مصنفات بايز الساذجة

from sklearn.naive_bayes import MultinomialNB, ComplementNB, GaussianNB
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.pipeline import Pipeline
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn.calibration import CalibratedClassifierCV
from sklearn.preprocessing import LabelEncoder

class="tok-comment"># ── Sample text data ───────────────────────────────────────────────────
X_text = [
    class="tok-str">"buy cheap pills now", class="tok-str">"get rich quick scheme", class="tok-str">"free money click here",
    class="tok-str">"meeting at 3pm tomorrow", class="tok-str">"quarterly report attached", class="tok-str">"team lunch Friday",
    class="tok-str">"win a prize enter now", class="tok-str">"limited offer act fast", class="tok-str">"investment opportunity",
    class="tok-str">"project deadline next week", class="tok-str">"budget review scheduled", class="tok-str">"please review document",
] * class="tok-num">20   class="tok-comment"># class="tok-num">240 samples
y_raw = ([class="tok-num">1, class="tok-num">1, class="tok-num">1, class="tok-num">0, class="tok-num">0, class="tok-num">0, class="tok-num">1, class="tok-num">1, class="tok-num">1, class="tok-num">0, class="tok-num">0, class="tok-num">0] * class="tok-num">20)  class="tok-comment"># class="tok-num">1=spam, class="tok-num">0=ham
import numpy as np
y = np.array(y_raw)
X_train, X_test, y_train, y_test = train_test_split(
    X_text, y, test_size=class="tok-num">0.2, random_state=class="tok-num">42)

class="tok-comment"># ── Text classification (spam detection) ──────────────────────────
pipe = Pipeline([
    (class="tok-str">'tfidf', TfidfVectorizer(
        ngram_range=(class="tok-num">1,class="tok-num">2),       class="tok-comment"># unigrams + bigrams
        max_features=50_000,
        sublinear_tf=True,       class="tok-comment"># log(class="tok-num">1+tf)
        min_df=class="tok-num">3,
    )),
    (class="tok-str">'clf', ComplementNB(alpha=class="tok-num">0.1)),  class="tok-comment"># best for text
])

scores = cross_val_score(pipe, X_text, y, cv=class="tok-num">5, scoring=class="tok-str">'f1_macro')
print(fclass="tok-str">"F1: {scores.mean():.3f} ± {scores.std():.3f}")

class="tok-comment"># ── Calibrated probabilities ───────────────────────────────────────
class="tok-comment"># NB probabilities are often poorly calibrated (overconfident)
class="tok-comment"># Use isotonic regression calibration for better probability estimates
pipe_cal = CalibratedClassifierCV(pipe, cv=class="tok-num">5, method=class="tok-str">'isotonic')
pipe_cal.fit(X_train, y_train)
probs = pipe_cal.predict_proba(X_test)

class="tok-comment"># ── Continuous features: GaussianNB ────────────────────────────────
from sklearn.preprocessing import StandardScaler
gnb = Pipeline([
    (class="tok-str">'scaler', StandardScaler()),
    (class="tok-str">'clf', GaussianNB(var_smoothing=class="tok-num">1e-9)),
])
gnb.fit(X_train, y_train)
print(fclass="tok-str">"GaussianNB accuracy: {gnb.score(X_test, y_test):.3f}")

class="tok-comment"># ── Inspect learned parameters ─────────────────────────────────────
nb = gnb.named_steps[class="tok-str">'clf']
print(class="tok-str">"Class priors:", nb.class_prior_)
print(class="tok-str">"Feature means per class:", nb.theta_)   class="tok-comment"># shape (n_classes, n_features)