Default to sample

conradtsang · Nov 8, 2022 · 11e6a66 · 11e6a66
1 parent c486ee9
commit 11e6a66
Showing 1 changed file with 17 additions and 9 deletions.
diff --git a/exploring-metadata.ipynb b/exploring-metadata.ipynb
@@ -116,17 +116,17 @@
    },
    "outputs": [],
    "source": [
-    "# Download the full dataset (up to a limit of 25,000 documents),\n",
-    "# request it first in the builder environment. See the Constellate Client\n",
-    "# documentation at: https://constellate.org/docs/constellate-client\n",
-    "# Then use the `constellate.download` method show below.\n",
-    "dataset_metadata = constellate.download(dataset_id, 'metadata')\n",
-    "\n",
     "# Pull in the sampled (1500 items) dataset CSV using\n",
     "# The .get_metadata() method downloads the CSV file for our metadata\n",
     "# to the /data folder and returns a string for the file name and location\n",
     "# dataset_metadata will be a string containing that file name and location\n",
-    "# dataset_metadata = constellate.get_metadata(dataset_id)"
+    "dataset_metadata = constellate.get_metadata(dataset_id)\n",
+    "\n",
+    "# Download the full dataset (up to a limit of 25,000 documents),\n",
+    "# request it first in the builder environment. See the Constellate Client\n",
+    "# documentation at: https://constellate.org/docs/constellate-client\n",
+    "# Then use the `constellate.download` method show below.\n",
+    "#dataset_metadata = constellate.download(dataset_id, 'metadata')"
    ]
   },
   {
@@ -450,7 +450,10 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can now download the full dataset file (JSON-L). See [more information about Constellate dataset types](https://constellate.org/docs/what-format-are-jstor-portico-datasets)."
+    "We can now download the sampled (1500 items) dataset (or the full dataset if it has been requested). See more:\n",
+    "* [Constellate dataset types](https://constellate.org/docs/what-format-are-jstor-portico-datasets)\n",
+    "* [Dataset options](https://constellate.org/docs/dataset-options)\n",
+    "* [Constellate client](https://constellate.org/docs/constellate-client)\n"
    ]
   },
   {
@@ -459,8 +462,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# Pull in the sampled (1500 items) dataset JSON using\n",
+    "# The .get_dataset() method downloads the sampled JSON file\n",
+    "dataset_file = constellate.get_dataset(dataset_id)\n",
+    "\n",
     "# Download the full dataset (JSON-L file)\n",
-    "dataset_file = constellate.download(dataset_id, 'jsonl')"
+    "# The full dataset must be requested first\n",
+    "#dataset_file = constellate.download(dataset_id, 'jsonl')"
    ]
   },
   {