FEATURE: Adding the secretaria de quito data

.gitignore

@@ -52,7 +52,7 @@ htmlcov/
 *.db
 *.mo
 
-*.parquet
+
 *.xlsx
 *.json
 **/AutogluonModels/**

notebooks/01_benchmark.ipynb

@@ -37,53 +37,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 197,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "ConnectTimeout",
-     "evalue": "HTTPSConnectionPool(host='www.kaggle.com', port=443): Max retries exceeded with url: /api/v1/datasets/view/rickandjoe/electricity-transformer-dataset-etdataset (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x34a15e910>, 'Connection to www.kaggle.com timed out. (connect timeout=5)'))",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
-      "\u001b[31mTimeoutError\u001b[39m                              Traceback (most recent call last)",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connection.py:198\u001b[39m, in \u001b[36mHTTPConnection._new_conn\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m    197\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m198\u001b[39m     sock = \u001b[43mconnection\u001b[49m\u001b[43m.\u001b[49m\u001b[43mcreate_connection\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    199\u001b[39m \u001b[43m        \u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_dns_host\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mport\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    200\u001b[39m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    201\u001b[39m \u001b[43m        \u001b[49m\u001b[43msource_address\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43msource_address\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    202\u001b[39m \u001b[43m        \u001b[49m\u001b[43msocket_options\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43msocket_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    203\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    204\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m socket.gaierror \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/util/connection.py:85\u001b[39m, in \u001b[36mcreate_connection\u001b[39m\u001b[34m(address, timeout, source_address, socket_options)\u001b[39m\n\u001b[32m     84\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m---> \u001b[39m\u001b[32m85\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m err\n\u001b[32m     86\u001b[39m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[32m     87\u001b[39m     \u001b[38;5;66;03m# Break explicitly a reference cycle\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/util/connection.py:73\u001b[39m, in \u001b[36mcreate_connection\u001b[39m\u001b[34m(address, timeout, source_address, socket_options)\u001b[39m\n\u001b[32m     72\u001b[39m     sock.bind(source_address)\n\u001b[32m---> \u001b[39m\u001b[32m73\u001b[39m \u001b[43msock\u001b[49m\u001b[43m.\u001b[49m\u001b[43mconnect\u001b[49m\u001b[43m(\u001b[49m\u001b[43msa\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m     74\u001b[39m \u001b[38;5;66;03m# Break explicitly a reference cycle\u001b[39;00m\n",
-      "\u001b[31mTimeoutError\u001b[39m: timed out",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[31mConnectTimeoutError\u001b[39m                       Traceback (most recent call last)",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connectionpool.py:787\u001b[39m, in \u001b[36mHTTPConnectionPool.urlopen\u001b[39m\u001b[34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)\u001b[39m\n\u001b[32m    786\u001b[39m \u001b[38;5;66;03m# Make the request on the HTTPConnection object\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m787\u001b[39m response = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_make_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    788\u001b[39m \u001b[43m    \u001b[49m\u001b[43mconn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    789\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    790\u001b[39m \u001b[43m    \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    791\u001b[39m \u001b[43m    \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtimeout_obj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    792\u001b[39m \u001b[43m    \u001b[49m\u001b[43mbody\u001b[49m\u001b[43m=\u001b[49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    793\u001b[39m \u001b[43m    \u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m=\u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    794\u001b[39m \u001b[43m    \u001b[49m\u001b[43mchunked\u001b[49m\u001b[43m=\u001b[49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    795\u001b[39m \u001b[43m    \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m=\u001b[49m\u001b[43mretries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    796\u001b[39m \u001b[43m    \u001b[49m\u001b[43mresponse_conn\u001b[49m\u001b[43m=\u001b[49m\u001b[43mresponse_conn\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    797\u001b[39m \u001b[43m    \u001b[49m\u001b[43mpreload_content\u001b[49m\u001b[43m=\u001b[49m\u001b[43mpreload_content\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    798\u001b[39m \u001b[43m    \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[43m=\u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    799\u001b[39m \u001b[43m    \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mresponse_kw\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    800\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    802\u001b[39m \u001b[38;5;66;03m# Everything went great!\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connectionpool.py:488\u001b[39m, in \u001b[36mHTTPConnectionPool._make_request\u001b[39m\u001b[34m(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)\u001b[39m\n\u001b[32m    487\u001b[39m         new_e = _wrap_proxy_error(new_e, conn.proxy.scheme)\n\u001b[32m--> \u001b[39m\u001b[32m488\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m new_e\n\u001b[32m    490\u001b[39m \u001b[38;5;66;03m# conn.request() calls http.client.*.request, not the method in\u001b[39;00m\n\u001b[32m    491\u001b[39m \u001b[38;5;66;03m# urllib3.request. It also calls makefile (recv) on the socket.\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connectionpool.py:464\u001b[39m, in \u001b[36mHTTPConnectionPool._make_request\u001b[39m\u001b[34m(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)\u001b[39m\n\u001b[32m    463\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m464\u001b[39m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_validate_conn\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconn\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    465\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m (SocketTimeout, BaseSSLError) \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connectionpool.py:1093\u001b[39m, in \u001b[36mHTTPSConnectionPool._validate_conn\u001b[39m\u001b[34m(self, conn)\u001b[39m\n\u001b[32m   1092\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m conn.is_closed:\n\u001b[32m-> \u001b[39m\u001b[32m1093\u001b[39m     \u001b[43mconn\u001b[49m\u001b[43m.\u001b[49m\u001b[43mconnect\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   1095\u001b[39m \u001b[38;5;66;03m# TODO revise this, see https://github.com/urllib3/urllib3/issues/2791\u001b[39;00m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connection.py:753\u001b[39m, in \u001b[36mHTTPSConnection.connect\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m    752\u001b[39m sock: socket.socket | ssl.SSLSocket\n\u001b[32m--> \u001b[39m\u001b[32m753\u001b[39m \u001b[38;5;28mself\u001b[39m.sock = sock = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_new_conn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    754\u001b[39m server_hostname: \u001b[38;5;28mstr\u001b[39m = \u001b[38;5;28mself\u001b[39m.host\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connection.py:207\u001b[39m, in \u001b[36mHTTPConnection._new_conn\u001b[39m\u001b[34m(self)\u001b[39m\n\u001b[32m    206\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m SocketTimeout \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[32m--> \u001b[39m\u001b[32m207\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m ConnectTimeoutError(\n\u001b[32m    208\u001b[39m         \u001b[38;5;28mself\u001b[39m,\n\u001b[32m    209\u001b[39m         \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mConnection to \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.host\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m timed out. (connect timeout=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m.timeout\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m)\u001b[39m\u001b[33m\"\u001b[39m,\n\u001b[32m    210\u001b[39m     ) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01me\u001b[39;00m\n\u001b[32m    212\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mOSError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
-      "\u001b[31mConnectTimeoutError\u001b[39m: (<urllib3.connection.HTTPSConnection object at 0x34a15e910>, 'Connection to www.kaggle.com timed out. (connect timeout=5)')",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[31mMaxRetryError\u001b[39m                             Traceback (most recent call last)",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/requests/adapters.py:644\u001b[39m, in \u001b[36mHTTPAdapter.send\u001b[39m\u001b[34m(self, request, stream, timeout, verify, cert, proxies)\u001b[39m\n\u001b[32m    643\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m644\u001b[39m     resp = \u001b[43mconn\u001b[49m\u001b[43m.\u001b[49m\u001b[43murlopen\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    645\u001b[39m \u001b[43m        \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m.\u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    646\u001b[39m \u001b[43m        \u001b[49m\u001b[43murl\u001b[49m\u001b[43m=\u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    647\u001b[39m \u001b[43m        \u001b[49m\u001b[43mbody\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m.\u001b[49m\u001b[43mbody\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    648\u001b[39m \u001b[43m        \u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m=\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m.\u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    649\u001b[39m \u001b[43m        \u001b[49m\u001b[43mredirect\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    650\u001b[39m \u001b[43m        \u001b[49m\u001b[43massert_same_host\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    651\u001b[39m \u001b[43m        \u001b[49m\u001b[43mpreload_content\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    652\u001b[39m \u001b[43m        \u001b[49m\u001b[43mdecode_content\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m    653\u001b[39m \u001b[43m        \u001b[49m\u001b[43mretries\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mmax_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    654\u001b[39m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    655\u001b[39m \u001b[43m        \u001b[49m\u001b[43mchunked\u001b[49m\u001b[43m=\u001b[49m\u001b[43mchunked\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    656\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    658\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m (ProtocolError, \u001b[38;5;167;01mOSError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m err:\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/connectionpool.py:841\u001b[39m, in \u001b[36mHTTPConnectionPool.urlopen\u001b[39m\u001b[34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)\u001b[39m\n\u001b[32m    839\u001b[39m     new_e = ProtocolError(\u001b[33m\"\u001b[39m\u001b[33mConnection aborted.\u001b[39m\u001b[33m\"\u001b[39m, new_e)\n\u001b[32m--> \u001b[39m\u001b[32m841\u001b[39m retries = \u001b[43mretries\u001b[49m\u001b[43m.\u001b[49m\u001b[43mincrement\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    842\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merror\u001b[49m\u001b[43m=\u001b[49m\u001b[43mnew_e\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_pool\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_stacktrace\u001b[49m\u001b[43m=\u001b[49m\u001b[43msys\u001b[49m\u001b[43m.\u001b[49m\u001b[43mexc_info\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m[\u001b[49m\u001b[32;43m2\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[32m    843\u001b[39m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    844\u001b[39m retries.sleep()\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/urllib3/util/retry.py:519\u001b[39m, in \u001b[36mRetry.increment\u001b[39m\u001b[34m(self, method, url, response, error, _pool, _stacktrace)\u001b[39m\n\u001b[32m    518\u001b[39m     reason = error \u001b[38;5;129;01mor\u001b[39;00m ResponseError(cause)\n\u001b[32m--> \u001b[39m\u001b[32m519\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m MaxRetryError(_pool, url, reason) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01mreason\u001b[39;00m  \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m    521\u001b[39m log.debug(\u001b[33m\"\u001b[39m\u001b[33mIncremented Retry for (url=\u001b[39m\u001b[33m'\u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33m): \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[33m\"\u001b[39m, url, new_retry)\n",
-      "\u001b[31mMaxRetryError\u001b[39m: HTTPSConnectionPool(host='www.kaggle.com', port=443): Max retries exceeded with url: /api/v1/datasets/view/rickandjoe/electricity-transformer-dataset-etdataset (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x34a15e910>, 'Connection to www.kaggle.com timed out. (connect timeout=5)'))",
-      "\nDuring handling of the above exception, another exception occurred:\n",
-      "\u001b[31mConnectTimeout\u001b[39m                            Traceback (most recent call last)",
-      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[197]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m path = \u001b[43mkagglehub\u001b[49m\u001b[43m.\u001b[49m\u001b[43mdataset_download\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mrickandjoe/electricity-transformer-dataset-etdataset\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/kagglehub/datasets.py:43\u001b[39m, in \u001b[36mdataset_download\u001b[39m\u001b[34m(handle, path, force_download)\u001b[39m\n\u001b[32m     41\u001b[39m h = parse_dataset_handle(handle)\n\u001b[32m     42\u001b[39m logger.info(\u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mDownloading Dataset: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mh.to_url()\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m ...\u001b[39m\u001b[33m\"\u001b[39m, extra={**EXTRA_CONSOLE_BLOCK})\n\u001b[32m---> \u001b[39m\u001b[32m43\u001b[39m path, _ = \u001b[43mregistry\u001b[49m\u001b[43m.\u001b[49m\u001b[43mdataset_resolver\u001b[49m\u001b[43m(\u001b[49m\u001b[43mh\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[43m=\u001b[49m\u001b[43mforce_download\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m     44\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m path\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/kagglehub/registry.py:28\u001b[39m, in \u001b[36mMultiImplRegistry.__call__\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m     26\u001b[39m \u001b[38;5;28;01mfor\u001b[39;00m impl \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mreversed\u001b[39m(\u001b[38;5;28mself\u001b[39m._impls):\n\u001b[32m     27\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m impl.is_supported(*args, **kwargs):\n\u001b[32m---> \u001b[39m\u001b[32m28\u001b[39m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mimpl\u001b[49m\u001b[43m(\u001b[49m\u001b[43m*\u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m     29\u001b[39m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m     30\u001b[39m         fails.append(\u001b[38;5;28mtype\u001b[39m(impl).\u001b[34m__name__\u001b[39m)\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/kagglehub/resolver.py:29\u001b[39m, in \u001b[36mResolver.__call__\u001b[39m\u001b[34m(self, handle, path, force_download)\u001b[39m\n\u001b[32m     15\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m__call__\u001b[39m(\n\u001b[32m     16\u001b[39m     \u001b[38;5;28mself\u001b[39m, handle: T, path: Optional[\u001b[38;5;28mstr\u001b[39m] = \u001b[38;5;28;01mNone\u001b[39;00m, *, force_download: Optional[\u001b[38;5;28mbool\u001b[39m] = \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[32m     17\u001b[39m ) -> \u001b[38;5;28mtuple\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Optional[\u001b[38;5;28mint\u001b[39m]]:\n\u001b[32m     18\u001b[39m \u001b[38;5;250m    \u001b[39m\u001b[33;03m\"\"\"Resolves a handle into a path with the requested file(s) and the resource's version number.\u001b[39;00m\n\u001b[32m     19\u001b[39m \n\u001b[32m     20\u001b[39m \u001b[33;03m    Args:\u001b[39;00m\n\u001b[32m   (...)\u001b[39m\u001b[32m     27\u001b[39m \u001b[33;03m        Some cases where version number might be missing: Competition datasource, API-based models.\u001b[39;00m\n\u001b[32m     28\u001b[39m \u001b[33;03m    \"\"\"\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m29\u001b[39m     path, version = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_resolve\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhandle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[43m=\u001b[49m\u001b[43mforce_download\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m     31\u001b[39m     \u001b[38;5;66;03m# Note handles are immutable, so _resolve() could not have altered our reference\u001b[39;00m\n\u001b[32m     32\u001b[39m     register_datasource_access(handle, version)\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/kagglehub/http_resolver.py:107\u001b[39m, in \u001b[36mDatasetHttpResolver._resolve\u001b[39m\u001b[34m(self, h, path, force_download)\u001b[39m\n\u001b[32m    104\u001b[39m api_client = KaggleApiV1Client()\n\u001b[32m    106\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m h.is_versioned():\n\u001b[32m--> \u001b[39m\u001b[32m107\u001b[39m     h = h.with_version(\u001b[43m_get_current_version\u001b[49m\u001b[43m(\u001b[49m\u001b[43mapi_client\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mh\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[32m    109\u001b[39m dataset_path = load_from_cache(h, path)\n\u001b[32m    110\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m dataset_path \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m force_download:\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/kagglehub/http_resolver.py:290\u001b[39m, in \u001b[36m_get_current_version\u001b[39m\u001b[34m(api_client, h)\u001b[39m\n\u001b[32m    287\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m json_response[MODEL_INSTANCE_VERSION_FIELD]\n\u001b[32m    289\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(h, DatasetHandle):\n\u001b[32m--> \u001b[39m\u001b[32m290\u001b[39m     json_response = \u001b[43mapi_client\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_build_get_dataset_url_path\u001b[49m\u001b[43m(\u001b[49m\u001b[43mh\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mh\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    291\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m DATASET_CURRENT_VERSION_FIELD \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m json_response:\n\u001b[32m    292\u001b[39m         msg = \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mInvalid GetDataset API response. Expected to include a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mDATASET_CURRENT_VERSION_FIELD\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m field\u001b[39m\u001b[33m\"\u001b[39m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/kagglehub/clients.py:133\u001b[39m, in \u001b[36mKaggleApiV1Client.get\u001b[39m\u001b[34m(self, path, resource_handle)\u001b[39m\n\u001b[32m    131\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mget\u001b[39m(\u001b[38;5;28mself\u001b[39m, path: \u001b[38;5;28mstr\u001b[39m, resource_handle: Optional[ResourceHandle] = \u001b[38;5;28;01mNone\u001b[39;00m) -> \u001b[38;5;28mdict\u001b[39m:\n\u001b[32m    132\u001b[39m     url = \u001b[38;5;28mself\u001b[39m._build_url(path)\n\u001b[32m--> \u001b[39m\u001b[32m133\u001b[39m     \u001b[38;5;28;01mwith\u001b[39;00m \u001b[43mrequests\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m    134\u001b[39m \u001b[43m        \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    135\u001b[39m \u001b[43m        \u001b[49m\u001b[43mheaders\u001b[49m\u001b[43m=\u001b[49m\u001b[43m{\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mUser-Agent\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mget_user_agent\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    136\u001b[39m \u001b[43m        \u001b[49m\u001b[43mauth\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_get_auth\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    137\u001b[39m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m=\u001b[49m\u001b[43m(\u001b[49m\u001b[43mDEFAULT_CONNECT_TIMEOUT\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mDEFAULT_READ_TIMEOUT\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[32m    138\u001b[39m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m response:\n\u001b[32m    139\u001b[39m         kaggle_api_raise_for_status(response, resource_handle)\n\u001b[32m    140\u001b[39m         \u001b[38;5;28mself\u001b[39m._check_for_version_update(response)\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/requests/api.py:73\u001b[39m, in \u001b[36mget\u001b[39m\u001b[34m(url, params, **kwargs)\u001b[39m\n\u001b[32m     62\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34mget\u001b[39m(url, params=\u001b[38;5;28;01mNone\u001b[39;00m, **kwargs):\n\u001b[32m     63\u001b[39m \u001b[38;5;250m    \u001b[39m\u001b[33mr\u001b[39m\u001b[33;03m\"\"\"Sends a GET request.\u001b[39;00m\n\u001b[32m     64\u001b[39m \n\u001b[32m     65\u001b[39m \u001b[33;03m    :param url: URL for the new :class:`Request` object.\u001b[39;00m\n\u001b[32m   (...)\u001b[39m\u001b[32m     70\u001b[39m \u001b[33;03m    :rtype: requests.Response\u001b[39;00m\n\u001b[32m     71\u001b[39m \u001b[33;03m    \"\"\"\u001b[39;00m\n\u001b[32m---> \u001b[39m\u001b[32m73\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mget\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mparams\u001b[49m\u001b[43m=\u001b[49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/requests/api.py:59\u001b[39m, in \u001b[36mrequest\u001b[39m\u001b[34m(method, url, **kwargs)\u001b[39m\n\u001b[32m     55\u001b[39m \u001b[38;5;66;03m# By using the 'with' statement we are sure the session is closed, thus we\u001b[39;00m\n\u001b[32m     56\u001b[39m \u001b[38;5;66;03m# avoid leaving sockets open which can trigger a ResourceWarning in some\u001b[39;00m\n\u001b[32m     57\u001b[39m \u001b[38;5;66;03m# cases, and look like a memory leak in others.\u001b[39;00m\n\u001b[32m     58\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m sessions.Session() \u001b[38;5;28;01mas\u001b[39;00m session:\n\u001b[32m---> \u001b[39m\u001b[32m59\u001b[39m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43msession\u001b[49m\u001b[43m.\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m=\u001b[49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43murl\u001b[49m\u001b[43m=\u001b[49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/requests/sessions.py:589\u001b[39m, in \u001b[36mSession.request\u001b[39m\u001b[34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[39m\n\u001b[32m    584\u001b[39m send_kwargs = {\n\u001b[32m    585\u001b[39m     \u001b[33m\"\u001b[39m\u001b[33mtimeout\u001b[39m\u001b[33m\"\u001b[39m: timeout,\n\u001b[32m    586\u001b[39m     \u001b[33m\"\u001b[39m\u001b[33mallow_redirects\u001b[39m\u001b[33m\"\u001b[39m: allow_redirects,\n\u001b[32m    587\u001b[39m }\n\u001b[32m    588\u001b[39m send_kwargs.update(settings)\n\u001b[32m--> \u001b[39m\u001b[32m589\u001b[39m resp = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprep\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43msend_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    591\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/requests/sessions.py:703\u001b[39m, in \u001b[36mSession.send\u001b[39m\u001b[34m(self, request, **kwargs)\u001b[39m\n\u001b[32m    700\u001b[39m start = preferred_clock()\n\u001b[32m    702\u001b[39m \u001b[38;5;66;03m# Send the request\u001b[39;00m\n\u001b[32m--> \u001b[39m\u001b[32m703\u001b[39m r = \u001b[43madapter\u001b[49m\u001b[43m.\u001b[49m\u001b[43msend\u001b[49m\u001b[43m(\u001b[49m\u001b[43mrequest\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m    705\u001b[39m \u001b[38;5;66;03m# Total elapsed time of the request (approximately)\u001b[39;00m\n\u001b[32m    706\u001b[39m elapsed = preferred_clock() - start\n",
-      "\u001b[36mFile \u001b[39m\u001b[32m/opt/anaconda3/envs/aws_conf/lib/python3.11/site-packages/requests/adapters.py:665\u001b[39m, in \u001b[36mHTTPAdapter.send\u001b[39m\u001b[34m(self, request, stream, timeout, verify, cert, proxies)\u001b[39m\n\u001b[32m    662\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e.reason, ConnectTimeoutError):\n\u001b[32m    663\u001b[39m     \u001b[38;5;66;03m# TODO: Remove this in 3.0.0: see #2811\u001b[39;00m\n\u001b[32m    664\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e.reason, NewConnectionError):\n\u001b[32m--> \u001b[39m\u001b[32m665\u001b[39m         \u001b[38;5;28;01mraise\u001b[39;00m ConnectTimeout(e, request=request)\n\u001b[32m    667\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e.reason, ResponseError):\n\u001b[32m    668\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m RetryError(e, request=request)\n",
-      "\u001b[31mConnectTimeout\u001b[39m: HTTPSConnectionPool(host='www.kaggle.com', port=443): Max retries exceeded with url: /api/v1/datasets/view/rickandjoe/electricity-transformer-dataset-etdataset (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x34a15e910>, 'Connection to www.kaggle.com timed out. (connect timeout=5)'))"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "path = kagglehub.dataset_download(\n",
     "    \"rickandjoe/electricity-transformer-dataset-etdataset\"\n",
@@ -99,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 198,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -108,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 199,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -117,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 200,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -126,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 201,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -142,7 +98,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 202,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -158,7 +114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 203,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -174,7 +130,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 204,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -190,7 +146,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 205,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -199,7 +155,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 206,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -208,13 +164,142 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 207,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
     "df_final = df_final.sort_values([\"unique_id\", \"ds\"])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ds</th>\n",
+       "      <th>unique_id</th>\n",
+       "      <th>y</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2016-07-01 00:00:00</td>\n",
+       "      <td>transformer_1</td>\n",
+       "      <td>30.531000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2016-07-01 01:00:00</td>\n",
+       "      <td>transformer_1</td>\n",
+       "      <td>27.787001</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2016-07-01 02:00:00</td>\n",
+       "      <td>transformer_1</td>\n",
+       "      <td>27.787001</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2016-07-01 03:00:00</td>\n",
+       "      <td>transformer_1</td>\n",
+       "      <td>25.044001</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2016-07-01 04:00:00</td>\n",
+       "      <td>transformer_1</td>\n",
+       "      <td>21.948000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34835</th>\n",
+       "      <td>2018-06-26 15:00:00</td>\n",
+       "      <td>transformer_2</td>\n",
+       "      <td>47.084999</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34836</th>\n",
+       "      <td>2018-06-26 16:00:00</td>\n",
+       "      <td>transformer_2</td>\n",
+       "      <td>48.183498</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34837</th>\n",
+       "      <td>2018-06-26 17:00:00</td>\n",
+       "      <td>transformer_2</td>\n",
+       "      <td>48.183498</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34838</th>\n",
+       "      <td>2018-06-26 18:00:00</td>\n",
+       "      <td>transformer_2</td>\n",
+       "      <td>46.865501</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34839</th>\n",
+       "      <td>2018-06-26 19:00:00</td>\n",
+       "      <td>transformer_2</td>\n",
+       "      <td>45.986500</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>34840 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       ds      unique_id          y\n",
+       "0     2016-07-01 00:00:00  transformer_1  30.531000\n",
+       "1     2016-07-01 01:00:00  transformer_1  27.787001\n",
+       "2     2016-07-01 02:00:00  transformer_1  27.787001\n",
+       "3     2016-07-01 03:00:00  transformer_1  25.044001\n",
+       "4     2016-07-01 04:00:00  transformer_1  21.948000\n",
+       "...                   ...            ...        ...\n",
+       "34835 2018-06-26 15:00:00  transformer_2  47.084999\n",
+       "34836 2018-06-26 16:00:00  transformer_2  48.183498\n",
+       "34837 2018-06-26 17:00:00  transformer_2  48.183498\n",
+       "34838 2018-06-26 18:00:00  transformer_2  46.865501\n",
+       "34839 2018-06-26 19:00:00  transformer_2  45.986500\n",
+       "\n",
+       "[34840 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -231,7 +316,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 208,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -247,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 209,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -278,7 +363,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 210,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -309,7 +394,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 211,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -346,7 +431,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 212,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -399,7 +484,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 213,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -408,7 +493,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 214,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -417,7 +502,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 215,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -426,7 +511,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 216,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -449,7 +534,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 217,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -458,7 +543,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 218,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -467,7 +552,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 219,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -483,7 +568,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 220,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -501,7 +586,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 221,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -511,7 +596,7 @@
        "<Figure size 1600x350 with 2 Axes>"
       ]
      },
-     "execution_count": 221,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -536,7 +621,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 222,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -556,7 +641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 223,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -565,7 +650,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 224,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -578,7 +663,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 225,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [
     {
@@ -625,7 +710,7 @@
        "0            9.148477  18.487053  27.713882  27.880458"
       ]
      },
-     "execution_count": 225,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }

notebooks/02_data_wrangling.ipynb

@@ -0,0 +1,773 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia = pd.read_excel(\n",
+    "    \"/Users/sebastianalejandrosarastizambonino/Documents/conferences/aws_community_day_2025/data/ambiente_quito/CO.xlsx\",\n",
+    "    skiprows=0,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Select useful raws"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia = df_lluvia[1:]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Rename the dates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia = df_lluvia.rename(columns={\"Unnamed: 0\": \"ds\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia[\"ds\"] = pd.to_datetime(df_lluvia[\"ds\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia_melted = pd.melt(\n",
+    "    df_lluvia, id_vars=[\"ds\"], var_name=\"station\", value_name=\"y\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia_melted = df_lluvia_melted.dropna()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Seleccionar los lugares disponibles para la lluvia"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "places_lluvia = df_lluvia_melted[\"station\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['BELISARIO' 'CARAPUNGO' 'CENTRO' 'COTOCOLLAO' 'EL CAMAL' 'GUAMANI'\n",
+      " 'LOS CHILLOS' 'TUMBACO' 'CONDADO' 'TURUBAMBA']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(places_lluvia)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "See the min and max dates for the lluvia places"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stats_lluvia = df_lluvia_melted.groupby(\"station\").agg({\"ds\": [\"min\", \"max\"]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr th {\n",
+       "        text-align: left;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr:last-of-type th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th colspan=\"2\" halign=\"left\">ds</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>min</th>\n",
+       "      <th>max</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>station</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>BELISARIO</th>\n",
+       "      <td>2004-01-01 00:00:00</td>\n",
+       "      <td>2025-09-30 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CARAPUNGO</th>\n",
+       "      <td>2005-03-16 15:00:00</td>\n",
+       "      <td>2025-09-30 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CENTRO</th>\n",
+       "      <td>2004-01-01 00:00:00</td>\n",
+       "      <td>2025-09-30 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CONDADO</th>\n",
+       "      <td>2004-01-01 00:00:00</td>\n",
+       "      <td>2005-02-21 09:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>COTOCOLLAO</th>\n",
+       "      <td>2005-02-25 14:00:00</td>\n",
+       "      <td>2025-09-30 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>EL CAMAL</th>\n",
+       "      <td>2004-01-01 00:00:00</td>\n",
+       "      <td>2025-09-30 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>GUAMANI</th>\n",
+       "      <td>2005-04-19 15:00:00</td>\n",
+       "      <td>2025-06-18 08:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LOS CHILLOS</th>\n",
+       "      <td>2014-01-21 00:00:00</td>\n",
+       "      <td>2025-09-30 12:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TUMBACO</th>\n",
+       "      <td>2019-06-10 17:00:00</td>\n",
+       "      <td>2025-09-28 07:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TURUBAMBA</th>\n",
+       "      <td>2004-01-01 00:00:00</td>\n",
+       "      <td>2005-03-08 09:00:00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                             ds                    \n",
+       "                            min                 max\n",
+       "station                                            \n",
+       "BELISARIO   2004-01-01 00:00:00 2025-09-30 23:00:00\n",
+       "CARAPUNGO   2005-03-16 15:00:00 2025-09-30 23:00:00\n",
+       "CENTRO      2004-01-01 00:00:00 2025-09-30 23:00:00\n",
+       "CONDADO     2004-01-01 00:00:00 2005-02-21 09:00:00\n",
+       "COTOCOLLAO  2005-02-25 14:00:00 2025-09-30 23:00:00\n",
+       "EL CAMAL    2004-01-01 00:00:00 2025-09-30 23:00:00\n",
+       "GUAMANI     2005-04-19 15:00:00 2025-06-18 08:00:00\n",
+       "LOS CHILLOS 2014-01-21 00:00:00 2025-09-30 12:00:00\n",
+       "TUMBACO     2019-06-10 17:00:00 2025-09-28 07:00:00\n",
+       "TURUBAMBA   2004-01-01 00:00:00 2005-03-08 09:00:00"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stats_lluvia"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "useful_places_lluvia = stats_lluvia[\n",
+    "    stats_lluvia[(\"ds\", \"max\")] >= \"2025-09-28 07:00:00\"\n",
+    "].index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia_melted = df_lluvia_melted[\n",
+    "    df_lluvia_melted[\"station\"].isin(useful_places_lluvia)\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia_melted[\"y\"] = df_lluvia_melted[\"y\"].apply(\n",
+    "    lambda x: np.nan if x == \"                        \" else x\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_lluvia_melted[\"property\"] = \"co\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## PM 2.5"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Read the pm2.5 dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm = pd.read_excel(\n",
+    "    \"/Users/sebastianalejandrosarastizambonino/Documents/conferences/aws_community_day_2025/data/ambiente_quito/PM2.5.xlsx\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm = df_pm[1:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm = df_pm.rename(columns={\"Unnamed: 0\": \"ds\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm_melted = pd.melt(df_pm, id_vars=[\"ds\"], var_name=\"station\", value_name=\"y\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm_melted[\"y\"] = df_pm_melted[\"y\"].apply(\n",
+    "    lambda x: np.nan if x == \"                        \" else x\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm_melted = df_pm_melted.dropna()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "places_pm = df_pm_melted[\"station\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['BELISARIO' 'CARAPUNGO' 'CENTRO' 'COTOCOLLAO' 'EL CAMAL' 'GUAMANI'\n",
+      " 'LOS CHILLOS' 'SAN ANTONIO' 'TUMBACO' 'TURUBAMBA']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(places_pm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm_melted[\"ds\"] = pd.to_datetime(df_pm_melted[\"ds\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metric_dates = df_pm_melted.groupby([\"station\"]).agg({\"ds\": [\"min\", \"max\"]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr th {\n",
+       "        text-align: left;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead tr:last-of-type th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th colspan=\"2\" halign=\"left\">ds</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th></th>\n",
+       "      <th>min</th>\n",
+       "      <th>max</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>station</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>BELISARIO</th>\n",
+       "      <td>2004-09-03 17:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CARAPUNGO</th>\n",
+       "      <td>2005-03-16 00:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>CENTRO</th>\n",
+       "      <td>2004-08-26 15:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>COTOCOLLAO</th>\n",
+       "      <td>2005-02-25 10:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>EL CAMAL</th>\n",
+       "      <td>2004-08-26 17:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>GUAMANI</th>\n",
+       "      <td>2013-10-28 00:00:00</td>\n",
+       "      <td>2025-06-18 08:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>LOS CHILLOS</th>\n",
+       "      <td>2014-01-21 00:00:00</td>\n",
+       "      <td>2025-03-31 14:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SAN ANTONIO</th>\n",
+       "      <td>2017-03-29 00:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TUMBACO</th>\n",
+       "      <td>2017-03-07 13:00:00</td>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TURUBAMBA</th>\n",
+       "      <td>2004-10-04 17:00:00</td>\n",
+       "      <td>2005-03-08 09:00:00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                             ds                    \n",
+       "                            min                 max\n",
+       "station                                            \n",
+       "BELISARIO   2004-09-03 17:00:00 2025-08-31 23:00:00\n",
+       "CARAPUNGO   2005-03-16 00:00:00 2025-08-31 23:00:00\n",
+       "CENTRO      2004-08-26 15:00:00 2025-08-31 23:00:00\n",
+       "COTOCOLLAO  2005-02-25 10:00:00 2025-08-31 23:00:00\n",
+       "EL CAMAL    2004-08-26 17:00:00 2025-08-31 23:00:00\n",
+       "GUAMANI     2013-10-28 00:00:00 2025-06-18 08:00:00\n",
+       "LOS CHILLOS 2014-01-21 00:00:00 2025-03-31 14:00:00\n",
+       "SAN ANTONIO 2017-03-29 00:00:00 2025-08-31 23:00:00\n",
+       "TUMBACO     2017-03-07 13:00:00 2025-08-31 23:00:00\n",
+       "TURUBAMBA   2004-10-04 17:00:00 2005-03-08 09:00:00"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "metric_dates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "useful_places_pm = metric_dates[\n",
+    "    metric_dates[(\"ds\", \"max\")] == \"2025-08-31 23:00:00\"\n",
+    "].index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm_melted = df_pm_melted[df_pm_melted[\"station\"].isin(useful_places_pm)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_pm_melted[\"property\"] = \"pm-2.5\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Temperature"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp = pd.read_excel(\n",
+    "    \"/Users/sebastianalejandrosarastizambonino/Documents/conferences/aws_community_day_2025/data/ambiente_quito/TMP.xlsx\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp = df_temp[1:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp = df_temp.rename(columns={\"Unnamed: 0\": \"ds\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp_melted = pd.melt(df_temp, id_vars=[\"ds\"], var_name=\"station\", value_name=\"y\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp_melted = df_temp_melted.dropna()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp_melted[\"ds\"] = pd.to_datetime(df_temp_melted[\"ds\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metrics_temp = df_temp_melted.groupby([\"station\"]).agg({\"ds\": [\"min\", \"max\"]})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "useful_places_temp = metrics_temp[\n",
+    "    metrics_temp[(\"ds\", \"max\")] == pd.to_datetime(\"2025-09-30 23:00:00\")\n",
+    "].index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp_melted = df_temp_melted[df_temp_melted[\"station\"].isin(useful_places_temp)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_temp_melted[\"property\"] = \"temperature\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Concat to have a single dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_final = pd.concat([df_lluvia_melted, df_pm_melted, df_temp_melted])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_final[\"station\"] = df_final[\"station\"].apply(lambda x: x.upper())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_final = df_final[df_final[\"ds\"] <= pd.to_datetime(\"2025-08-31 23:00:00\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_final[\"station\"] = df_final[\"station\"].apply(\n",
+    "    lambda x: \"SAN ANTONIO\" if x == \"SANANTONIO\" else x\n",
+    ")\n",
+    "\n",
+    "df_final[\"station\"] = df_final[\"station\"].apply(\n",
+    "    lambda x: \"EL CAMAL\" if x == \"ELCAMAL\" else x\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['BELISARIO', 'CARAPUNGO', 'CENTRO', 'COTOCOLLAO', 'EL CAMAL',\n",
+       "       'LOS CHILLOS', 'TUMBACO', 'SAN ANTONIO'], dtype=object)"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final[\"station\"].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "FINAL_PATH = \"/Users/sebastianalejandrosarastizambonino/Documents/conferences/aws_community_day_2025/data\"\n",
+    "df_final.to_parquet(f\"{FINAL_PATH}/datos_ambiente_quito.parquet\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "aws_conf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/03_data_verification.ipynb

@@ -0,0 +1,193 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_parquet(\n",
+    "    \"/Users/sebastianalejandrosarastizambonino/Documents/conferences/aws_community_day_2025/data/datos_ambiente_quito.parquet\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>ds</th>\n",
+       "      <th>station</th>\n",
+       "      <th>y</th>\n",
+       "      <th>property</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2004-01-01 00:00:00</td>\n",
+       "      <td>BELISARIO</td>\n",
+       "      <td>7.42</td>\n",
+       "      <td>co</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2004-01-01 01:00:00</td>\n",
+       "      <td>BELISARIO</td>\n",
+       "      <td>7.96</td>\n",
+       "      <td>co</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2004-01-01 02:00:00</td>\n",
+       "      <td>BELISARIO</td>\n",
+       "      <td>8.42</td>\n",
+       "      <td>co</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2004-01-01 03:00:00</td>\n",
+       "      <td>BELISARIO</td>\n",
+       "      <td>9.06</td>\n",
+       "      <td>co</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2004-01-01 04:00:00</td>\n",
+       "      <td>BELISARIO</td>\n",
+       "      <td>6.57</td>\n",
+       "      <td>co</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1524523</th>\n",
+       "      <td>2025-08-31 19:00:00</td>\n",
+       "      <td>SAN ANTONIO</td>\n",
+       "      <td>12.78</td>\n",
+       "      <td>Temperature</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1524524</th>\n",
+       "      <td>2025-08-31 20:00:00</td>\n",
+       "      <td>SAN ANTONIO</td>\n",
+       "      <td>12.28</td>\n",
+       "      <td>Temperature</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1524525</th>\n",
+       "      <td>2025-08-31 21:00:00</td>\n",
+       "      <td>SAN ANTONIO</td>\n",
+       "      <td>12.21</td>\n",
+       "      <td>Temperature</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1524526</th>\n",
+       "      <td>2025-08-31 22:00:00</td>\n",
+       "      <td>SAN ANTONIO</td>\n",
+       "      <td>12.35</td>\n",
+       "      <td>Temperature</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1524527</th>\n",
+       "      <td>2025-08-31 23:00:00</td>\n",
+       "      <td>SAN ANTONIO</td>\n",
+       "      <td>12.22</td>\n",
+       "      <td>Temperature</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>2828207 rows × 4 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                         ds      station      y     property\n",
+       "0       2004-01-01 00:00:00    BELISARIO   7.42           co\n",
+       "1       2004-01-01 01:00:00    BELISARIO   7.96           co\n",
+       "2       2004-01-01 02:00:00    BELISARIO   8.42           co\n",
+       "3       2004-01-01 03:00:00    BELISARIO   9.06           co\n",
+       "4       2004-01-01 04:00:00    BELISARIO   6.57           co\n",
+       "...                     ...          ...    ...          ...\n",
+       "1524523 2025-08-31 19:00:00  SAN ANTONIO  12.78  Temperature\n",
+       "1524524 2025-08-31 20:00:00  SAN ANTONIO  12.28  Temperature\n",
+       "1524525 2025-08-31 21:00:00  SAN ANTONIO  12.21  Temperature\n",
+       "1524526 2025-08-31 22:00:00  SAN ANTONIO  12.35  Temperature\n",
+       "1524527 2025-08-31 23:00:00  SAN ANTONIO  12.22  Temperature\n",
+       "\n",
+       "[2828207 rows x 4 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "aws_conf",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/chronos_conference/adapters/filter_ts.py

@@ -2,9 +2,26 @@ import pandas as pd
 
 
 def filter_ts(
-    df: pd.DataFrame, date_col: str, min_date: str, max_date: str
+    df: pd.DataFrame,
+    date_col: str,
+    min_date: str,
+    max_date: str,
+    city_col: str,
+    city_choice: list,
+    property_col: str,
+    property_choice: list,
 ) -> pd.DataFrame:
     df = df.copy()
     if pd.api.types.is_datetime64_any_dtype(df[date_col]) is False:
         df[date_col] = pd.to_datetime(df[date_col])
-    return df[(df[date_col] >= min_date) & (df[date_col] <= max_date)]
+    df = df[(df[date_col] >= min_date) & (df[date_col] <= max_date)]
+    if isinstance(property_choice, str):
+        property_choice = [property_choice]
+    df_final = df[
+        (df[city_col] == city_choice) & (df[property_col].isin(property_choice))
+    ]
+    return df_final
+
+
+def get_properties(df: pd.DataFrame, city_col: str, property_given: str) -> list:
+    return df[df[city_col] == property_given]["property"].unique().tolist()

src/chronos_conference/adapters/model_instance.py

@@ -45,7 +45,6 @@ class ChronosForecaster(ForecastingBaseModel):
         results = results.rename(
             columns={
                 "mean": "AWSChronosForecast",
-                "item_id": "unique_id",
                 "timestamp": "ds",
             }
         )

src/chronos_conference/adapters/ts_plot.py

@@ -1,16 +1,77 @@
-import plotly.express as px
+# ruff: noqa: F403, F405
+
+import plotly.graph_objects as go
+from plotly.subplots import make_subplots
 import pandas as pd
+from chronos_conference.settings import *
 
 
 def get_plot(df_story: pd.DataFrame, df_pred: pd.DataFrame):
-    if pd.api.types.is_datetime64_any_dtype(df_story["datetime"]) is False:
-        df_story["datetime"] = pd.to_datetime(df_story["datetime"])
+    if not pd.api.types.is_datetime64_any_dtype(df_story[HISTORICAL_DATE_COLUMN]):
+        df_story[HISTORICAL_DATE_COLUMN] = pd.to_datetime(
+            df_story[HISTORICAL_DATE_COLUMN]
+        )
+
+    df_story = df_story.rename(
+        columns={
+            HISTORICAL_DATE_COLUMN: "datetime",
+            HISTORICAL_TARGET_COLUMN: "value",
+            HISTORICAL_ITEM_COLUMN: "item_id",
+        }
+    )
 
-    if pd.api.types.is_datetime64_any_dtype(df_pred["ds"]) is False:
+    if not pd.api.types.is_datetime64_any_dtype(df_pred["ds"]):
         df_pred["ds"] = pd.to_datetime(df_pred["ds"])
 
-    fig = px.line(df_story, x="datetime", y="value", title="Historical Information")
-    fig.add_scatter(
-        x=df_pred["ds"], y=df_pred["AWSChronosForecast"], mode="lines", name="Forecast"
+    item_ids = df_story["item_id"].unique()
+    number_columns = len(item_ids)
+
+    subplot_titles = [
+        f"{item}<br><span style='font-size:10px;color:gray;'>Unidad: {UNITS_MEASURED[item]} | "
+        f"Límite máx: {MAX_SAFETY_LIMITS[item]}</span>"
+        for item in item_ids
+    ]
+
+    fig = make_subplots(rows=1, cols=number_columns, subplot_titles=subplot_titles)
+
+    for idx, value in enumerate(item_ids):
+        df_story_subset = df_story[df_story["item_id"] == value]
+        df_pred_subset = df_pred[df_pred["item_id"] == value]
+
+        show_legend = idx == 0
+
+        fig.add_trace(
+            go.Scatter(
+                x=df_story_subset["datetime"],
+                y=df_story_subset["value"],
+                mode="lines",
+                name="Histórico",
+                line=dict(color="blue", width=2),
+                showlegend=show_legend,
+            ),
+            row=1,
+            col=idx + 1,
+        )
+
+        fig.add_trace(
+            go.Scatter(
+                x=df_pred_subset["ds"],
+                y=df_pred_subset["AWSChronosForecast"],
+                mode="lines+markers",
+                name="Predicción",
+                line=dict(color="orange", dash="dash"),
+                marker=dict(symbol="x", size=8, color="orange"),
+                showlegend=show_legend,
+            ),
+            row=1,
+            col=idx + 1,
+        )
+
+    fig.update_layout(
+        showlegend=True,
+        height=400,
+        width=300 * number_columns,
+        title_text="Serie histórica y predicción por ítem",
     )
+
     return fig

src/chronos_conference/service_layer/main.py

@@ -4,11 +4,12 @@ import streamlit as st
 import pandas as pd
 
 from chronos_conference.domain.inference import get_forecast
-from chronos_conference.adapters.filter_ts import filter_ts
+from chronos_conference.adapters.filter_ts import filter_ts, get_properties
 from chronos_conference.adapters.model_instance import ChronosForecaster
 from chronos_conference.adapters.ts_plot import get_plot
 from chronos_conference.settings import *
 
+
 st.title("AWS Community Day Ecuador 2025")
 st.header(
     "Conferencia: Aprendiendo el Lenguaje de las series de tiempo con AWS Chronos Bolt"
@@ -22,9 +23,9 @@ datos abiertos obtenidos del INAMHI.
 """
 )
 
-df = pd.read_csv(PATH_DATA)
+df = pd.read_parquet(PATH_DATA)
 
-col1, col2, col3 = st.columns(3)
+col1, col2 = st.columns(2)
 
 with col1:
     min_date = st.date_input("Fecha mínima", value=MIN_PRED_DATE)
@@ -32,7 +33,29 @@ with col1:
 with col2:
     max_date = st.date_input("Fecha máxima", value=MAX_PRED_DATE)
 
-with col3:
+
+city_choice = st.selectbox(
+    "Seleccione la zona de la ciudad a predecir", ZONES_TO_PREDICT
+)
+
+if not city_choice:
+    st.stop()
+
+available_properties = get_properties(df, ZONE_COL, city_choice)
+
+if not available_properties:
+    st.stop()
+
+col1, col2 = st.columns(2)
+
+with col1:
+    property_choice = st.pills(
+        "Seleccione la propiedad a predecir",
+        available_properties,
+        selection_mode="multi",
+    )
+
+with col2:
     n_steps = st.number_input(
         "Número de pasos a predecir",
         min_value=MIN_PRED_DATE_LIMIT,
@@ -40,6 +63,9 @@ with col3:
         value=N_PRED_STEPS,
     )
 
+if not property_choice:
+    st.stop()
+
 execution_button = st.button("Ejecutar modelo")
 
 if not execution_button:
@@ -51,6 +77,10 @@ with st.spinner("Filtrando datos..."):
         date_col=HISTORICAL_DATE_COLUMN,
         min_date=str(min_date),
         max_date=str(max_date),
+        city_col=ZONE_COL,
+        city_choice=city_choice,
+        property_col=HISTORICAL_ITEM_COLUMN,
+        property_choice=property_choice,
     )
 
 model = ChronosForecaster(freq=FREQUENCY)

src/chronos_conference/settings.py

@@ -1,13 +1,35 @@
-HISTORICAL_DATE_COLUMN = "datetime"
-HISTORICAL_ITEM_COLUMN = "unique_id"
-HISTORICAL_TARGET_COLUMN = "value"
+HISTORICAL_DATE_COLUMN = "ds"
+HISTORICAL_ITEM_COLUMN = "property"
+ZONE_COL = "station"
+HISTORICAL_TARGET_COLUMN = "y"
 
-PATH_DATA = "data/historical_simulation_9023624.csv"
+PATH_DATA = "data/datos_ambiente_quito.parquet"
+# PATH_DATA = "/Users/sebastianalejandrosarastizambonino/Documents/conferences/aws_community_day_2025/data/datos_ambiente_quito.parquet"
 
-FREQUENCY = "D"
+FREQUENCY = "h"
 
-MIN_PRED_DATE = "2022-01-01"
-MAX_PRED_DATE = "2023-06-30"
+MIN_PRED_DATE = "2025-08-29 23:00:00"
+MAX_PRED_DATE = "2025-08-31 23:00:00"
 N_PRED_STEPS = 48
 MIN_PRED_DATE_LIMIT = 1
 MAX_PRED_DATE_LIMIT = 128
+
+PROPERTIES_TO_PREDICT = ["co", "pm-2.5", "temperature"]
+ZONES_TO_PREDICT = [
+    "BELISARIO",
+    "CARAPUNGO",
+    "CENTRO",
+    "COTOCOLLAO",
+    "EL CAMAL",
+    "LOS CHILLOS",
+    "TUMBACO",
+    "SAN ANTONIO",
+]
+
+UNITS_MEASURED = {"co": "mg/m3", "pm-2.5": "µg/m3", "temperature": "°C"}
+
+MAX_SAFETY_LIMITS = {
+    "pm-2.5": "35 µg/m3 daily",  # reference: https://ww2.arb.ca.gov/es/resources/inhalable-particulate-matter-and-health
+    "co": "23 mg/m3",  # reference: https://www.healthcouncil.nl/documents/2024/09/09/carbon-monoxide
+    "temperature": "N/A",
+}