examples/xgboost/2_xgboost_With_Scaling.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# XGBoost → PMML\n",
    "\n",
    "\n",
    "### Exporter: XGboost Classifier\n",
    "### Data Set used: Iris\n",
    "\n",
    "\n",
    "### **STEPS**:\n",
    "- Build the Pipeline with preprocessing \n",
    "- Build PMML using Nyoka exporter"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Pre-processing, Model building (using pipeline) for Iris data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-08-13T17:23:34.023366Z",
     "start_time": "2018-08-13T17:23:33.043866Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;scaling&#x27;, StandardScaler()),\n",
       "                (&#x27;xgbc_preprocess&#x27;,\n",
       "                 XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "                               colsample_bylevel=None, colsample_bynode=None,\n",
       "                               colsample_bytree=None,\n",
       "                               early_stopping_rounds=None,\n",
       "                               enable_categorical=False, eval_metric=None,\n",
       "                               feature_types=None, gamma=None, gpu_id=None,\n",
       "                               grow_policy=None, importance_type=None,\n",
       "                               interaction_constraints=None, learning_rate=None,\n",
       "                               max_bin=None, max_cat_threshold=None,\n",
       "                               max_cat_to_onehot=None, max_delta_step=None,\n",
       "                               max_depth=None, max_leaves=None,\n",
       "                               min_child_weight=None, missing=nan,\n",
       "                               monotone_constraints=None, n_estimators=5,\n",
       "                               n_jobs=None, num_parallel_tree=None,\n",
       "                               objective=&#x27;multi:softprob&#x27;, predictor=None, ...))])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;scaling&#x27;, StandardScaler()),\n",
       "                (&#x27;xgbc_preprocess&#x27;,\n",
       "                 XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "                               colsample_bylevel=None, colsample_bynode=None,\n",
       "                               colsample_bytree=None,\n",
       "                               early_stopping_rounds=None,\n",
       "                               enable_categorical=False, eval_metric=None,\n",
       "                               feature_types=None, gamma=None, gpu_id=None,\n",
       "                               grow_policy=None, importance_type=None,\n",
       "                               interaction_constraints=None, learning_rate=None,\n",
       "                               max_bin=None, max_cat_threshold=None,\n",
       "                               max_cat_to_onehot=None, max_delta_step=None,\n",
       "                               max_depth=None, max_leaves=None,\n",
       "                               min_child_weight=None, missing=nan,\n",
       "                               monotone_constraints=None, n_estimators=5,\n",
       "                               n_jobs=None, num_parallel_tree=None,\n",
       "                               objective=&#x27;multi:softprob&#x27;, predictor=None, ...))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              n_estimators=5, n_jobs=None, num_parallel_tree=None,\n",
       "              objective=&#x27;multi:softprob&#x27;, predictor=None, ...)</pre></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "Pipeline(steps=[('scaling', StandardScaler()),\n",
       "                ('xgbc_preprocess',\n",
       "                 XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "                               colsample_bylevel=None, colsample_bynode=None,\n",
       "                               colsample_bytree=None,\n",
       "                               early_stopping_rounds=None,\n",
       "                               enable_categorical=False, eval_metric=None,\n",
       "                               feature_types=None, gamma=None, gpu_id=None,\n",
       "                               grow_policy=None, importance_type=None,\n",
       "                               interaction_constraints=None, learning_rate=None,\n",
       "                               max_bin=None, max_cat_threshold=None,\n",
       "                               max_cat_to_onehot=None, max_delta_step=None,\n",
       "                               max_depth=None, max_leaves=None,\n",
       "                               min_child_weight=None, missing=nan,\n",
       "                               monotone_constraints=None, n_estimators=5,\n",
       "                               n_jobs=None, num_parallel_tree=None,\n",
       "                               objective='multi:softprob', predictor=None, ...))])"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from sklearn import datasets\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from xgboost import XGBClassifier,XGBRegressor\n",
    "\n",
    "iris = datasets.load_iris()\n",
    "irisd = pd.DataFrame(iris.data,columns=iris.feature_names)\n",
    "irisd['Species'] = iris.target\n",
    "\n",
    "features = irisd.columns.drop('Species')\n",
    "target = 'Species'\n",
    "\n",
    "pipeline_obj = Pipeline([\n",
    "    ('scaling',StandardScaler()), \n",
    "    ('xgbc_preprocess',XGBClassifier(n_estimators=5))\n",
    "])\n",
    "\n",
    "pipeline_obj.fit(irisd[features],irisd[target])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Export the Pipeline object into PMML using the Nyoka package"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-08-13T17:23:36.956866Z",
     "start_time": "2018-08-13T17:23:36.319366Z"
    }
   },
   "outputs": [],
   "source": [
    "from nyoka import xgboost_to_pmml\n",
    "xgboost_to_pmml(pipeline_obj,features,target,\"xgbc_pmml_preprocess.pmml\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.8.17"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}