test_model.py

import pickle
import string
import numpy as np
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from tensorflow.keras.preprocessing.text import one_hot
from tensorflow.keras.preprocessing.sequence import pad_sequences

# Load the model
with open('review.pkl', 'rb') as f:
    model = pickle.load(f)

# Settings (must match training)
DIC_SIZE = 10000
MAXLEN = 953
lem = WordNetLemmatizer()

def clean_text(text):
    text = text.lower()
    text = ''.join([ch for ch in text if ch not in string.punctuation])
    words = text.split()
    words = [lem.lemmatize(w) for w in words if w not in stopwords.words('english')]
    return ' '.join(words)

# Test reviews
test_reviews = [
    "I loved this movie! It was amazing.",
    "Terrible film, waste of time.",
    "Hated every minute of it.",
    "Great acting and story.",
    "Awful, boring, complete garbage."
]

print("="*60)
print("MODEL TEST")
print("="*60)
for review in test_reviews:
    cleaned = clean_text(review)
    encoded = [one_hot(cleaned, DIC_SIZE)]
    padded = pad_sequences(encoded, maxlen=MAXLEN, padding='post')
    pred = model.predict(padded, verbose=0)[0][0]
    sentiment = 'positive' if pred > 0.5 else 'negative'
    print(f"Review: {review}")
    print(f"Cleaned: {cleaned}")
    print(f"Prediction score: {pred:.4f}")
    print(f"Sentiment: {sentiment}")
    print("-"*60)