serverfiles_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Orange datasets are hosted on http://datasets.biolab.si/\n",
    "\n",
    "Folder structure:\n",
    "\n",
    "\"core\" -> publicly available datasets in Orange\n",
    "\"sc \"  -> publicly available datasets in scOrange\n",
    "\n",
    "To read and download datasets we use \"https://github.com/biolab/serverfiles\"\n",
    "installable trough \"pip install serverfiles\"\n",
    "\n",
    "\"\"\"\n",
    "\n",
    "import serverfiles\n",
    "from Orange.data import Table"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('DC_expMatrix_DCnMono.tab.gz',),\n",
       " ('DC_expMatrix_deeper.characterization.tab.gz',),\n",
       " ('aml-1k.pickle',),\n",
       " ('aml-8k.pickle',),\n",
       " ('ccp_data_Tcells_normCounts.counts.all_genes.tab.gz',),\n",
       " ('ccp_data_Tcells_normCounts.counts.cycle_genes.tab.gz',),\n",
       " ('ccp_data_liver.counts.all_genes.tab.gz',),\n",
       " ('ccp_data_liver.counts.cycle_genes.tab.gz',),\n",
       " ('ccp_data_mESCbulk.counts.all_genes.tab.gz',),\n",
       " ('ccp_data_mESCbulk.counts.cycle_genes.tab.gz',),\n",
       " ('ccp_normCountsBuettnerEtAl.counts.all_genes.tab.gz',),\n",
       " ('ccp_normCountsBuettnerEtAl.counts.cycle_genes.tab.gz',),\n",
       " ('ccp_normCounts_mESCquartz.counts.all_genes.tab.gz',),\n",
       " ('ccp_normCounts_mESCquartz.counts.cycle_genes.tab.gz',),\n",
       " ('cdp_expression_macosko.tab.gz',),\n",
       " ('cdp_expression_shekhar.tab.gz',),\n",
       " ('dm_proj_neurons_li2017.pkl.gz',),\n",
       " ('nestorawa_forcellcycle.pkl.gz',),\n",
       " ('pbmc_kang2018_raw_control.pkl.gz',),\n",
       " ('pbmc_kang2018_raw_stimulated.pkl.gz',),\n",
       " ('pbmc_kang2018_sample.pkl.gz',)]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "single_cell_url = 'http://datasets.biolab.si/sc'\n",
    "\n",
    "# connect to the HTTP file server\n",
    "sf = serverfiles.ServerFiles(server=single_cell_url)\n",
    "\n",
    "# list all available files\n",
    "sf.listfiles()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# setup local folder structure\n",
    "lf = serverfiles.LocalFiles('path_to_my_data', serverfiles=sf)\n",
    "lf.listfiles()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('aml-1k.pickle',)]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Download data from serverfiles to localfiles\n",
    "lf.download('aml-1k.pickle')\n",
    "lf.listfiles()\n",
    "\n",
    "# to get the path of downloaded file\n",
    "# lf.localpath('aml-1k.pickle')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "path_to_my_data/aml-1k.pickle\n",
      "[('aml-1k.pickle',)]\n",
      "path_to_my_data/aml-8k.pickle\n",
      "[('aml-8k.pickle',), ('aml-1k.pickle',)]\n"
     ]
    }
   ],
   "source": [
    "# to get a path of a given file use localpath_download,\n",
    "# if the file does not exist it will be downloaded from the\n",
    "# serverfiles automatically\n",
    "\n",
    "aml_1k = lf.localpath_download('aml-1k.pickle')\n",
    "print(aml_1k)\n",
    "print(lf.listfiles())\n",
    "aml_8k = lf.localpath_download('aml-8k.pickle')\n",
    "print(aml_8k)\n",
    "print(lf.listfiles())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[0.000, 0.000, 5.648, 5.267, 0.000, ... | healthy] {1, 6681b0788fc2b2e21975e26f588cc7a9, ACGGGAGATGACCA-1},\n",
       " [0.983, 0.573, 0.000, 0.000, 0.000, ... | AML] {1, 7c1e27874a82e7d5c1c877fa2cba7ba7, GAACAGCTGCTTAG-1},\n",
       " [0.000, 0.000, 0.000, 0.000, 4.069, ... | healthy] {2, b9d78fbc8b1bf9aa478e1fbd93ac883c, TCTTACGAAAAAGC-1},\n",
       " [0.000, 0.000, 0.000, 0.000, 2.304, ... | healthy] {1, 841c0e79f017a8ece40b2532f82a9c7a, CGAGCCGACTCTAT-1},\n",
       " [0.000, 0.000, 0.000, 0.000, 0.000, ... | healthy] {2, 08c51bbdc6bb95fc17cd3965e6d6c4fb, GCAAACTGTTGGCA-1},\n",
       " ...\n",
       "]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This is useful because now we can do something like this:\n",
    "def load(experiment):\n",
    "    # checks if new version available\n",
    "    lf.update(experiment)\n",
    "    # ensures that we have the data localy\n",
    "    return Table(lf.localpath_download(experiment))\n",
    "\n",
    "# note that using load method we keep our localfiles and serverfiles in sync.\n",
    "# it will always get the latest version from the serverfiles.\n",
    "load('aml-1k.pickle')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# if one does not want to work with LocalFiles \n",
    "# access data directly trough ServerFiles\n",
    "\n",
    "sf.download('aml-1k.pickle', target='./my_downloaded_file.pickle')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![alt text](https://user-images.githubusercontent.com/15876321/53346326-16bc9700-3917-11e9-835d-00a5407310ea.png)"
   ]
  },
  {
   "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}