127 lines (126 with data), 3.1 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "#10-fold cross validation, and this was repeated for 100 times."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dfx = pd.read_excel('C1_train.xlsx', sheet_name='Proteins', index_col = 'Proteins')\n",
    "test_dfx = pd.read_excel('C2_test.xlsx', sheet_name='Proteins', index_col = 'Proteins')\n",
    "\n",
    "dfy = pd.read_excel('C0_subject_info.xlsx', index_col = 'Patient ID')\n",
    "\n",
    "comm_proteins = list(set(train_dfx.index) & set(test_dfx.index))\n",
    "\n",
    "comm_proteins.sort()\n",
    "\n",
    "train_x = train_dfx.loc[comm_proteins].fillna(0)\n",
    "test_x = test_dfx.loc[comm_proteins].fillna(0)\n",
    "\n",
    "testX = test_x[test_x.columns[1:]].T\n",
    "trainX = train_x[train_x.columns[1:]].T\n",
    "\n",
    "dfx = trainX.append(testX)\n",
    "dfx = dfx.join(dfy['severe'])\n",
    "dfx['Train_Test'] = dfx.index.isin(train_dfx.columns[1:])\n",
    "dfx['Train_Test'] = dfx['Train_Test'].apply(lambda x:'Train' if x else 'Test')\n",
    "dfx = dfx[['severe', 'Train_Test']].join(dfx[dfx.columns[:-2]])\n",
    "dfx = dfx.rename(columns={'severe':'Severe'})\n",
    "\n",
    "dfx.to_excel('./proteins_processed.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dfx = pd.read_excel('C1_train.xlsx', sheet_name='Metabolites', index_col = 'Metabolites')\n",
    "test_dfx = pd.read_excel('C2_test.xlsx', sheet_name='Metabolites', index_col = 'Metabolites')\n",
    "test_dfx = test_dfx[test_dfx.columns[1:]].T\n",
    "train_dfx = train_dfx[train_dfx.columns[1:]].T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfx = train_dfx.append(test_dfx)\n",
    "dfx = dfx.fillna(dfx.min())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfx.to_excel('./Metabolites_processed.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}