From c78a1c7bd0da13fdb2ec3b2bf2207a8cf8d7ad3e Mon Sep 17 00:00:00 2001
From: Scott Stevenson <scott@stevenson.io>
Date: Tue, 3 Dec 2024 22:19:49 +0000
Subject: [PATCH] Add missing call to parent constructor in SimulationDataset

The `SimulationDataset` was missing a call to the parent
`StreamingDataset` constructor, which led to errors when
accessing attributes that are set in that constructor, such as
`epoch_seed_change`:

```
AttributeError: 'SimulationDataset' object has no attribute 'epoch_seed_change'
Traceback:
File "/home/scott/projects/streaming/.venv/lib64/python3.12/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 88, in exec_func_with_error_handling
    result = func()
             ^^^^^^
File "/home/scott/projects/streaming/.venv/lib64/python3.12/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 579, in code_to_exec
    exec(code, module.__dict__)
File "/home/scott/projects/streaming/simulation/interfaces/sim_ui.py", line 409, in <module>
    submit_jobs(shuffle_quality, dataset, time_per_sample, node_internet_bandwidth,
File "/home/scott/projects/streaming/simulation/interfaces/sim_ui.py", line 110, in submit_jobs
    for output in gen_sim:
                  ^^^^^^^
File "/home/scott/projects/streaming/simulation/core/main.py", line 110, in simulate
    samples_per_node = dataset.get_samples_per_node(epoch, 0)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/scott/projects/streaming/simulation/core/sim_dataset.py", line 367, in get_samples_per_node
    partition = generate_work(self.batching_method, self, self.world, epoch, sample_in_epoch)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/scott/projects/streaming/streaming/base/batching/__init__.py", line 45, in generate_work
    return get(dataset, world, epoch, sample_in_epoch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/scott/projects/streaming/streaming/base/batching/random.py", line 49, in generate_work_random_batching
    shuffle_units, small_per_big = dataset.resample_streams(epoch)
                                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/scott/projects/streaming/streaming/base/dataset.py", line 878, in resample_streams
    epoch, self.epoch_seed_change)
           ^^^^^^^^^^^^^^^^^^^^^^
```

Closes https://github.com/mosaicml/streaming/issues/831
---
 simulation/core/sim_dataset.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/simulation/core/sim_dataset.py b/simulation/core/sim_dataset.py
index 8d1fb176e..3d083fb8d 100644
--- a/simulation/core/sim_dataset.py
+++ b/simulation/core/sim_dataset.py
@@ -135,6 +135,29 @@ def __init__(self,
         # Time how long it takes for StreamingDataset instantiation
         t0 = time.time()
 
+        super().__init__(streams=streams,
+                         remote=remote,
+                         local=local,
+                         split=split,
+                         download_retry=download_retry,
+                         download_timeout=download_timeout,
+                         validate_hash=validate_hash,
+                         keep_zip=keep_zip,
+                         epoch_size=epoch_size,
+                         predownload=predownload,
+                         cache_limit=cache_limit,
+                         partition_algo=partition_algo,
+                         num_canonical_nodes=num_canonical_nodes,
+                         batch_size=batch_size,
+                         shuffle=shuffle,
+                         shuffle_algo=shuffle_algo,
+                         shuffle_seed=shuffle_seed,
+                         shuffle_block_size=shuffle_block_size,
+                         sampling_method=sampling_method,
+                         sampling_granularity=sampling_granularity,
+                         batching_method=batching_method,
+                         allow_unsafe_types=allow_unsafe_types)
+
         # Global arguments (which do not live in Streams).
         self.nodes = nodes
         self.devices = devices