Updating with comparison from sklearn/lale pipeline in timing for cross validation, on MacBook Pro 8 core, scale out goes from 433s to 72s

Author: raghukiran1224

notebooks/lale_cross_val_score.ipynb

@@ -42,13 +42,7 @@
    "execution_count": 5,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# from lale.lib.sklearn import PCA, Nystroem, SelectKBest, RandomForestClassifier\n",
-    "# from lale.lib.lale import ConcatFeatures\n",
-    "\n",
-    "# pipeline = (PCA() & Nystroem() & SelectKBest(k=3)) >> ConcatFeatures() >> RandomForestClassifier(n_estimators=200)\n",
-    "# # pipeline.visualize()"
-   ]
+   "source": []
   },
   {
    "cell_type": "code",
@@ -77,7 +71,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "2021-05-25 15:55:50,487\tINFO services.py:1269 -- View the Ray dashboard at \u001b[1m\u001b[32mhttp://127.0.0.1:8265\u001b[39m\u001b[22m\n"
+      "2021-05-26 08:32:21,221\tINFO services.py:1269 -- View the Ray dashboard at \u001b[1m\u001b[32mhttp://127.0.0.1:8265\u001b[39m\u001b[22m\n"
      ]
     },
     {
@@ -86,12 +80,12 @@
        "{'node_ip_address': '9.163.5.112',\n",
        " 'raylet_ip_address': '9.163.5.112',\n",
        " 'redis_address': '9.163.5.112:6379',\n",
-       " 'object_store_address': '/tmp/ray/session_2021-05-25_15-55-48_881861_17264/sockets/plasma_store',\n",
-       " 'raylet_socket_name': '/tmp/ray/session_2021-05-25_15-55-48_881861_17264/sockets/raylet',\n",
+       " 'object_store_address': '/tmp/ray/session_2021-05-26_08-32-19_645025_30302/sockets/plasma_store',\n",
+       " 'raylet_socket_name': '/tmp/ray/session_2021-05-26_08-32-19_645025_30302/sockets/raylet',\n",
        " 'webui_url': '127.0.0.1:8265',\n",
-       " 'session_dir': '/tmp/ray/session_2021-05-25_15-55-48_881861_17264',\n",
-       " 'metrics_export_port': 63066,\n",
-       " 'node_id': 'd067798c6a3d62df2148c17631b1a63b58e53a141542f7697fe29297'}"
+       " 'session_dir': '/tmp/ray/session_2021-05-26_08-32-19_645025_30302',\n",
+       " 'metrics_export_port': 65535,\n",
+       " 'node_id': '1eb8277b22f236079beacdbd19b26d419304b495f01a69a7c4dc3a26'}"
       ]
      },
      "execution_count": 8,
@@ -219,8 +213,18 @@
    "cell_type": "code",
    "execution_count": 20,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 2.61 s, sys: 1.34 s, total: 3.96 s\n",
+      "Wall time: 1min 12s\n"
+     ]
+    }
+   ],
    "source": [
+    "%%time\n",
     "scores = rt.cross_validate(kf, pipeline, pipeline_input)"
    ]
   },
@@ -232,16 +236,16 @@
     {
      "data": {
       "text/plain": [
-       "[0.8145188145188145,\n",
-       " 0.8115218115218116,\n",
-       " 0.8161838161838162,\n",
-       " 0.8168498168498168,\n",
-       " 0.8171828171828172,\n",
+       "[0.8185148185148186,\n",
        " 0.8175158175158175,\n",
-       " 0.8105228105228105,\n",
-       " 0.8211788211788211,\n",
-       " 0.8031312458361093,\n",
-       " 0.8154563624250499]"
+       " 0.8128538128538129,\n",
+       " 0.8195138195138195,\n",
+       " 0.8228438228438228,\n",
+       " 0.8168498168498168,\n",
+       " 0.8131868131868132,\n",
+       " 0.8161838161838162,\n",
+       " 0.7991339107261826,\n",
+       " 0.8077948034643571]"
       ]
      },
      "execution_count": 21,
@@ -262,46 +266,53 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from lale.lib.sklearn import PCA, Nystroem, SelectKBest, RandomForestClassifier\n",
+    "from lale.lib.lale import ConcatFeatures\n",
+    "\n",
+    "pipeline = (PCA() & Nystroem() & SelectKBest(k=3)) >> ConcatFeatures() >> RandomForestClassifier(n_estimators=200)\n",
+    "# pipeline.visualize()"
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "CPU times: user 7min 45s, sys: 12.4 s, total: 7min 57s\n",
-      "Wall time: 7min 30s\n"
+      "CPU times: user 7min 39s, sys: 13.1 s, total: 7min 52s\n",
+      "Wall time: 7min 13s\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "[0.8168498168498168,\n",
-       " 0.8215118215118216,\n",
-       " 0.8138528138528138,\n",
+       "[0.8185148185148186,\n",
+       " 0.8101898101898102,\n",
+       " 0.8148518148518149,\n",
+       " 0.8201798201798202,\n",
+       " 0.8145188145188145,\n",
        " 0.8185148185148186,\n",
-       " 0.8178488178488178,\n",
-       " 0.8215118215118216,\n",
-       " 0.8121878121878122,\n",
-       " 0.8191808191808192,\n",
-       " 0.8021319120586275,\n",
-       " 0.8074616922051966]"
+       " 0.8168498168498168,\n",
+       " 0.8125208125208125,\n",
+       " 0.7978014656895404,\n",
+       " 0.8114590273151232]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "%%time \n",
+    "%%time\n",
+    "from lale.helpers import cross_val_score\n",
     "cross_val_score(pipeline, X_train, y_train, cv=10)"
    ]
   },