Upload folder using huggingface_hub

README.md

@@ -1,4 +1,14 @@
-# My Cool Submission 2025
+# Empty solution example for the S23DR competition
 
-This repo contains a submission to the [S23DR Challenge](https://huggingface.co/spaces/usm3d/S23DR) (part of the [USM3D](https://usm3d.github.io/) workshop at CVPR2025). It was prepared by [jacklangerman](https://huggingface.co/jacklangerman).
+This repo provides a minimalistic example of a valid, but empty submission to S23DR competition.
+We recommend you take a look at [this example](https://huggingface.co/usm3d/handcrafted_baseline_submission),
+which implements some primitive algorithms and provides useful I/O and visualization functions.
+
+This example seeks to simply provide minimal code which succeeds at reading the dataset and producing a solution (in this case two vertices at the origin and edge of zero length connecting them).
+
+`script.py` - is the main file which is run by the competition space. It should produce `submission.parquet` as the result of the run. Please see the additional comments in the `script.py` file. 
+
+---
+license: apache-2.0
+---
 

script.py

@@ -1,58 +1,56 @@
 ### This is example of the script that will be run in the test environment.
-### Some parts of the code are compulsory and you should NOT CHANGE THEM.
-### They are between '''---compulsory---''' comments.
+
 ### 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 would save "submission.parquet" file in the current directory.
+### The script saves "submission.parquet" file in the current directory.
 ### You can use any additional files and subdirectories to organize your code.
 
-'''---compulsory---'''
-import hoho; hoho.setup() # YOU MUST CALL hoho.setup() BEFORE ANYTHING ELSE
-'''---compulsory---'''
-
 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()})
+    
 
 if __name__ == "__main__":
     print ("------------ Loading dataset------------ ")
-    params = hoho.get_params()
-    
-    # by default it is usually better to use `get_dataset()` like this
-    # 
-    # dataset = hoho.get_dataset(split='all')
-    # 
-    # but in this case (because we don't do anything with the sample 
-    # anyway) we set `decode=None`. We can set the `split` argument 
-    # to 'train' or 'val' ('all' defaults back to 'train') if we are 
-    # testing ourselves locally. 
-    # 
-    # dataset = hoho.get_dataset(split='val', decode=None)
-    #
-    # On the test server *`split` must be set to 'all'* 
-    # to compute both the public and private leaderboards.
-    # 
-    dataset = hoho.get_dataset(split='all', decode=None)
+    dataset = load_dataset("usm3d/hoho25k_test_x", trust_remote_code=True)
+
     
     print('------------ Now you can do your solution ---------------')
     solution = []
-    for i, sample in enumerate(tqdm(dataset)):
-        # replace this with your solution
-        pred_vertices, pred_edges = empty_solution(sample)
+    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
+                        })
         
-        solution.append({
-                        '__key__': sample['__key__'], 
-                        'wf_vertices': pred_vertices.tolist(),
-                        'wf_edges': pred_edges
-                    })
     print('------------ Saving results ---------------')
-    sub = pd.DataFrame(solution, columns=["__key__", "wf_vertices", "wf_edges"])
-    sub.to_parquet(Path(params['output_path']) / "submission.parquet")
+    sub = pd.DataFrame(solution, columns=["order_id", "wf_vertices", "wf_edges"])
+    sub.to_parquet("submission.parquet")
     print("------------ Done ------------ ")