2024-04-16 18:58:43 +02:00
|
|
|
import pandas as pd
|
|
|
|
|
import numpy as np
|
|
|
|
|
import tensorflow as tf
|
|
|
|
|
|
|
|
|
|
test_data = pd.read_csv('./beer_reviews_test.csv')
|
|
|
|
|
X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
|
2024-05-06 19:39:44 +02:00
|
|
|
y_test = test_data['review_overall']
|
2024-04-16 18:58:43 +02:00
|
|
|
|
|
|
|
|
model = tf.keras.models.load_model('beer_review_sentiment_model.h5')
|
|
|
|
|
|
|
|
|
|
tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=10000)
|
2024-05-06 19:39:44 +02:00
|
|
|
tokenizer.fit_on_texts(X_test)
|
2024-04-16 18:58:43 +02:00
|
|
|
X_test_seq = tokenizer.texts_to_sequences(X_test)
|
|
|
|
|
X_test_pad = tf.keras.preprocessing.sequence.pad_sequences(X_test_seq, maxlen=100)
|
|
|
|
|
|
|
|
|
|
predictions = model.predict(X_test_pad)
|
|
|
|
|
|
2024-05-06 19:39:44 +02:00
|
|
|
results = pd.DataFrame({'Predictions': predictions.flatten(), 'Actual': y_test})
|
|
|
|
|
results.to_csv('beer_review_sentiment_predictions.csv', index=False)
|
