{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from IPython.core.interactiveshell import InteractiveShell\n",
    "import math\n",
    "import re\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt # for plotting \n",
    "import seaborn as sns # for plotting\n",
    "       \n",
    "# Feature and Model Selection:\n",
    "import lightgbm as lgb\n",
    "from sklearn.svm import LinearSVC\n",
    "from sklearn.linear_model import LogisticRegression, SGDClassifier  # linear classifiers\n",
    "from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, ExtraTreesClassifier\n",
    "from sklearn.model_selection import StratifiedKFold  # train/test splitting tool for cross-validation\n",
    "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_curve, auc  # scoring metrics\n",
    "from sklearn.impute import SimpleImputer, MissingIndicator\n",
    "from sklearn.experimental import enable_iterative_imputer\n",
    "from sklearn.impute import IterativeImputer\n",
    "from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder, MinMaxScaler, StandardScaler\n",
    "from sklearn.compose import ColumnTransformer, make_column_transformer\n",
    "from sklearn.pipeline import FeatureUnion, make_pipeline, Pipeline\n",
    "\n",
    "# My own packages/modules\n",
    "import rek_ml.dsets_t as dst\n",
    "import rek_ml.ml_misc as rml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up some notebook display defaults\n",
    "InteractiveShell.ast_node_interactivity = \"all\"\n",
    "%matplotlib inline\n",
    "plt.style.use('default')\n",
    "sns.set()\n",
    "pd.options.display.float_format = '{:,.2f}'.format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# load the datasets currently of interest\n",
    "k_trn = pd.read_csv(dst.oma_trn_5, dtype=dst.d_types_5)\n",
    "y_trn = k_trn[\"Survived\"]\n",
    "_ = k_trn.drop(\"Survived\", axis=1, inplace=True)\n",
    "# _ = k_trn.drop(\"Cabin\", axis=1, inplace=True)\n",
    "\n",
    "k_tst = pd.read_csv(dst.oma_tst_5, dtype=dst.d_types_5)\n",
    "y_tst = k_tst[\"Survived\"]\n",
    "_ = k_tst.drop(\"Survived\", axis=1, inplace=True)\n",
    "# _ = k_tst.drop(\"Cabin\", axis=1, inplace=True)\n",
    "\n",
    "k_all = k_trn\n",
    "k_all = pd.concat([k_all, k_tst], ignore_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# let's try the full feature set\n",
    "X_trn = k_trn[dst.full_trn_features]"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "a27d3f2bf68df5402465348834a2195030d3fc5bfc8e594e2a17c8c7e2447c85"
  },
  "kernelspec": {
   "display_name": "Python 3.9.2 64-bit ('ds-3.9': conda)",
   "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": "3.9.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}