuffle=True, random_state=42)
metrics = ["roc_auc", "balanced_accuracy", "f1"]

# Benchmark a flexible model against a transparent baseline
models = {
    "logit": make_pipeline(StandardScaler(),
                           LogisticRegression(max_iter=1000)),
    "gbm": HistGradientBoostingClassifier(random_state=42),
}
for name, m in models.items():
    r = cross_validate(m, X, y, cv=cv, scoring=metrics)
    out = [f"{k}={r['test_'+k].mean():.3f}" for k in metrics]
    print(name, *out)

import numpy as np

# Synthetic 10 x 10 grid of areas with a spatial trend
rng = np.random.default_rng(1)
i, j = np.indices((10, 10))
x = (i + j + rng.normal(0, 3, (10, 10))).ravel()

# Rook contiguity weights, row-standardised
idx = np.arange(100).reshape(10, 10)
W = np.zeros((100, 100))
pairs = [(idx[:-1], idx[1:]), (idx[:, :-1], idx[:, 1:])]
for a, b in pairs:
    W[a.ravel(), b.ravel()] = W[b.ravel(), a.ravel()] = 1
W /= W.sum(axis=1, keepdims=True)

# Global Moran's I with a permutation test
z = x - x.mean()
moran = z @ W @ z / (z @ z)
sims = np.array([p @ W @ p / (p @ p) for p in
                 (rng.permutation(z) for _ in range(999))])
p_val = (np.sum(sims >= moran) + 1) / 1000
print(f"Moran's I = {moran:.3f}, pseudo p = {p_val:.3f}")