229 lines (228 with data), 5.9 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from clinical_ts.timeseries_utils import *\n",
    "from clinical_ts.ecg_utils import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# prepare data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "target_fs=100\n",
    "data_root=Path(\"./ecg_data/\")\n",
    "target_root=Path(\"./ecg_data_processed\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Ribeiro 2020"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Download the test set from Ribeiro et al 2020 (https://www.nature.com/articles/s41467-020-15432-4) https://doi.org/10.5281/zenodo.3625006 and place it in data_folder_ribeiro_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_folder_ribeiro_test = data_root/\"ribeiro2020_test\"\n",
    "target_folder_ribeiro_test = target_root/(\"ribeiro_fs\"+str(target_fs))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "df_ribeiro_test, lbl_itos_ribeiro_test,  mean_ribeiro_test, std_ribeiro_test = prepare_data_ribeiro_test(data_folder_ribeiro_test, target_fs=target_fs, channels=12, channel_stoi=channel_stoi_default, target_folder=target_folder_ribeiro_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#reformat everything as memmap for efficiency\n",
    "reformat_as_memmap(df_ribeiro_test, target_folder_ribeiro_test/(\"memmap.npy\"),data_folder=target_folder_ribeiro_test,delete_npys=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Zheng 2020"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Download the dataset from Zheng et al 2020 (https://www.nature.com/articles/s41597-020-0386-x) https://figshare.com/collections/ChapmanECG/4560497/2 and place it in data_folder_zheng"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_folder_zheng = data_root/\"zheng2020/\"\n",
    "target_folder_zheng = target_root/(\"zheng_fs\"+str(target_fs))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "df_zheng, lbl_itos_zheng,  mean_zheng, std_zheng = prepare_data_zheng(data_folder_zheng, denoised=False, target_fs=target_fs, channels=12, channel_stoi=channel_stoi_default, target_folder=target_folder_zheng)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#reformat everything as memmap for efficiency\n",
    "reformat_as_memmap(df_zheng, target_folder_zheng/(\"memmap.npy\"),data_folder=target_folder_zheng,delete_npys=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CinC2020 Challenge"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Download the training set of the CinC Challenge 2020 https://physionetchallenges.org/2020/ and place it in data_folder_cinc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_folder_cinc = data_root/\"cinc2020/\"\n",
    "target_folder_cinc = target_root/(\"cinc_fs\"+str(target_fs))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "df_cinc, lbl_itos_cinc,  mean_cinc, std_cinc = prepare_data_cinc(data_folder_cinc, target_fs=target_fs, channels=12, channel_stoi=channel_stoi_default, target_folder=target_folder_cinc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#reformat everything as memmap for efficiency\n",
    "reformat_as_memmap(df_cinc, target_folder_cinc/(\"memmap.npy\"),data_folder=target_folder_cinc,delete_npys=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## PTB-XL"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Download the PTB-XL dataset (https://www.nature.com/articles/s41597-020-0495-6) https://physionet.org/content/ptb-xl/1.0.1/ and place it in data_folder_ptb_xl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_folder_ptb_xl = data_root/\"ptb_xl/\"\n",
    "target_folder_ptb_xl = target_root/(\"ptb_xl_fs\"+str(target_fs))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_ptb_xl, lbl_itos_ptb_xl,  mean_ptb_xl, std_ptb_xl = prepare_data_ptb_xl(data_folder_ptb_xl, min_cnt=0, target_fs=target_fs, channels=input_channels, channel_stoi=channel_stoi_default, target_folder=target_folder_ptb_xl)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#reformat everything as memmap for efficiency\n",
    "reformat_as_memmap(df_ptb_xl, target_folder_ptb_xl/(\"memmap.npy\"),data_folder=target_folder_ptb_xl,delete_npys=True)"
   ]
  }
 ],
 "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}