{ "cells": [ { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [], "source": [ "# General Utility\n", "import os\n", "import pandas as pd\n", "import numpy as np\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "from IPython.core.display import display, HTML\n", "sns.set()\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import StratifiedKFold\n", "from sklearn.model_selection import RepeatedStratifiedKFold\n", "from sklearn.model_selection import train_test_split " ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [], "source": [ "nb_seed = 1234" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [], "source": [ "from imblearn.datasets import make_imbalance" ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | attr1 | \n", "attr2 | \n", "attr3 | \n", "attr4 | \n", "attr5 | \n", "attr6 | \n", "class | \n", "
---|---|---|---|---|---|---|---|
0 | \n", "0.230020 | \n", "5.072578 | \n", "-0.276061 | \n", "0.832444 | \n", "-0.377866 | \n", "0.480322 | \n", "'-1' | \n", "
1 | \n", "0.155491 | \n", "-0.169390 | \n", "0.670652 | \n", "-0.859553 | \n", "-0.377866 | \n", "-0.945723 | \n", "'-1' | \n", "
2 | \n", "-0.784415 | \n", "-0.443654 | \n", "5.674705 | \n", "-0.859553 | \n", "-0.377866 | \n", "-0.945723 | \n", "'-1' | \n", "
3 | \n", "0.546088 | \n", "0.131415 | \n", "-0.456387 | \n", "-0.859553 | \n", "-0.377866 | \n", "-0.945723 | \n", "'-1' | \n", "
4 | \n", "-0.102987 | \n", "-0.394994 | \n", "-0.140816 | \n", "0.979703 | \n", "-0.377866 | \n", "1.013566 | \n", "'-1' | \n", "