test.py

# 1. Importera nödvändiga bibliotek
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import classification_report, confusion_matrix

# 2. Ladda in datan
df = pd.read_csv("cleaned_spam_dataset.csv")

# 3. Undersök datan
print("Första raderna i datan:")
print(df.head())
print("\nInformation om dataset:")
print(df.info())
print("\nKlassfördelning:")
print(df['label'].value_counts())

# 4. Förbered message (om inte redan städat – här antar vi att den är städad)
texts = df['message']
labels = df['label'].map({'ham': 0, 'spam': 1})  # konvertera till 0/1

# 5. Text -> TF-IDF
vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(texts)
y = labels

# 6. Dela upp i tränings- och testdata
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 7. Träna modellen
model = MultinomialNB()
model.fit(X_train, y_train)

# 8. Testa modellen
y_pred = model.predict(X_test)

# 9. Utvärdera
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

print("\nConfusion Matrix:")
conf_matrix = confusion_matrix(y_test, y_pred)
sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=['Ham', 'Spam'], yticklabels=['Ham', 'Spam'])
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.title('Confusion Matrix')
plt.show()