{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install pandas_profiling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install lightgbm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd \n",
    "import matplotlib.pyplot as plt\n",
    "import ipaddress\n",
    "import pandas_profiling as pp\n",
    "%matplotlib inline\n",
    "from sklearn import preprocessing\n",
    "plt.rc(\"font\", size=14)\n",
    "import warnings\n",
    "warnings.simplefilter(action='ignore', category=FutureWarning)\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "import time\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.model_selection import train_test_split\n",
    "import lightgbm as lgb\n",
    "from lightgbm import LGBMClassifier\n",
    "import seaborn as sns\n",
    "sns.set(style=\"white\")\n",
    "sns.set(style=\"whitegrid\", color_codes=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import types\n",
    "import pandas as pd\n",
    "\n",
    "url = 'https://raw.githubusercontent.com/IBM/predict-fraud-using-auto-ai/master/data/fraud_dataset.csv'\n",
    "df = pd.read_csv(url)\n",
    "\n",
    "print(df.head())\n",
    "print(df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "count_fraud = len(df[df['Fraud_Risk']==0])\n",
    "count_non_fraud = len(df[df['Fraud_Risk']==1])\n",
    "pct_of_non_fraud = count_non_fraud/(count_non_fraud +count_fraud)\n",
    "print(\"percentage of non Fraud Risk is\", round(pct_of_non_fraud*100,2))\n",
    "pct_of_fraud = count_fraud/(count_non_fraud +count_fraud)\n",
    "print(\"percentage of Fraud Risk\", round(pct_of_fraud*100,2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.countplot(x='Fraud_Risk',data=df, palette='hls')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.groupby('Fraud_Risk').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.corr(method ='pearson')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df[df.columns[0:12]]\n",
    "y = df[df.columns[12:]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.isna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Train_x Shape :: \", X_train.shape)\n",
    "print(\"Train_y Shape :: \", y_train.shape)\n",
    "print(\"Test_x Shape :: \", X_test.shape)\n",
    "print(\"Test_y Shape :: \", y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "d_train = lgb.Dataset(X_train, label=y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def LGBM_classifier(features, target):\n",
    "    \"\"\"\n",
    "    To train the LGBM classifier with features and target data\n",
    "    :param features:\n",
    "    :param target:\n",
    "    :return: trained LGBM classifier\n",
    "    \"\"\"\n",
    "    model = LGBMClassifier(metric='binary_logloss', objective='binary')\n",
    "    model.fit(features, target)\n",
    "    return model\n",
    "\n",
    "start = time.time()\n",
    "trained_model = LGBM_classifier(X_train, y_train.values.ravel())\n",
    "print(\"> Completion Time : \", time.time() - start)\n",
    "print(\"Trained LGBM model :: \", trained_model)\n",
    "predictions = trained_model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Train Accuracy :: \", accuracy_score(y_train, trained_model.predict(X_train)))\n",
    "print(\"LGBM Model Test Accuracy is :: \", accuracy_score(y_test, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\" Confusion matrix \", confusion_matrix(y_test, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "feat_imp = pd.Series(trained_model.feature_importances_, index=X.columns)\n",
    "feat_imp.nlargest(12).plot(kind='barh', figsize=(8,10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install shap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import shap\n",
    "shap.initjs()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "shap_values = shap.TreeExplainer(trained_model.booster_).shap_values(X_train)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.7",
   "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": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}