use pandas dtype helper in example notebook

interpretml · Oct 8, 2021 · a3241a6 · a3241a6
1 parent 9be960d
commit a3241a6
Showing 1 changed file with 29 additions and 35 deletions.
diff --git a/examples/convert.ipynb b/examples/convert.ipynb
@@ -211,18 +211,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 4,
    "id": "corporate-bleeding",
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/home/sah0023/venv/ebm2onnx/lib/python3.6/site-packages/sklearn/utils/validation.py:63: DataConversionWarning:\n",
-      "\n",
-      "A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
-      "\n"
+      "/home/sah0023/venv/ebm2onnx/lib/python3.6/site-packages/sklearn/utils/validation.py:63: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
+      "  return f(*args, **kwargs)\n"
      ]
     },
     {
@@ -237,7 +235,7 @@
        "                              interactions=2)"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -260,7 +258,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "id": "canadian-telephone",
    "metadata": {
     "scrolled": false
@@ -269,8 +267,8 @@
     {
      "data": {
       "text/html": [
-       "<!-- http://127.0.0.1:7001/140115281061760/ -->\n",
-       "<iframe src=\"http://127.0.0.1:7001/140115281061760/\" width=100% height=800 frameBorder=\"0\"></iframe>"
+       "<!-- http://127.0.0.1:7001/140010521935944/ -->\n",
+       "<iframe src=\"http://127.0.0.1:7001/140010521935944/\" width=100% height=800 frameBorder=\"0\"></iframe>"
       ]
      },
      "metadata": {},
@@ -293,18 +291,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 7,
    "id": "vocational-globe",
    "metadata": {},
    "outputs": [],
    "source": [
     "onnx_model = ebm2onnx.to_onnx(\n",
     "    model=ebm,\n",
-    "    dtype={\n",
-    "        'Age': 'double',\n",
-    "        'Fare': 'double',\n",
-    "        'Pclass': 'int',\n",
-    "    },\n",
+    "    dtype=ebm2onnx.get_dtype_from_pandas(x_train),\n",
     "    name=\"ebm\",\n",
     ")"
    ]
@@ -319,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 8,
    "id": "appropriate-powder",
    "metadata": {},
    "outputs": [
@@ -351,18 +345,18 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Precision</th>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>0.750000</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.738095</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Recall</th>\n",
        "      <td>0.153846</td>\n",
-       "      <td>1.000000</td>\n",
+       "      <td>0.939394</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>FScore</th>\n",
-       "      <td>0.266667</td>\n",
-       "      <td>0.857143</td>\n",
+       "      <td>0.235294</td>\n",
+       "      <td>0.826667</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Support</th>\n",
@@ -375,13 +369,13 @@
       ],
       "text/plain": [
        "                   0          1\n",
-       "Precision   1.000000   0.750000\n",
-       "Recall      0.153846   1.000000\n",
-       "FScore      0.266667   0.857143\n",
+       "Precision   0.500000   0.738095\n",
+       "Recall      0.153846   0.939394\n",
+       "FScore      0.235294   0.826667\n",
        "Support    13.000000  33.000000"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -401,7 +395,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 9,
    "id": "described-beatles",
    "metadata": {},
    "outputs": [
@@ -440,18 +434,18 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>Precision</th>\n",
-       "      <td>1.000000</td>\n",
-       "      <td>0.750000</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.738095</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Recall</th>\n",
        "      <td>0.153846</td>\n",
-       "      <td>1.000000</td>\n",
+       "      <td>0.939394</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>FScore</th>\n",
-       "      <td>0.266667</td>\n",
-       "      <td>0.857143</td>\n",
+       "      <td>0.235294</td>\n",
+       "      <td>0.826667</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>Support</th>\n",
@@ -464,13 +458,13 @@
       ],
       "text/plain": [
        "                   0          1\n",
-       "Precision   1.000000   0.750000\n",
-       "Recall      0.153846   1.000000\n",
-       "FScore      0.266667   0.857143\n",
+       "Precision   0.500000   0.738095\n",
+       "Recall      0.153846   0.939394\n",
+       "FScore      0.235294   0.826667\n",
        "Support    13.000000  33.000000"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }