vis_bl.py

import json
import os
from sklearn.metrics import classification_report

def cn(data):
    languages = ['C', 'C#', 'C++', 'Go', 'OCaml', 'PHP', 'Python', 'Ruby', 'Rust', 'JavaScript']
    for lang in languages:
        lang_data = [element for element in data if element['ll2'] == lang]
        view(ll2=lang, data=lang_data)


def view(ll2, data):
    print(ll2)
    
    data = [entry for entry in data if entry['output'] != '']

    for item in data:
        item["output"] = item['output'].split()[0].strip().replace(",", "").replace(".", "")
        item["output"] = item["output"].lower().replace("no", "0").replace("yes", "1")
        item["type"] = item["type"].lower().replace("nonclone", "0").replace("clone", "1")

    all_true_labels = [int(item["type"]) for item in data]
    all_predictions = [int(item["output"]) for item in data]

    print(classification_report(all_true_labels, all_predictions, digits=2))


def main():
    directory = "results/codenet"
    files = os.listdir(directory)

    files=[file for file in files if not (file.startswith('.') or file.startswith('~') or file.startswith('sim') or file.endswith('_xl.json')) ]

    files = sorted(files)

    for filename in files:
        filepath = os.path.join(directory, filename)
        
        try:
            with open(filepath, "r") as file:
                result = json.load(file)

            print("######################", str(filename), "########################")
            #To view all the results for all the LLMs
            #view(ll2="none", data=result)

            #View results for all the LLMs by languages
            cn(result)

        except Exception as e:
            print(f"Error processing file {filename}: {e}")
    

if __name__ == "__main__":
    main()