{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# UMAP projection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "import numpy as np\n",
    "\n",
    "from bokeh.plotting import figure, output_file, show, save\n",
    "from bokeh.io import output_notebook, export_png\n",
    "from bokeh.palettes import colorblind\n",
    "from bokeh.models import CategoricalColorMapper, ColumnDataSource, LassoSelectTool, WheelZoomTool, ZoomInTool,  BoxZoomTool, ResetTool\n",
    "from bokeh.layouts import gridplot\n",
    "from bokeh.resources import CDN\n",
    "from bokeh.embed import file_html\n",
    "\n",
    "import numpy as np\n",
    "import umap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "    <div class=\"bk-root\">\n",
       "        <a href=\"https://bokeh.org\" target=\"_blank\" class=\"bk-logo bk-logo-small bk-logo-notebook\"></a>\n",
       "        <span id=\"1001\">Loading BokehJS ...</span>\n",
       "    </div>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/javascript": [
       "\n",
       "(function(root) {\n",
       "  function now() {\n",
       "    return new Date();\n",
       "  }\n",
       "\n",
       "  var force = true;\n",
       "\n",
       "  if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n",
       "    root._bokeh_onload_callbacks = [];\n",
       "    root._bokeh_is_loading = undefined;\n",
       "  }\n",
       "\n",
       "  var JS_MIME_TYPE = 'application/javascript';\n",
       "  var HTML_MIME_TYPE = 'text/html';\n",
       "  var EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n",
       "  var CLASS_NAME = 'output_bokeh rendered_html';\n",
       "\n",
       "  /**\n",
       "   * Render data to the DOM node\n",
       "   */\n",
       "  function render(props, node) {\n",
       "    var script = document.createElement(\"script\");\n",
       "    node.appendChild(script);\n",
       "  }\n",
       "\n",
       "  /**\n",
       "   * Handle when an output is cleared or removed\n",
       "   */\n",
       "  function handleClearOutput(event, handle) {\n",
       "    var cell = handle.cell;\n",
       "\n",
       "    var id = cell.output_area._bokeh_element_id;\n",
       "    var server_id = cell.output_area._bokeh_server_id;\n",
       "    // Clean up Bokeh references\n",
       "    if (id != null && id in Bokeh.index) {\n",
       "      Bokeh.index[id].model.document.clear();\n",
       "      delete Bokeh.index[id];\n",
       "    }\n",
       "\n",
       "    if (server_id !== undefined) {\n",
       "      // Clean up Bokeh references\n",
       "      var cmd = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n",
       "      cell.notebook.kernel.execute(cmd, {\n",
       "        iopub: {\n",
       "          output: function(msg) {\n",
       "            var id = msg.content.text.trim();\n",
       "            if (id in Bokeh.index) {\n",
       "              Bokeh.index[id].model.document.clear();\n",
       "              delete Bokeh.index[id];\n",
       "            }\n",
       "          }\n",
       "        }\n",
       "      });\n",
       "      // Destroy server and session\n",
       "      var cmd = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n",
       "      cell.notebook.kernel.execute(cmd);\n",
       "    }\n",
       "  }\n",
       "\n",
       "  /**\n",
       "   * Handle when a new output is added\n",
       "   */\n",
       "  function handleAddOutput(event, handle) {\n",
       "    var output_area = handle.output_area;\n",
       "    var output = handle.output;\n",
       "\n",
       "    // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n",
       "    if ((output.output_type != \"display_data\") || (!output.data.hasOwnProperty(EXEC_MIME_TYPE))) {\n",
       "      return\n",
       "    }\n",
       "\n",
       "    var toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n",
       "\n",
       "    if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n",
       "      toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n",
       "      // store reference to embed id on output_area\n",
       "      output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n",
       "    }\n",
       "    if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n",
       "      var bk_div = document.createElement(\"div\");\n",
       "      bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n",
       "      var script_attrs = bk_div.children[0].attributes;\n",
       "      for (var i = 0; i < script_attrs.length; i++) {\n",
       "        toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n",
       "      }\n",
       "      // store reference to server id on output_area\n",
       "      output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n",
       "    }\n",
       "  }\n",
       "\n",
       "  function register_renderer(events, OutputArea) {\n",
       "\n",
       "    function append_mime(data, metadata, element) {\n",
       "      // create a DOM node to render to\n",
       "      var toinsert = this.create_output_subarea(\n",
       "        metadata,\n",
       "        CLASS_NAME,\n",
       "        EXEC_MIME_TYPE\n",
       "      );\n",
       "      this.keyboard_manager.register_events(toinsert);\n",
       "      // Render to node\n",
       "      var props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n",
       "      render(props, toinsert[toinsert.length - 1]);\n",
       "      element.append(toinsert);\n",
       "      return toinsert\n",
       "    }\n",
       "\n",
       "    /* Handle when an output is cleared or removed */\n",
       "    events.on('clear_output.CodeCell', handleClearOutput);\n",
       "    events.on('delete.Cell', handleClearOutput);\n",
       "\n",
       "    /* Handle when a new output is added */\n",
       "    events.on('output_added.OutputArea', handleAddOutput);\n",
       "\n",
       "    /**\n",
       "     * Register the mime type and append_mime function with output_area\n",
       "     */\n",
       "    OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n",
       "      /* Is output safe? */\n",
       "      safe: true,\n",
       "      /* Index of renderer in `output_area.display_order` */\n",
       "      index: 0\n",
       "    });\n",
       "  }\n",
       "\n",
       "  // register the mime type if in Jupyter Notebook environment and previously unregistered\n",
       "  if (root.Jupyter !== undefined) {\n",
       "    var events = require('base/js/events');\n",
       "    var OutputArea = require('notebook/js/outputarea').OutputArea;\n",
       "\n",
       "    if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n",
       "      register_renderer(events, OutputArea);\n",
       "    }\n",
       "  }\n",
       "\n",
       "  \n",
       "  if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n",
       "    root._bokeh_timeout = Date.now() + 5000;\n",
       "    root._bokeh_failed_load = false;\n",
       "  }\n",
       "\n",
       "  var NB_LOAD_WARNING = {'data': {'text/html':\n",
       "     \"<div style='background-color: #fdd'>\\n\"+\n",
       "     \"<p>\\n\"+\n",
       "     \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n",
       "     \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n",
       "     \"</p>\\n\"+\n",
       "     \"<ul>\\n\"+\n",
       "     \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n",
       "     \"<li>use INLINE resources instead, as so:</li>\\n\"+\n",
       "     \"</ul>\\n\"+\n",
       "     \"<code>\\n\"+\n",
       "     \"from bokeh.resources import INLINE\\n\"+\n",
       "     \"output_notebook(resources=INLINE)\\n\"+\n",
       "     \"</code>\\n\"+\n",
       "     \"</div>\"}};\n",
       "\n",
       "  function display_loaded() {\n",
       "    var el = document.getElementById(\"1001\");\n",
       "    if (el != null) {\n",
       "      el.textContent = \"BokehJS is loading...\";\n",
       "    }\n",
       "    if (root.Bokeh !== undefined) {\n",
       "      if (el != null) {\n",
       "        el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n",
       "      }\n",
       "    } else if (Date.now() < root._bokeh_timeout) {\n",
       "      setTimeout(display_loaded, 100)\n",
       "    }\n",
       "  }\n",
       "\n",
       "\n",
       "  function run_callbacks() {\n",
       "    try {\n",
       "      root._bokeh_onload_callbacks.forEach(function(callback) {\n",
       "        if (callback != null)\n",
       "          callback();\n",
       "      });\n",
       "    } finally {\n",
       "      delete root._bokeh_onload_callbacks\n",
       "    }\n",
       "    console.debug(\"Bokeh: all callbacks have finished\");\n",
       "  }\n",
       "\n",
       "  function load_libs(css_urls, js_urls, callback) {\n",
       "    if (css_urls == null) css_urls = [];\n",
       "    if (js_urls == null) js_urls = [];\n",
       "\n",
       "    root._bokeh_onload_callbacks.push(callback);\n",
       "    if (root._bokeh_is_loading > 0) {\n",
       "      console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n",
       "      return null;\n",
       "    }\n",
       "    if (js_urls == null || js_urls.length === 0) {\n",
       "      run_callbacks();\n",
       "      return null;\n",
       "    }\n",
       "    console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n",
       "    root._bokeh_is_loading = css_urls.length + js_urls.length;\n",
       "\n",
       "    function on_load() {\n",
       "      root._bokeh_is_loading--;\n",
       "      if (root._bokeh_is_loading === 0) {\n",
       "        console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n",
       "        run_callbacks()\n",
       "      }\n",
       "    }\n",
       "\n",
       "    function on_error() {\n",
       "      console.error(\"failed to load \" + url);\n",
       "    }\n",
       "\n",
       "    for (var i = 0; i < css_urls.length; i++) {\n",
       "      var url = css_urls[i];\n",
       "      const element = document.createElement(\"link\");\n",
       "      element.onload = on_load;\n",
       "      element.onerror = on_error;\n",
       "      element.rel = \"stylesheet\";\n",
       "      element.type = \"text/css\";\n",
       "      element.href = url;\n",
       "      console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n",
       "      document.body.appendChild(element);\n",
       "    }\n",
       "\n",
       "    for (var i = 0; i < js_urls.length; i++) {\n",
       "      var url = js_urls[i];\n",
       "      var element = document.createElement('script');\n",
       "      element.onload = on_load;\n",
       "      element.onerror = on_error;\n",
       "      element.async = false;\n",
       "      element.src = url;\n",
       "      console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n",
       "      document.head.appendChild(element);\n",
       "    }\n",
       "  };var element = document.getElementById(\"1001\");\n",
       "  if (element == null) {\n",
       "    console.error(\"Bokeh: ERROR: autoload.js configured with elementid '1001' but no matching script tag was found. \")\n",
       "    return false;\n",
       "  }\n",
       "\n",
       "  function inject_raw_css(css) {\n",
       "    const element = document.createElement(\"style\");\n",
       "    element.appendChild(document.createTextNode(css));\n",
       "    document.body.appendChild(element);\n",
       "  }\n",
       "\n",
       "  \n",
       "  var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-1.4.0.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-1.4.0.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-1.4.0.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-1.4.0.min.js\"];\n",
       "  var css_urls = [];\n",
       "  \n",
       "\n",
       "  var inline_js = [\n",
       "    function(Bokeh) {\n",
       "      Bokeh.set_log_level(\"info\");\n",
       "    },\n",
       "    function(Bokeh) {\n",
       "    \n",
       "    \n",
       "    }\n",
       "  ];\n",
       "\n",
       "  function run_inline_js() {\n",
       "    \n",
       "    if (root.Bokeh !== undefined || force === true) {\n",
       "      \n",
       "    for (var i = 0; i < inline_js.length; i++) {\n",
       "      inline_js[i].call(root, root.Bokeh);\n",
       "    }\n",
       "    if (force === true) {\n",
       "        display_loaded();\n",
       "      }} else if (Date.now() < root._bokeh_timeout) {\n",
       "      setTimeout(run_inline_js, 100);\n",
       "    } else if (!root._bokeh_failed_load) {\n",
       "      console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n",
       "      root._bokeh_failed_load = true;\n",
       "    } else if (force !== true) {\n",
       "      var cell = $(document.getElementById(\"1001\")).parents('.cell').data().cell;\n",
       "      cell.output_area.append_execute_result(NB_LOAD_WARNING)\n",
       "    }\n",
       "\n",
       "  }\n",
       "\n",
       "  if (root._bokeh_is_loading === 0) {\n",
       "    console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n",
       "    run_inline_js();\n",
       "  } else {\n",
       "    load_libs(css_urls, js_urls, function() {\n",
       "      console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n",
       "      run_inline_js();\n",
       "    });\n",
       "  }\n",
       "}(window));"
      ],
      "application/vnd.bokehjs_load.v0+json": "\n(function(root) {\n  function now() {\n    return new Date();\n  }\n\n  var force = true;\n\n  if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n    root._bokeh_onload_callbacks = [];\n    root._bokeh_is_loading = undefined;\n  }\n\n  \n\n  \n  if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n    root._bokeh_timeout = Date.now() + 5000;\n    root._bokeh_failed_load = false;\n  }\n\n  var NB_LOAD_WARNING = {'data': {'text/html':\n     \"<div style='background-color: #fdd'>\\n\"+\n     \"<p>\\n\"+\n     \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n     \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n     \"</p>\\n\"+\n     \"<ul>\\n\"+\n     \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n     \"<li>use INLINE resources instead, as so:</li>\\n\"+\n     \"</ul>\\n\"+\n     \"<code>\\n\"+\n     \"from bokeh.resources import INLINE\\n\"+\n     \"output_notebook(resources=INLINE)\\n\"+\n     \"</code>\\n\"+\n     \"</div>\"}};\n\n  function display_loaded() {\n    var el = document.getElementById(\"1001\");\n    if (el != null) {\n      el.textContent = \"BokehJS is loading...\";\n    }\n    if (root.Bokeh !== undefined) {\n      if (el != null) {\n        el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n      }\n    } else if (Date.now() < root._bokeh_timeout) {\n      setTimeout(display_loaded, 100)\n    }\n  }\n\n\n  function run_callbacks() {\n    try {\n      root._bokeh_onload_callbacks.forEach(function(callback) {\n        if (callback != null)\n          callback();\n      });\n    } finally {\n      delete root._bokeh_onload_callbacks\n    }\n    console.debug(\"Bokeh: all callbacks have finished\");\n  }\n\n  function load_libs(css_urls, js_urls, callback) {\n    if (css_urls == null) css_urls = [];\n    if (js_urls == null) js_urls = [];\n\n    root._bokeh_onload_callbacks.push(callback);\n    if (root._bokeh_is_loading > 0) {\n      console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n      return null;\n    }\n    if (js_urls == null || js_urls.length === 0) {\n      run_callbacks();\n      return null;\n    }\n    console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n    root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n    function on_load() {\n      root._bokeh_is_loading--;\n      if (root._bokeh_is_loading === 0) {\n        console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n        run_callbacks()\n      }\n    }\n\n    function on_error() {\n      console.error(\"failed to load \" + url);\n    }\n\n    for (var i = 0; i < css_urls.length; i++) {\n      var url = css_urls[i];\n      const element = document.createElement(\"link\");\n      element.onload = on_load;\n      element.onerror = on_error;\n      element.rel = \"stylesheet\";\n      element.type = \"text/css\";\n      element.href = url;\n      console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n      document.body.appendChild(element);\n    }\n\n    for (var i = 0; i < js_urls.length; i++) {\n      var url = js_urls[i];\n      var element = document.createElement('script');\n      element.onload = on_load;\n      element.onerror = on_error;\n      element.async = false;\n      element.src = url;\n      console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n      document.head.appendChild(element);\n    }\n  };var element = document.getElementById(\"1001\");\n  if (element == null) {\n    console.error(\"Bokeh: ERROR: autoload.js configured with elementid '1001' but no matching script tag was found. \")\n    return false;\n  }\n\n  function inject_raw_css(css) {\n    const element = document.createElement(\"style\");\n    element.appendChild(document.createTextNode(css));\n    document.body.appendChild(element);\n  }\n\n  \n  var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-1.4.0.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-1.4.0.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-1.4.0.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-1.4.0.min.js\"];\n  var css_urls = [];\n  \n\n  var inline_js = [\n    function(Bokeh) {\n      Bokeh.set_log_level(\"info\");\n    },\n    function(Bokeh) {\n    \n    \n    }\n  ];\n\n  function run_inline_js() {\n    \n    if (root.Bokeh !== undefined || force === true) {\n      \n    for (var i = 0; i < inline_js.length; i++) {\n      inline_js[i].call(root, root.Bokeh);\n    }\n    if (force === true) {\n        display_loaded();\n      }} else if (Date.now() < root._bokeh_timeout) {\n      setTimeout(run_inline_js, 100);\n    } else if (!root._bokeh_failed_load) {\n      console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n      root._bokeh_failed_load = true;\n    } else if (force !== true) {\n      var cell = $(document.getElementById(\"1001\")).parents('.cell').data().cell;\n      cell.output_area.append_execute_result(NB_LOAD_WARNING)\n    }\n\n  }\n\n  if (root._bokeh_is_loading === 0) {\n    console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n    run_inline_js();\n  } else {\n    load_libs(css_urls, js_urls, function() {\n      console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n      run_inline_js();\n    });\n  }\n}(window));"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "output_notebook()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load Features datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "TASK = 'subtypes'\n",
    "DATASET = 'tcga_breast'\n",
    "MODEL = 'randomForest'\n",
    "\n",
    "layers = 'gene_cnv_prot'\n",
    "\n",
    "PATH = Path('data') / DATASET / TASK\n",
    "PATH_RESULTS =  Path('results') / DATASET / TASK / MODEL\n",
    "\n",
    "SPLIT = 2# choose a random split for the train, test, and test2 files\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file_tr = f'{PATH}/{SPLIT}/{layers}_tr.txt' # Fit UMAP \n",
    "file_test = f'{PATH}/{SPLIT}/{layers}_ts.txt' # test UMAP on TS\n",
    "file_test2 = f'{PATH}/{SPLIT}/{layers}_ts2.txt' # test UMAP on TS2\n",
    "\n",
    "features_train = pd.read_csv(file_tr, sep='\\t', header=0, index_col=0)\n",
    "features_test = pd.read_csv(file_test, sep='\\t', header=0, index_col=0)\n",
    "features_test2 = pd.read_csv(file_test2, sep='\\t', header=0, index_col=0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "BEST = False # restrict the features to the INF signature\n",
    "\n",
    "INF_feats = pd.read_csv(f'{PATH_RESULTS}/{SPLIT}/rSNFi/{layers}_ts_RandomForest_KBest_featurelist.txt', sep='\\t')['FEATURE_NAME'].values.tolist()\n",
    "\n",
    "best_train = features_train[INF_feats]\n",
    "best_test = features_test[INF_feats]\n",
    "best_test2 = features_test2[INF_feats]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "if BEST:\n",
    "    features_train = best_train\n",
    "    features_test = best_test\n",
    "    features_test2 = best_test2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "samples_tr = features_train.index\n",
    "labels_tr = pd.read_csv(f'{PATH}/{SPLIT}/labels_{TASK}_tr.txt', sep='\\t', header=None)[0].tolist()\n",
    "\n",
    "features_train['labels'] = labels_tr\n",
    "labels_tr = features_train['labels']\n",
    "features_tr = features_train[features_train.columns[:-1]].values\n",
    "\n",
    "\n",
    "samples_test = features_test.index\n",
    "labels_test = pd.read_csv(f'{PATH}/{SPLIT}/labels_{TASK}_ts.txt', sep='\\t', header=None)[0].tolist()\n",
    "\n",
    "features_test['labels'] = labels_test\n",
    "labels_test = features_test['labels']\n",
    "features_ts = features_test[features_test.columns[:-1]].values\n",
    "\n",
    "\n",
    "samples_test2 = features_test2.index\n",
    "labels_test2 = pd.read_csv(f'{PATH}/{SPLIT}/labels_{TASK}_ts2.txt', sep='\\t', header=None)[0].tolist()\n",
    "\n",
    "\n",
    "features_test2['labels'] = labels_test2\n",
    "labels_test2 = features_test2['labels']\n",
    "features_ts2 = features_test2[features_test2.columns[:-1]].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_data = features_tr\n",
    "test_data = features_ts\n",
    "test2_data = features_ts2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Check\n",
    "print(len(features_tr),len(samples_tr),len(labels_tr))\n",
    "print(len(features_ts),len(samples_test),len(labels_test))\n",
    "print(len(features_ts2),len(samples_test2),len(labels_test2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fit on the training data and transform the test set into the learned space"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mapper = umap.UMAP(n_neighbors=40, min_dist=0.01, n_components=2,\n",
    "                   metric='euclidean').fit(train_data)\n",
    "test_embedding = mapper.transform(test_data)\n",
    "test2_embedding = mapper.transform(test2_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Check\n",
    "len(mapper.embedding_), len(test_embedding),len(test2_embedding)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plot UMAP 2D projection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "TOOLTIPS = [\n",
    "    (\"index\", \"$index\"),\n",
    "    (\"(x,y)\", \"($x, $y)\"),\n",
    "    (\"desc\", \"@desc\"),\n",
    "]\n",
    "\n",
    "mycols = colorblind['Colorblind'][4]\n",
    "myclasses = pd.unique(labels_tr).tolist()\n",
    "\n",
    "p = figure(plot_width=1200, plot_height=1200, tooltips = TOOLTIPS, tools='save', toolbar_location=\"left\")\n",
    "\n",
    "\n",
    "p.title.align = \"center\"\n",
    "p.title.text_color = \"black\"\n",
    "p.title.text_font_size = \"25px\"\n",
    "\n",
    "size=12\n",
    "\n",
    "for col, theclass in zip(mycols,myclasses):\n",
    "\n",
    "    idx_tr = np.where(np.array(labels_tr)==theclass)[0].tolist()\n",
    "    samples_train = np.expand_dims(samples_tr[idx_tr,], axis=1)\n",
    "    data_tr = np.hstack((mapper.embedding_[idx_tr,], samples_train))    \n",
    "    df_tr = pd.DataFrame(data_tr,columns=['x','y','sample'])\n",
    "\n",
    "    source_tr = ColumnDataSource(data=dict(\n",
    "    x=df_tr['x'],\n",
    "    y=df_tr['y'],\n",
    "    desc=df_tr['sample']))\n",
    "    p.circle(x='x',y='y',size=size,source=source_tr,color=col,alpha=0.8,legend=str(theclass))\n",
    "       \n",
    "    idx_ts = np.where(np.array(labels_test)==theclass)[0].tolist()\n",
    "    samples_ts = np.expand_dims(samples_test[idx_ts,], axis=1)\n",
    "    data_ts = np.hstack((test_embedding[idx_ts,], samples_ts))    \n",
    "    df_ts = pd.DataFrame(data_ts,columns=['x','y','sample'])\n",
    "\n",
    "    source_ts = ColumnDataSource(data=dict(\n",
    "    x=df_ts['x'],\n",
    "    y=df_ts['y'],\n",
    "    desc=df_ts['sample']))\n",
    "    p.triangle(x='x',y='y',size=size,source=source_ts,color=col,alpha=0.8)\n",
    "\n",
    "    idx_ts2 = np.where(np.array(labels_test2)==theclass)[0].tolist()\n",
    "    samples_ts2 = np.expand_dims(samples_test2[idx_ts2,], axis=1)\n",
    "    data_ts2 = np.hstack((test2_embedding[idx_ts2,], samples_ts2))    \n",
    "    df_ts2 = pd.DataFrame(data_ts2,columns=['x','y','sample'])\n",
    "\n",
    "    source_ts2 = ColumnDataSource(data=dict(\n",
    "    x=df_ts2['x'],\n",
    "    y=df_ts2['y'],\n",
    "    desc=df_ts2['sample']))\n",
    "    p.diamond(x='x',y='y',size=size,source=source_ts2,color=col,alpha=0.8)\n",
    "\n",
    "  \n",
    "p.add_tools(LassoSelectTool())\n",
    "p.add_tools(WheelZoomTool())\n",
    "p.legend.label_text_font_size = \"20pt\"\n",
    "p.yaxis.major_label_text_font_size = \"15pt\"\n",
    "p.xaxis.major_label_text_font_size = \"15pt\"\n",
    "\n",
    "\n",
    "p.add_tools(ZoomInTool())\n",
    "p.add_tools(ResetTool())\n",
    "p.add_tools(BoxZoomTool())\n",
    "p.legend.location = \"top_left\"\n",
    "p.legend.click_policy='hide'\n",
    "# p.title()\n",
    "\n",
    "if BEST:\n",
    "    export_png(p, filename=f\"subtypes_INF_split{SPLIT}.png\") #save the plot\n",
    "else:\n",
    "    export_png(p, filename=f\"subtypes_juXT_split{SPLIT}.png\")\n",
    "\n",
    "show(p)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Grid plot for all other splits"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def range_with_ignore(start, stop, ignore):\n",
    "    return np.concatenate([\n",
    "        np.arange(start, ignore),\n",
    "        np.arange(ignore + 1, stop)\n",
    "    ])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "BEST = False\n",
    "\n",
    "mycols = colorblind['Colorblind'][4]\n",
    "plots = []\n",
    "size = 12\n",
    "\n",
    "for split in range_with_ignore(0,10,SPLIT).tolist():\n",
    "    \n",
    "    file_tr = f'{PATH}/{split}/{layers}_tr.txt' # Fit UMAP \n",
    "    file_test = f'{PATH}/{split}/{layers}_ts.txt' # test UMAP \n",
    "    file_test2 = f'{PATH}/{split}/{layers}_ts2.txt' # test UMAP \n",
    "\n",
    "    features_train = pd.read_csv(file_tr, sep='\\t', header=0, index_col=0)\n",
    "    features_test = pd.read_csv(file_test, sep='\\t', header=0, index_col=0)\n",
    "    features_test2 = pd.read_csv(file_test2, sep='\\t', header=0, index_col=0)\n",
    "\n",
    "\n",
    "    INF_feats = pd.read_csv(f'{PATH_RESULTS}/{split}/rSNFi/{layers}_ts_RandomForest_KBest_featurelist.txt', sep='\\t')['FEATURE_NAME'].values.tolist()\n",
    "\n",
    "    best_train = features_train[INF_feats]\n",
    "    best_test = features_test[INF_feats]\n",
    "    best_test2 = features_test2[INF_feats]\n",
    "\n",
    "\n",
    "    if BEST:\n",
    "        features_train = best_train\n",
    "        features_test = best_test\n",
    "        features_test2 = best_test2\n",
    "\n",
    "\n",
    "\n",
    "    samples_tr = features_train.index\n",
    "    labels_tr = pd.read_csv(f'{PATH}/{split}/labels_{TASK}_tr.txt', sep='\\t', header=None)[0].tolist()\n",
    "\n",
    "    features_train['labels'] = labels_tr\n",
    "    labels_tr = features_train['labels']\n",
    "    features_tr = features_train[features_train.columns[:-1]].values\n",
    "\n",
    "\n",
    "    samples_test = features_test.index\n",
    "    labels_test = pd.read_csv(f'{PATH}/{split}/labels_{TASK}_ts.txt', sep='\\t', header=None)[0].tolist()\n",
    "\n",
    "    features_test['labels'] = labels_test\n",
    "    labels_test = features_test['labels']\n",
    "    features_ts = features_test[features_test.columns[:-1]].values\n",
    "\n",
    "\n",
    "    samples_test2 = features_test2.index\n",
    "    labels_test2 = pd.read_csv(f'{PATH}/{split}/labels_{TASK}_ts2.txt', sep='\\t', header=None)[0].tolist()\n",
    "\n",
    "\n",
    "    features_test2['labels'] = labels_test2\n",
    "    labels_test2 = features_test2['labels']\n",
    "    features_ts2 = features_test2[features_test2.columns[:-1]].values\n",
    "\n",
    "\n",
    "    train_data = features_tr\n",
    "    test_data = features_ts\n",
    "    test2_data = features_ts2\n",
    "\n",
    "\n",
    "    mapper = umap.UMAP(n_neighbors=40, min_dist=0.01, n_components=2, metric='euclidean').fit(train_data)\n",
    "    test_embedding = mapper.transform(test_data)\n",
    "    test2_embedding = mapper.transform(test2_data)\n",
    "\n",
    "\n",
    "\n",
    "    myclasses = pd.unique(labels_tr).tolist()\n",
    "\n",
    "    p = figure(title=f'split {split}')\n",
    "    p.title.text_font_size = '25pt'\n",
    "\n",
    "\n",
    "    p.title.align = \"center\"\n",
    "    p.title.text_color = \"black\"\n",
    "    p.title.text_font_size = \"25px\"\n",
    "\n",
    "\n",
    "    for col, theclass in zip(mycols,myclasses):\n",
    "\n",
    "        idx_tr = np.where(np.array(labels_tr)==theclass)[0].tolist()\n",
    "        samples_train = np.expand_dims(samples_tr[idx_tr,], axis=1)\n",
    "        data_tr = np.hstack((mapper.embedding_[idx_tr,], samples_train))    \n",
    "        df_tr = pd.DataFrame(data_tr,columns=['x','y','sample'])\n",
    "\n",
    "        source_tr = ColumnDataSource(data=dict(\n",
    "        x=df_tr['x'],\n",
    "        y=df_tr['y'],\n",
    "        desc=df_tr['sample']))\n",
    "        p.circle(x='x',y='y',size=size,source=source_tr,color=col,alpha=0.8,legend=str(theclass))\n",
    "        \n",
    "        idx_ts = np.where(np.array(labels_test)==theclass)[0].tolist()\n",
    "        samples_ts = np.expand_dims(samples_test[idx_ts,], axis=1)\n",
    "        data_ts = np.hstack((test_embedding[idx_ts,], samples_ts))    \n",
    "        df_ts = pd.DataFrame(data_ts,columns=['x','y','sample'])\n",
    "\n",
    "        source_ts = ColumnDataSource(data=dict(\n",
    "        x=df_ts['x'],\n",
    "        y=df_ts['y'],\n",
    "        desc=df_ts['sample']))\n",
    "        p.triangle(x='x',y='y',size=size,source=source_ts,color=col,alpha=0.8)\n",
    "\n",
    "        idx_ts2 = np.where(np.array(labels_test2)==theclass)[0].tolist()\n",
    "        samples_ts2 = np.expand_dims(samples_test2[idx_ts2,], axis=1)\n",
    "        data_ts2 = np.hstack((test2_embedding[idx_ts2,], samples_ts2))    \n",
    "        df_ts2 = pd.DataFrame(data_ts2,columns=['x','y','sample'])\n",
    "\n",
    "        source_ts2 = ColumnDataSource(data=dict(\n",
    "        x=df_ts2['x'],\n",
    "        y=df_ts2['y'],\n",
    "        desc=df_ts2['sample']))\n",
    "        p.diamond(x='x',y='y',size=size,source=source_ts2,color=col,alpha=0.8)\n",
    "        \n",
    "#     p.legend.location = \"bottom_left\"\n",
    "    p.legend.label_text_font_size = \"20pt\"\n",
    "    p.yaxis.major_label_text_font_size = \"15pt\"\n",
    "    p.xaxis.major_label_text_font_size = \"15pt\"\n",
    "    plots.append(p)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "grid = gridplot([[plots[0], plots[1], plots[2]], [plots[3], plots[4], plots[5]], [plots[6], plots[7], plots[8]]], plot_width=1200, plot_height=1200)\n",
    "\n",
    "if BEST:\n",
    "    export_png(grid, filename=\"subtypes_INF_suppl.png\")\n",
    "else:\n",
    "    export_png(grid, filename=\"subtypes_juXT_suppl.png\")\n",
    "    \n",
    "show(grid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.6.9 64-bit ('inf_env': conda)",
   "language": "python",
   "name": "python36964bitinfenvconda17aeaf48b6154bb383fac738bc345b49"
  },
  "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": 2
}