Sampling data

gwu-libraries · Jan 15, 2025 · 7492ba9 · 7492ba9
1 parent 3deda1b
commit 7492ba9
Show file tree

Hide file tree

Showing 2 changed files with 54 additions and 6,790 deletions.
diff --git a/text-as-data/course_bulletin.ipynb b/text-as-data/course_bulletin.ipynb
@@ -165,6 +165,56 @@
   {
    "cell_type": "code",
    "execution_count": 2,
+   "id": "ad769062-acf7-4be8-90c2-7577d2e8e573",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from random import sample"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e2d53e37-7f6c-494b-acf7-609995603067",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sample_keys = sample(list(cleaned_courses.keys()), k=10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e306ed9c-13ff-4753-930e-6d67f9880140",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['International Business (IBUS)',\n",
+       " 'Anatomy and Cell Biology (ANAT)',\n",
+       " 'Management (MGT)',\n",
+       " 'Sustainability (SUST)',\n",
+       " 'Health Services Management and Leadership (HSML)',\n",
+       " 'Counseling (CNSL)',\n",
+       " 'Sociology (SOC)',\n",
+       " 'Geology (GEOL)',\n",
+       " 'Speech, Language, and Hearing Science (SLHS)',\n",
+       " 'Business Administration (BADM)']"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sample_keys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
    "id": "b1eab6dc-3e72-49db-bf7c-02252e17f5e6",
    "metadata": {},
    "outputs": [],
@@ -174,7 +224,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 9,
    "id": "363ea68b-5af8-4fd0-9d39-bdfff3162499",
    "metadata": {},
    "outputs": [],
@@ -184,8 +234,9 @@
     "    writer = DictWriter(f, fieldnames)\n",
     "    writer.writeheader()\n",
     "    for dept, course_dict in cleaned_courses.items():\n",
-    "        for title, desc in course_dict.items():\n",
-    "            writer.writerow(dict(zip(fieldnames, (dept, title, '|'.join(desc)))))"
+    "        if dept in sample_keys:\n",
+    "            for title, desc in course_dict.items():\n",
+    "                writer.writerow(dict(zip(fieldnames, (dept, title, '|'.join(desc)))))"
    ]
   }
  ],