Using OpenML 1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import openml\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(2958, 16)\n",
      "did\n",
      "name\n",
      "version\n",
      "uploader\n",
      "status\n",
      "format\n",
      "MajorityClassSize\n",
      "MaxNominalAttDistinctValues\n",
      "MinorityClassSize\n",
      "NumberOfClasses\n",
      "NumberOfFeatures\n",
      "NumberOfInstances\n",
      "NumberOfInstancesWithMissingValues\n",
      "NumberOfMissingValues\n",
      "NumberOfNumericFeatures\n",
      "NumberOfSymbolicFeatures\n"
     ]
    }
   ],
   "source": [
    "# Fetching the list of all available datasets on OpenML\n",
    "d = openml.datasets.list_datasets(output_format='dataframe')\n",
    "print(d.shape)\n",
    "\n",
    "# Listing column names or attributes that OpenML offers\n",
    "for name in d.columns:\n",
    "    print(name)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   did        name  version uploader  status format  MajorityClassSize  \\\n",
      "2    2      anneal        1        1  active   ARFF              684.0   \n",
      "3    3    kr-vs-kp        1        1  active   ARFF             1669.0   \n",
      "4    4       labor        1        1  active   ARFF               37.0   \n",
      "5    5  arrhythmia        1        1  active   ARFF              245.0   \n",
      "6    6      letter        1        1  active   ARFF              813.0   \n",
      "\n",
      "   MaxNominalAttDistinctValues  MinorityClassSize  NumberOfClasses  \\\n",
      "2                          7.0                8.0              5.0   \n",
      "3                          3.0             1527.0              2.0   \n",
      "4                          3.0               20.0              2.0   \n",
      "5                         13.0                2.0             13.0   \n",
      "6                         26.0              734.0             26.0   \n",
      "\n",
      "   NumberOfFeatures  NumberOfInstances  NumberOfInstancesWithMissingValues  \\\n",
      "2              39.0              898.0                               898.0   \n",
      "3              37.0             3196.0                                 0.0   \n",
      "4              17.0               57.0                                56.0   \n",
      "5             280.0              452.0                               384.0   \n",
      "6              17.0            20000.0                                 0.0   \n",
      "\n",
      "   NumberOfMissingValues  NumberOfNumericFeatures  NumberOfSymbolicFeatures  \n",
      "2                22175.0                      6.0                      33.0  \n",
      "3                    0.0                      0.0                      37.0  \n",
      "4                  326.0                      8.0                       9.0  \n",
      "5                  408.0                    206.0                      74.0  \n",
      "6                    0.0                     16.0                       1.0  \n"
     ]
    }
   ],
   "source": [
    "print(d.head())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}