Split slow(?) cell in sklearn_tiledb_models_example notebook

TileDB-Inc · Oct 4, 2022 · 768d66c · 768d66c
1 parent 7f029ca
commit 768d66c
Showing 1 changed file with 43 additions and 29 deletions.
diff --git a/examples/models/sklearn_tiledb_models_example.ipynb b/examples/models/sklearn_tiledb_models_example.ipynb
@@ -65,8 +65,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Data fetching...\n",
-      "Data scaling...\n"
+      "Data fetching...\n"
      ]
     }
    ],
@@ -76,8 +75,23 @@
     "\n",
     "# Load data from https://www.openml.org/d/554\n",
     "print('Data fetching...')\n",
-    "X, y = fetch_openml('mnist_784', version=1, return_X_y=True, as_frame=False, data_home=data_home)\n",
-    "\n",
+    "X, y = fetch_openml('mnist_784', version=1, return_X_y=True, as_frame=False, data_home=data_home)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data scaling...\n"
+     ]
+    }
+   ],
+   "source": [
     "random_state = check_random_state(0)\n",
     "permutation = random_state.permutation(X.shape[0])\n",
     "X = X[permutation]\n",
@@ -106,7 +120,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -119,8 +133,8 @@
      "text": [
       "Model fit...\n",
       "Model score...\n",
-      "Sparsity with L1 penalty: 61.53%\n",
-      "Test score with L1 penalty: 0.8325\n"
+      "Sparsity with L1 penalty: 77.93%\n",
+      "Test score with L1 penalty: 0.8298\n"
      ]
     }
    ],
@@ -158,7 +172,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -184,7 +198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -201,13 +215,13 @@
       " '../data/sklearn-mnist-1/__commits',\n",
       " '../data/sklearn-mnist-1/__schema']\n",
       "\n",
-      "Key: Sparsity_with_L1_penalty, Value: 61.530612244897966\n",
+      "Key: Sparsity_with_L1_penalty, Value: 77.93367346938776\n",
       "Key: TILEDB_ML_MODEL_ML_FRAMEWORK, Value: SKLEARN\n",
       "Key: TILEDB_ML_MODEL_ML_FRAMEWORK_VERSION, Value: 1.0.2\n",
       "Key: TILEDB_ML_MODEL_PREVIEW, Value: LogisticRegression(C=0.01, penalty='l1', solver='saga', tol=0.1)\n",
       "Key: TILEDB_ML_MODEL_PYTHON_VERSION, Value: 3.7.13\n",
       "Key: TILEDB_ML_MODEL_STAGE, Value: STAGING\n",
-      "Key: score, Value: 0.8325\n"
+      "Key: score, Value: 0.8298\n"
      ]
     }
    ],
@@ -236,7 +250,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -247,14 +261,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Key: Sparsity_with_L1_penalty, Value: 61.530612244897966\n",
+      "Key: Sparsity_with_L1_penalty, Value: 77.93367346938776\n",
       "Key: TILEDB_ML_MODEL_ML_FRAMEWORK, Value: SKLEARN\n",
       "Key: TILEDB_ML_MODEL_ML_FRAMEWORK_VERSION, Value: 1.0.2\n",
       "Key: TILEDB_ML_MODEL_PREVIEW, Value: LogisticRegression(C=0.01, penalty='l1', solver='saga', tol=0.1)\n",
       "Key: TILEDB_ML_MODEL_PYTHON_VERSION, Value: 3.7.13\n",
       "Key: TILEDB_ML_MODEL_STAGE, Value: STAGING\n",
       "Key: new_meta, Value: [\"Any kind of info\"]\n",
-      "Key: score, Value: 0.8325\n"
+      "Key: score, Value: 0.8298\n"
      ]
     }
    ],
@@ -281,7 +295,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -293,12 +307,12 @@
      "output_type": "stream",
      "text": [
       "Model score...\n",
-      "Sparsity with L1 penalty: 61.53%\n",
-      "Test score with L1 penalty: 0.8325\n",
+      "Sparsity with L1 penalty: 77.93%\n",
+      "Test score with L1 penalty: 0.8298\n",
       "Model fit...\n",
       "Model score...\n",
-      "Sparsity with L1 penalty: 46.21%\n",
-      "Test score with L1 penalty: 0.7401\n",
+      "Sparsity with L1 penalty: 44.07%\n",
+      "Test score with L1 penalty: 0.7194\n",
       "\n",
       "['../data/sklearn-mnist-1/__fragment_meta',\n",
       " '../data/sklearn-mnist-1/__meta',\n",
@@ -311,14 +325,14 @@
       "number of fragments: 2\n",
       "\n",
       "===== FRAGMENT NUMBER 0 =====\n",
-      "timestamp range: (1660134739235, 1660134739235)\n",
+      "timestamp range: (1664858394611, 1664858394611)\n",
       "number of unconsolidated metadata: 2\n",
-      "version: 14\n",
+      "version: 15\n",
       "\n",
       "===== FRAGMENT NUMBER 1 =====\n",
-      "timestamp range: (1660134745067, 1660134745067)\n",
+      "timestamp range: (1664858399506, 1664858399506)\n",
       "number of unconsolidated metadata: 2\n",
-      "version: 14\n"
+      "version: 15\n"
      ]
     }
    ],
@@ -390,7 +404,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -402,7 +416,7 @@
      "output_type": "stream",
      "text": [
       "Fit...\n",
-      "Test score: 0.7698\n"
+      "Test score: 0.7755\n"
      ]
     }
    ],
@@ -436,7 +450,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -449,7 +463,7 @@
        "'../data/tiledb-sklearn-mnist/sklearn-mnist-2'"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -470,7 +484,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "metadata": {
     "pycharm": {
      "name": "#%%\n"
@@ -512,4 +526,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}