Merge pull request #36 from Kostee/main

Kompletne pd2 #17

PraceDomowe/PracaDomowa2/Kosterna_Jakub/.ipynb_checkpoints/xgboost_model-checkpoint.ipynb

@@ -0,0 +1,160 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Jakub Kosterna - przygotowanie modelu\n",
+    "## Warsztaty Badawcze 2021: XAI-1\n",
+    "### Skrypt dodatkowy do pracy domowej 2"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Co ja tu robię"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Czyż druga praca domowa nie jest wspaniałą okazją, aby jeszcze lepiej poznać **<font color=\"red\">Red Wine Quality</font>**?\n",
+    "\n",
+    "Metodę **LIME** będę badał na najlepszym znalezionym przez mój zespół modelu *XGBoost* z tuningiem wybranych hyperparametrów."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Potrzebne pakiety i ziarno generatora"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import pickle\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn import preprocessing\n",
+    "\n",
+    "import xgboost as xgb\n",
+    "\n",
+    "from sklearn.model_selection import RandomizedSearchCV\n",
+    "\n",
+    "np.random.seed = 42"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Przygotowanie zbiorów treningowego i testowego"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_wines = pd.read_csv('winequality-red.csv')\n",
+    "df_wines[\"is_good\"] = df_wines.apply(lambda row: 1 if row.quality > 5 else 0, axis = 1)\n",
+    "X = df_wines.drop([\"is_good\", 'quality'], axis=1)\n",
+    "y = df_wines[\"is_good\"]\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y,random_state = 42)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model i tuning hyperparametrów"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'min_child_weight': 1,\n",
+       " 'max_depth': 5,\n",
+       " 'learning_rate': 0.15,\n",
+       " 'gamma': 0.4,\n",
+       " 'colsample_bytree': 0.5}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "xgb_param_grid = {\n",
+    "    \"learning_rate\": [0.05, 0.10, 0.15, 0.20, 0.25, 0.30] ,\n",
+    "    \"max_depth\": [ 3, 4, 5, 6, 8, 10, 12, 15],\n",
+    "    \"min_child_weight\": [ 1, 3, 5, 7],\n",
+    "    \"gamma\": [ 0.0, 0.1, 0.2 , 0.3, 0.4],\n",
+    "    \"colsample_bytree\": [ 0.3, 0.4, 0.5 , 0.7]\n",
+    "}\n",
+    "\n",
+    "xgb = xgb.XGBClassifier(objective = \"binary:logistic\", eval_metric = \"logloss\", use_label_encoder = False, seed = 42)\n",
+    "\n",
+    "randomized_mse = RandomizedSearchCV(param_distributions = xgb_param_grid,\n",
+    "    estimator = xgb,\n",
+    "    cv = 4,\n",
+    "    n_iter = 1000)\n",
+    "\n",
+    "randomized_mse.fit(X_train, y_train)\n",
+    "randomized_mse.best_params_"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Zapis modelu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pickle.dump(randomized_mse, open(\"xgb\", 'wb'))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}