Bagging va Random Forest

import pandas as pd
import numpy as np

r = np.random.default_rng(42)
n_model, n_namuna = 100, 2000
haqiqat = r.choice([0, 1], n_namuna)

# har bir "model" 60% aniqlikda, lekin xatolari MUSTAQIL
mustaqil = np.array([np.where(r.random(n_namuna) < 0.60, haqiqat, 1 - haqiqat)
                     for _ in range(n_model)])
ovoz = (mustaqil.mean(axis=0) > 0.5).astype(int)

print(f"Bitta modelning aniqligi      : {(mustaqil[0] == haqiqat).mean():.4f}")
print(f"100 ta modelning o'rtacha ball: {(mustaqil == haqiqat).mean():.4f}")
print(f"OVOZ BERISH natijasi          : {(ovoz == haqiqat).mean():.4f}")

# hamma model BIR XIL xato qiladi (to'liq bog'liq)
bitta_naqsh = np.where(r.random(n_namuna) < 0.60, haqiqat, 1 - haqiqat)
bogliq = np.array([bitta_naqsh for _ in range(n_model)])
ovoz_b = (bogliq.mean(axis=0) > 0.5).astype(int)
print(f"Xatolar BOG'LIQ bo'lsa, ovoz berish: {(ovoz_b == haqiqat).mean():.4f}")
print()
print("Xulosa: ensemble faqat modellar BIR-BIRIDAN FARQ qilsa ishlaydi.")

namuna = np.arange(10)
for i in range(3):
    bs = np.random.default_rng(i).choice(namuna, size=10, replace=True)
    yoq = sorted(set(namuna) - set(bs))
    print(f"  {i+1}-bootstrap: {bs}  |  tushmagan: {yoq}")
print()
# har bootstrap da taxminan 37% qator tushmaydi
tushmagan = [len(set(np.arange(1000)) - set(np.random.default_rng(s).choice(1000, 1000, replace=True)))/1000
             for s in range(50)]
print(f"O'rtacha necha foiz qator tushmaydi: {np.mean(tushmagan):.1%}")
print("Bu — matematik fakt: (1 - 1/n)^n -> 1/e = 0.368")

from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import BaggingClassifier, RandomForestClassifier

df = pd.read_csv(DATA / "uy_ijara.csv")
son = ["xonalar", "maydon_m2", "qavat", "qavatlar_soni", "metro_km", "mebel"]
X, y = df[son], df["ijaraga_berildi_30k"]
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.3, random_state=42, stratify=y)

print(f"{'model':<40} {'CV F1':>9} {'±':>8}")
print("-" * 58)
for nom, m in [
    ("Bitta daraxt (chegarasiz)", DecisionTreeClassifier(random_state=42)),
    ("Bitta daraxt (max_depth=6)", DecisionTreeClassifier(max_depth=6, random_state=42)),
    ("Bagging (100 chegarasiz daraxt)", BaggingClassifier(
        DecisionTreeClassifier(random_state=42), n_estimators=100, random_state=42)),
]:
    b = cross_val_score(m, X, y, cv=5, scoring="f1")
    print(f"{nom:<40} {b.mean():>9.4f} {b.std():>8.4f}")

show(pd.DataFrame([
    {"Qadam": "1. Bootstrap namuna", "Bagging": "HA", "Random Forest": "HA"},
    {"Qadam": "2. Har bo'linishda ustunlarning QISMI", "Bagging": "yo'q (hammasi)",
     "Random Forest": "HA — max_features"},
]))
print()
print("Shu bitta qo'shimcha daraxtlarni ancha farqli qiladi.")

print(f"{'model':<40} {'CV F1':>9} {'±':>8}")
print("-" * 58)
for nom, m in [
    ("Bagging (hamma ustun)", BaggingClassifier(
        DecisionTreeClassifier(random_state=42), n_estimators=100, random_state=42)),
    ("Random Forest (max_features='sqrt')", RandomForestClassifier(
        n_estimators=100, random_state=42)),
    ("Random Forest (max_features=None)", RandomForestClassifier(
        n_estimators=100, max_features=None, random_state=42)),
]:
    b = cross_val_score(m, X, y, cv=5, scoring="f1")
    print(f"{nom:<40} {b.mean():>9.4f} {b.std():>8.4f}")
print()
print("Uchinchi qator — max_features=None bo'lsa RF aslida Bagging ga aylanadi.")

from sklearn.metrics import f1_score

print(f"{'random_state':>13} {'bitta daraxt':>14} {'Random Forest':>15}")
print("-" * 46)
d_ballar, rf_ballar = [], []
for rs in [0, 1, 7, 13, 42, 99, 123, 2026]:
    Xa, Xb, ya, yb = train_test_split(X, y, test_size=0.3, random_state=rs, stratify=y)
    d = DecisionTreeClassifier(random_state=42).fit(Xa, ya)
    rf = RandomForestClassifier(n_estimators=100, random_state=42).fit(Xa, ya)
    df_ = f1_score(yb, d.predict(Xb)); rf_ = f1_score(yb, rf.predict(Xb))
    d_ballar.append(df_); rf_ballar.append(rf_)
    print(f"{rs:>13} {df_:>14.4f} {rf_:>15.4f}")
print("-" * 46)
print(f"{'tarqalish':>13} {np.std(d_ballar):>14.4f} {np.std(rf_ballar):>15.4f}")

rf_oob = RandomForestClassifier(n_estimators=300, oob_score=True, random_state=42).fit(X_tr, y_tr)
print(f"OOB score (bepul, CV kerak emas): {rf_oob.oob_score_:.4f}")
print(f"Test to'plamidagi accuracy       : {rf_oob.score(X_te, y_te):.4f}")
cv_acc = cross_val_score(RandomForestClassifier(n_estimators=300, random_state=42), X, y, cv=5).mean()
print(f"5-fold CV accuracy (qimmat)      : {cv_acc:.4f}")

import time
print(f"{'n_estimators':>13} {'CV F1':>9} {'±':>8} {'vaqt':>9}")
print("-" * 44)
for n in [1, 10, 50, 200, 500]:
    t0 = time.perf_counter()
    b = cross_val_score(RandomForestClassifier(n_estimators=n, random_state=42, n_jobs=1),
                        X, y, cv=5, scoring="f1")
    dt = time.perf_counter() - t0
    print(f"{n:>13} {b.mean():>9.4f} {b.std():>8.4f} {dt:>8.1f}s")

show(pd.DataFrame([
    {"": "Bagging / RF", "Daraxtlar qanday o'stiriladi": "PARALLEL — bir-biridan mustaqil",
     "Har daraxt nima qiladi": "Butun vazifani mustaqil hal qiladi",
     "Nimani kamaytiradi": "VARIANCE (beqarorlik)",
     "Daraxt turi": "Chuqur, chegarasiz"},
    {"": "Boosting", "Daraxtlar qanday o'stiriladi": "KETMA-KET — har biri oldingisining xatosiga qaraydi",
     "Har daraxt nima qiladi": "Oldingi xatoni tuzatadi",
     "Nimani kamaytiradi": "BIAS (aniqlik yetishmasligi)",
     "Daraxt turi": "Sayoz (depth 3-6)"},
]))

from sklearn.inspection import permutation_importance

rf = RandomForestClassifier(n_estimators=300, random_state=42).fit(X_tr, y_tr)
d1 = DecisionTreeClassifier(max_depth=6, random_state=42).fit(X_tr, y_tr)
pi = permutation_importance(rf, X_te, y_te, n_repeats=20, random_state=42, scoring="f1")

show(pd.DataFrame({
    "xususiyat": son,
    "bitta daraxt": d1.feature_importances_.round(4),
    "Random Forest": rf.feature_importances_.round(4),
    "RF permutation": pi.importances_mean.round(4),
}).sort_values("RF permutation", ascending=False))

from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

yn = df["narx_usd"]
print(f"{'model':<34} {'CV R2':>9} {'±':>8}")
print("-" * 52)
for nom, m in [
    ("LinearRegression (14-bob)", Pipeline([("sc", StandardScaler()), ("m", LinearRegression())])),
    ("DecisionTreeRegressor", __import__("sklearn.tree", fromlist=["DecisionTreeRegressor"]).DecisionTreeRegressor(max_depth=8, random_state=42)),
    ("RandomForestRegressor", RandomForestRegressor(n_estimators=200, random_state=42)),
]:
    b = cross_val_score(m, X, yn, cv=5, scoring="r2")
    print(f"{nom:<34} {b.mean():>9.4f} {b.std():>8.4f}")

katta = pd.DataFrame([{"xonalar": 10, "maydon_m2": 500.0, "qavat": 3,
                       "qavatlar_soni": 5, "metro_km": 1.0, "mebel": 1}])
lin = Pipeline([("sc", StandardScaler()), ("m", LinearRegression())]).fit(X, yn)
rfr = RandomForestRegressor(n_estimators=200, random_state=42).fit(X, yn)
print(f"Train dagi eng katta narx : {yn.max()}")
print(f"500 m2 kvartira uchun bashorat:")
print(f"  LinearRegression : {lin.predict(katta)[0]:.0f}   <- diapazondan CHIQDI")
print(f"  RandomForest     : {rfr.predict(katta)[0]:.0f}   <- diapazonda QOLDI")

show(pd.DataFrame([
    {"Tushuncha": "Ensemble sharti", "Bitta jumla": "Modellar bir-biridan FARQ qilishi kerak"},
    {"Tushuncha": "Bootstrap", "Bitta jumla": "Qaytarish bilan namuna; ~37% qator tushmaydi"},
    {"Tushuncha": "Bagging", "Bitta jumla": "Har daraxtga boshqa namuna"},
    {"Tushuncha": "Random Forest", "Bitta jumla": "Bagging + har bo'linishda ustunlarning qismi"},
    {"Tushuncha": "Nimani tuzatadi", "Bitta jumla": "Variance — bitta daraxtning beqarorligi"},
    {"Tushuncha": "OOB score", "Bitta jumla": "Bepul validation, CV dan 5 marta arzon"},
    {"Tushuncha": "n_estimators", "Bitta jumla": "Oshirish overfitting QILMAYDI — faqat vaqt"},
    {"Tushuncha": "Bagging vs Boosting", "Bitta jumla": "Parallel+mustaqil vs ketma-ket+bog'liq"},
    {"Tushuncha": "Regression cheklovi", "Bitta jumla": "Daraxt ekstrapolyatsiya qilmaydi"},
]))