import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report

# 1. Cargar dataset
df = pd.read_csv("emails_phishing.csv")
X_train, X_test, y_train, y_test = train_test_split(
    df['text'], df['label'], test_size=0.2, random_state=42)

# 2. Vectorización TF-IDF
vectorizer = TfidfVectorizer(max_features=3000)
X_train_vec = vectorizer.fit_transform(X_train)
X_test_vec = vectorizer.transform(X_test)

# 3. Entrenamiento
model = RandomForestClassifier(n_estimators=200, random_state=42)
model.fit(X_train_vec, y_train)

# 4. Evaluación
y_pred = model.predict(X_test_vec)
print(classification_report(y_test, y_pred))