import pandas as pd
from sklearn.metrics import accuracy_score, precision_recall_fscore_support, mean_squared_error
from math import sqrt
import sys

data = pd.read_csv('beer_review_sentiment_predictions.csv')
y_pred = data['Predictions']
y_test = data['Actual']
y_test_binary = (y_test >= 3).astype(int)

build_number = sys.argv[1]

accuracy = accuracy_score(y_test_binary, y_pred.round())
precision, recall, f1, _ = precision_recall_fscore_support(y_test_binary, y_pred.round(), average='micro')
rmse = sqrt(mean_squared_error(y_test, y_pred))

print(f'Accuracy: {accuracy}')
print(f'Micro-avg Precision: {precision}')
print(f'Micro-avg Recall: {recall}')
print(f'F1 Score: {f1}')
print(f'RMSE: {rmse}')

with open(r"beer_metrics.txt", "a") as f:
    f.write(f"{accuracy},{build_number}\n")