Mashq 1: penguins — uchta sinf

import pandas as pd

pg = pd.read_csv(DATA / "penguins.csv")
print("shakli:", pg.shape)
print()
print(pg.dtypes.to_string())
print()
show(pg.head(6))

print("Sinflar:")
print(pg.species.value_counts().to_string())
print()
print("nisbat:")
print(pg.species.value_counts(normalize=True).round(3).to_string())
print()
yoq = pg.isna().sum()
print("Bo'sh qiymatlar:")
print(yoq[yoq > 0].to_string())

import pandas as pd
show(pd.DataFrame([
    {"#": 1, "Yozib qo'yiladigan javob": "Nechta qator, nechta ustun"},
    {"#": 2, "Yozib qo'yiladigan javob": "\"Men ___ ni ___ dan bashorat qilaman\" — bitta jumla"},
    {"#": 3, "Yozib qo'yiladigan javob": "Vazifa turi: regression / binary / multiclass"},
    {"#": 4, "Yozib qo'yiladigan javob": "Target nisbati va BAZA raqami"},
    {"#": 5, "Yozib qo'yiladigan javob": "Split qildingizmi? stratify kerakmi?"},
    {"#": 6, "Yozib qo'yiladigan javob": "Dummy natijasi"},
    {"#": 7, "Yozib qo'yiladigan javob": "Qaysi ustunlarni tashladingiz va NEGA"},
    {"#": 8, "Yozib qo'yiladigan javob": "Missing va turlar bilan nima qildingiz"},
    {"#": 9, "Yozib qo'yiladigan javob": "Birinchi halol natijangiz"},
    {"#": 10, "Yozib qo'yiladigan javob": "Qaysi metrikani tanladingiz va NEGA"},
    {"#": 11, "Yozib qo'yiladigan javob": "Xatolar qaysi guruhda to'plangan"},
    {"#": 12, "Yozib qo'yiladigan javob": "Qaysi BITTA o'zgarishni qildingiz va natija"},
]))

from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
from sklearn.dummy import DummyClassifier
from sklearn.metrics import accuracy_score, f1_score, confusion_matrix, classification_report

son = ["bill_length_mm", "bill_depth_mm", "flipper_length_mm", "body_mass_g"]
matn = ["island", "sex"]
X, y = pg[son + matn], pg["species"]
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.3, random_state=42, stratify=y)

baza = accuracy_score(y_te, DummyClassifier(strategy="most_frequent").fit(X_tr[son], y_tr).predict(X_te[son]))

quvur = Pipeline([
    ("tayyorla", ColumnTransformer([
        ("son", Pipeline([("toldir", SimpleImputer(strategy="median")),
                          ("shkala", StandardScaler())]), son),
        ("matn", Pipeline([("toldir", SimpleImputer(strategy="most_frequent")),
                           ("kod", OneHotEncoder(handle_unknown="ignore"))]), matn),
    ])),
    ("model", LogisticRegression(max_iter=3000)),
]).fit(X_tr, y_tr)

b = quvur.predict(X_te)
print(f"BAZA (most_frequent): {baza:.4f}")
print(f"Model accuracy      : {accuracy_score(y_te, b):.4f}")
print(f"Model macro F1      : {f1_score(y_te, b, average='macro'):.4f}")
print(f"Model weighted F1   : {f1_score(y_te, b, average='weighted'):.4f}")
cv = cross_val_score(quvur, X, y, cv=5, scoring="f1_macro")
print(f"CV macro F1         : {cv.mean():.4f} ±{cv.std():.4f}")

print("3x3 confusion matrix:")
sinflar = sorted(y.unique())
cm = confusion_matrix(y_te, b, labels=sinflar)
print(pd.DataFrame(cm, index=[f"haqiqat: {s}" for s in sinflar],
                   columns=[f"bashorat: {s}" for s in sinflar]).to_string())
print()
print(classification_report(y_te, b, digits=4))

print("island ustuni target bilan:")
print(pd.crosstab(pg.island, pg.species).to_string())