import pandas as pd
import os
file1 = 'SnakeCLEF2023-TrainMetadata-iNat.csv'
root = '/data1/dataset/SnakeCLEF2024/'
filehmp = 'SnakeCLEF2023-TrainMetadata-HM.csv'

df1 = pd.read_csv(file1)
path1 = 'SnakeCLEF2023-large_size/'
df1['image_path'] = path1 + df1['image_path']
df2 = pd.read_csv(filehmp)
df_full = pd.concat([df1, df2],axis=0, ignore_index=True)
df_full['endemic'] = df_full['endemic'].astype(bool)
df_full['class_id'] = df_full['class_id'].astype(int)
for col in df_full.columns:
    if col not in ['endemic', 'class_id']:
        df_full[col] = df_full[col].astype(str)


image_exists = df_full['image_path'].apply(lambda x: os.path.exists(os.path.join(root, x)))
df_full = df_full[image_exists].reset_index(drop=True)

df_full.to_csv('train_full.csv', index=False)
print('suceess')