script.py

### This is example of the script that will be run in the test environment.

### You can change the rest of the code to define and test your solution.
### However, you should not change the signature of the provided function.
### The script saves "submission.parquet" file in the current directory.
### You can use any additional files and subdirectories to organize your code.

from pathlib import Path
from tqdm import tqdm
import pandas as pd
import numpy as np
from datasets import load_dataset
from typing import Dict

def empty_solution(sample):
    '''Return a minimal valid solution, i.e. 2 vertices and 1 edge.'''
    return np.zeros((2,3)), [(0, 1)]

class Sample(Dict):
    def pick_repr_data(self, x):
        if hasattr(x, 'shape'):
            return x.shape
        if isinstance(x, (str, float, int)):
            return x
        if isinstance(x, list):
            return [type(x[0])] if len(x) > 0 else []
        return type(x)

    def __repr__(self):
        # return str({k: v.shape if hasattr(v, 'shape') else [type(v[0])] if isinstance(v, list) else type(v) for k,v in self.items()})
        return str({k: self.pick_repr_data(v) for k,v in self.items()})
    
import json
if __name__ == "__main__":
    print ("------------ Loading dataset------------ ")
    param_path = Path('params.json')
    print(param_path)
    with param_path.open() as f:
        params = json.load(f)
    print(params)
    import os
    
    print('pwd:')
    os.system('pwd')
    print(os.system('ls -lahtr'))
    print('/tmp/data/')
    print(os.system('ls -lahtrR /tmp/data/'))
    

    data_path_test_server = Path('/tmp/data')
    data_path_local = Path().home() / '.cache/huggingface/datasets/usm3d___hoho25k_test_x/'

    if data_path_test_server.exists():
        data_path = data_path_test_server
    else: 
        data_path = data_path_local
    
    print(data_path)

    # dataset = load_dataset(params['dataset'], trust_remote_code=True, use_auth_token=params['token'])
    data_files = {
        "validation": [str(p) for p in [*data_path.rglob('*validation*.arrow')]+[*data_path.rglob('*public*/**/*.tar')]],
        "test": [str(p) for p in [*data_path.rglob('*test*.arrow')]+[*data_path.rglob('*private*/**/*.tar')]],
    }
    print(data_files)


    try:
        dataset = load_dataset(
            "arrow", 
            data_files=data_files,
            trust_remote_code=True,
            # streaming=True
        )
        print('load with arrow')
    except:
        dataset = load_dataset(
            "webdataset", 
            data_files=data_files,
            trust_remote_code=True,
            # streaming=True
        )
        print('load with webdataset')

    print(dataset, flush=True)
    # dataset = load_dataset('webdataset', data_files={)
    
    print('------------ Now you can do your solution ---------------')
    solution = []
    for subset_name in dataset:
        for i, sample in enumerate(tqdm(dataset[subset_name])):
            # replace this with your solution
            print(Sample(sample), flush=True)
            print('------')
            pred_vertices, pred_edges = empty_solution(sample)
            solution.append({
                            'order_id': sample['order_id'], 
                            'wf_vertices': pred_vertices.tolist(),
                            'wf_edges': pred_edges
                        })
        
    print('------------ Saving results ---------------')
    sub = pd.DataFrame(solution, columns=["order_id", "wf_vertices", "wf_edges"])
    sub.to_parquet("submission.parquet")
    print("------------ Done ------------ ")