{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Taking `examples/examples.ipynb` as a starting point. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"%matplotlib inline\n",
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import os\n",
"import sys\n",
"\n",
"sys.path.append(\"..\")\n",
"sys.path.append(\"../..\")\n",
"\n",
"import numpy as np \n",
"import pandas as pd\n",
"import yellowbrick as yb"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from yellowbrick.features import (ParallelCoordinates,\n",
" parallel_coordinates)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Dataset"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from download import download_all \n",
"\n",
"## The path to the test data sets\n",
"FIXTURES = os.path.join(os.getcwd(), \"data\")\n",
"\n",
"## Dataset loading mechanisms\n",
"datasets = {\n",
" \"credit\": os.path.join(FIXTURES, \"credit\", \"credit.csv\"),\n",
" \"concrete\": os.path.join(FIXTURES, \"concrete\", \"concrete.csv\"),\n",
" \"occupancy\": os.path.join(FIXTURES, \"occupancy\", \"occupancy.csv\"),\n",
" \"mushroom\": os.path.join(FIXTURES, \"mushroom\", \"mushroom.csv\"),\n",
"}\n",
"\n",
"def load_data(name, download=True):\n",
" \"\"\"\n",
" Loads and wrangles the passed in dataset by name.\n",
" If download is specified, this method will download any missing files. \n",
" \"\"\"\n",
" # Get the path from the datasets \n",
" path = datasets[name]\n",
" \n",
" # Check if the data exists, otherwise download or raise \n",
" if not os.path.exists(path):\n",
" if download:\n",
" download_all() \n",
" else:\n",
" raise ValueError((\n",
" \"'{}' dataset has not been downloaded, \"\n",
" \"use the download.py module to fetch datasets\"\n",
" ).format(name))\n",
" \n",
" # Return the data frame\n",
" return pd.read_csv(path)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"20560\n"
]
},
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" datetime | \n",
" temperature | \n",
" relative humidity | \n",
" light | \n",
" C02 | \n",
" humidity | \n",
" occupancy | \n",
"
\n",
" \n",
" \n",
" \n",
" | 0 | \n",
" 2015-02-04 17:51:00 | \n",
" 23.18 | \n",
" 27.2720 | \n",
" 426.0 | \n",
" 721.25 | \n",
" 0.004793 | \n",
" 1 | \n",
"
\n",
" \n",
" | 1 | \n",
" 2015-02-04 17:51:59 | \n",
" 23.15 | \n",
" 27.2675 | \n",
" 429.5 | \n",
" 714.00 | \n",
" 0.004783 | \n",
" 1 | \n",
"
\n",
" \n",
" | 2 | \n",
" 2015-02-04 17:53:00 | \n",
" 23.15 | \n",
" 27.2450 | \n",
" 426.0 | \n",
" 713.50 | \n",
" 0.004779 | \n",
" 1 | \n",
"
\n",
" \n",
" | 3 | \n",
" 2015-02-04 17:54:00 | \n",
" 23.15 | \n",
" 27.2000 | \n",
" 426.0 | \n",
" 708.25 | \n",
" 0.004772 | \n",
" 1 | \n",
"
\n",
" \n",
" | 4 | \n",
" 2015-02-04 17:55:00 | \n",
" 23.10 | \n",
" 27.2000 | \n",
" 426.0 | \n",
" 704.50 | \n",
" 0.004757 | \n",
" 1 | \n",
"
\n",
" \n",
"
\n",
"