change readme

Author: SahitiSarva

.gitignore

@@ -93,3 +93,5 @@ _build/
 
 # setuptools-scm/
 src/*/_version.py
+
+data

README.md

@@ -1,3 +1,11 @@
 # West Africa Labor Market Analysis
 
-[Table of contents](docs/_toc.yml)
+## Assignment
+
+The Poverty team in West Africa is seeking to study labor market trends from LinkedIn and GitHub data. 
+
+## Contents
+
+```{tableofcontents}
+
+```

notebooks/github-trends/software-development.ipynb

@@ -1818,6 +1818,64 @@
     "    collaborators_chart, \"Source: GitHub Innovation Graph economy collaborators data.\"\n",
     ")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "id": "682b3c86",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Wrote data/GitHub/developers.csv\n",
+      "Wrote data/GitHub/repositories.csv\n",
+      "Wrote data/GitHub/organizations.csv\n",
+      "Wrote data/GitHub/git_pushes.csv\n",
+      "Wrote data/GitHub/languages.csv\n",
+      "Wrote data/GitHub/economy_collaborators.csv\n",
+      "Wrote data/GitHub/language_to_cluster_mapping.csv\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/ssarva/west-africa-labor-market-analysis/.venv/lib/python3.14/site-packages/urllib3/connectionpool.py:1110: InsecureRequestWarning: Unverified HTTPS request is being made to host 'raw.githubusercontent.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pathlib import Path\n",
+    "\n",
+    "output_dir = Path(\"data/GitHub\")\n",
+    "output_dir.mkdir(parents=True, exist_ok=True)\n",
+    "\n",
+    "github_csv_sources = {\n",
+    "    \"developers.csv\": f\"{INNOVATION_GRAPH_DATA_URL}/developers.csv\",\n",
+    "    \"repositories.csv\": f\"{INNOVATION_GRAPH_DATA_URL}/repositories.csv\",\n",
+    "    \"organizations.csv\": f\"{INNOVATION_GRAPH_DATA_URL}/organizations.csv\",\n",
+    "    \"git_pushes.csv\": f\"{INNOVATION_GRAPH_DATA_URL}/git_pushes.csv\",\n",
+    "    \"languages.csv\": f\"{INNOVATION_GRAPH_DATA_URL}/languages.csv\",\n",
+    "    \"economy_collaborators.csv\": (\n",
+    "        f\"{INNOVATION_GRAPH_DATA_URL}/economy_collaborators.csv\"\n",
+    "    ),\n",
+    "    \"language_to_cluster_mapping.csv\": LANGUAGE_CLUSTER_MAPPING_URL,\n",
+    "}\n",
+    "\n",
+    "for filename, url in github_csv_sources.items():\n",
+    "    response = requests.get(\n",
+    "        url,\n",
+    "        timeout=30,\n",
+    "        verify=filename != \"language_to_cluster_mapping.csv\",\n",
+    "    )\n",
+    "    response.raise_for_status()\n",
+    "    output_path = output_dir / filename\n",
+    "    output_path.write_bytes(response.content)\n",
+    "    print(f\"Wrote {output_path}\")"
+   ]
   }
  ],
  "metadata": {