File size: 1,300 Bytes
61c5e06 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
import joblib
# Load dataset
df = pd.read_csv("spam.csv", encoding="latin-1")
# Your dataset uses columns: email, label
df = df[['email', 'label']]
df.columns = ["text", "label"]
# Clean text column
df['text'] = df['text'].astype(str).fillna('').str.strip()
# Clean label column (labels are already 0/1)
df['label'] = pd.to_numeric(df['label'], errors='coerce')
df = df.dropna(subset=['label']) # remove rows if label still NaN
df['label'] = df['label'].astype(int) # ensure int type
# Train-test split
X_train, X_test, y_train, y_test = train_test_split(
df['text'], df['label'], test_size=0.2, random_state=42
)
# TF-IDF
tfidf = TfidfVectorizer(stop_words="english")
X_train_tfidf = tfidf.fit_transform(X_train)
X_test_tfidf = tfidf.transform(X_test)
# Train model
model = LogisticRegression()
model.fit(X_train_tfidf, y_train)
# Accuracy
pred = model.predict(X_test_tfidf)
print("Accuracy:", accuracy_score(y_test, pred))
# Save artifacts
joblib.dump(model, "model.pkl")
joblib.dump(tfidf, "vectorizer.pkl")
|