spam_ham_prediction.py

x = np.random.randint(0, Xtest.shape[0] - 1)

sentence = test_df['Message'].values[x]
print("Sentence: ", sentence)

cleaned_sentence = []
sentence = removeURL(sentence) 
sentence = removeHTML(sentence)
sentence = onlyAlphabets(sentence) 
sentence = sentence.lower() 
sentence = removeRecurring(sentence)

for word in sentence.split():
    #if word not in stop:
        stemmed = sno.stem(word)
        cleaned_sentence.append(stemmed)

sentence = [' '.join(cleaned_sentence)]
print("\nCleaned sentence: ", sentence[0])

sentence = cv.transform(sentence)
sentence = tfidf.transform(sentence)

print("\nTrue value: ", columns[test_df['Category'].values[x]])

pred = model.predict(sentence.toarray())[0][0]
print("\nPredicted value: ", columns[int(pred>0.5)], "(", pred, "-->", (pred>0.5).astype('int'), ")")