مشروع: مصنّف Spam

1. تحميل / إنشاء البيانات
2. فصل X (الميزات) و y (الهدف)
3. تقسيم train/test
4. تدريب LogisticRegression
5. تنبّؤ على test
6. تقييم الدقّة + Precision/Recall/F1 + confusion matrix
7. تجربة + تعديل

import numpy as np
import pandas as pd

# كل رسالة: [contains_offer, has_free_word, has_money_word, has_urgent, has_link, length_normal]
data = [
    # 10 عادية
    [0, 0, 0, 0, 1, 1], [0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 1, 0],
    [0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 1, 1], [0, 0, 0, 0, 0, 1],
    [0, 0, 0, 0, 1, 0], [0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 1, 0],
    [0, 0, 0, 0, 0, 1],
    # 10 مزعجة
    [1, 1, 1, 1, 1, 0], [1, 1, 1, 1, 1, 0], [1, 1, 1, 1, 1, 0],
    [1, 1, 0, 1, 1, 0], [1, 1, 1, 1, 1, 0], [0, 1, 1, 1, 1, 0],
    [1, 1, 1, 1, 1, 0], [1, 1, 1, 0, 1, 0], [1, 1, 1, 1, 1, 0],
    [1, 1, 1, 1, 1, 0],
]
labels = [0]*10 + [1]*10

df = pd.DataFrame(data, columns=['offer', 'free', 'money', 'urgent', 'link', 'normal_len'])
df['is_spam'] = labels

print(f"عدد الرسائل: {len(df)}")
print(f"مزعج: {df['is_spam'].sum()}, عادي: {(df['is_spam']==0).sum()}")

X = df.drop('is_spam', axis=1)
y = df['is_spam']

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42, stratify=y
)
print(f"Train: {len(X_train)}, Test: {len(X_test)}")

from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

# Pipeline: تطبيع + نموذج
pipe = Pipeline([
    ('scaler', StandardScaler()),
    ('model', LogisticRegression(random_state=42, max_iter=1000))
])

pipe.fit(X_train, y_train)

y_pred = pipe.predict(X_test)
y_proba = pipe.predict_proba(X_test)
print("احتمالات (P(0), P(1)):", y_proba[:3])

from sklearn.metrics import (
    accuracy_score, precision_score, recall_score,
    f1_score, confusion_matrix, classification_report
)

print(f"Accuracy:  {accuracy_score(y_test, y_pred):.3f}")
print(f"Precision: {precision_score(y_test, y_pred):.3f}")
print(f"Recall:    {recall_score(y_test, y_pred):.3f}")
print(f"F1:        {f1_score(y_test, y_pred):.3f}")
print()
print("Confusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print()
print(classification_report(y_test, y_pred, target_names=['عادي', 'مزعج']))

import numpy as np

# المعاملات بعد التطبيع
model = pipe.named_steps['model']
coef = model.coef_[0]

print("معاملات النموذج (بعد التطبيع):")
for feature, c in zip(X.columns, coef):
    direction = "يزيد احتمال spam" if c > 0 else "يقلل احتمال spam"
    print(f"  {feature:15s}: {c:+.3f}  ({direction})")

from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

pipe_rf = Pipeline([
    ('scaler', StandardScaler()),
    ('model', RandomForestClassifier(n_estimators=100, max_depth=3, random_state=42))
])

pipe_rf.fit(X_train, y_train)
y_pred_rf = pipe_rf.predict(X_test)
print(f"RF Accuracy: {accuracy_score(y_test, y_pred_rf):.3f}")

from sklearn.model_selection import cross_val_score

scores = cross_val_score(pipe, X, y, cv=5, scoring='accuracy')
print(f"CV accuracy: {scores.mean():.3f} ± {scores.std():.3f}")