This commit is contained in:
AWieczarek 2024-05-06 19:39:44 +02:00
parent f5f69a488b
commit 4e825aa649
2 changed files with 19 additions and 18 deletions

View File

@ -4,15 +4,16 @@ import tensorflow as tf
test_data = pd.read_csv('./beer_reviews_test.csv') test_data = pd.read_csv('./beer_reviews_test.csv')
X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']] X_test = test_data[['review_aroma', 'review_appearance', 'review_palate', 'review_taste']]
y_test = test_data['review_overall']
model = tf.keras.models.load_model('beer_review_sentiment_model.h5') model = tf.keras.models.load_model('beer_review_sentiment_model.h5')
tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=10000) tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=10000)
tokenizer.fit_on_texts(X_test)
X_test_seq = tokenizer.texts_to_sequences(X_test) X_test_seq = tokenizer.texts_to_sequences(X_test)
X_test_pad = tf.keras.preprocessing.sequence.pad_sequences(X_test_seq, maxlen=100) X_test_pad = tf.keras.preprocessing.sequence.pad_sequences(X_test_seq, maxlen=100)
predictions = model.predict(X_test_pad) predictions = model.predict(X_test_pad)
np.savetxt('beer_review_sentiment_predictions.csv', predictions, delimiter=',', fmt='%.10f') results = pd.DataFrame({'Predictions': predictions.flatten(), 'Actual': y_test})
results.to_csv('beer_review_sentiment_predictions.csv', index=False)

View File

@ -1,19 +1,19 @@
from sklearn.metrics import confusion_matrix
import pandas as pd import pandas as pd
import sys from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
from math import sqrt
# Load the predictions data
data = pd.read_csv('beer_review_sentiment_predictions.csv')
y_pred = data['Predictions']
y_test = data['Actual']
def main(): # Calculate metrics
y_test = pd.read_csv("beer_reviews_test.csv") accuracy = accuracy_score(y_test, y_pred.round())
y_pred = pd.read_csv("beer_review_sentiment_predictions.csv", header=None) precision, recall, f1, _ = precision_recall_fscore_support(y_test, y_pred.round(), average='micro')
build_number = sys.argv[1] rmse = sqrt(mean_squared_error(y_test, y_pred))
cm = confusion_matrix(y_test, y_pred) print(f'Accuracy: {accuracy}')
accuracy = cm[1, 1] / (cm[1, 0] + cm[1, 1]) print(f'Micro-avg Precision: {precision}')
print(f'Micro-avg Recall: {recall}')
with open(r"beer_metrics.txt", "a") as f: print(f'F1 Score: {f1}')
f.write(f"{accuracy},{build_number}\n") print(f'RMSE: {rmse}')
if __name__ == "__main__":
main()