36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
# --- Import librerie ---
|
|
import pandas as pd
|
|
from openai import AzureOpenAI
|
|
import os
|
|
import json
|
|
from sentence_transformers import SentenceTransformer
|
|
import numpy as np
|
|
|
|
base_folder = r"C:\Users\Arianna\Desktop\AutomationDataset"
|
|
dataset_rows = []
|
|
subfolders = [f for f in os.listdir(base_folder) if os.path.isdir(os.path.join(base_folder, f))]
|
|
for subfolder in subfolders:
|
|
subfolder_path = os.path.join(base_folder, subfolder)
|
|
#Cerco file "automation-descriptions" (json)
|
|
for file_name in os.listdir(subfolder_path):
|
|
if "automation-descriptions" in file_name and file_name.endswith(".json"):
|
|
file_path = os.path.join(subfolder_path, file_name)
|
|
with open(file_path, "r", encoding="utf-8") as f:
|
|
try:
|
|
data = json.load(f)
|
|
for entry in data:
|
|
# Prendo solo il campo human_like
|
|
row = {
|
|
"automation_id": entry.get("id", ""),
|
|
"human_like": entry.get("result", {}).get("human_like", ""),
|
|
"folder": subfolder
|
|
}
|
|
dataset_rows.append(row)
|
|
except Exception as e:
|
|
print(f"Errore nel file {file_path}: {e}")
|
|
|
|
df_unlabeled = pd.DataFrame(dataset_rows)
|
|
path = r"C:\Users\Arianna\Desktop\secureTAP+\main\datasets\unlabeled_dataset2.xlsx"
|
|
df_unlabeled.to_excel(path, index=False)
|
|
|