minor tutorial updates

Signed-off-by: Sarah Yurick <[email protected]>
NVIDIA · Feb 13, 2025 · 85133a2 · 85133a2
1 parent 7d006e8
commit 85133a2
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/tutorials/pretraining-data-curation/red-pajama-v2-curation-tutorial.ipynb b/tutorials/pretraining-data-curation/red-pajama-v2-curation-tutorial.ipynb
@@ -1804,7 +1804,7 @@
     "components_stage = ConnectedComponents(\n",
     "    cache_dir=cache_dir,\n",
     "    jaccard_pairs_path=edgelist_path,\n",
-    "    id_column=id_field,\n",
+    "    id_field=id_field,\n",
     ")\n",
     "components_stage.cc_workflow(output_path=output_path)\n",
     "print(f\"Connected Component took {time.time()-t0} seconds\")"

diff --git a/tutorials/single_node_tutorial/single_gpu_tutorial.ipynb b/tutorials/single_node_tutorial/single_gpu_tutorial.ipynb
@@ -1338,7 +1338,7 @@
     "t0 = time.time()\n",
     "print(f\"Computing minhashes for {minhash_data_path}\")\n",
     "\n",
-    "# Load data. Only the [minhash_id_field, text_field] columns are needed\n",
+    "# Load data. Only the [minhash_id_field, minhash_text_field] columns are needed\n",
     "files = get_all_files_paths_under(root=minhash_data_path, recurse_subdirectories=False)\n",
     "files = [f for f in files if f.endswith(\".jsonl\")]\n",
     "df = read_data(\n",
@@ -1597,7 +1597,7 @@
     "ddf_bk = DocumentDataset.read_parquet(input_bucket_path, backend=\"cudf\")\n",
     "\n",
     "#Run _MapBuckets()\n",
-    "buckets_to_edges = BucketsToEdges(cache_dir=edgelist_output_dir, id_fields=input_id_field, logger=buckets_to_edges_log_path)\n",
+    "buckets_to_edges = BucketsToEdges(cache_dir=edgelist_output_dir, id_fields=id_field, logger=buckets_to_edges_log_path)\n",
     "res = buckets_to_edges(ddf_bk)\n",
     "\n",
     "print(f\"Time taken for Bucket->Edgelist:{time.time()-t0} s\")"
@@ -1750,7 +1750,7 @@
    },
    "outputs": [],
    "source": [
-    "# cc_compute_res.groupby('group')[input_id_field].agg(list).reset_index()"
+    "# cc_compute_res.groupby('group')[id_field].agg(list).reset_index()"
    ]
   },
   {