diff --git a/chierici_practical_part1.ipynb b/chierici_practical_part1.ipynb index 1a9668c..753d381 100644 --- a/chierici_practical_part1.ipynb +++ b/chierici_practical_part1.ipynb @@ -55,7 +55,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": { "colab": {}, "colab_type": "code", @@ -73,9 +73,298 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "
\n", + " \n", + " Loading BokehJS ...\n", + "
" + ] + }, + "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 !== undefined) {\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 element_id = msg.content.text.trim();\n", + " Bokeh.index[element_id].model.document.clear();\n", + " delete Bokeh.index[element_id];\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", + " \"
\\n\"+\n", + " \"

\\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", + " \"

\\n\"+\n", + " \"\\n\"+\n", + " \"\\n\"+\n", + " \"from bokeh.resources import INLINE\\n\"+\n", + " \"output_notebook(resources=INLINE)\\n\"+\n", + " \"\\n\"+\n", + " \"
\"}};\n", + "\n", + " function display_loaded() {\n", + " var el = document.getElementById(\"52087260-467f-4d6b-a799-4d1bf12bb4de\");\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) { callback() });\n", + " }\n", + " finally {\n", + " delete root._bokeh_onload_callbacks\n", + " }\n", + " console.info(\"Bokeh: all callbacks have finished\");\n", + " }\n", + "\n", + " function load_libs(js_urls, callback) {\n", + " root._bokeh_onload_callbacks.push(callback);\n", + " if (root._bokeh_is_loading > 0) {\n", + " console.log(\"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.log(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", + " root._bokeh_is_loading = js_urls.length;\n", + " for (var i = 0; i < js_urls.length; i++) {\n", + " var url = js_urls[i];\n", + " var s = document.createElement('script');\n", + " s.src = url;\n", + " s.async = false;\n", + " s.onreadystatechange = s.onload = function() {\n", + " root._bokeh_is_loading--;\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.log(\"Bokeh: all BokehJS libraries loaded\");\n", + " run_callbacks()\n", + " }\n", + " };\n", + " s.onerror = function() {\n", + " console.warn(\"failed to load library \" + url);\n", + " };\n", + " console.log(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", + " document.getElementsByTagName(\"head\")[0].appendChild(s);\n", + " }\n", + " };var element = document.getElementById(\"52087260-467f-4d6b-a799-4d1bf12bb4de\");\n", + " if (element == null) {\n", + " console.log(\"Bokeh: ERROR: autoload.js configured with elementid '52087260-467f-4d6b-a799-4d1bf12bb4de' but no matching script tag was found. \")\n", + " return false;\n", + " }\n", + "\n", + " var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-0.12.16.min.js\"];\n", + "\n", + " var inline_js = [\n", + " function(Bokeh) {\n", + " Bokeh.set_log_level(\"info\");\n", + " },\n", + " \n", + " function(Bokeh) {\n", + " \n", + " },\n", + " function(Bokeh) {\n", + " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n", + " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n", + " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n", + " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n", + " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n", + " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n", + " }\n", + " ];\n", + "\n", + " function run_inline_js() {\n", + " \n", + " if ((root.Bokeh !== undefined) || (force === true)) {\n", + " for (var i = 0; i < inline_js.length; i++) {\n", + " inline_js[i].call(root, root.Bokeh);\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(\"52087260-467f-4d6b-a799-4d1bf12bb4de\")).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.log(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", + " run_inline_js();\n", + " } else {\n", + " load_libs(js_urls, function() {\n", + " console.log(\"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 \"
\\n\"+\n \"

\\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 \"

\\n\"+\n \"\\n\"+\n \"\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"\\n\"+\n \"
\"}};\n\n function display_loaded() {\n var el = document.getElementById(\"52087260-467f-4d6b-a799-4d1bf12bb4de\");\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) { callback() });\n }\n finally {\n delete root._bokeh_onload_callbacks\n }\n console.info(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(js_urls, callback) {\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.log(\"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.log(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = js_urls.length;\n for (var i = 0; i < js_urls.length; i++) {\n var url = js_urls[i];\n var s = document.createElement('script');\n s.src = url;\n s.async = false;\n s.onreadystatechange = s.onload = function() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.log(\"Bokeh: all BokehJS libraries loaded\");\n run_callbacks()\n }\n };\n s.onerror = function() {\n console.warn(\"failed to load library \" + url);\n };\n console.log(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.getElementsByTagName(\"head\")[0].appendChild(s);\n }\n };var element = document.getElementById(\"52087260-467f-4d6b-a799-4d1bf12bb4de\");\n if (element == null) {\n console.log(\"Bokeh: ERROR: autoload.js configured with elementid '52087260-467f-4d6b-a799-4d1bf12bb4de' but no matching script tag was found. \")\n return false;\n }\n\n var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-0.12.16.min.js\"];\n\n var inline_js = [\n function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\n \n function(Bokeh) {\n \n },\n function(Bokeh) {\n console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n }\n ];\n\n function run_inline_js() {\n \n if ((root.Bokeh !== undefined) || (force === true)) {\n for (var i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\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(\"52087260-467f-4d6b-a799-4d1bf12bb4de\")).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.log(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(js_urls, function() {\n console.log(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));" + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "output_notebook()" ] @@ -92,7 +381,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": { "colab": {}, "colab_type": "code", @@ -106,7 +395,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": { "colab": {}, "colab_type": "code", @@ -132,7 +421,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": { "colab": {}, "colab_type": "code", @@ -161,7 +450,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -202,7 +491,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -223,7 +512,280 @@ "id": "CoWDeDBl2wHQ", "outputId": "5a41d67f-63d7-4365-c170-ee04ef5727c1" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Help on function read_csv in module pandas.io.parsers:\n", + "\n", + "read_csv(filepath_or_buffer, sep=',', delimiter=None, header='infer', names=None, index_col=None, usecols=None, squeeze=False, prefix=None, mangle_dupe_cols=True, dtype=None, engine=None, converters=None, true_values=None, false_values=None, skipinitialspace=False, skiprows=None, nrows=None, na_values=None, keep_default_na=True, na_filter=True, verbose=False, skip_blank_lines=True, parse_dates=False, infer_datetime_format=False, keep_date_col=False, date_parser=None, dayfirst=False, iterator=False, chunksize=None, compression='infer', thousands=None, decimal=b'.', lineterminator=None, quotechar='\"', quoting=0, escapechar=None, comment=None, encoding=None, dialect=None, tupleize_cols=None, error_bad_lines=True, warn_bad_lines=True, skipfooter=0, doublequote=True, delim_whitespace=False, low_memory=True, memory_map=False, float_precision=None)\n", + " Read CSV (comma-separated) file into DataFrame\n", + " \n", + " Also supports optionally iterating or breaking of the file\n", + " into chunks.\n", + " \n", + " Additional help can be found in the `online docs for IO Tools\n", + " `_.\n", + " \n", + " Parameters\n", + " ----------\n", + " filepath_or_buffer : str, pathlib.Path, py._path.local.LocalPath or any \\\n", + " object with a read() method (such as a file handle or StringIO)\n", + " The string could be a URL. Valid URL schemes include http, ftp, s3, and\n", + " file. For file URLs, a host is expected. For instance, a local file could\n", + " be file://localhost/path/to/table.csv\n", + " sep : str, default ','\n", + " Delimiter to use. If sep is None, the C engine cannot automatically detect\n", + " the separator, but the Python parsing engine can, meaning the latter will\n", + " be used and automatically detect the separator by Python's builtin sniffer\n", + " tool, ``csv.Sniffer``. In addition, separators longer than 1 character and\n", + " different from ``'\\s+'`` will be interpreted as regular expressions and\n", + " will also force the use of the Python parsing engine. Note that regex\n", + " delimiters are prone to ignoring quoted data. Regex example: ``'\\r\\t'``\n", + " delimiter : str, default ``None``\n", + " Alternative argument name for sep.\n", + " delim_whitespace : boolean, default False\n", + " Specifies whether or not whitespace (e.g. ``' '`` or ``'\\t'``) will be\n", + " used as the sep. Equivalent to setting ``sep='\\s+'``. If this option\n", + " is set to True, nothing should be passed in for the ``delimiter``\n", + " parameter.\n", + " \n", + " .. versionadded:: 0.18.1 support for the Python parser.\n", + " \n", + " header : int or list of ints, default 'infer'\n", + " Row number(s) to use as the column names, and the start of the\n", + " data. Default behavior is to infer the column names: if no names\n", + " are passed the behavior is identical to ``header=0`` and column\n", + " names are inferred from the first line of the file, if column\n", + " names are passed explicitly then the behavior is identical to\n", + " ``header=None``. Explicitly pass ``header=0`` to be able to\n", + " replace existing names. The header can be a list of integers that\n", + " specify row locations for a multi-index on the columns\n", + " e.g. [0,1,3]. Intervening rows that are not specified will be\n", + " skipped (e.g. 2 in this example is skipped). Note that this\n", + " parameter ignores commented lines and empty lines if\n", + " ``skip_blank_lines=True``, so header=0 denotes the first line of\n", + " data rather than the first line of the file.\n", + " names : array-like, default None\n", + " List of column names to use. If file contains no header row, then you\n", + " should explicitly pass header=None. Duplicates in this list will cause\n", + " a ``UserWarning`` to be issued.\n", + " index_col : int or sequence or False, default None\n", + " Column to use as the row labels of the DataFrame. If a sequence is given, a\n", + " MultiIndex is used. If you have a malformed file with delimiters at the end\n", + " of each line, you might consider index_col=False to force pandas to _not_\n", + " use the first column as the index (row names)\n", + " usecols : list-like or callable, default None\n", + " Return a subset of the columns. If list-like, all elements must either\n", + " be positional (i.e. integer indices into the document columns) or strings\n", + " that correspond to column names provided either by the user in `names` or\n", + " inferred from the document header row(s). For example, a valid list-like\n", + " `usecols` parameter would be [0, 1, 2] or ['foo', 'bar', 'baz']. Element\n", + " order is ignored, so ``usecols=[0, 1]`` is the same as ``[1, 0]``.\n", + " To instantiate a DataFrame from ``data`` with element order preserved use\n", + " ``pd.read_csv(data, usecols=['foo', 'bar'])[['foo', 'bar']]`` for columns\n", + " in ``['foo', 'bar']`` order or\n", + " ``pd.read_csv(data, usecols=['foo', 'bar'])[['bar', 'foo']]``\n", + " for ``['bar', 'foo']`` order.\n", + " \n", + " If callable, the callable function will be evaluated against the column\n", + " names, returning names where the callable function evaluates to True. An\n", + " example of a valid callable argument would be ``lambda x: x.upper() in\n", + " ['AAA', 'BBB', 'DDD']``. Using this parameter results in much faster\n", + " parsing time and lower memory usage.\n", + " squeeze : boolean, default False\n", + " If the parsed data only contains one column then return a Series\n", + " prefix : str, default None\n", + " Prefix to add to column numbers when no header, e.g. 'X' for X0, X1, ...\n", + " mangle_dupe_cols : boolean, default True\n", + " Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than\n", + " 'X'...'X'. Passing in False will cause data to be overwritten if there\n", + " are duplicate names in the columns.\n", + " dtype : Type name or dict of column -> type, default None\n", + " Data type for data or columns. E.g. {'a': np.float64, 'b': np.int32}\n", + " Use `str` or `object` together with suitable `na_values` settings\n", + " to preserve and not interpret dtype.\n", + " If converters are specified, they will be applied INSTEAD\n", + " of dtype conversion.\n", + " engine : {'c', 'python'}, optional\n", + " Parser engine to use. The C engine is faster while the python engine is\n", + " currently more feature-complete.\n", + " converters : dict, default None\n", + " Dict of functions for converting values in certain columns. Keys can either\n", + " be integers or column labels\n", + " true_values : list, default None\n", + " Values to consider as True\n", + " false_values : list, default None\n", + " Values to consider as False\n", + " skipinitialspace : boolean, default False\n", + " Skip spaces after delimiter.\n", + " skiprows : list-like or integer or callable, default None\n", + " Line numbers to skip (0-indexed) or number of lines to skip (int)\n", + " at the start of the file.\n", + " \n", + " If callable, the callable function will be evaluated against the row\n", + " indices, returning True if the row should be skipped and False otherwise.\n", + " An example of a valid callable argument would be ``lambda x: x in [0, 2]``.\n", + " skipfooter : int, default 0\n", + " Number of lines at bottom of file to skip (Unsupported with engine='c')\n", + " nrows : int, default None\n", + " Number of rows of file to read. Useful for reading pieces of large files\n", + " na_values : scalar, str, list-like, or dict, default None\n", + " Additional strings to recognize as NA/NaN. If dict passed, specific\n", + " per-column NA values. By default the following values are interpreted as\n", + " NaN: '', '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN', '-NaN', '-nan',\n", + " '1.#IND', '1.#QNAN', 'N/A', 'NA', 'NULL', 'NaN', 'n/a', 'nan',\n", + " 'null'.\n", + " keep_default_na : bool, default True\n", + " Whether or not to include the default NaN values when parsing the data.\n", + " Depending on whether `na_values` is passed in, the behavior is as follows:\n", + " \n", + " * If `keep_default_na` is True, and `na_values` are specified, `na_values`\n", + " is appended to the default NaN values used for parsing.\n", + " * If `keep_default_na` is True, and `na_values` are not specified, only\n", + " the default NaN values are used for parsing.\n", + " * If `keep_default_na` is False, and `na_values` are specified, only\n", + " the NaN values specified `na_values` are used for parsing.\n", + " * If `keep_default_na` is False, and `na_values` are not specified, no\n", + " strings will be parsed as NaN.\n", + " \n", + " Note that if `na_filter` is passed in as False, the `keep_default_na` and\n", + " `na_values` parameters will be ignored.\n", + " na_filter : boolean, default True\n", + " Detect missing value markers (empty strings and the value of na_values). In\n", + " data without any NAs, passing na_filter=False can improve the performance\n", + " of reading a large file\n", + " verbose : boolean, default False\n", + " Indicate number of NA values placed in non-numeric columns\n", + " skip_blank_lines : boolean, default True\n", + " If True, skip over blank lines rather than interpreting as NaN values\n", + " parse_dates : boolean or list of ints or names or list of lists or dict, default False\n", + " \n", + " * boolean. If True -> try parsing the index.\n", + " * list of ints or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3\n", + " each as a separate date column.\n", + " * list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as\n", + " a single date column.\n", + " * dict, e.g. {'foo' : [1, 3]} -> parse columns 1, 3 as date and call result\n", + " 'foo'\n", + " \n", + " If a column or index contains an unparseable date, the entire column or\n", + " index will be returned unaltered as an object data type. For non-standard\n", + " datetime parsing, use ``pd.to_datetime`` after ``pd.read_csv``\n", + " \n", + " Note: A fast-path exists for iso8601-formatted dates.\n", + " infer_datetime_format : boolean, default False\n", + " If True and `parse_dates` is enabled, pandas will attempt to infer the\n", + " format of the datetime strings in the columns, and if it can be inferred,\n", + " switch to a faster method of parsing them. In some cases this can increase\n", + " the parsing speed by 5-10x.\n", + " keep_date_col : boolean, default False\n", + " If True and `parse_dates` specifies combining multiple columns then\n", + " keep the original columns.\n", + " date_parser : function, default None\n", + " Function to use for converting a sequence of string columns to an array of\n", + " datetime instances. The default uses ``dateutil.parser.parser`` to do the\n", + " conversion. Pandas will try to call `date_parser` in three different ways,\n", + " advancing to the next if an exception occurs: 1) Pass one or more arrays\n", + " (as defined by `parse_dates`) as arguments; 2) concatenate (row-wise) the\n", + " string values from the columns defined by `parse_dates` into a single array\n", + " and pass that; and 3) call `date_parser` once for each row using one or\n", + " more strings (corresponding to the columns defined by `parse_dates`) as\n", + " arguments.\n", + " dayfirst : boolean, default False\n", + " DD/MM format dates, international and European format\n", + " iterator : boolean, default False\n", + " Return TextFileReader object for iteration or getting chunks with\n", + " ``get_chunk()``.\n", + " chunksize : int, default None\n", + " Return TextFileReader object for iteration.\n", + " See the `IO Tools docs\n", + " `_\n", + " for more information on ``iterator`` and ``chunksize``.\n", + " compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer'\n", + " For on-the-fly decompression of on-disk data. If 'infer' and\n", + " `filepath_or_buffer` is path-like, then detect compression from the\n", + " following extensions: '.gz', '.bz2', '.zip', or '.xz' (otherwise no\n", + " decompression). If using 'zip', the ZIP file must contain only one data\n", + " file to be read in. Set to None for no decompression.\n", + " \n", + " .. versionadded:: 0.18.1 support for 'zip' and 'xz' compression.\n", + " \n", + " thousands : str, default None\n", + " Thousands separator\n", + " decimal : str, default '.'\n", + " Character to recognize as decimal point (e.g. use ',' for European data).\n", + " float_precision : string, default None\n", + " Specifies which converter the C engine should use for floating-point\n", + " values. The options are `None` for the ordinary converter,\n", + " `high` for the high-precision converter, and `round_trip` for the\n", + " round-trip converter.\n", + " lineterminator : str (length 1), default None\n", + " Character to break file into lines. Only valid with C parser.\n", + " quotechar : str (length 1), optional\n", + " The character used to denote the start and end of a quoted item. Quoted\n", + " items can include the delimiter and it will be ignored.\n", + " quoting : int or csv.QUOTE_* instance, default 0\n", + " Control field quoting behavior per ``csv.QUOTE_*`` constants. Use one of\n", + " QUOTE_MINIMAL (0), QUOTE_ALL (1), QUOTE_NONNUMERIC (2) or QUOTE_NONE (3).\n", + " doublequote : boolean, default ``True``\n", + " When quotechar is specified and quoting is not ``QUOTE_NONE``, indicate\n", + " whether or not to interpret two consecutive quotechar elements INSIDE a\n", + " field as a single ``quotechar`` element.\n", + " escapechar : str (length 1), default None\n", + " One-character string used to escape delimiter when quoting is QUOTE_NONE.\n", + " comment : str, default None\n", + " Indicates remainder of line should not be parsed. If found at the beginning\n", + " of a line, the line will be ignored altogether. This parameter must be a\n", + " single character. Like empty lines (as long as ``skip_blank_lines=True``),\n", + " fully commented lines are ignored by the parameter `header` but not by\n", + " `skiprows`. For example, if ``comment='#'``, parsing\n", + " ``#empty\\na,b,c\\n1,2,3`` with ``header=0`` will result in 'a,b,c' being\n", + " treated as the header.\n", + " encoding : str, default None\n", + " Encoding to use for UTF when reading/writing (ex. 'utf-8'). `List of Python\n", + " standard encodings\n", + " `_\n", + " dialect : str or csv.Dialect instance, default None\n", + " If provided, this parameter will override values (default or not) for the\n", + " following parameters: `delimiter`, `doublequote`, `escapechar`,\n", + " `skipinitialspace`, `quotechar`, and `quoting`. If it is necessary to\n", + " override values, a ParserWarning will be issued. See csv.Dialect\n", + " documentation for more details.\n", + " tupleize_cols : boolean, default False\n", + " .. deprecated:: 0.21.0\n", + " This argument will be removed and will always convert to MultiIndex\n", + " \n", + " Leave a list of tuples on columns as is (default is to convert to\n", + " a MultiIndex on the columns)\n", + " error_bad_lines : boolean, default True\n", + " Lines with too many fields (e.g. a csv line with too many commas) will by\n", + " default cause an exception to be raised, and no DataFrame will be returned.\n", + " If False, then these \"bad lines\" will dropped from the DataFrame that is\n", + " returned.\n", + " warn_bad_lines : boolean, default True\n", + " If error_bad_lines is False, and warn_bad_lines is True, a warning for each\n", + " \"bad line\" will be output.\n", + " low_memory : boolean, default True\n", + " Internally process the file in chunks, resulting in lower memory use\n", + " while parsing, but possibly mixed type inference. To ensure no mixed\n", + " types either set False, or specify the type with the `dtype` parameter.\n", + " Note that the entire file is read into a single DataFrame regardless,\n", + " use the `chunksize` or `iterator` parameter to return the data in chunks.\n", + " (Only valid with C parser)\n", + " memory_map : boolean, default False\n", + " If a filepath is provided for `filepath_or_buffer`, map the file object\n", + " directly onto memory and access the data directly from there. Using this\n", + " option can improve performance because there is no longer any I/O overhead.\n", + " \n", + " Returns\n", + " -------\n", + " result : DataFrame or TextParser\n", + "\n" + ] + } + ], "source": [ "help(pd.read_csv)" ] @@ -240,14 +802,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": { "colab": {}, "colab_type": "code", "id": "2iltS1Q-k3Wn", "outputId": "ea81462d-8a49-406b-c933-182c49379053" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(136, 52230)" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "data_tr.shape" ] @@ -266,14 +839,242 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": { "colab": {}, "colab_type": "code", "id": "TVfPwU6-k3Wt", "outputId": "884dd460-6c53-4bf4-9c37-f7c7299b37a2" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sampleIDALB.Gene_AceViewCD24L4.1.Gene_AceViewRPS11.Gene_RefSeqRPS18.Gene_AceViewC5orf13.Gene_AceViewCCT2.Gene_AceViewCOL1A1.Gene_AceViewDDX1.Gene_AceViewEEF1A1.Gene_AceView...zawskaw.Gene_AceViewzeedor.Gene_AceViewzergor.Gene_AceViewzorsa.Gene_AceViewzoychabu.Gene_AceViewzoysteeby.Gene_AceViewzudee.Gene_AceViewzureyby.Gene_AceViewzuswoybu.Gene_AceViewzyjee.Gene_AceView
0SEQC_NB0019.2918.8221.1720.9020.0216.3118.6015.7321.71...0.00.000.00.000.00.00.000.00.00.0
1SEQC_NB0039.2520.2522.4422.0021.0517.0619.3922.8422.72...0.05.540.03.390.00.05.450.00.00.0
2SEQC_NB0058.9920.0922.0921.7121.6516.8523.0215.7922.24...0.00.000.03.750.00.00.000.00.00.0
3SEQC_NB0117.3219.8220.5220.9021.5816.4918.9115.4522.06...0.00.000.00.000.00.00.000.00.00.0
4SEQC_NB01310.5621.1920.6921.2920.2816.2217.1516.0121.84...0.00.000.05.200.00.00.000.00.00.0
\n", + "

5 rows × 52230 columns

\n", + "
" + ], + "text/plain": [ + " sampleID ALB.Gene_AceView CD24L4.1.Gene_AceView RPS11.Gene_RefSeq \\\n", + "0 SEQC_NB001 9.29 18.82 21.17 \n", + "1 SEQC_NB003 9.25 20.25 22.44 \n", + "2 SEQC_NB005 8.99 20.09 22.09 \n", + "3 SEQC_NB011 7.32 19.82 20.52 \n", + "4 SEQC_NB013 10.56 21.19 20.69 \n", + "\n", + " RPS18.Gene_AceView C5orf13.Gene_AceView CCT2.Gene_AceView \\\n", + "0 20.90 20.02 16.31 \n", + "1 22.00 21.05 17.06 \n", + "2 21.71 21.65 16.85 \n", + "3 20.90 21.58 16.49 \n", + "4 21.29 20.28 16.22 \n", + "\n", + " COL1A1.Gene_AceView DDX1.Gene_AceView EEF1A1.Gene_AceView \\\n", + "0 18.60 15.73 21.71 \n", + "1 19.39 22.84 22.72 \n", + "2 23.02 15.79 22.24 \n", + "3 18.91 15.45 22.06 \n", + "4 17.15 16.01 21.84 \n", + "\n", + " ... zawskaw.Gene_AceView zeedor.Gene_AceView \\\n", + "0 ... 0.0 0.00 \n", + "1 ... 0.0 5.54 \n", + "2 ... 0.0 0.00 \n", + "3 ... 0.0 0.00 \n", + "4 ... 0.0 0.00 \n", + "\n", + " zergor.Gene_AceView zorsa.Gene_AceView zoychabu.Gene_AceView \\\n", + "0 0.0 0.00 0.0 \n", + "1 0.0 3.39 0.0 \n", + "2 0.0 3.75 0.0 \n", + "3 0.0 0.00 0.0 \n", + "4 0.0 5.20 0.0 \n", + "\n", + " zoysteeby.Gene_AceView zudee.Gene_AceView zureyby.Gene_AceView \\\n", + "0 0.0 0.00 0.0 \n", + "1 0.0 5.45 0.0 \n", + "2 0.0 0.00 0.0 \n", + "3 0.0 0.00 0.0 \n", + "4 0.0 0.00 0.0 \n", + "\n", + " zuswoybu.Gene_AceView zyjee.Gene_AceView \n", + "0 0.0 0.0 \n", + "1 0.0 0.0 \n", + "2 0.0 0.0 \n", + "3 0.0 0.0 \n", + "4 0.0 0.0 \n", + "\n", + "[5 rows x 52230 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "data_tr.head()" ] @@ -290,7 +1091,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": { "colab": {}, "colab_type": "code", @@ -314,14 +1115,242 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": { "colab": {}, "colab_type": "code", "id": "QgcQgBVek3W1", "outputId": "6cbec2e0-0001-4e03-c040-0bbddd51db5b" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ALB.Gene_AceViewCD24L4.1.Gene_AceViewRPS11.Gene_RefSeqRPS18.Gene_AceViewC5orf13.Gene_AceViewCCT2.Gene_AceViewCOL1A1.Gene_AceViewDDX1.Gene_AceViewEEF1A1.Gene_AceViewFLT3LG_.Gene_AceView...zawskaw.Gene_AceViewzeedor.Gene_AceViewzergor.Gene_AceViewzorsa.Gene_AceViewzoychabu.Gene_AceViewzoysteeby.Gene_AceViewzudee.Gene_AceViewzureyby.Gene_AceViewzuswoybu.Gene_AceViewzyjee.Gene_AceView
09.2918.8221.1720.9020.0216.3118.6015.7321.7120.02...0.00.000.00.000.00.00.000.00.00.0
19.2520.2522.4422.0021.0517.0619.3922.8422.7221.26...0.05.540.03.390.00.05.450.00.00.0
28.9920.0922.0921.7121.6516.8523.0215.7922.2420.75...0.00.000.03.750.00.00.000.00.00.0
37.3219.8220.5220.9021.5816.4918.9115.4522.0619.59...0.00.000.00.000.00.00.000.00.00.0
410.5621.1920.6921.2920.2816.2217.1516.0121.8419.74...0.00.000.05.200.00.00.000.00.00.0
\n", + "

5 rows × 52229 columns

\n", + "
" + ], + "text/plain": [ + " ALB.Gene_AceView CD24L4.1.Gene_AceView RPS11.Gene_RefSeq \\\n", + "0 9.29 18.82 21.17 \n", + "1 9.25 20.25 22.44 \n", + "2 8.99 20.09 22.09 \n", + "3 7.32 19.82 20.52 \n", + "4 10.56 21.19 20.69 \n", + "\n", + " RPS18.Gene_AceView C5orf13.Gene_AceView CCT2.Gene_AceView \\\n", + "0 20.90 20.02 16.31 \n", + "1 22.00 21.05 17.06 \n", + "2 21.71 21.65 16.85 \n", + "3 20.90 21.58 16.49 \n", + "4 21.29 20.28 16.22 \n", + "\n", + " COL1A1.Gene_AceView DDX1.Gene_AceView EEF1A1.Gene_AceView \\\n", + "0 18.60 15.73 21.71 \n", + "1 19.39 22.84 22.72 \n", + "2 23.02 15.79 22.24 \n", + "3 18.91 15.45 22.06 \n", + "4 17.15 16.01 21.84 \n", + "\n", + " FLT3LG_.Gene_AceView ... zawskaw.Gene_AceView \\\n", + "0 20.02 ... 0.0 \n", + "1 21.26 ... 0.0 \n", + "2 20.75 ... 0.0 \n", + "3 19.59 ... 0.0 \n", + "4 19.74 ... 0.0 \n", + "\n", + " zeedor.Gene_AceView zergor.Gene_AceView zorsa.Gene_AceView \\\n", + "0 0.00 0.0 0.00 \n", + "1 5.54 0.0 3.39 \n", + "2 0.00 0.0 3.75 \n", + "3 0.00 0.0 0.00 \n", + "4 0.00 0.0 5.20 \n", + "\n", + " zoychabu.Gene_AceView zoysteeby.Gene_AceView zudee.Gene_AceView \\\n", + "0 0.0 0.0 0.00 \n", + "1 0.0 0.0 5.45 \n", + "2 0.0 0.0 0.00 \n", + "3 0.0 0.0 0.00 \n", + "4 0.0 0.0 0.00 \n", + "\n", + " zureyby.Gene_AceView zuswoybu.Gene_AceView zyjee.Gene_AceView \n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 0.0 0.0 0.0 \n", + "3 0.0 0.0 0.0 \n", + "4 0.0 0.0 0.0 \n", + "\n", + "[5 rows x 52229 columns]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "data_tr.head()" ] @@ -338,14 +1367,95 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": { "colab": {}, "colab_type": "code", "id": "7Vbq9mqXk3W5", "outputId": "6bc4f986-30e2-4953-fc78-80b80982ba47" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
sampleIDCLASSSEXRND
0SEQC_NB001011
1SEQC_NB003000
2SEQC_NB005001
3SEQC_NB011111
4SEQC_NB013011
\n", + "
" + ], + "text/plain": [ + " sampleID CLASS SEX RND\n", + "0 SEQC_NB001 0 1 1\n", + "1 SEQC_NB003 0 0 0\n", + "2 SEQC_NB005 0 0 1\n", + "3 SEQC_NB011 1 1 1\n", + "4 SEQC_NB013 0 1 1" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "labs_tr = pd.read_csv(LABS_TR, sep = \"\\t\")\n", "labs_ts = pd.read_csv(LABS_TS, sep = \"\\t\")\n", @@ -364,14 +1474,77 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": { "colab": {}, "colab_type": "code", "id": "pyTfzujJk3W9", "outputId": "cd7cf62a-c5b1-491a-853e-631b5cc9a4d2" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CLASS
00
10
20
31
40
\n", + "
" + ], + "text/plain": [ + " CLASS\n", + "0 0\n", + "1 0\n", + "2 0\n", + "3 1\n", + "4 0" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "class_lab_tr = labs_tr[['CLASS']]\n", "class_lab_ts = labs_ts[['CLASS']]\n", @@ -391,7 +1564,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": { "colab": {}, "colab_type": "code", @@ -438,13 +1611,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": { "colab": {}, "colab_type": "code", "id": "XYs3b6JJ3qrn" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 9.29, 18.82, 21.17, ..., 0. , 0. , 0. ],\n", + " [ 9.25, 20.25, 22.44, ..., 0. , 0. , 0. ],\n", + " [ 8.99, 20.09, 22.09, ..., 0. , 0. , 0. ],\n", + " ...,\n", + " [ 8.47, 20.75, 20.08, ..., 0. , 0. , 0. ],\n", + " [ 8.58, 20.57, 20.67, ..., 0. , 0. , 0. ],\n", + " [ 8.62, 20.13, 21.04, ..., 0. , 0. , 0. ]])" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "x_tr" ] @@ -461,13 +1651,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": { "colab": {}, "colab_type": "code", "id": "iwI8uSvC4BbC" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", + " 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1,\n", + " 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1,\n", + " 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0,\n", + " 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1,\n", + " 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0,\n", + " 1, 1, 1, 1])" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "y_tr" ] @@ -512,7 +1719,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, "outputs": [], "source": [ @@ -566,7 +1773,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "metadata": { "colab": {}, "colab_type": "code", @@ -592,7 +1799,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": { "colab": {}, "colab_type": "code", @@ -605,7 +1812,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, "outputs": [], "source": [ @@ -615,9 +1822,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(136, 2)" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "z_tr.shape" ] @@ -634,13 +1852,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": { "colab": {}, "colab_type": "code", "id": "Cma7FaOd6F1M" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[0.08194369 0.0433671 ]\n" + ] + } + ], "source": [ "print(pca.explained_variance_ratio_)" ] @@ -669,9 +1895,60 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "
\n", + "
\n", + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/javascript": [ + "(function(root) {\n", + " function embed_document(root) {\n", + " \n", + " var docs_json = {\"f581f7f5-ad4a-4b4d-9c36-5011c136da3e\":{\"roots\":{\"references\":[{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"578311d8-8ca8-43a6-806a-dd2afe910f4c\",\"type\":\"Circle\"},{\"attributes\":{},\"id\":\"0ac9d99f-4445-4568-ac9e-69f19a680599\",\"type\":\"Selection\"},{\"attributes\":{\"active_drag\":\"auto\",\"active_inspect\":\"auto\",\"active_scroll\":\"auto\",\"active_tap\":\"auto\",\"tools\":[{\"id\":\"7ab9fdfb-298b-4b61-a00a-fecfda8ae28d\",\"type\":\"PanTool\"},{\"id\":\"30243c20-8f2c-4f7f-a05e-e3956e59775e\",\"type\":\"WheelZoomTool\"},{\"id\":\"1beec0d7-5cc8-481c-9e26-923bd16df227\",\"type\":\"BoxZoomTool\"},{\"id\":\"5ebd41b2-5f1c-4b19-ad41-495539ca8c9b\",\"type\":\"SaveTool\"},{\"id\":\"350ce84d-0611-4f8a-9f43-8258d5482ea6\",\"type\":\"ResetTool\"},{\"id\":\"7d66043f-2f80-4c49-b7c1-1e7b29a0af66\",\"type\":\"HelpTool\"}]},\"id\":\"5e61b569-21fd-4636-b89b-c58313b596d7\",\"type\":\"Toolbar\"},{\"attributes\":{},\"id\":\"207017d5-7c07-4632-9ca7-0467df0c7e70\",\"type\":\"UnionRenderers\"},{\"attributes\":{\"fill_color\":{\"value\":\"orange\"},\"line_color\":{\"value\":\"orange\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"55788bac-0509-4db3-851e-2ad5507b44bc\",\"type\":\"Circle\"},{\"attributes\":{},\"id\":\"20a06083-a08f-402e-a166-53e00ae3d1c6\",\"type\":\"Selection\"},{\"attributes\":{},\"id\":\"9104b613-185a-4605-897a-65b840848b66\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"below\":[{\"id\":\"66a59647-cfb3-48f5-853c-e378edb23566\",\"type\":\"LinearAxis\"}],\"left\":[{\"id\":\"636f73f8-4a94-4984-a157-007a9c1f92e9\",\"type\":\"LinearAxis\"}],\"plot_height\":400,\"plot_width\":400,\"renderers\":[{\"id\":\"66a59647-cfb3-48f5-853c-e378edb23566\",\"type\":\"LinearAxis\"},{\"id\":\"6414f74a-4633-4213-ba59-4d8b09cf032c\",\"type\":\"Grid\"},{\"id\":\"636f73f8-4a94-4984-a157-007a9c1f92e9\",\"type\":\"LinearAxis\"},{\"id\":\"4aaa0bc4-228d-4266-b8dc-4213fe5042f6\",\"type\":\"Grid\"},{\"id\":\"4a9f91d0-bd1e-4b38-bffa-5b3399973856\",\"type\":\"BoxAnnotation\"},{\"id\":\"4703dd56-5d0b-49f2-963e-c2562d3796aa\",\"type\":\"GlyphRenderer\"},{\"id\":\"790faec9-4ab0-4793-9e2e-62921cf31ce8\",\"type\":\"GlyphRenderer\"}],\"title\":{\"id\":\"28b7adc3-9383-4511-afaa-69e6be05de92\",\"type\":\"Title\"},\"toolbar\":{\"id\":\"5e61b569-21fd-4636-b89b-c58313b596d7\",\"type\":\"Toolbar\"},\"x_range\":{\"id\":\"9fcb5a73-6302-457a-8b58-231b497ac950\",\"type\":\"DataRange1d\"},\"x_scale\":{\"id\":\"f599e90b-7a15-4166-865e-6dd7eee1ea31\",\"type\":\"LinearScale\"},\"y_range\":{\"id\":\"1f914f1e-26b6-4362-baa6-f4ed9bae91ae\",\"type\":\"DataRange1d\"},\"y_scale\":{\"id\":\"d9ed750a-2348-490a-9871-5c18a14160f8\",\"type\":\"LinearScale\"}},\"id\":\"162587d8-457e-4ad3-8646-f6b67d9afcaa\",\"subtype\":\"Figure\",\"type\":\"Plot\"},{\"attributes\":{\"callback\":null,\"data\":{\"x\":{\"__ndarray__\":\"s4dscZTUFsCsUR4MMntMQEacKLQ+z0dAZjHJmj/mKMDavt88hvAvQPepnplzfeQ/iRqKdbXJRUDD41gKeYQzQOEzq9HxPkdAof95CJrpUUCXVoj1RC9SQFRDbl6DGfW//wiVFHpZJEDanZ+ntBVJQPXwzwnJIlNAD4fQrjFbQkApN+KVnwFMQJZQEet7gUJAB8OIkj+NPkA6POlDoostwF2LPGBkvxtAb0MN5dbzFEBG8wS/hXFOQNvWE0osDk1AAx0Rr8ddOEBhAMw5xFA0QMbOy//t9VFAuP2PyC4xN0C918OCG0c4QNvLJkWY3EFAWeQZTmXUSUB6OcmTg1E5QP7aMVQ/kSHA3uDhUYTsDkBfqygeHqg1QBm4Scy720JAYGv9cKPgREC3MSH71K8tQLpNrTITFlRAHXxspr3+SEDjaqfxTofxv1Zkp2gpcSNAyZ7O8pNKUEDDp6vqvAxQQO/AHnRFIlNA\",\"dtype\":\"float64\",\"shape\":[45]},\"y\":{\"__ndarray__\":\"5PVobXIYNEAbI7kdXVw2wEpKDc6nBgHAtMNFMWd/NMAQK6V1J5EJwB7i+V5UxxZA8RXRZPOeIcBhsnMT6sE3wJFnXaFJpxhAhHAj30TDz7/KqmMKc+w9wH/oBR/sckJAJuQKfyZNL0B5ResFsvEoQF959I4Mn0PAoDzn6xhBNkB4LAS7Jfk1wDIPw4n7pChAzQEh+La0F8DzZ9i1DoIowBGmZti8ByRA6Nnjzr/EQsAKobWnnulFQG7mTrGWVzTA9GZR60VCFkCj1E4NSO1BQORR0RpiqwrArZcb6qPaTUBb9JxAoDQ8QETAWzE+bjNAbjnJ9riZNUDio8BMqBFGQJr/aX26KUNALA4ZgbopSUBeJV1jAgM1QH555P1vjyxAc92EhwMyRUBzj8fL9JlDQF+DmsrFiBVA58tVN1cLQMAVcmzzh0k/QDILsl0qHyhAZg3FVBo0OcDfvGZhQ6Y2wHad6WtZ/hjA\",\"dtype\":\"float64\",\"shape\":[45]}},\"selected\":{\"id\":\"0ac9d99f-4445-4568-ac9e-69f19a680599\",\"type\":\"Selection\"},\"selection_policy\":{\"id\":\"7766407d-4b55-46d4-bb9a-74298e71f74a\",\"type\":\"UnionRenderers\"}},\"id\":\"6f41ebaf-8e24-4b1f-9943-8e92b50e40a2\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"plot\":null,\"text\":\"PCA of Train data\"},\"id\":\"28b7adc3-9383-4511-afaa-69e6be05de92\",\"type\":\"Title\"},{\"attributes\":{\"callback\":null},\"id\":\"1f914f1e-26b6-4362-baa6-f4ed9bae91ae\",\"type\":\"DataRange1d\"},{\"attributes\":{},\"id\":\"d9ed750a-2348-490a-9871-5c18a14160f8\",\"type\":\"LinearScale\"},{\"attributes\":{},\"id\":\"f599e90b-7a15-4166-865e-6dd7eee1ea31\",\"type\":\"LinearScale\"},{\"attributes\":{\"source\":{\"id\":\"6f41ebaf-8e24-4b1f-9943-8e92b50e40a2\",\"type\":\"ColumnDataSource\"}},\"id\":\"677bd7ee-c5eb-42a9-a2d6-be65c7da20d5\",\"type\":\"CDSView\"},{\"attributes\":{\"axis_label\":\"PC1\",\"formatter\":{\"id\":\"00c06ead-0e6d-4bb5-a14e-4e78d94233df\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"162587d8-457e-4ad3-8646-f6b67d9afcaa\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"f88296ac-67a5-4059-b98c-b4e252b6fa1d\",\"type\":\"BasicTicker\"}},\"id\":\"66a59647-cfb3-48f5-853c-e378edb23566\",\"type\":\"LinearAxis\"},{\"attributes\":{},\"id\":\"f88296ac-67a5-4059-b98c-b4e252b6fa1d\",\"type\":\"BasicTicker\"},{\"attributes\":{\"callback\":null},\"id\":\"9fcb5a73-6302-457a-8b58-231b497ac950\",\"type\":\"DataRange1d\"},{\"attributes\":{\"plot\":{\"id\":\"162587d8-457e-4ad3-8646-f6b67d9afcaa\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"f88296ac-67a5-4059-b98c-b4e252b6fa1d\",\"type\":\"BasicTicker\"}},\"id\":\"6414f74a-4633-4213-ba59-4d8b09cf032c\",\"type\":\"Grid\"},{\"attributes\":{\"axis_label\":\"PC2\",\"formatter\":{\"id\":\"9104b613-185a-4605-897a-65b840848b66\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"162587d8-457e-4ad3-8646-f6b67d9afcaa\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"6da6b1cc-0947-4d17-b3ea-e1d619d0cc1d\",\"type\":\"BasicTicker\"}},\"id\":\"636f73f8-4a94-4984-a157-007a9c1f92e9\",\"type\":\"LinearAxis\"},{\"attributes\":{},\"id\":\"6da6b1cc-0947-4d17-b3ea-e1d619d0cc1d\",\"type\":\"BasicTicker\"},{\"attributes\":{\"dimension\":1,\"plot\":{\"id\":\"162587d8-457e-4ad3-8646-f6b67d9afcaa\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"6da6b1cc-0947-4d17-b3ea-e1d619d0cc1d\",\"type\":\"BasicTicker\"}},\"id\":\"4aaa0bc4-228d-4266-b8dc-4213fe5042f6\",\"type\":\"Grid\"},{\"attributes\":{\"bottom_units\":\"screen\",\"fill_alpha\":{\"value\":0.5},\"fill_color\":{\"value\":\"lightgrey\"},\"left_units\":\"screen\",\"level\":\"overlay\",\"line_alpha\":{\"value\":1.0},\"line_color\":{\"value\":\"black\"},\"line_dash\":[4,4],\"line_width\":{\"value\":2},\"plot\":null,\"render_mode\":\"css\",\"right_units\":\"screen\",\"top_units\":\"screen\"},\"id\":\"4a9f91d0-bd1e-4b38-bffa-5b3399973856\",\"type\":\"BoxAnnotation\"},{\"attributes\":{\"fill_color\":{\"value\":\"blue\"},\"line_color\":{\"value\":\"blue\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"bc1afe64-4989-434a-9ccf-3b70f18a4f8f\",\"type\":\"Circle\"},{\"attributes\":{\"callback\":null,\"data\":{\"x\":{\"__ndarray__\":\"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\",\"dtype\":\"float64\",\"shape\":[91]},\"y\":{\"__ndarray__\":\"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\",\"dtype\":\"float64\",\"shape\":[91]}},\"selected\":{\"id\":\"20a06083-a08f-402e-a166-53e00ae3d1c6\",\"type\":\"Selection\"},\"selection_policy\":{\"id\":\"207017d5-7c07-4632-9ca7-0467df0c7e70\",\"type\":\"UnionRenderers\"}},\"id\":\"2fad3807-14d5-4105-8d10-df5d2260103e\",\"type\":\"ColumnDataSource\"},{\"attributes\":{},\"id\":\"7ab9fdfb-298b-4b61-a00a-fecfda8ae28d\",\"type\":\"PanTool\"},{\"attributes\":{\"data_source\":{\"id\":\"6f41ebaf-8e24-4b1f-9943-8e92b50e40a2\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"55788bac-0509-4db3-851e-2ad5507b44bc\",\"type\":\"Circle\"},\"hover_glyph\":null,\"muted_glyph\":null,\"nonselection_glyph\":{\"id\":\"578311d8-8ca8-43a6-806a-dd2afe910f4c\",\"type\":\"Circle\"},\"selection_glyph\":null,\"view\":{\"id\":\"677bd7ee-c5eb-42a9-a2d6-be65c7da20d5\",\"type\":\"CDSView\"}},\"id\":\"4703dd56-5d0b-49f2-963e-c2562d3796aa\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"055b002b-75de-4d85-bdaf-f896de75b7a5\",\"type\":\"Circle\"},{\"attributes\":{},\"id\":\"30243c20-8f2c-4f7f-a05e-e3956e59775e\",\"type\":\"WheelZoomTool\"},{\"attributes\":{\"overlay\":{\"id\":\"4a9f91d0-bd1e-4b38-bffa-5b3399973856\",\"type\":\"BoxAnnotation\"}},\"id\":\"1beec0d7-5cc8-481c-9e26-923bd16df227\",\"type\":\"BoxZoomTool\"},{\"attributes\":{},\"id\":\"5ebd41b2-5f1c-4b19-ad41-495539ca8c9b\",\"type\":\"SaveTool\"},{\"attributes\":{},\"id\":\"350ce84d-0611-4f8a-9f43-8258d5482ea6\",\"type\":\"ResetTool\"},{\"attributes\":{},\"id\":\"7d66043f-2f80-4c49-b7c1-1e7b29a0af66\",\"type\":\"HelpTool\"},{\"attributes\":{},\"id\":\"00c06ead-0e6d-4bb5-a14e-4e78d94233df\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"data_source\":{\"id\":\"2fad3807-14d5-4105-8d10-df5d2260103e\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"bc1afe64-4989-434a-9ccf-3b70f18a4f8f\",\"type\":\"Circle\"},\"hover_glyph\":null,\"muted_glyph\":null,\"nonselection_glyph\":{\"id\":\"055b002b-75de-4d85-bdaf-f896de75b7a5\",\"type\":\"Circle\"},\"selection_glyph\":null,\"view\":{\"id\":\"a2ddf5c0-8f4e-4312-96e6-f199ecabe5a8\",\"type\":\"CDSView\"}},\"id\":\"790faec9-4ab0-4793-9e2e-62921cf31ce8\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"source\":{\"id\":\"2fad3807-14d5-4105-8d10-df5d2260103e\",\"type\":\"ColumnDataSource\"}},\"id\":\"a2ddf5c0-8f4e-4312-96e6-f199ecabe5a8\",\"type\":\"CDSView\"},{\"attributes\":{},\"id\":\"7766407d-4b55-46d4-bb9a-74298e71f74a\",\"type\":\"UnionRenderers\"}],\"root_ids\":[\"162587d8-457e-4ad3-8646-f6b67d9afcaa\"]},\"title\":\"Bokeh Application\",\"version\":\"0.12.16\"}};\n", + " var render_items = [{\"docid\":\"f581f7f5-ad4a-4b4d-9c36-5011c136da3e\",\"elementid\":\"fd92f5ec-a952-4c56-9f57-280a5da5f624\",\"modelid\":\"162587d8-457e-4ad3-8646-f6b67d9afcaa\"}];\n", + " root.Bokeh.embed.embed_items_notebook(docs_json, render_items);\n", + "\n", + " }\n", + " if (root.Bokeh !== undefined) {\n", + " embed_document(root);\n", + " } else {\n", + " var attempts = 0;\n", + " var timer = setInterval(function(root) {\n", + " if (root.Bokeh !== undefined) {\n", + " embed_document(root);\n", + " clearInterval(timer);\n", + " }\n", + " attempts++;\n", + " if (attempts > 100) {\n", + " console.log(\"Bokeh: ERROR: Unable to run BokehJS code because BokehJS library is missing\")\n", + " clearInterval(timer);\n", + " }\n", + " }, 10, root)\n", + " }\n", + "})(window);" + ], + "application/vnd.bokehjs_exec.v0+json": "" + }, + "metadata": { + "application/vnd.bokehjs_exec.v0+json": { + "id": "162587d8-457e-4ad3-8646-f6b67d9afcaa" + } + }, + "output_type": "display_data" + } + ], "source": [ "p = figure(plot_width=400, plot_height=400, title=\"PCA of Train data\")\n", "p.circle(z_tr[y_tr==0, 0], z_tr[y_tr==0, 1], line_color=\"orange\", fill_color=\"orange\")\n", @@ -693,9 +1970,60 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "
\n", + "
\n", + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/javascript": [ + "(function(root) {\n", + " function embed_document(root) {\n", + " \n", + " var docs_json = {\"8569d5e9-157c-4830-b35b-978236e6dc15\":{\"roots\":{\"references\":[{\"attributes\":{\"plot\":null,\"text\":\"PCA of Train data\"},\"id\":\"6cdf3505-a1b2-4907-ac0b-5aff466f3395\",\"type\":\"Title\"},{\"attributes\":{},\"id\":\"6a0308b0-15ee-4b19-85fd-d89463b3e43c\",\"type\":\"Selection\"},{\"attributes\":{},\"id\":\"d9d33ed3-0481-437f-ba80-47ea8a19d71e\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"callback\":null},\"id\":\"e48717ee-bf3b-4969-8118-daa1b2c244ea\",\"type\":\"DataRange1d\"},{\"attributes\":{},\"id\":\"c0456d6f-b7f4-495b-98c7-9a353993e75f\",\"type\":\"ResetTool\"},{\"attributes\":{},\"id\":\"83504468-f82a-4bf7-ae7b-5534254eb89f\",\"type\":\"UnionRenderers\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"ca1a5fd6-322b-4699-9f7f-c77e4d41f869\",\"type\":\"Circle\"},{\"attributes\":{\"callback\":null,\"data\":{\"x\":{\"__ndarray__\":\"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\",\"dtype\":\"float64\",\"shape\":[91]},\"y\":{\"__ndarray__\":\"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\",\"dtype\":\"float64\",\"shape\":[91]}},\"selected\":{\"id\":\"609655c7-ca0a-423a-a954-f4399ff7e1b1\",\"type\":\"Selection\"},\"selection_policy\":{\"id\":\"83504468-f82a-4bf7-ae7b-5534254eb89f\",\"type\":\"UnionRenderers\"}},\"id\":\"2c6b05b4-3dea-437e-85b6-d6fd26465ccd\",\"type\":\"ColumnDataSource\"},{\"attributes\":{},\"id\":\"609655c7-ca0a-423a-a954-f4399ff7e1b1\",\"type\":\"Selection\"},{\"attributes\":{\"data_source\":{\"id\":\"5f5a8c6c-8687-4192-aa48-f8aa6e6ebcdb\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"c48cf889-1333-4f02-b9b9-47dcabe0bb11\",\"type\":\"Circle\"},\"hover_glyph\":null,\"muted_glyph\":null,\"nonselection_glyph\":{\"id\":\"b8b8b120-30d7-4df9-919b-208d14e0d65b\",\"type\":\"Circle\"},\"selection_glyph\":null,\"view\":{\"id\":\"495c8052-152a-4c48-8c3d-e63a2614b1ca\",\"type\":\"CDSView\"}},\"id\":\"bd77004f-0489-4dec-8f84-df0960786485\",\"type\":\"GlyphRenderer\"},{\"attributes\":{},\"id\":\"8c4d7994-41c3-4c45-a459-a1ba0ffab41a\",\"type\":\"SaveTool\"},{\"attributes\":{},\"id\":\"fa323ccb-57fd-41f8-8522-884d3656e065\",\"type\":\"UnionRenderers\"},{\"attributes\":{\"fill_color\":{\"value\":\"blue\"},\"line_color\":{\"value\":\"blue\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"38e529b8-e78d-4d85-bc5a-176b1ed6e178\",\"type\":\"Circle\"},{\"attributes\":{\"axis_label\":\"PC2 (4.34%)\",\"formatter\":{\"id\":\"4abadc12-fd9e-4b6a-89e7-431cf3a75ddf\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"390e51ff-5e3c-4937-b317-74c5a60029ce\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"7fdb54ab-10a6-4b09-b51e-3b050fc3bb97\",\"type\":\"BasicTicker\"}},\"id\":\"c99f729d-8d33-4caf-8de5-d53abcd686b9\",\"type\":\"LinearAxis\"},{\"attributes\":{\"plot\":{\"id\":\"390e51ff-5e3c-4937-b317-74c5a60029ce\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"039a5711-406b-4a5a-a42f-c8de30ced1c4\",\"type\":\"BasicTicker\"}},\"id\":\"8c2df2b2-e145-4505-987a-82c74afe4988\",\"type\":\"Grid\"},{\"attributes\":{},\"id\":\"1d874b4c-adce-4779-97b8-3ea94b8bb012\",\"type\":\"LinearScale\"},{\"attributes\":{},\"id\":\"ad0b799f-0136-47e4-8b25-ad01995ce2af\",\"type\":\"PanTool\"},{\"attributes\":{},\"id\":\"4abadc12-fd9e-4b6a-89e7-431cf3a75ddf\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{},\"id\":\"0582132a-56c4-4ab9-b4cf-259ed9fb9b1c\",\"type\":\"WheelZoomTool\"},{\"attributes\":{},\"id\":\"7fdb54ab-10a6-4b09-b51e-3b050fc3bb97\",\"type\":\"BasicTicker\"},{\"attributes\":{\"active_drag\":\"auto\",\"active_inspect\":\"auto\",\"active_scroll\":\"auto\",\"active_tap\":\"auto\",\"tools\":[{\"id\":\"ad0b799f-0136-47e4-8b25-ad01995ce2af\",\"type\":\"PanTool\"},{\"id\":\"0582132a-56c4-4ab9-b4cf-259ed9fb9b1c\",\"type\":\"WheelZoomTool\"},{\"id\":\"2a316f43-749b-438b-bdac-d17e0e6e238a\",\"type\":\"BoxZoomTool\"},{\"id\":\"8c4d7994-41c3-4c45-a459-a1ba0ffab41a\",\"type\":\"SaveTool\"},{\"id\":\"c0456d6f-b7f4-495b-98c7-9a353993e75f\",\"type\":\"ResetTool\"},{\"id\":\"1e63ae9d-2b09-409b-bc14-bff773d7b7dc\",\"type\":\"HelpTool\"}]},\"id\":\"9a9bcbb2-3163-4ff0-8839-6b822fe59f97\",\"type\":\"Toolbar\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"b8b8b120-30d7-4df9-919b-208d14e0d65b\",\"type\":\"Circle\"},{\"attributes\":{},\"id\":\"2da31b5d-fb5f-498f-835e-4f2c71c9b3a4\",\"type\":\"LinearScale\"},{\"attributes\":{\"below\":[{\"id\":\"819d78a8-e36f-497f-a1f1-9eaea3c71e05\",\"type\":\"LinearAxis\"}],\"left\":[{\"id\":\"c99f729d-8d33-4caf-8de5-d53abcd686b9\",\"type\":\"LinearAxis\"}],\"plot_height\":400,\"plot_width\":400,\"renderers\":[{\"id\":\"819d78a8-e36f-497f-a1f1-9eaea3c71e05\",\"type\":\"LinearAxis\"},{\"id\":\"8c2df2b2-e145-4505-987a-82c74afe4988\",\"type\":\"Grid\"},{\"id\":\"c99f729d-8d33-4caf-8de5-d53abcd686b9\",\"type\":\"LinearAxis\"},{\"id\":\"6a6dff96-2af8-4b2a-ac25-7dcdbf91f7d2\",\"type\":\"Grid\"},{\"id\":\"0da4ffd8-03dd-4d25-896c-a2cb21a991dc\",\"type\":\"BoxAnnotation\"},{\"id\":\"bd77004f-0489-4dec-8f84-df0960786485\",\"type\":\"GlyphRenderer\"},{\"id\":\"438675e5-f102-4891-8bcf-c2a9d3c48b11\",\"type\":\"GlyphRenderer\"}],\"title\":{\"id\":\"6cdf3505-a1b2-4907-ac0b-5aff466f3395\",\"type\":\"Title\"},\"toolbar\":{\"id\":\"9a9bcbb2-3163-4ff0-8839-6b822fe59f97\",\"type\":\"Toolbar\"},\"x_range\":{\"id\":\"29b236fa-aed7-4bee-8d07-f0d3fcb965a1\",\"type\":\"DataRange1d\"},\"x_scale\":{\"id\":\"1d874b4c-adce-4779-97b8-3ea94b8bb012\",\"type\":\"LinearScale\"},\"y_range\":{\"id\":\"e48717ee-bf3b-4969-8118-daa1b2c244ea\",\"type\":\"DataRange1d\"},\"y_scale\":{\"id\":\"2da31b5d-fb5f-498f-835e-4f2c71c9b3a4\",\"type\":\"LinearScale\"}},\"id\":\"390e51ff-5e3c-4937-b317-74c5a60029ce\",\"subtype\":\"Figure\",\"type\":\"Plot\"},{\"attributes\":{\"fill_color\":{\"value\":\"orange\"},\"line_color\":{\"value\":\"orange\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"c48cf889-1333-4f02-b9b9-47dcabe0bb11\",\"type\":\"Circle\"},{\"attributes\":{\"axis_label\":\"PC1 (8.19%)\",\"formatter\":{\"id\":\"d9d33ed3-0481-437f-ba80-47ea8a19d71e\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"390e51ff-5e3c-4937-b317-74c5a60029ce\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"039a5711-406b-4a5a-a42f-c8de30ced1c4\",\"type\":\"BasicTicker\"}},\"id\":\"819d78a8-e36f-497f-a1f1-9eaea3c71e05\",\"type\":\"LinearAxis\"},{\"attributes\":{\"bottom_units\":\"screen\",\"fill_alpha\":{\"value\":0.5},\"fill_color\":{\"value\":\"lightgrey\"},\"left_units\":\"screen\",\"level\":\"overlay\",\"line_alpha\":{\"value\":1.0},\"line_color\":{\"value\":\"black\"},\"line_dash\":[4,4],\"line_width\":{\"value\":2},\"plot\":null,\"render_mode\":\"css\",\"right_units\":\"screen\",\"top_units\":\"screen\"},\"id\":\"0da4ffd8-03dd-4d25-896c-a2cb21a991dc\",\"type\":\"BoxAnnotation\"},{\"attributes\":{\"callback\":null},\"id\":\"29b236fa-aed7-4bee-8d07-f0d3fcb965a1\",\"type\":\"DataRange1d\"},{\"attributes\":{},\"id\":\"039a5711-406b-4a5a-a42f-c8de30ced1c4\",\"type\":\"BasicTicker\"},{\"attributes\":{\"dimension\":1,\"plot\":{\"id\":\"390e51ff-5e3c-4937-b317-74c5a60029ce\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"7fdb54ab-10a6-4b09-b51e-3b050fc3bb97\",\"type\":\"BasicTicker\"}},\"id\":\"6a6dff96-2af8-4b2a-ac25-7dcdbf91f7d2\",\"type\":\"Grid\"},{\"attributes\":{\"data_source\":{\"id\":\"2c6b05b4-3dea-437e-85b6-d6fd26465ccd\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"38e529b8-e78d-4d85-bc5a-176b1ed6e178\",\"type\":\"Circle\"},\"hover_glyph\":null,\"muted_glyph\":null,\"nonselection_glyph\":{\"id\":\"ca1a5fd6-322b-4699-9f7f-c77e4d41f869\",\"type\":\"Circle\"},\"selection_glyph\":null,\"view\":{\"id\":\"d819e735-b24e-4248-861f-06dd05f4e277\",\"type\":\"CDSView\"}},\"id\":\"438675e5-f102-4891-8bcf-c2a9d3c48b11\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"source\":{\"id\":\"2c6b05b4-3dea-437e-85b6-d6fd26465ccd\",\"type\":\"ColumnDataSource\"}},\"id\":\"d819e735-b24e-4248-861f-06dd05f4e277\",\"type\":\"CDSView\"},{\"attributes\":{},\"id\":\"1e63ae9d-2b09-409b-bc14-bff773d7b7dc\",\"type\":\"HelpTool\"},{\"attributes\":{\"source\":{\"id\":\"5f5a8c6c-8687-4192-aa48-f8aa6e6ebcdb\",\"type\":\"ColumnDataSource\"}},\"id\":\"495c8052-152a-4c48-8c3d-e63a2614b1ca\",\"type\":\"CDSView\"},{\"attributes\":{\"callback\":null,\"data\":{\"x\":{\"__ndarray__\":\"s4dscZTUFsCsUR4MMntMQEacKLQ+z0dAZjHJmj/mKMDavt88hvAvQPepnplzfeQ/iRqKdbXJRUDD41gKeYQzQOEzq9HxPkdAof95CJrpUUCXVoj1RC9SQFRDbl6DGfW//wiVFHpZJEDanZ+ntBVJQPXwzwnJIlNAD4fQrjFbQkApN+KVnwFMQJZQEet7gUJAB8OIkj+NPkA6POlDoostwF2LPGBkvxtAb0MN5dbzFEBG8wS/hXFOQNvWE0osDk1AAx0Rr8ddOEBhAMw5xFA0QMbOy//t9VFAuP2PyC4xN0C918OCG0c4QNvLJkWY3EFAWeQZTmXUSUB6OcmTg1E5QP7aMVQ/kSHA3uDhUYTsDkBfqygeHqg1QBm4Scy720JAYGv9cKPgREC3MSH71K8tQLpNrTITFlRAHXxspr3+SEDjaqfxTofxv1Zkp2gpcSNAyZ7O8pNKUEDDp6vqvAxQQO/AHnRFIlNA\",\"dtype\":\"float64\",\"shape\":[45]},\"y\":{\"__ndarray__\":\"5PVobXIYNEAbI7kdXVw2wEpKDc6nBgHAtMNFMWd/NMAQK6V1J5EJwB7i+V5UxxZA8RXRZPOeIcBhsnMT6sE3wJFnXaFJpxhAhHAj30TDz7/KqmMKc+w9wH/oBR/sckJAJuQKfyZNL0B5ResFsvEoQF959I4Mn0PAoDzn6xhBNkB4LAS7Jfk1wDIPw4n7pChAzQEh+La0F8DzZ9i1DoIowBGmZti8ByRA6Nnjzr/EQsAKobWnnulFQG7mTrGWVzTA9GZR60VCFkCj1E4NSO1BQORR0RpiqwrArZcb6qPaTUBb9JxAoDQ8QETAWzE+bjNAbjnJ9riZNUDio8BMqBFGQJr/aX26KUNALA4ZgbopSUBeJV1jAgM1QH555P1vjyxAc92EhwMyRUBzj8fL9JlDQF+DmsrFiBVA58tVN1cLQMAVcmzzh0k/QDILsl0qHyhAZg3FVBo0OcDfvGZhQ6Y2wHad6WtZ/hjA\",\"dtype\":\"float64\",\"shape\":[45]}},\"selected\":{\"id\":\"6a0308b0-15ee-4b19-85fd-d89463b3e43c\",\"type\":\"Selection\"},\"selection_policy\":{\"id\":\"fa323ccb-57fd-41f8-8522-884d3656e065\",\"type\":\"UnionRenderers\"}},\"id\":\"5f5a8c6c-8687-4192-aa48-f8aa6e6ebcdb\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"overlay\":{\"id\":\"0da4ffd8-03dd-4d25-896c-a2cb21a991dc\",\"type\":\"BoxAnnotation\"}},\"id\":\"2a316f43-749b-438b-bdac-d17e0e6e238a\",\"type\":\"BoxZoomTool\"}],\"root_ids\":[\"390e51ff-5e3c-4937-b317-74c5a60029ce\"]},\"title\":\"Bokeh Application\",\"version\":\"0.12.16\"}};\n", + " var render_items = [{\"docid\":\"8569d5e9-157c-4830-b35b-978236e6dc15\",\"elementid\":\"d0c9488f-b9af-4105-b2c0-dd93310660ef\",\"modelid\":\"390e51ff-5e3c-4937-b317-74c5a60029ce\"}];\n", + " root.Bokeh.embed.embed_items_notebook(docs_json, render_items);\n", + "\n", + " }\n", + " if (root.Bokeh !== undefined) {\n", + " embed_document(root);\n", + " } else {\n", + " var attempts = 0;\n", + " var timer = setInterval(function(root) {\n", + " if (root.Bokeh !== undefined) {\n", + " embed_document(root);\n", + " clearInterval(timer);\n", + " }\n", + " attempts++;\n", + " if (attempts > 100) {\n", + " console.log(\"Bokeh: ERROR: Unable to run BokehJS code because BokehJS library is missing\")\n", + " clearInterval(timer);\n", + " }\n", + " }, 10, root)\n", + " }\n", + "})(window);" + ], + "application/vnd.bokehjs_exec.v0+json": "" + }, + "metadata": { + "application/vnd.bokehjs_exec.v0+json": { + "id": "390e51ff-5e3c-4937-b317-74c5a60029ce" + } + }, + "output_type": "display_data" + } + ], "source": [ "vars = pca.explained_variance_ratio_\n", "p = figure(plot_width=400, plot_height=400, title=\"PCA of Train data\")\n", @@ -718,11 +2046,70 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "
\n", + "
\n", + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "application/javascript": [ + "(function(root) {\n", + " function embed_document(root) {\n", + " \n", + " var docs_json = {\"9462ff19-ef8a-43b7-bc28-c2ae0b0ca382\":{\"roots\":{\"references\":[{\"attributes\":{},\"id\":\"b378cb1e-4305-4c29-a742-a30eacc219c4\",\"type\":\"PanTool\"},{\"attributes\":{\"bottom_units\":\"screen\",\"fill_alpha\":{\"value\":0.5},\"fill_color\":{\"value\":\"lightgrey\"},\"left_units\":\"screen\",\"level\":\"overlay\",\"line_alpha\":{\"value\":1.0},\"line_color\":{\"value\":\"black\"},\"line_dash\":[4,4],\"line_width\":{\"value\":2},\"plot\":null,\"render_mode\":\"css\",\"right_units\":\"screen\",\"top_units\":\"screen\"},\"id\":\"2089e332-ca04-4e4d-bbe0-b5b0bbd065db\",\"type\":\"BoxAnnotation\"},{\"attributes\":{\"active_drag\":\"auto\",\"active_inspect\":\"auto\",\"active_scroll\":\"auto\",\"active_tap\":\"auto\",\"tools\":[{\"id\":\"b378cb1e-4305-4c29-a742-a30eacc219c4\",\"type\":\"PanTool\"},{\"id\":\"43630d74-5f58-4a69-b8cc-09b48ec548bc\",\"type\":\"WheelZoomTool\"},{\"id\":\"2cfc85ae-c3f1-433a-a8af-2f294f9e339c\",\"type\":\"BoxZoomTool\"},{\"id\":\"0d7d47eb-f357-4219-be39-7f6c3913df48\",\"type\":\"SaveTool\"},{\"id\":\"8783b23a-5b83-442b-baae-22d06a3d77de\",\"type\":\"ResetTool\"},{\"id\":\"83816b07-f311-491a-8543-c26247ea8a36\",\"type\":\"HelpTool\"}]},\"id\":\"ada31b3a-3c21-46c4-9768-41986fcef0ea\",\"type\":\"Toolbar\"},{\"attributes\":{},\"id\":\"43630d74-5f58-4a69-b8cc-09b48ec548bc\",\"type\":\"WheelZoomTool\"},{\"attributes\":{\"overlay\":{\"id\":\"2089e332-ca04-4e4d-bbe0-b5b0bbd065db\",\"type\":\"BoxAnnotation\"}},\"id\":\"2cfc85ae-c3f1-433a-a8af-2f294f9e339c\",\"type\":\"BoxZoomTool\"},{\"attributes\":{},\"id\":\"0d7d47eb-f357-4219-be39-7f6c3913df48\",\"type\":\"SaveTool\"},{\"attributes\":{\"callback\":null},\"id\":\"eb051b83-72e5-4188-b22d-798ba987aab6\",\"type\":\"DataRange1d\"},{\"attributes\":{},\"id\":\"8783b23a-5b83-442b-baae-22d06a3d77de\",\"type\":\"ResetTool\"},{\"attributes\":{},\"id\":\"28f202ff-4ff3-4908-8881-242f880d380f\",\"type\":\"UnionRenderers\"},{\"attributes\":{\"axis_label\":\"PC2 (4.34%)\",\"formatter\":{\"id\":\"ebe9c16d-612d-4f7b-bbac-a61ecdc4d0f1\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"0066e7da-e2c2-41e8-a3fe-3990150548a4\",\"type\":\"BasicTicker\"}},\"id\":\"313df7bc-1e81-4fb1-8f77-7f2be3aa608f\",\"type\":\"LinearAxis\"},{\"attributes\":{},\"id\":\"83816b07-f311-491a-8543-c26247ea8a36\",\"type\":\"HelpTool\"},{\"attributes\":{},\"id\":\"ebe9c16d-612d-4f7b-bbac-a61ecdc4d0f1\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"c0b5b80d-9461-4c9a-8149-4f73129df83c\",\"type\":\"Circle\"},{\"attributes\":{\"data_source\":{\"id\":\"024379a1-fd21-4dd2-b715-dfb296d7e044\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"0870a187-f7e5-4cd6-8d42-55f96bb5461c\",\"type\":\"Circle\"},\"hover_glyph\":null,\"muted_glyph\":null,\"nonselection_glyph\":{\"id\":\"c0b5b80d-9461-4c9a-8149-4f73129df83c\",\"type\":\"Circle\"},\"selection_glyph\":null,\"view\":{\"id\":\"d29987fe-1bd6-4fc5-9a14-95d3cca6b413\",\"type\":\"CDSView\"}},\"id\":\"7cbf1114-36ef-4d48-b794-ff9274370312\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"source\":{\"id\":\"024379a1-fd21-4dd2-b715-dfb296d7e044\",\"type\":\"ColumnDataSource\"}},\"id\":\"d29987fe-1bd6-4fc5-9a14-95d3cca6b413\",\"type\":\"CDSView\"},{\"attributes\":{\"callback\":null,\"data\":{\"x\":{\"__ndarray__\":\"Da7fNG/ZJkBX5akTCONLQGb3T+26HENA3OF45a/OJ0A+JQtYuggxwMYlG5/G+xdApYP2gR10I0A3HiM2XrNBQNiOs4ipuhdAMafuYwmhPED949T2x+grQDrwNWw3Eh5Axip2+RdmOkBJaK26QqNMQLygwDyKsEVAooGu1FToMcBt/YFUOrkrQEdMTS6sgzpAge2H7Ye+TUAPRy+5QxVPQMEVm/y+ODlAmKTj5CPNTUAW77J6yXFKQFzxE58baUVAYpWdPdxUKkAGJqtYjfdBQE1u1lwi4EZAMnZzibN0SECqWw5yqmxKQN1ek4f7K0FAysHtN/+MOkAN0LlLVmg0QNMNQXxgUUFAPd/CO/QrVEC95q9DZpMrQHT8e3lxmATAHRhOYh5/PkCmr3vvifUyQCxme02yAzVATeUPDNgyQEC6639iDPEsQGogX/VFfUZAyDbFMA1qT0ARGOcQsxs2QFcOicPHYTpAUIm5K/zeQkA=\",\"dtype\":\"float64\",\"shape\":[46]},\"y\":{\"__ndarray__\":\"0xj+K4X0BkAj47n5AJ81wF5jdJKTKDvADYnUrxgY+T9yGkH3vuk6QHNMAWPEpS5ABHLTkA6hL0DfG3VYvrQhQDA7ukLW8RvAXWkywkuLMkAdV8lfgP4sQAz1wqSZXRtACVDi38HRBsCTlfU106YEQOVgO6PDxijAHohBcumMQEC40j2lqLAjwFuxwupljR7Atk0pha0OIsCvBQh9al4uwGTcLA36tA1AuclownL4OMC2keS665cwwJWuUjRjpRpA7v2Egz3IAcDvyCxRfnMkwOJMp66qwzDA0Z6z+SVPMMD/VDyPhj0zwKD2HyVJ4R3A+bJ3Rma6EEAkodSlxMRBQD/zIkvPa01AKBCUmVGLEsB2JCFLCfQwwAfmxFWGqkZAWzW/3xqtHUBRaZkJWDUtQKg8OGl9bSlAAORyNSRh0D+BmYhY9QkgQOYI4pwItTHA5eLVdfOlI8CAgsx3axhJQKYfJ+x0iytAeYCv7TRIFMA=\",\"dtype\":\"float64\",\"shape\":[46]}},\"selected\":{\"id\":\"b59c2931-86f7-4e88-9cd4-edf5927916ba\",\"type\":\"Selection\"},\"selection_policy\":{\"id\":\"670bdd62-8431-437d-a621-aeb874396b4a\",\"type\":\"UnionRenderers\"}},\"id\":\"09cd2f5d-a2e5-461b-a5ae-763b5682b3a7\",\"type\":\"ColumnDataSource\"},{\"attributes\":{},\"id\":\"865697d8-682e-4995-8a94-bc9eb4deac4f\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{},\"id\":\"047e2375-f530-4bbb-ba68-2e759bb40ac2\",\"type\":\"LinearScale\"},{\"attributes\":{\"dimension\":1,\"plot\":{\"id\":\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"0066e7da-e2c2-41e8-a3fe-3990150548a4\",\"type\":\"BasicTicker\"}},\"id\":\"11436559-e5fa-4e94-93d1-3e57f22d24b8\",\"type\":\"Grid\"},{\"attributes\":{},\"id\":\"0066e7da-e2c2-41e8-a3fe-3990150548a4\",\"type\":\"BasicTicker\"},{\"attributes\":{\"fill_color\":{\"value\":\"blue\"},\"line_color\":{\"value\":\"blue\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"0870a187-f7e5-4cd6-8d42-55f96bb5461c\",\"type\":\"Circle\"},{\"attributes\":{},\"id\":\"670bdd62-8431-437d-a621-aeb874396b4a\",\"type\":\"UnionRenderers\"},{\"attributes\":{\"axis_label\":\"PC1 (8.19%)\",\"formatter\":{\"id\":\"865697d8-682e-4995-8a94-bc9eb4deac4f\",\"type\":\"BasicTickFormatter\"},\"plot\":{\"id\":\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"13528d4a-0f2e-4629-810d-2de948b9833f\",\"type\":\"BasicTicker\"}},\"id\":\"ace706a4-075f-4d90-9264-d4abce004f08\",\"type\":\"LinearAxis\"},{\"attributes\":{\"fill_color\":{\"value\":\"orange\"},\"line_color\":{\"value\":\"orange\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"2148dbde-ad02-4142-9239-9de7ea263ed6\",\"type\":\"Circle\"},{\"attributes\":{\"fill_alpha\":{\"value\":0.1},\"fill_color\":{\"value\":\"#1f77b4\"},\"line_alpha\":{\"value\":0.1},\"line_color\":{\"value\":\"#1f77b4\"},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"433ed932-afd7-4e0f-be6c-491087a7c97b\",\"type\":\"Circle\"},{\"attributes\":{},\"id\":\"b6e5b1cd-5027-43e0-bbcd-21b12cddfb98\",\"type\":\"Selection\"},{\"attributes\":{\"source\":{\"id\":\"09cd2f5d-a2e5-461b-a5ae-763b5682b3a7\",\"type\":\"ColumnDataSource\"}},\"id\":\"f5749626-f5b9-45b3-aca3-6cc155bb7359\",\"type\":\"CDSView\"},{\"attributes\":{\"below\":[{\"id\":\"ace706a4-075f-4d90-9264-d4abce004f08\",\"type\":\"LinearAxis\"}],\"left\":[{\"id\":\"313df7bc-1e81-4fb1-8f77-7f2be3aa608f\",\"type\":\"LinearAxis\"}],\"plot_height\":400,\"plot_width\":400,\"renderers\":[{\"id\":\"ace706a4-075f-4d90-9264-d4abce004f08\",\"type\":\"LinearAxis\"},{\"id\":\"a6b68a1a-d626-4b97-9940-8b8f461e18e9\",\"type\":\"Grid\"},{\"id\":\"313df7bc-1e81-4fb1-8f77-7f2be3aa608f\",\"type\":\"LinearAxis\"},{\"id\":\"11436559-e5fa-4e94-93d1-3e57f22d24b8\",\"type\":\"Grid\"},{\"id\":\"2089e332-ca04-4e4d-bbe0-b5b0bbd065db\",\"type\":\"BoxAnnotation\"},{\"id\":\"cbbce434-c409-4019-9255-e686122e7422\",\"type\":\"GlyphRenderer\"},{\"id\":\"7cbf1114-36ef-4d48-b794-ff9274370312\",\"type\":\"GlyphRenderer\"}],\"title\":{\"id\":\"6279164d-1d6c-4095-854d-88f37333827c\",\"type\":\"Title\"},\"toolbar\":{\"id\":\"ada31b3a-3c21-46c4-9768-41986fcef0ea\",\"type\":\"Toolbar\"},\"x_range\":{\"id\":\"eb051b83-72e5-4188-b22d-798ba987aab6\",\"type\":\"DataRange1d\"},\"x_scale\":{\"id\":\"047e2375-f530-4bbb-ba68-2e759bb40ac2\",\"type\":\"LinearScale\"},\"y_range\":{\"id\":\"c0fa0dd3-f4e4-49e9-824b-04b94b09c30d\",\"type\":\"DataRange1d\"},\"y_scale\":{\"id\":\"b93b4687-55cb-4723-b5d6-eefbdbc61cb5\",\"type\":\"LinearScale\"}},\"id\":\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\",\"subtype\":\"Figure\",\"type\":\"Plot\"},{\"attributes\":{\"callback\":null,\"data\":{\"x\":{\"__ndarray__\":\"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\",\"dtype\":\"float64\",\"shape\":[90]},\"y\":{\"__ndarray__\":\"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\",\"dtype\":\"float64\",\"shape\":[90]}},\"selected\":{\"id\":\"b6e5b1cd-5027-43e0-bbcd-21b12cddfb98\",\"type\":\"Selection\"},\"selection_policy\":{\"id\":\"28f202ff-4ff3-4908-8881-242f880d380f\",\"type\":\"UnionRenderers\"}},\"id\":\"024379a1-fd21-4dd2-b715-dfb296d7e044\",\"type\":\"ColumnDataSource\"},{\"attributes\":{\"data_source\":{\"id\":\"09cd2f5d-a2e5-461b-a5ae-763b5682b3a7\",\"type\":\"ColumnDataSource\"},\"glyph\":{\"id\":\"2148dbde-ad02-4142-9239-9de7ea263ed6\",\"type\":\"Circle\"},\"hover_glyph\":null,\"muted_glyph\":null,\"nonselection_glyph\":{\"id\":\"433ed932-afd7-4e0f-be6c-491087a7c97b\",\"type\":\"Circle\"},\"selection_glyph\":null,\"view\":{\"id\":\"f5749626-f5b9-45b3-aca3-6cc155bb7359\",\"type\":\"CDSView\"}},\"id\":\"cbbce434-c409-4019-9255-e686122e7422\",\"type\":\"GlyphRenderer\"},{\"attributes\":{\"plot\":{\"id\":\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\",\"subtype\":\"Figure\",\"type\":\"Plot\"},\"ticker\":{\"id\":\"13528d4a-0f2e-4629-810d-2de948b9833f\",\"type\":\"BasicTicker\"}},\"id\":\"a6b68a1a-d626-4b97-9940-8b8f461e18e9\",\"type\":\"Grid\"},{\"attributes\":{},\"id\":\"13528d4a-0f2e-4629-810d-2de948b9833f\",\"type\":\"BasicTicker\"},{\"attributes\":{},\"id\":\"b93b4687-55cb-4723-b5d6-eefbdbc61cb5\",\"type\":\"LinearScale\"},{\"attributes\":{\"callback\":null},\"id\":\"c0fa0dd3-f4e4-49e9-824b-04b94b09c30d\",\"type\":\"DataRange1d\"},{\"attributes\":{},\"id\":\"b59c2931-86f7-4e88-9cd4-edf5927916ba\",\"type\":\"Selection\"},{\"attributes\":{\"plot\":null,\"text\":\"PCA of Test data\"},\"id\":\"6279164d-1d6c-4095-854d-88f37333827c\",\"type\":\"Title\"}],\"root_ids\":[\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\"]},\"title\":\"Bokeh Application\",\"version\":\"0.12.16\"}};\n", + " var render_items = [{\"docid\":\"9462ff19-ef8a-43b7-bc28-c2ae0b0ca382\",\"elementid\":\"ecbd62b0-3e13-4340-8ac1-4971af0727b5\",\"modelid\":\"3b01317b-4560-4a65-ba6d-7e2742aa01c3\"}];\n", + " root.Bokeh.embed.embed_items_notebook(docs_json, render_items);\n", + "\n", + " }\n", + " if (root.Bokeh !== undefined) {\n", + " embed_document(root);\n", + " } else {\n", + " var attempts = 0;\n", + " var timer = setInterval(function(root) {\n", + " if (root.Bokeh !== undefined) {\n", + " embed_document(root);\n", + " clearInterval(timer);\n", + " }\n", + " attempts++;\n", + " if (attempts > 100) {\n", + " console.log(\"Bokeh: ERROR: Unable to run BokehJS code because BokehJS library is missing\")\n", + " clearInterval(timer);\n", + " }\n", + " }, 10, root)\n", + " }\n", + "})(window);" + ], + "application/vnd.bokehjs_exec.v0+json": "" + }, + "metadata": { + "application/vnd.bokehjs_exec.v0+json": { + "id": "3b01317b-4560-4a65-ba6d-7e2742aa01c3" + } + }, + "output_type": "display_data" + } + ], "source": [ - "## exercise here" + "## exercise here\n", + "z_ts = pca.transform(x_ts)\n", + "vars = pca.explained_variance_ratio_\n", + "p = figure(plot_width=400, plot_height=400, title=\"PCA of Test data\")\n", + "p.circle(z_ts[y_ts==0, 0], z_ts[y_ts==0, 1], line_color=\"orange\", fill_color=\"orange\")\n", + "p.circle(z_ts[y_ts==1, 0], z_ts[y_ts==1, 1], line_color=\"blue\", fill_color=\"blue\")\n", + "p.xaxis.axis_label = \"PC1 (%.2f%%)\" % (100*vars[0])\n", + "p.yaxis.axis_label = \"PC2 (%.2f%%)\" % (100*vars[1])\n", + "show(p)" ] }, { @@ -761,7 +2148,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": { "colab": {}, "colab_type": "code", @@ -774,21 +2161,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": { "colab": {}, "colab_type": "code", "id": "Cg8TpDATk3XI", "outputId": "e9658389-474c-4bf5-f196-11d4518311b7" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n", + " metric_params=None, n_jobs=1, n_neighbors=10, p=2,\n", + " weights='uniform')" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "knn.fit(x_tr, y_tr)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": { "colab": {}, "colab_type": "code", @@ -845,13 +2245,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": { "colab": {}, "colab_type": "code", "id": "JISD2EVQ9Q9Z" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "array([[27, 19],\n", + " [ 0, 90]])" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "from sklearn.metrics import confusion_matrix\n", "conf = confusion_matrix(y_ts, y_pred_knn)\n", @@ -870,13 +2282,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": { "colab": {}, "colab_type": "code", "id": "pZVN8GKKdOhy" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "46" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "np.sum(y_ts==0) # total number of \"class 0\" samples in the test set" ] @@ -893,13 +2316,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "metadata": { "colab": {}, "colab_type": "code", "id": "1PVj7JbxdVk0" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "90" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "np.sum(y_ts==1) # total number of \"class 1\" samples in the test set" ] @@ -928,13 +2362,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "metadata": { "colab": {}, "colab_type": "code", "id": "-1-40TyQeAIt" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.8602941176470589" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "(conf[0,0] + conf[1,1])/y_ts.shape[0] # y_ts.shape[0] is the sample size of the test set" ] @@ -951,13 +2396,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "metadata": { "colab": {}, "colab_type": "code", "id": "q0emRGAvfWi4" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.8602941176470589\n" + ] + } + ], "source": [ "tp = conf[1,1]\n", "tn = conf[0,0]\n", @@ -984,13 +2437,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "metadata": { "colab": {}, "colab_type": "code", "id": "a9JlR-LNe5ZI" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "1.0" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "conf[1,1] / (conf[1,1] + conf[1,0])" ] @@ -1021,13 +2485,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "metadata": { "colab": {}, "colab_type": "code", "id": "3KeLJcCbkSo6" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.8602941176470589" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "from sklearn.metrics import accuracy_score\n", "accuracy_score(y_ts, y_pred_knn)" @@ -1045,13 +2520,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 40, "metadata": { "colab": {}, "colab_type": "code", "id": "MgfhssjZmsg3" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "1.0" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "from sklearn.metrics import recall_score\n", "recall_score(y_ts, y_pred_knn)" @@ -1069,13 +2555,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 41, "metadata": { "colab": {}, "colab_type": "code", "id": "AKiUXIkPm-N3" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.8602941176470589\n", + "1.0\n" + ] + } + ], "source": [ "from sklearn import metrics\n", "print(metrics.accuracy_score(y_ts, y_pred_knn))\n", @@ -1094,14 +2589,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "metadata": { "colab": {}, "colab_type": "code", "id": "HXgvIJM2k3XQ", "outputId": "0d2d0773-a292-40cb-d8e7-df6b6ee29ff2" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " precision recall f1-score support\n", + "\n", + " 0 1.00 0.59 0.74 46\n", + " 1 0.83 1.00 0.90 90\n", + "\n", + "avg / total 0.88 0.86 0.85 136\n", + "\n" + ] + } + ], "source": [ "from sklearn import metrics\n", "print(metrics.classification_report(y_ts, y_pred_knn))" @@ -1159,14 +2668,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 43, "metadata": { "colab": {}, "colab_type": "code", "id": "OuoRfictk3XW", "outputId": "9119acba-9d18-4076-eb3c-8346ba420579" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.6961630553262051\n" + ] + } + ], "source": [ "print(metrics.matthews_corrcoef(y_ts, y_pred_knn))" ] @@ -1241,7 +2758,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 44, "metadata": { "colab": {}, "colab_type": "code", @@ -1291,13 +2808,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "metadata": { "colab": {}, "colab_type": "code", "id": "n12boA3k3Neo" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy = 0.750\n", + "MCC = 0.538\n" + ] + } + ], "source": [ "from sklearn import metrics\n", "knn = neighbors.KNeighborsClassifier(n_neighbors=10)\n", @@ -1356,7 +2882,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "metadata": { "colab": {}, "colab_type": "code", @@ -1390,13 +2916,70 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 48, "metadata": { "colab": {}, "colab_type": "code", "id": "-uoahY6yNcIv" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "### Fold 1 / 5 ###\n", + "TRAIN size: 108\n", + "-- class 0: 36 class 1: 72\n", + "TEST size: 28\n", + "-- class 0: 9 class 1: 19\n", + "\n", + "Model performance\n", + "Accuracy on TEST set: 0.929\n", + "MCC on TEST set: 0.839\n", + "\n", + "### Fold 2 / 5 ###\n", + "TRAIN size: 109\n", + "-- class 0: 36 class 1: 73\n", + "TEST size: 27\n", + "-- class 0: 9 class 1: 18\n", + "\n", + "Model performance\n", + "Accuracy on TEST set: 0.852\n", + "MCC on TEST set: 0.674\n", + "\n", + "### Fold 3 / 5 ###\n", + "TRAIN size: 109\n", + "-- class 0: 36 class 1: 73\n", + "TEST size: 27\n", + "-- class 0: 9 class 1: 18\n", + "\n", + "Model performance\n", + "Accuracy on TEST set: 0.815\n", + "MCC on TEST set: 0.567\n", + "\n", + "### Fold 4 / 5 ###\n", + "TRAIN size: 109\n", + "-- class 0: 36 class 1: 73\n", + "TEST size: 27\n", + "-- class 0: 9 class 1: 18\n", + "\n", + "Model performance\n", + "Accuracy on TEST set: 0.815\n", + "MCC on TEST set: 0.590\n", + "\n", + "### Fold 5 / 5 ###\n", + "TRAIN size: 109\n", + "-- class 0: 36 class 1: 73\n", + "TEST size: 27\n", + "-- class 0: 9 class 1: 18\n", + "\n", + "Model performance\n", + "Accuracy on TEST set: 0.926\n", + "MCC on TEST set: 0.837\n", + "\n" + ] + } + ], "source": [ "## get the number of splitting operations\n", "N = skf.get_n_splits(x_tr, y_tr)\n", @@ -1412,7 +2995,7 @@ "## computing kNN accuracy & MCC on each test partition\n", "i = 1\n", "for (idx_tr, idx_ts) in skf.split(x_tr, y_tr):\n", - " print(f\"### Fold {i+1} / {N:d} ###\")\n", + " print(f\"### Fold {i} / {N:d} ###\")\n", " X_train, Y_train = x_tr[idx_tr], y_tr[idx_tr]\n", " X_test, Y_test = x_tr[idx_ts], y_tr[idx_ts]\n", " print(\"TRAIN size:\", X_train.shape[0])\n", @@ -1451,9 +3034,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 49, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average cross-validation accuracy: 0.867\n", + "Average cross-validation MCC: 0.701\n" + ] + } + ], "source": [ "## note: we need to convert the lists to numpy arrays before computing the means\n", "acc_avg = np.mean(np.array(acc_list))\n", @@ -1472,13 +3064,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 50, "metadata": { "colab": {}, "colab_type": "code", "id": "-uoahY6yNcIv" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "### Iteration 1 ###\n", + "### Iteration 2 ###\n", + "### Iteration 3 ###\n", + "### Iteration 4 ###\n", + "### Iteration 5 ###\n", + "### Iteration 6 ###\n", + "### Iteration 7 ###\n", + "### Iteration 8 ###\n", + "### Iteration 9 ###\n", + "### Iteration 10 ###\n" + ] + } + ], "source": [ "## how many repetitions?\n", "N_CV = 10\n", @@ -1519,13 +3128,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 52, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average cross-validation accuracy: 0.854\n", + "Average cross-validation MCC: 0.670\n" + ] + } + ], "source": [ "## note: we need to convert the lists to numpy arrays before computing the means\n", - "# acc_avg = ...\n", - "# mcc_avg = ...\n", + "acc_avg = np.mean(np.array(acc_list))\n", + "mcc_avg = np.mean(np.array(mcc_list))\n", "\n", "print(f\"Average cross-validation accuracy: {acc_avg:.3f}\")\n", "print(f\"Average cross-validation MCC: {mcc_avg:.3f}\")" @@ -1572,7 +3190,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.6.5" } }, "nbformat": 4, diff --git a/chierici_practical_part2.ipynb b/chierici_practical_part2.ipynb index a658b47..fbec1a2 100644 --- a/chierici_practical_part2.ipynb +++ b/chierici_practical_part2.ipynb @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": { "colab": {}, "colab_type": "code", @@ -56,9 +56,298 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "
\n", + " \n", + " Loading BokehJS ...\n", + "
" + ] + }, + "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 !== undefined) {\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 element_id = msg.content.text.trim();\n", + " Bokeh.index[element_id].model.document.clear();\n", + " delete Bokeh.index[element_id];\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", + " \"
\\n\"+\n", + " \"

\\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", + " \"

\\n\"+\n", + " \"
    \\n\"+\n", + " \"
  • re-rerun `output_notebook()` to attempt to load from CDN again, or
    • \\n\"+\n", + " \"
  • use INLINE resources instead, as so:
    • \\n\"+\n", + " \"
\\n\"+\n", + " \"\\n\"+\n", + " \"from bokeh.resources import INLINE\\n\"+\n", + " \"output_notebook(resources=INLINE)\\n\"+\n", + " \"\\n\"+\n", + " \"
\"}};\n", + "\n", + " function display_loaded() {\n", + " var el = document.getElementById(\"5cac4085-57f7-4935-8294-6fc71ea061bf\");\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) { callback() });\n", + " }\n", + " finally {\n", + " delete root._bokeh_onload_callbacks\n", + " }\n", + " console.info(\"Bokeh: all callbacks have finished\");\n", + " }\n", + "\n", + " function load_libs(js_urls, callback) {\n", + " root._bokeh_onload_callbacks.push(callback);\n", + " if (root._bokeh_is_loading > 0) {\n", + " console.log(\"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.log(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n", + " root._bokeh_is_loading = js_urls.length;\n", + " for (var i = 0; i < js_urls.length; i++) {\n", + " var url = js_urls[i];\n", + " var s = document.createElement('script');\n", + " s.src = url;\n", + " s.async = false;\n", + " s.onreadystatechange = s.onload = function() {\n", + " root._bokeh_is_loading--;\n", + " if (root._bokeh_is_loading === 0) {\n", + " console.log(\"Bokeh: all BokehJS libraries loaded\");\n", + " run_callbacks()\n", + " }\n", + " };\n", + " s.onerror = function() {\n", + " console.warn(\"failed to load library \" + url);\n", + " };\n", + " console.log(\"Bokeh: injecting script tag for BokehJS library: \", url);\n", + " document.getElementsByTagName(\"head\")[0].appendChild(s);\n", + " }\n", + " };var element = document.getElementById(\"5cac4085-57f7-4935-8294-6fc71ea061bf\");\n", + " if (element == null) {\n", + " console.log(\"Bokeh: ERROR: autoload.js configured with elementid '5cac4085-57f7-4935-8294-6fc71ea061bf' but no matching script tag was found. \")\n", + " return false;\n", + " }\n", + "\n", + " var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-0.12.16.min.js\"];\n", + "\n", + " var inline_js = [\n", + " function(Bokeh) {\n", + " Bokeh.set_log_level(\"info\");\n", + " },\n", + " \n", + " function(Bokeh) {\n", + " \n", + " },\n", + " function(Bokeh) {\n", + " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n", + " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n", + " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n", + " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n", + " console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n", + " Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n", + " }\n", + " ];\n", + "\n", + " function run_inline_js() {\n", + " \n", + " if ((root.Bokeh !== undefined) || (force === true)) {\n", + " for (var i = 0; i < inline_js.length; i++) {\n", + " inline_js[i].call(root, root.Bokeh);\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(\"5cac4085-57f7-4935-8294-6fc71ea061bf\")).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.log(\"Bokeh: BokehJS loaded, going straight to plotting\");\n", + " run_inline_js();\n", + " } else {\n", + " load_libs(js_urls, function() {\n", + " console.log(\"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 \"
\\n\"+\n \"

\\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 \"

\\n\"+\n \"
    \\n\"+\n \"
  • re-rerun `output_notebook()` to attempt to load from CDN again, or
    • \\n\"+\n \"
  • use INLINE resources instead, as so:
    • \\n\"+\n \"
\\n\"+\n \"\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"\\n\"+\n \"
\"}};\n\n function display_loaded() {\n var el = document.getElementById(\"5cac4085-57f7-4935-8294-6fc71ea061bf\");\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) { callback() });\n }\n finally {\n delete root._bokeh_onload_callbacks\n }\n console.info(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(js_urls, callback) {\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.log(\"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.log(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = js_urls.length;\n for (var i = 0; i < js_urls.length; i++) {\n var url = js_urls[i];\n var s = document.createElement('script');\n s.src = url;\n s.async = false;\n s.onreadystatechange = s.onload = function() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.log(\"Bokeh: all BokehJS libraries loaded\");\n run_callbacks()\n }\n };\n s.onerror = function() {\n console.warn(\"failed to load library \" + url);\n };\n console.log(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.getElementsByTagName(\"head\")[0].appendChild(s);\n }\n };var element = document.getElementById(\"5cac4085-57f7-4935-8294-6fc71ea061bf\");\n if (element == null) {\n console.log(\"Bokeh: ERROR: autoload.js configured with elementid '5cac4085-57f7-4935-8294-6fc71ea061bf' but no matching script tag was found. \")\n return false;\n }\n\n var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-0.12.16.min.js\"];\n\n var inline_js = [\n function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\n \n function(Bokeh) {\n \n },\n function(Bokeh) {\n console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-0.12.16.min.css\");\n console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-widgets-0.12.16.min.css\");\n console.log(\"Bokeh: injecting CSS: https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n Bokeh.embed.inject_css(\"https://cdn.pydata.org/bokeh/release/bokeh-tables-0.12.16.min.css\");\n }\n ];\n\n function run_inline_js() {\n \n if ((root.Bokeh !== undefined) || (force === true)) {\n for (var i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\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(\"5cac4085-57f7-4935-8294-6fc71ea061bf\")).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.log(\"Bokeh: BokehJS loaded, going straight to plotting\");\n run_inline_js();\n } else {\n load_libs(js_urls, function() {\n console.log(\"Bokeh: BokehJS plotting callback run at\", now());\n run_inline_js();\n });\n }\n}(window));" + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "output_notebook()" ] @@ -75,7 +364,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -85,7 +374,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": { "colab": {}, "colab_type": "code", @@ -111,7 +400,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": { "colab": {}, "colab_type": "code", @@ -145,7 +434,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": { "colab": {}, "colab_type": "code", @@ -169,16 +458,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": { "colab": {}, "colab_type": "code", "id": "Mua2Ajr-LKKa" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "(136, 52229)" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "x_tr = data_tr.values\n", - "x_ts = data_ts.values" + "x_ts = data_ts.values\n", + "x_ts.shape" ] }, { @@ -193,7 +494,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "metadata": { "colab": {}, "colab_type": "code", @@ -231,7 +532,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ @@ -246,7 +547,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": { "colab": {}, "colab_type": "code", @@ -281,14 +582,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": { "colab": {}, "colab_type": "code", "id": "Qqc3TmFBLKKn", "outputId": "d9ef6c64-9f18-4bea-9167-decaa0ca1820" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[LibSVM]" + ] + } + ], "source": [ "## fit the model and get the predictions\n", "svc.fit(x_tr, y_tr)\n", @@ -307,14 +616,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "metadata": { "colab": {}, "colab_type": "code", "id": "Ku0JSF_ALKKs", "outputId": "94585c0e-534a-445d-d0ba-92a9bf3a9388" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556\n" + ] + } + ], "source": [ "from sklearn import metrics\n", "print('MCC = ', metrics.matthews_corrcoef(class_lab_ts, class_pred_ts))\n", @@ -334,14 +653,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "metadata": { "colab": {}, "colab_type": "code", "id": "whSZnHGALKKx", "outputId": "2c471734-3504-4af7-8ebb-74e5a02be301" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " precision recall f1-score support\n", + "\n", + " 0 0.91 0.93 0.92 46\n", + " 1 0.97 0.96 0.96 90\n", + "\n", + "avg / total 0.95 0.95 0.95 136\n", + "\n" + ] + } + ], "source": [ "print(metrics.classification_report(class_lab_ts, class_pred_ts))" ] @@ -358,15 +691,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": { "colab": {}, "colab_type": "code", "id": "ZT6XjB20LKK0" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "MCC = 0.8357487922705314\n", + "ACC = 0.9264705882352942\n", + "SENS = 0.9444444444444444\n" + ] + } + ], "source": [ - "## space for exercise\n" + "## space for exercise\n", + "from sklearn.ensemble import RandomForestClassifier\n", + "\n", + "clf = RandomForestClassifier(502)\n", + "clf.fit(x_tr, y_tr)\n", + "y_ts = clf.predict(x_ts)\n", + "\n", + "print('MCC = ', metrics.matthews_corrcoef(class_lab_ts, y_ts))\n", + "print('ACC = ', metrics.accuracy_score(class_lab_ts, y_ts))\n", + "print('SENS = ', metrics.recall_score(class_lab_ts, y_ts))" ] }, { @@ -393,7 +745,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": { "colab": {}, "colab_type": "code", @@ -401,7 +753,58 @@ "outputId": "099e6404-c7fd-414a-b49a-4092af095c57", "scrolled": true }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "C = 1e-06\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/neeyanthkvk/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py:538: RuntimeWarning: invalid value encountered in double_scalars\n", + " mcc = cov_ytyp / np.sqrt(cov_ytyt * cov_ypyp)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "MCC = 0.0\n", + "ACC = 0.6617647058823529\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-05\n", + "MCC = 0.6310547428675068\n", + "ACC = 0.8308823529411765\n", + "SENS = 1.0 \n", + "\n", + "C = 0.0001\n", + "MCC = 0.9014492753623189\n", + "ACC = 0.9558823529411765\n", + "SENS = 0.9666666666666667 \n", + "\n", + "C = 0.001\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.01\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n" + ] + } + ], "source": [ "## define the sequence of C values we want to use in the search of the best one\n", "C_list = [0.000001, 0.00001, 0.0001, 0.001, 0.01, 0.1]\n", @@ -437,15 +840,167 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": { "colab": {}, "colab_type": "code", "id": "BPtC-EBSLKK_" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "C = 1e-06 gamma = 0.001\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/neeyanthkvk/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py:538: RuntimeWarning: invalid value encountered in double_scalars\n", + " mcc = cov_ytyp / np.sqrt(cov_ytyt * cov_ypyp)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "MCC = 0.0\n", + "ACC = 0.6617647058823529\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-06 gamma = 0.01\n", + "MCC = 0.0\n", + "ACC = 0.6617647058823529\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-06 gamma = 0.1\n", + "MCC = 0.0\n", + "ACC = 0.6617647058823529\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-06 gamma = 1\n", + "MCC = 0.0\n", + "ACC = 0.6617647058823529\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-05 gamma = 0.001\n", + "MCC = 0.6310547428675068\n", + "ACC = 0.8308823529411765\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-05 gamma = 0.01\n", + "MCC = 0.6310547428675068\n", + "ACC = 0.8308823529411765\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-05 gamma = 0.1\n", + "MCC = 0.6310547428675068\n", + "ACC = 0.8308823529411765\n", + "SENS = 1.0 \n", + "\n", + "C = 1e-05 gamma = 1\n", + "MCC = 0.6310547428675068\n", + "ACC = 0.8308823529411765\n", + "SENS = 1.0 \n", + "\n", + "C = 0.0001 gamma = 0.001\n", + "MCC = 0.9014492753623189\n", + "ACC = 0.9558823529411765\n", + "SENS = 0.9666666666666667 \n", + "\n", + "C = 0.0001 gamma = 0.01\n", + "MCC = 0.9014492753623189\n", + "ACC = 0.9558823529411765\n", + "SENS = 0.9666666666666667 \n", + "\n", + "C = 0.0001 gamma = 0.1\n", + "MCC = 0.9014492753623189\n", + "ACC = 0.9558823529411765\n", + "SENS = 0.9666666666666667 \n", + "\n", + "C = 0.0001 gamma = 1\n", + "MCC = 0.9014492753623189\n", + "ACC = 0.9558823529411765\n", + "SENS = 0.9666666666666667 \n", + "\n", + "C = 0.001 gamma = 0.001\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.001 gamma = 0.01\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.001 gamma = 0.1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.001 gamma = 1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.01 gamma = 0.001\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.01 gamma = 0.01\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.01 gamma = 0.1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.01 gamma = 1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.1 gamma = 0.001\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.1 gamma = 0.01\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.1 gamma = 0.1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n", + "C = 0.1 gamma = 1\n", + "MCC = 0.8857501367027195\n", + "ACC = 0.9485294117647058\n", + "SENS = 0.9555555555555556 \n", + "\n" + ] + } + ], "source": [ - "## space for exercise" + "## space for exercise\n", + "C_list = [0.000001, 0.00001, 0.0001, 0.001, 0.01, 0.1]\n", + "gamma_list = [0.001, 0.01, 0.1, 1]\n", + "for C in C_list:\n", + " for gamma in gamma_list:\n", + " print('C = ', C, ' gamma = ', gamma)\n", + " svc = svm.SVC(kernel = 'linear', C=C, gamma = gamma)\n", + " svc.fit(x_tr, class_lab_tr.values.ravel())\n", + " class_pred_ts = svc.predict(x_ts)\n", + " print('MCC = ', metrics.matthews_corrcoef(class_lab_ts, class_pred_ts))\n", + " print('ACC = ', metrics.accuracy_score(class_lab_ts, class_pred_ts))\n", + " print('SENS = ', metrics.recall_score(class_lab_ts, class_pred_ts), \"\\n\")" ] }, { @@ -460,14 +1015,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": { "colab": {}, "colab_type": "code", "id": "utM1ALBfLKLC", "outputId": "d96dc041-2f6f-4f1a-bca5-70310d1f79ee" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "{'C': 0.001, 'gamma': 0.001}" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "from sklearn.model_selection import GridSearchCV\n", "\n", @@ -505,14 +1071,31 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "metadata": { "colab": {}, "colab_type": "code", "id": "2lZAaTXJLKLH", "outputId": "2155231c-e50c-4c06-82c4-6b6a5f7c4ee2" }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n", + " max_depth=None, max_features='auto', max_leaf_nodes=None,\n", + " min_impurity_decrease=0.0, min_impurity_split=None,\n", + " min_samples_leaf=1, min_samples_split=2,\n", + " min_weight_fraction_leaf=0.0, n_estimators=250, n_jobs=1,\n", + " oob_score=False, random_state=None, verbose=0,\n", + " warm_start=False)" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Build a forest and compute the feature importances\n", "rf = RandomForestClassifier(n_estimators=250)\n", @@ -531,14 +1114,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "metadata": { "colab": {}, "colab_type": "code", "id": "rspvHmO0LKLK", "outputId": "7b131d8f-ebc8-4d03-9f38-ad90de735367" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "MCC = 0.8357487922705314\n", + "ACC = 0.9264705882352942\n", + "SENS = 0.9444444444444444\n" + ] + } + ], "source": [ "class_pred_ts = rf.predict(x_ts)\n", "print('MCC = ', metrics.matthews_corrcoef(class_lab_ts, class_pred_ts))\n", @@ -558,14 +1151,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "metadata": { "colab": {}, "colab_type": "code", "id": "7g9k5EHsLKLU", "outputId": "aa26094b-0e4a-48f0-be91-ecd2874ab204" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Feature ranking (top 10 features):\n", + "1. feature 7448 (0.008498)\n", + "2. feature 17952 (0.007474)\n", + "3. feature 450 (0.006937)\n", + "4. feature 16266 (0.006608)\n", + "5. feature 5719 (0.006272)\n", + "6. feature 8357 (0.006259)\n", + "7. feature 21809 (0.006237)\n", + "8. feature 3556 (0.005993)\n", + "9. feature 12169 (0.005958)\n", + "10. feature 3112 (0.005879)\n" + ] + } + ], "source": [ "importances = rf.feature_importances_\n", "indices = np.argsort(importances)[::-1]\n", @@ -588,14 +1199,31 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "metadata": { "colab": {}, "colab_type": "code", "id": "2fSkitN7LKLY", "outputId": "73191a71-9657-4582-ede6-7fb14cd3fc05" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "VPS53.Gene_AceView\n", + "ERCC6L.Gene_AceView\n", + "CHD5.Gene_RefSeq\n", + "dawfloyby.Gene_AceView\n", + "LOC100287397.Gene_RefSeq\n", + "C4orf46.Gene_AceView\n", + "snawjarby.Gene_AceView\n", + "SNORD1C.Gene_AceView\n", + "cheymey.Gene_AceView\n", + "NRBP2.Gene_AceView\n" + ] + } + ], "source": [ "columnsNamesArr = data_tr.columns.values\n", "for i in range(10):\n", @@ -732,7 +1360,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.6.5" } }, "nbformat": 4,