2017_03_07_DC_Intro/src/clustering_and_pca.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# imports\n",
    "import h2o \n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from h2o.estimators.deeplearning import H2ODeepLearningEstimator\n",
    "from h2o.estimators.kmeans import H2OKMeansEstimator\n",
    "from h2o.estimators.pca import H2OPrincipalComponentAnalysisEstimator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# display matplotlib graphics in notebook\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Checking whether there is an H2O instance running at http://localhost:54321. connected.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div style=\"overflow:auto\"><table style=\"width:50%\"><tr><td>H2O cluster uptime:</td>\n",
       "<td>35 mins 50 secs</td></tr>\n",
       "<tr><td>H2O cluster version:</td>\n",
       "<td>3.11.0.3873</td></tr>\n",
       "<tr><td>H2O cluster version age:</td>\n",
       "<td>5 days </td></tr>\n",
       "<tr><td>H2O cluster name:</td>\n",
       "<td>H2O_from_python_phall_a04e7d</td></tr>\n",
       "<tr><td>H2O cluster total nodes:</td>\n",
       "<td>1</td></tr>\n",
       "<tr><td>H2O cluster free memory:</td>\n",
       "<td>2.969 Gb</td></tr>\n",
       "<tr><td>H2O cluster total cores:</td>\n",
       "<td>8</td></tr>\n",
       "<tr><td>H2O cluster allowed cores:</td>\n",
       "<td>8</td></tr>\n",
       "<tr><td>H2O cluster status:</td>\n",
       "<td>locked, healthy</td></tr>\n",
       "<tr><td>H2O connection url:</td>\n",
       "<td>http://localhost:54321</td></tr>\n",
       "<tr><td>H2O connection proxy:</td>\n",
       "<td>None</td></tr>\n",
       "<tr><td>H2O internal security:</td>\n",
       "<td>False</td></tr>\n",
       "<tr><td>Python version:</td>\n",
       "<td>3.5.2 final</td></tr></table></div>"
      ],
      "text/plain": [
       "--------------------------  ----------------------------\n",
       "H2O cluster uptime:         35 mins 50 secs\n",
       "H2O cluster version:        3.11.0.3873\n",
       "H2O cluster version age:    5 days\n",
       "H2O cluster name:           H2O_from_python_phall_a04e7d\n",
       "H2O cluster total nodes:    1\n",
       "H2O cluster free memory:    2.969 Gb\n",
       "H2O cluster total cores:    8\n",
       "H2O cluster allowed cores:  8\n",
       "H2O cluster status:         locked, healthy\n",
       "H2O connection url:         http://localhost:54321\n",
       "H2O connection proxy:\n",
       "H2O internal security:      False\n",
       "Python version:             3.5.2 final\n",
       "--------------------------  ----------------------------"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# start and connect to h2o server\n",
    "h2o.init()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# load clean data\n",
    "path = 'https://raw.githubusercontent.com/h2oai/app-consumer-loan/master/data/loan.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# define input variable measurement levels \n",
    "# strings automatically parsed as enums (nominal)\n",
    "# numbers automatically parsed as numeric\n",
    "col_types = {'bad_loan': 'enum'}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parse progress: |█████████████████████████████████████████████████████████| 100%\n"
     ]
    }
   ],
   "source": [
    "frame = h2o.import_file(path=path, col_types=col_types) # multi-threaded import"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Rows:163987\n",
      "Cols:15\n",
      "\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th>       </th><th>loan_amnt         </th><th>term     </th><th>int_rate          </th><th>emp_length       </th><th>home_ownership  </th><th>annual_inc       </th><th>purpose           </th><th>addr_state  </th><th>dti               </th><th>delinq_2yrs        </th><th>revol_util        </th><th>total_acc         </th><th>bad_loan  </th><th>longest_credit_length  </th><th>verification_status  </th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td>type   </td><td>int               </td><td>enum     </td><td>real              </td><td>int              </td><td>enum            </td><td>real             </td><td>enum              </td><td>enum        </td><td>real              </td><td>int                </td><td>real              </td><td>int               </td><td>enum      </td><td>int                    </td><td>enum                 </td></tr>\n",
       "<tr><td>mins   </td><td>500.0             </td><td>         </td><td>5.42              </td><td>0.0              </td><td>                </td><td>1896.0           </td><td>                  </td><td>            </td><td>0.0               </td><td>0.0                </td><td>0.0               </td><td>1.0               </td><td>          </td><td>0.0                    </td><td>                     </td></tr>\n",
       "<tr><td>mean   </td><td>13074.169141456332</td><td>         </td><td>13.715904065566189</td><td>5.684352932995338</td><td>                </td><td>71915.67051974905</td><td>                  </td><td>            </td><td>15.881530121290167</td><td>0.22735700606252723</td><td>54.07917280242262 </td><td>24.579733834274574</td><td>          </td><td>14.854273655448333     </td><td>                     </td></tr>\n",
       "<tr><td>maxs   </td><td>35000.0           </td><td>         </td><td>26.060000000000002</td><td>10.0             </td><td>                </td><td>7141778.0        </td><td>                  </td><td>            </td><td>39.99             </td><td>29.0               </td><td>150.70000000000002</td><td>118.0             </td><td>          </td><td>65.0                   </td><td>                     </td></tr>\n",
       "<tr><td>sigma  </td><td>7993.556188734672 </td><td>         </td><td>4.391939870545809 </td><td>3.610663731100238</td><td>                </td><td>59070.91565491818</td><td>                  </td><td>            </td><td>7.5876682241925355</td><td>0.6941679229284191 </td><td>25.285366766770498</td><td>11.685190365910666</td><td>          </td><td>6.947732922546689      </td><td>                     </td></tr>\n",
       "<tr><td>zeros  </td><td>0                 </td><td>         </td><td>0                 </td><td>14248            </td><td>                </td><td>0                </td><td>                  </td><td>            </td><td>270               </td><td>139459             </td><td>1562              </td><td>0                 </td><td>          </td><td>11                     </td><td>                     </td></tr>\n",
       "<tr><td>missing</td><td>0                 </td><td>0        </td><td>0                 </td><td>5804             </td><td>0               </td><td>4                </td><td>0                 </td><td>0           </td><td>0                 </td><td>29                 </td><td>193               </td><td>29                </td><td>0         </td><td>29                     </td><td>0                    </td></tr>\n",
       "<tr><td>0      </td><td>5000.0            </td><td>36 months</td><td>10.65             </td><td>10.0             </td><td>RENT            </td><td>24000.0          </td><td>credit_card       </td><td>AZ          </td><td>27.650000000000002</td><td>0.0                </td><td>83.7              </td><td>9.0               </td><td>0         </td><td>26.0                   </td><td>verified             </td></tr>\n",
       "<tr><td>1      </td><td>2500.0            </td><td>60 months</td><td>15.27             </td><td>0.0              </td><td>RENT            </td><td>30000.0          </td><td>car               </td><td>GA          </td><td>1.0               </td><td>0.0                </td><td>9.4               </td><td>4.0               </td><td>1         </td><td>12.0                   </td><td>verified             </td></tr>\n",
       "<tr><td>2      </td><td>2400.0            </td><td>36 months</td><td>15.96             </td><td>10.0             </td><td>RENT            </td><td>12252.0          </td><td>small_business    </td><td>IL          </td><td>8.72              </td><td>0.0                </td><td>98.5              </td><td>10.0              </td><td>0         </td><td>10.0                   </td><td>not verified         </td></tr>\n",
       "<tr><td>3      </td><td>10000.0           </td><td>36 months</td><td>13.49             </td><td>10.0             </td><td>RENT            </td><td>49200.0          </td><td>other             </td><td>CA          </td><td>20.0              </td><td>0.0                </td><td>21.0              </td><td>37.0              </td><td>0         </td><td>15.0                   </td><td>verified             </td></tr>\n",
       "<tr><td>4      </td><td>5000.0            </td><td>36 months</td><td>7.9               </td><td>3.0              </td><td>RENT            </td><td>36000.0          </td><td>wedding           </td><td>AZ          </td><td>11.200000000000001</td><td>0.0                </td><td>28.3              </td><td>12.0              </td><td>0         </td><td>7.0                    </td><td>verified             </td></tr>\n",
       "<tr><td>5      </td><td>3000.0            </td><td>36 months</td><td>18.64             </td><td>9.0              </td><td>RENT            </td><td>48000.0          </td><td>car               </td><td>CA          </td><td>5.3500000000000005</td><td>0.0                </td><td>87.5              </td><td>4.0               </td><td>0         </td><td>4.0                    </td><td>verified             </td></tr>\n",
       "<tr><td>6      </td><td>5600.0            </td><td>60 months</td><td>21.28             </td><td>4.0              </td><td>OWN             </td><td>40000.0          </td><td>small_business    </td><td>CA          </td><td>5.55              </td><td>0.0                </td><td>32.6              </td><td>13.0              </td><td>1         </td><td>7.0                    </td><td>verified             </td></tr>\n",
       "<tr><td>7      </td><td>5375.0            </td><td>60 months</td><td>12.69             </td><td>0.0              </td><td>RENT            </td><td>15000.0          </td><td>other             </td><td>TX          </td><td>18.080000000000002</td><td>0.0                </td><td>36.5              </td><td>3.0               </td><td>1         </td><td>7.0                    </td><td>verified             </td></tr>\n",
       "<tr><td>8      </td><td>6500.0            </td><td>60 months</td><td>14.65             </td><td>5.0              </td><td>OWN             </td><td>72000.0          </td><td>debt_consolidation</td><td>AZ          </td><td>16.12             </td><td>0.0                </td><td>20.6              </td><td>23.0              </td><td>0         </td><td>13.0                   </td><td>not verified         </td></tr>\n",
       "<tr><td>9      </td><td>12000.0           </td><td>36 months</td><td>12.69             </td><td>10.0             </td><td>OWN             </td><td>75000.0          </td><td>debt_consolidation</td><td>CA          </td><td>10.78             </td><td>0.0                </td><td>67.10000000000001 </td><td>34.0              </td><td>0         </td><td>22.0                   </td><td>verified             </td></tr>\n",
       "</tbody>\n",
       "</table>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "frame.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "bad_loan\n",
      "['loan_amnt', 'term', 'int_rate', 'emp_length', 'home_ownership', 'annual_inc', 'purpose', 'addr_state', 'dti', 'delinq_2yrs', 'revol_util', 'total_acc', 'longest_credit_length', 'verification_status']\n"
     ]
    }
   ],
   "source": [
    "# assign target and inputs\n",
    "y = 'bad_loan'\n",
    "X = [name for name in frame.columns if name != y]\n",
    "print(y)\n",
    "print(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['addr_state', 'verification_status', 'purpose', 'home_ownership', 'term']\n",
      "['emp_length', 'longest_credit_length', 'revol_util', 'loan_amnt', 'annual_inc', 'int_rate', 'delinq_2yrs', 'total_acc', 'dti']\n"
     ]
    }
   ],
   "source": [
    "# determine column types\n",
    "reals, enums = [], []\n",
    "for key, val in frame.types.items():\n",
    "    if key in X:\n",
    "        if val == 'enum':\n",
    "            enums.append(key)\n",
    "        else: \n",
    "            reals.append(key)\n",
    "\n",
    "print(enums)\n",
    "print(reals)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# impute missing values\n",
    "# standardize for both clustering and PCA\n",
    "frame[reals].impute(method='mean')\n",
    "frame[reals] = frame[reals].scale()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "kmeans Model Build progress: |████████████████████████████████████████████| 100%\n",
      "Model Details\n",
      "=============\n",
      "H2OKMeansEstimator :  K-means\n",
      "Model Key:  KMeans_model_python_1494881414327_1523\n",
      "\n",
      "\n",
      "ModelMetricsClustering: kmeans\n",
      "** Reported on train data. **\n",
      "\n",
      "MSE: NaN\n",
      "RMSE: NaN\n",
      "Total Within Cluster Sum of Square Error: 1597695.0117686177\n",
      "Total Sum of Square Error to Grand Mean: 1859349.9953409024\n",
      "Between Cluster Sum of Square Error: 261654.9835722847\n",
      "Centroid Statistics: \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div style=\"overflow:auto\"><table style=\"width:50%\"><tr><td><b></b></td>\n",
       "<td><b>centroid</b></td>\n",
       "<td><b>size</b></td>\n",
       "<td><b>within_cluster_sum_of_squares</b></td></tr>\n",
       "<tr><td></td>\n",
       "<td>1.0</td>\n",
       "<td>102044.0</td>\n",
       "<td>848132.4869012</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2.0</td>\n",
       "<td>6.0</td>\n",
       "<td>1899.4841206</td></tr>\n",
       "<tr><td></td>\n",
       "<td>3.0</td>\n",
       "<td>61937.0</td>\n",
       "<td>747663.0407469</td></tr></table></div>"
      ],
      "text/plain": [
       "    centroid    size    within_cluster_sum_of_squares\n",
       "--  ----------  ------  -------------------------------\n",
       "    1           102044  848132\n",
       "    2           6       1899.48\n",
       "    3           61937   747663"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scoring History: \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div style=\"overflow:auto\"><table style=\"width:50%\"><tr><td><b></b></td>\n",
       "<td><b>timestamp</b></td>\n",
       "<td><b>duration</b></td>\n",
       "<td><b>iteration</b></td>\n",
       "<td><b>number_of_reassigned_observations</b></td>\n",
       "<td><b>within_cluster_sum_of_squares</b></td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:13</td>\n",
       "<td> 0.063 sec</td>\n",
       "<td>0.0</td>\n",
       "<td>nan</td>\n",
       "<td>nan</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:13</td>\n",
       "<td> 0.557 sec</td>\n",
       "<td>1.0</td>\n",
       "<td>163987.0</td>\n",
       "<td>3748306.5105250</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:13</td>\n",
       "<td> 0.762 sec</td>\n",
       "<td>2.0</td>\n",
       "<td>217.0</td>\n",
       "<td>1775427.0474256</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:13</td>\n",
       "<td> 0.885 sec</td>\n",
       "<td>3.0</td>\n",
       "<td>411.0</td>\n",
       "<td>1771667.8630573</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.177 sec</td>\n",
       "<td>4.0</td>\n",
       "<td>747.0</td>\n",
       "<td>1766087.4662912</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.236 sec</td>\n",
       "<td>5.0</td>\n",
       "<td>1522.0</td>\n",
       "<td>1758472.7083499</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.470 sec</td>\n",
       "<td>6.0</td>\n",
       "<td>3710.0</td>\n",
       "<td>1744870.7418730</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.581 sec</td>\n",
       "<td>7.0</td>\n",
       "<td>9178.0</td>\n",
       "<td>1714168.6983033</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.878 sec</td>\n",
       "<td>8.0</td>\n",
       "<td>12886.0</td>\n",
       "<td>1671183.7363382</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.902 sec</td>\n",
       "<td>9.0</td>\n",
       "<td>14173.0</td>\n",
       "<td>1631656.6814824</td></tr>\n",
       "<tr><td></td>\n",
       "<td>2017-05-15 17:26:14</td>\n",
       "<td> 1.926 sec</td>\n",
       "<td>10.0</td>\n",
       "<td>11393.0</td>\n",
       "<td>1609675.5923421</td></tr></table></div>"
      ],
      "text/plain": [
       "    timestamp            duration    iteration    number_of_reassigned_observations    within_cluster_sum_of_squares\n",
       "--  -------------------  ----------  -----------  -----------------------------------  -------------------------------\n",
       "    2017-05-15 17:26:13  0.063 sec   0            nan                                  nan\n",
       "    2017-05-15 17:26:13  0.557 sec   1            163987                               3.74831e+06\n",
       "    2017-05-15 17:26:13  0.762 sec   2            217                                  1.77543e+06\n",
       "    2017-05-15 17:26:13  0.885 sec   3            411                                  1.77167e+06\n",
       "    2017-05-15 17:26:14  1.177 sec   4            747                                  1.76609e+06\n",
       "    2017-05-15 17:26:14  1.236 sec   5            1522                                 1.75847e+06\n",
       "    2017-05-15 17:26:14  1.470 sec   6            3710                                 1.74487e+06\n",
       "    2017-05-15 17:26:14  1.581 sec   7            9178                                 1.71417e+06\n",
       "    2017-05-15 17:26:14  1.878 sec   8            12886                                1.67118e+06\n",
       "    2017-05-15 17:26:14  1.902 sec   9            14173                                1.63166e+06\n",
       "    2017-05-15 17:26:14  1.926 sec   10           11393                                1.60968e+06"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# train k-means cluster model\n",
    "# print summary\n",
    "clusters = H2OKMeansEstimator(standardize=False, k=3, seed=12345)\n",
    "clusters.train(x=X, training_frame=frame)\n",
    "print(clusters)\n",
    "\n",
    "# view detailed results at http://ip:port/flow/index.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "kmeans prediction progress: |█████████████████████████████████████████████| 100%\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th style=\"text-align: right;\">  predict</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        0</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        2</td></tr>\n",
       "</tbody>\n",
       "</table>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# join cluster labels to original data for further analysis\n",
    "labels = clusters.predict(frame)\n",
    "labeled_frame = frame.cbind(labels)\n",
    "labeled_frame[-1].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th style=\"text-align: right;\">  predict</th><th style=\"text-align: right;\">  mean_delinq_2yrs</th><th style=\"text-align: right;\">  mean_int_rate</th><th style=\"text-align: right;\">  mean_emp_length</th><th style=\"text-align: right;\">  mean_longest_credit_length</th><th style=\"text-align: right;\">  mean_loan_amnt</th><th style=\"text-align: right;\">  mean_dti</th><th style=\"text-align: right;\">  mean_annual_inc</th><th style=\"text-align: right;\">  mean_total_acc</th><th style=\"text-align: right;\">  mean_revol_util</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td style=\"text-align: right;\">        0</td><td style=\"text-align: right;\">         -0.145322</td><td style=\"text-align: right;\">      -0.172252</td><td style=\"text-align: right;\">        -0.261724</td><td style=\"text-align: right;\">                   -0.368099</td><td style=\"text-align: right;\">       -0.448524</td><td style=\"text-align: right;\"> -0.123311</td><td style=\"text-align: right;\">        -0.250118</td><td style=\"text-align: right;\">      -0.417512 </td><td style=\"text-align: right;\">       -0.0872035</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        1</td><td style=\"text-align: right;\">          0.15268 </td><td style=\"text-align: right;\">      -0.406632</td><td style=\"text-align: right;\">         0.793992</td><td style=\"text-align: right;\">                   -0.410857</td><td style=\"text-align: right;\">        0.979539</td><td style=\"text-align: right;\"> -2.02388 </td><td style=\"text-align: right;\">        92.01    </td><td style=\"text-align: right;\">       0.0930262</td><td style=\"text-align: right;\">       -0.561096 </td></tr>\n",
       "<tr><td style=\"text-align: right;\">        2</td><td style=\"text-align: right;\">          0.239409</td><td style=\"text-align: right;\">       0.283832</td><td style=\"text-align: right;\">         0.431126</td><td style=\"text-align: right;\">                    0.606499</td><td style=\"text-align: right;\">        0.738868</td><td style=\"text-align: right;\">  0.203356</td><td style=\"text-align: right;\">         0.403167</td><td style=\"text-align: right;\">       0.687861 </td><td style=\"text-align: right;\">        0.143726 </td></tr>\n",
       "</tbody>\n",
       "</table>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# profile clusters by means\n",
    "grouped = labeled_frame.group_by(by=['predict'])\n",
    "means = grouped.mean(col=reals).get_frame()\n",
    "print(means)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "<thead>\n",
       "<tr><th style=\"text-align: right;\">  predict</th><th style=\"text-align: right;\">  mode_purpose</th><th style=\"text-align: right;\">  mode_home_ownership</th><th style=\"text-align: right;\">  mode_addr_state</th><th style=\"text-align: right;\">  mode_term</th><th style=\"text-align: right;\">  mode_verification_status</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "<tr><td style=\"text-align: right;\">        0</td><td style=\"text-align: right;\">             2</td><td style=\"text-align: right;\">                    5</td><td style=\"text-align: right;\">                4</td><td style=\"text-align: right;\">          0</td><td style=\"text-align: right;\">                         1</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        1</td><td style=\"text-align: right;\">             2</td><td style=\"text-align: right;\">                    1</td><td style=\"text-align: right;\">                4</td><td style=\"text-align: right;\">          0</td><td style=\"text-align: right;\">                         1</td></tr>\n",
       "<tr><td style=\"text-align: right;\">        2</td><td style=\"text-align: right;\">             2</td><td style=\"text-align: right;\">                    1</td><td style=\"text-align: right;\">                4</td><td style=\"text-align: right;\">          0</td><td style=\"text-align: right;\">                         1</td></tr>\n",
       "</tbody>\n",
       "</table>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# profile clusters by modes\n",
    "grouped = labeled_frame.group_by(by=['predict'])\n",
    "modes = grouped.mode(col=enums).get_frame()\n",
    "print(modes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# define a function for plotting clusters in 2-d\n",
    "def plot(_2d_labeled_frame):\n",
    "\n",
    "    _0 = plt.scatter(features_pandas[_2d_labeled_frame.label == 0].iloc[0:750, 0], \n",
    "                     features_pandas[_2d_labeled_frame.label == 0].iloc[0:750, 1],\n",
    "                     color='m', marker='^', alpha=.15)\n",
    "\n",
    "    _1 = plt.scatter(features_pandas[_2d_labeled_frame.label == 1].iloc[0:750, 0], \n",
    "                     features_pandas[_2d_labeled_frame.label == 1].iloc[0:750, 1],\n",
    "                     color='c', alpha=.15)\n",
    "\n",
    "    _2 = plt.scatter(features_pandas[_2d_labeled_frame.label == 2].iloc[0:750, 0], \n",
    "                     features_pandas[_2d_labeled_frame.label == 2].iloc[0:750, 1],\n",
    "                     color='g', marker='s', alpha=.15)               \n",
    "                     \n",
    "    plt.legend([_0, _1, _2], \n",
    "               ['Cluster 0', 'Cluster 1', 'Cluster 2'],\n",
    "               bbox_to_anchor=(1.05, 0.0), \n",
    "               loc=3, borderaxespad=0.)\n",
    "    \n",
    "    plt.xlabel('Dimension 1')\n",
    "    plt.ylabel('Dimension 2')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pca Model Build progress: |███████████████████████████████████████████████| 100%\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/phall/anaconda/lib/python3.5/site-packages/h2o/job.py:65: UserWarning: _train: Dataset used may contain fewer number of rows due to removal of rows with NA/missing values.  If this is not desirable, set impute_missing argument in pca call to TRUE/True/true/... depending on the client language.\n",
      "  warnings.warn(w)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "pca prediction progress: |████████████████████████████████████████████████| 100%\n",
      "        PC1       PC2  label\n",
      "0  0.055350 -0.839534      0\n",
      "1 -3.112822  0.793804      0\n",
      "2 -1.266717 -1.537850      0\n",
      "3  0.407435  0.792267      0\n",
      "4 -2.601477  0.798351      0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAArsAAAF5CAYAAACfq+KgAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAAPYQAAD2EBqD+naQAAIABJREFUeJzs3Xt83XWd7/vX93dZtyRNmqZJy7VNy6XItR3LOAfFYWZT\ndXRbkWGsunmMVREYGTcziodzUIGe7d7qCB5mRuHhQYHtUGXczAzInmFGcaaiI0JBkatTSrmUNL3m\ntm6/2/f8sZKQpAlNVlaaZOX95JEHK9/fb/3Wp+vRNu/17ef3/RprLSIiIiIi9ciZ7QJERERERGaK\nwq6IiIiI1C2FXRERERGpWwq7IiIiIlK3FHZFREREpG4p7IqIiIhI3VLYFREREZG6pbArIiIiInVL\nYVdERERE6pbCroiIiIjUrXkddo0x/6cxJjHG3DRm/EZjzGvGmIIx5l+MMatnq0YRERERmT3zNuwa\nY94MXAb8asz4Z4FPDh5bD+SBB40xqaNepIiIiIjMqnkZdo0xjcB3gI8BPWMOfwrYYq39gbX2KeBS\n4Bhg49GtUkRERERm27wMu8BfA/dbax8aOWiMWQksA340NGat7QMeAd5yVCsUERERkVnnzXYBU2WM\n+QBwNvBb4xxeBlige8x49+AxEREREVlA5lXYNcYcB3wN+H1rbVjD6y4BNgC7gFKtrisiIrIAZIAV\nwIPW2gOzXIvIYeZV2AXWAUuBx40xZnDMBd5mjPkkcCpggA5Gz+52AE+8wXU3AH9T+3JFREQWjA8B\nd892ESJjzbew+0PgjDFjdwDPAv/DWrvTGLMH+D3gSQBjzCLgXCp9vhPZBfCd73yHNWvW1Ljk+nX1\n1Vdz8803z3YZ847et6nTe1YdvW9Tp/ds6p599lk+/OEPw+DPUpG5Zl6FXWttHnhm5JgxJg8csNY+\nOzj0NeA6Y8wOKn/wtgCvAv/wBpcuAaxZs4a1a9fWuuy61dzcrPerCnrfpk7vWXX0vk2d3rNpURug\nzEnzKuxOwI76xtovG2NywG1AC/AT4J3W2mA2ihMRERGR2TPvw6619oJxxq4Hrj/qxYiIiIjInDJf\n19kVERERETkihV2p2qZNm2a7hHlJ79vU6T2rjt63qdN7JlJ/jLX2yGfVOWPMWmD79u3bdWOCiIjI\nFDz++OOsW7cOYJ219vHZrkdkLM3sioiIiEjdUtgVERERkbqlsCsiIiIidUthV0RERETqlsKuiIiI\niNQthV0RERERqVsKuyIiIiJStxR2RURERKRuKeyKiIiISN1S2BURERGRuqWwKyIiIiJ1S2FXRERE\nROqWwq6IiIiI1C2FXRERERGpWwq7IiIiIlK3FHZFREREpG4p7IqIiIhI3VLYFREREZG6pbArIiIi\nInVLYVdERERE6pbCroiIiIjULYVdEREREalbCrsiIiIiUrcUdkVERESkbinsioiIiEjd8ma7ABER\nkbkuSBJCa/GNIeVonkhkPlHYFRERmUBsLV3lMt1hSDlJSDsOHb7P8nQa15jZLk9EJkEfT0VERCbQ\nVS6zs1TCAC2ehwF2lkp0lcuzXZqITJLCroiIyDiCJKE7DGl0XRpdF8+Y4cfdYUiQJLNdoohMgsKu\niIjIOEJrKScJmTE9uhnHGe7hFZG5T2FXRERkHL4xpB2H0pgZ3FKSkHIcfPXsiswLCrsiIiLjSA3e\njDYQxwzEMZG1w487fF+rMojME1qNQUREZALL02kAusOQ3igi5Th0ZjLD4yIy9ynsioiITMA1huMy\nGdpTKa2zKzJPKeyKiIgcQcpxSM12ESJSFX08FREREZG6pbArIiIiInVLYVdERERE6pbCroiIiIjU\nLYVdEREREalbCrsiIiIiUrcUdkVERESkbinsioiIiEjdUtgVERERkbqlsCsiIiIidUthV0RERETq\nlsKuiIiIiNQthV0RERERqVvzLuwaYy43xvzKGNM7+PUzY8w7xpxzozHmNWNMwRjzL8aY1bNVr4iI\niIjMnnkXdoFXgM8Ca4F1wEPAPxhj1gAYYz4LfBK4DFgP5IEHjTGp2SlXRERERGbLvAu71toHrLX/\nZK19wVq7w1p7HTAA/PbgKZ8Ctlhrf2CtfQq4FDgG2DhLJYuIiIjILJl3YXckY4xjjPkAkAN+ZoxZ\nCSwDfjR0jrW2D3gEeMvsVCkiIiIis8Wb7QKqYYw5Hfh3IAP0A++z1j5vjHkLYIHuMU/pphKCRURE\nRGQBmZdhF3gOOAtoBi4G7jLGvG12SxIRERGRuWZehl1rbQTsHPz2CWPMeiq9ul8GDNDB6NndDuCJ\nI1336quvprm5edTYpk2b2LRpUy3KFhERmde2bt3K1q1bR4319vbOUjUik2OstbNdw7QZY34EvGSt\n3WyMeQ34irX25sFji6gE30uttX87wfPXAtu3b9/O2rVrj1rdIiIi893jjz/OunXrANZZax+f7XpE\nxpp3M7vGmC8C/wi8DDQBHwLOBy4cPOVrwHXGmB3ALmAL8CrwD0e9WBERERGZVfMu7ALtwJ3AcqAX\neBK40Fr7EIC19svGmBxwG9AC/AR4p7U2mKV6RUTmpSBJCK3FN4aUM68X7xGRBWzehV1r7ccmcc71\nwPUzXoyISB2KraWrXKY7DCknCWnHocP3WZ5O4xoz2+WJiEyJPqqLiMgoXeUyO0slDNDieRhgZ6lE\nV7k826WJiEyZwq6IiAwLkoTuMKTRdWl0XTxjhh93hyFBksx2iSIiU6KwKyIiw0JrKScJmTE9uhnH\nGe7hnY4gScjHsUKziBw1865nV0REZo5vDGnHoZQkNLru8HgpSUg5Dn6VPbvqAxaR2aKZXRERGZYa\nDKEDccxAHBNZO/y4w/erXpVBfcAiMlsUdkVEZJTl6TSdmQwW6I0iLNCZybA8na7qeuoDFpHZpDYG\nEREZxTWG4zIZ2lOpmqyzO9QH3OKN/pGTcRx6o4jQWlLTLVpEZAIKuyIiMq6U49QkhM5UH7CIyGSo\njUFERGbUTPUBi4hMhmZ2RURkxg31+3aHIb1RRMpxptUHLCIyWQq7IiIy42rdBywiMlkKuyIictTU\nqg9YRGSy9LFaREREROqWwq6IiIiI1C2FXRERERGpWwq7IiIiIlK3FHZFREREpG4p7IqIiIhI3VLY\nFREREZG6pbArIiIiInVLm0qIiNShIEm0U5mICAq7IiJ1JbaWrnKZ7jCknCSkHYcO32d5Oo1rzGyX\nJyJy1OnjvohIHekql9lZKmGAFs/DADtLJbrK5dkuTURkVijsiogcZUGSkI9jgiSp+XW7w5BG16XR\ndfGMGX7cHYY1fz0RkflAbQwiIkfJTLcYhNZSThJavNF/tWcch94oIrSW1LRfRURkftHMrojIUTLT\nLQa+MaQdh9KYGdxSkpByHHz17IrIAqSwKyJyFByNFoPU4EzxQBwzEMdE1g4/7vB9rcogIguS/uYT\nETkKhloMMmMCZ8ZxhpcJq4Xl6TSdmQwW6I0iLNCZybA8na7J9UVE5hv17IqIHAUjWwwaXXd4vNYt\nBq4xHJfJ0J5KaZ1dERE0sysiclQc7RaDlOPQ4LoKuiKy4GlmV0TkKBlqJegOQ3qjiJTjqMVARGSG\nKeyKiBwlajEQETn6FHZFRI6ylONovVsRkaNEUwoiIiIiUrcUdkVERESkbinsioiIiEjdUtgVERER\nkbqlsCsiIiIidUthV0RERETqlsKuiIiIiNQthV0RERERqVsKuyIiIiJStxR2RURERKRuKeyKiIiI\nSN1S2BURERGRuqWwKyIiIiJ1a0ph1xiTNcacZ4w5bZxjGWPMpbUrTURERERkeiYddo0xJwPPAtuA\nXxtj/s0Ys3zEKc3At2tcn4iIiIhI1aYys/sl4CmgHTgF6Ad+aow5YSYKExERERGZrqmE3d8BrrXW\n7rfW7gDeAzwI/MQY0zkj1YmIiIiITMNUwm4WiIa+sRVXAPcD/wacXOPaRERERESmZSph9zngt8YO\nWms/CfwDcF+tinojxphrjTG/MMb0GWO6jTF/N9hPPPa8G40xrxljCsaYfzHGrD4a9YmIiIjI3DGV\nsPt3wKbxDgwG3q2AqUVRR/BW4C+Bc4HfB3zgn40x2aETjDGfBT4JXAasB/LAg8aY1FGoT0RmSZAk\n5OOYIElmuxQREZkjvMmeaK3978B/f4PjVwJX1qKoI9TxrpHfG2P+GNgLrAMeHhz+FLDFWvuDwXMu\nBbqBjcA9M12jiBxdsbV0lct0hyHlJCHtOHT4PsvTaVxzND6Di4jIXFUPm0q0ABY4CGCMWQksA340\ndIK1tg94BHjLbBQoIjOrq1xmZ6mEAVo8DwPsLJXoKpdnuzQREZll8zrsGmMM8DXgYWvtM4PDy6iE\n3+4xp3cPHhOROhIkCd1hSKPr0ui6eMYMP+4OQ7U0iIgscPM67AJfB04DPjDbhYjI7AitpZwkZJzR\nf51lHIcgSQitnaXKRERkLph0z+5cY4z5K+BdwFuttV0jDu2hcqNcB6NndzuAJ97omldffTXNzc2j\nxjZt2sSmTePelycic4BvDGnHoZQkNLru8HgpSUg5Dr56dkVqZuvWrWzdunXUWG9v7yxVIzI5xs7D\nWY/BoPte4Hxr7c5xjr8GfMVae/Pg94uoBN9LrbV/O875a4Ht27dvZ+3atTNbvIjU3KulEjtLJRpd\nl8xg8B2IYzozGY7LZGa7PJG69vjjj7Nu3TqAddbax2e7HpGxqprZNcacBPwula2DR/3bobX2xhrU\n9Uav/XUqS6D9ZyBvjOkYPNRrrS0NPv4acJ0xZgewC9gCvEplPWARqTPL02kAusOQ3igi5Th0ZjLD\n4yIisnBNOewaYz4OfAPYT6VlYOTUsAVmNOwClw++zr+OGf8IcBeAtfbLxpgccBuV1Rp+ArzTWhvM\ncG0iMgtcYzguk6E9lSK0Ft8YUs58vyVBRERqoZqZ3euA/9ta+6VaFzMZ1tpJ/QSz1l4PXD+jxYjI\nnJJyHLRzjIiIjFTN1Mdi4LC+VxERERGRuaaasPu3wIW1LkREREREpNaqaWPYAWwxxvw28GsgHHnQ\nWntLLQoTEREREZmuasLuZcAAcP7g10gWUNgVERERkTlhymHXWrtyJgoREREREam1aa3NYwbVqhgR\nERERkVqqKuwaYy41xvwaKAJFY8yTxpj/UtvSRERERESmp5pNJf6Myo5kfwX8dHD4POBWY0zb0Ba9\nIiIiIiKzrZob1K4CrrDW3jVi7D5jzNNUNnFQ2BURERGROaGaNoblwM/GGf/Z4DERERERkTmhmrC7\nA7hknPE/Av5jeuWIiIiIiNRONW0MXwC+Z4x5G6/37P4fwO8xfggWEREREZkVU57Ztdb+L+BcYD+w\ncfBrP7DeWvt3tS1PRERERKR61czsYq3dDny4xrWIiIiIiNTUpMKuMWaRtbZv6PEbnTt0noiIiIjI\nbJvszO4hY8xya+1eoAew45xjBsfdWhUnIiIiIjIdkw27FwAHBx//7gzVIiIiIiJSU5MKu9bafxvv\nsYiIiIjIXDbl1RiMMe8wxpw34vs/Mcb80hhztzFmcW3LExERERGpXjWbSnwFWARgjDkDuAn438DK\nwcciIiIiInNCNUuPrQSeGXz8fuB+a+3/ZYxZSyX0ioiIiIjMCdXM7AZAbvDx7wP/PPj4IIMzviIi\nIiIic0E1M7sPAzcZY34KrAf+aHD8ZODVWhUmIiIiIjJd1czsfhKIgIuBK6y1uwfH3wn8U60KExER\nERGZrinP7FprXwbePc741TWpSERERESkRqppY8AY4wCrgXbGzA5ba7fVoC4RERERkWmbctg1xvw2\ncDdwIpUtgkfSdsEiIiIiMmdUM7N7K/AY8AdAF5WAKyIiIiIy51QTdk8CLrbW7qh1MSIiIiIitVTN\nagyPUOnXFRERERGZ06qZ2f1L4KvGmGXAr4Fw5EFr7ZO1KExEREREZLqqCbv/a/D/3xoxZqncrKYb\n1ERERERkzqgm7K6seRUiIiIiIjOgmk0lXpqJQkREREREaq2aG9QwxvwXY8xPjTGvGWNOHBz7r8aY\n99a2PBERERGR6k057BpjrgBuAv430MLrPbo9wH+tXWkiIiIiItNTzczuVcDHrbX/DYhHjD8GnFGT\nqkREREREaqCasLsSeGKc8TLQML1yRERERERqp5qw+yJw9jjj7wCenV45IiIiIiK1U83SYzcBf22M\nyVBZW3e9MWYTcC3wsVoWJyIiIiIyHdUsPfb/GWOKwP8D5IC7gdeAT1lrv1vj+kREREREqlbNzC7W\n2r8B/sYYkwMarbV7a1uWiIiIiMj0VRV2h1hrC0ChRrWIiIiIiNTUlMOuMWYJcCPwu0A7Y25ys9a2\n1qY0EREREZHpqWZm938Cq4HbgW7A1rQiEREREZEaqSbsvhU4z1r7q1oXIyIiIiJSS9Wss/sckK11\nISIiIiIitVZN2L0S+G/GmPONMUuMMYtGftW6QBERERGRalXTxtADLAIeGjNuqPTvutMtSkRERESk\nFqoJu38DhMAH0Q1qIiIiIjKHVRN2TwfOsdY+X+tiRERERERqqZqe3ceA42tdyGQZY95qjLnPGLPb\nGJMYY/7zOOfcaIx5zRhTMMb8izFm9WzUKiIiIiKzq5qw+5fA/2uM+WNjzDpjzJkjv2pd4DgagF9S\nuVHusBYKY8xngU8ClwHrgTzwoDEmdRRqExEREZE5pJo2hu8N/v9bI8YsR+kGNWvtPwH/BGCMMeOc\n8ilgi7X2B4PnXEqlt3gjcM9M1iYiIiIic0s1YXdlzauoEWPMSmAZ8KOhMWttnzHmEeAtKOyKiIiI\nLChTDrvW2pdmopAaWUZldrl7zHj34DERERERWUAmFXYHbwL7R2ttON4NYSNZa++rSWUiIiIiItM0\n2Zndv6cyM7p38PFEZntTiT1Ueoc7GD272wE8caQnX3311TQ3N48a27RpE5s2bapljSIiIvPS1q1b\n2bp166ix3t7eWapGZHKMtfN3TwhjTAJsHDmbbIx5DfiKtfbmwe8XUQm+l1pr/3aC66wFtm/fvp21\na9cehcpFRETqw+OPP866desA1llrH5/tekTGquYGtVlljGkAVlOZwQXoNMacBRy01r4CfA24zhiz\nA9gFbAFeBf5hFsoVERERkVk0pbBrjHGAPwYuAlZQaVt4Efg+8D/t0Zkm/i3gx4OvbYGvDo7fCWy2\n1n7ZGJMDbgNagJ8A77TWBkehNhERERGZQyYddgfXtL0PeBfwK+DXVGZX1wB3UAnAG2tf4mjW2n/j\nCJthWGuvB66f6VpEREREZG6byszuHwNvA37PWvvjkQeMMRcAf2+MudRae1cN6xMRERERqdpUtgve\nBHxxbNAFsNY+BPwP4EO1KkxEREREZLqmEnbPZHCb3gn8I3DW9MoREREREamdqYTdVg7fmWykbmDx\n9MoREREREamdqYRdF4je4HjMPFzKTERERETq11TCqQHuMMaUJzierkE9IiIiIiI1M5Wwe+ckztFK\nDCIiIiIyZ0w67FprPzKThYiIiIiI1NpUenZFREREROYVhV0RERERqVsKuyIiIiJStxR2RURERKRu\nKeyKiIiISN1S2BURERGRuqWwKyIiIiJ1S2FXREREROqWwq6IiIiI1C2FXRERERGpWwq7IiIiIlK3\nFHZFREREpG4p7IqIiIhI3VLYFREREZG65c12ASLTFcQB1trDxo0xpNzULFQkIiIic4XCrsxrQRzw\n7L5nKUWlw45lvAxrlq5R4BUREVnAFHZlXrPWUopK+K4/KtQGcUApKo074ysiIiILh8Ku1IWUmzps\nBjeMw1mqRkREROYK3aAmIiIiInVLYVdERERE6pbaGGRKprPywUyumhDEwRt+LyIiIguTwq5M2mRX\nPhgv1AZxwPMHnidO4jd87tjnHCkcG2PIeBlKUemwHt2Ml8EYM+Vfp4iIiNQPhV2ZtIlWPsgHefrK\nfZTCEuWozHP7n6O/3F85aCrPC+KAV3tfZVXrKloyLWAYDsbjrZow2WCdclOsWbpG6+yKiIjIuBR2\nZcpGrnwQxAGv9L1CX6kPgDAJeaLrCfbm92KxONYhsQnlpMyB/AH25PewavEqGlONdLZ2knJT466a\nMJUlxRRoRUREZCIKuzJpSZCMOx7EAa7j4rs+Ow7u4OFdD7O/uB8Axzi4xsUYQ0RE55JOPNejHJfB\nAkfoMtCSYiIiIjIdCrsyKcGBgMKrBUqpErbJknJen9ktBkWiJCKMQgbKAxwsH6QYFXGNi2McPKcS\nbqM4IoojfMevnB+HWFNpcShH5eHXMsYQxAH5II+1dvTMbhIQxdFR//WLiIjI/KSwKyRBgpOaeBW6\nqD+i/5F+eku9PN/4PN3p7uE2giiJ2HlgJwPRADsO7aC/1M/+wn6KYRHXcUmbNLl0jiCqtB905bso\nhpVw/NyB5wiSgDiu3LQ2FGpdxyVfzrPtpW04OHju679NHRyWLVrGWcvOIu2lZ/BdERGRucAYcwLQ\nNtt1yJy031r78pFOUthd4KL+iNJLJTInZvCavFHBd+hx8cUihR0FWA5hb0gpVyLXlMNgKJaKvNT/\nEj3FHvYM7CGIAvb27yWMQxzHocFvwHEdrLVYLPlyfvjmtWJYJONnaE4305BqGL5hLR/kKUQFEhIy\nfoaMm6nUmkTkwzzlsKxtgEVEFgBjzAmO4zyfJElmtmuRucdxnJIx5pQjBV6F3QUu3BtSfqWMm3MB\nhoPv0GOv1aPwdAEn6+DFHsuCZdiCpXVxK3uDvezbv4+efA+HyofoKfaQJAn5ME+QVNa5DeKAclzG\nd31MYjhUPEQpKnFK2ymk3BQtmRZS3ui+3Dx5DIasl8V3/OHlw4wxGAwpL6UlxUREFoa2JEky3/nO\nd1izZs1s1yJzyLPPPsuHP/zhDJVZf4VdGV/UH1H4jwJRb0TxxSJxf0ywL6gEXwvlV8oMPDtA/pk8\njW9qJIoi4t6YfE+efClPV66LX+/7NXsLeykkhUoYtYbQhsRUWhPCOCRwAuIkxjUuh4qHeOHgC6xu\nXV353TeYWcfbBKKjoYPGVOPwOWEc0lfq45imY4aXM9NKDCIi9W/NmjWsXbt2tsuQeUphdwErvlik\n/8l+vCaPuBgT9URkTshUgm8hJtwf0r+9H0ylfSHIBfzHwf9ge7Cd519+nv5UPwNmgD7bVwm343QW\nDI07rkPaTZNyU7w28BpP732atJ+myW/C9Vx8p7LE2PGLjicf5tl5cCf7i/tJe2kOFA4QJVHlK45I\nSPBdn6ZUE6e2nToq8GptXRERERlJYXeBivoj8r/MEx4IcRtcwgMhUU9EdmWWcF9I0B0QHggrbQ0n\nZMj/Mk+xrUipt0S/6acr10WYhJSd8vAs7nhiYnqjXrzII23SFIMi+4v7sVgavUayqSxpN01rQyvG\nGnpKPZSjMq/2vYrv+aRsiiAJhpcvS2yCa1x29+4mTEJKUWlUuJ1oNzYRERFZmBR2F5ihtXKLLxYp\n7iri5lzivpiwJ8Rf7FN6tUSwL6DUVSLqjYjLMVE+Ii7EDPQN4LQ7FOMiA84ASZQQpyYOuiNFRJXN\nJcIy4UBIk99Ec6aZYxcdi5t28fCIbYxvfBzPwTEOPj5BVFmWzDc+GPBdn4ZUA9ZaXNcdvrENxt9w\nQkRERBY2hd0FJOqPyD+TJwkSSi+WiPtj3BaXclcZG1rcnEv/4/0MPDNA3B9DDFFfhJtyCf2QncFO\nCkGB/KI8ISFMvFrZuJLB/8pRmd6gl5iYlmwLq1tXc1LrSUQ24tS2Uytr6SYRa9rW4Ls+z+9/nqyX\nBaAYFzm59WReOPTC8JbDI2dxteGEiIiIjKSwu4CUd5cpPlckHAhJSgmp5Snicoy3xMOGliRMKO0q\nUXimQHl/Gcd38Bo88j154oaYYkuR8v4yhVwBUkACBFQeT5LBDPf2JklCKSwBlRlbYysrLRCB53g0\npBtIOSlyqRxZP4u1FhMZfNev9VsjIiIyp61YsYILLriAb33rW7Ndyrwzxbk5ma+Ku4r0PNxDsbtI\n4dkChZ0Fgn0BhWcL2KDSElDaXSLqj4iDGFuwJOUE4xmS/oQoH1GICryYfpEDzoHXLzzF1liLpUyZ\nrr4uXul9hV2HdvFy78v0lfsqKzdEwahly4I4IIxDCkGBYlQkTMLKWKIZXBERmf927tzJJz7xCVat\nWkU2m6W5uZnzzjuPW265hVKpNHzeTC65WSwWueGGG9i2bduMvcZEbr/9dk477TSy2Swnn3wyf/VX\nf1Xz19DM7gIQ9Ucc/OFBBp4cIB6ISfIJYW/IwMAANraEB0OyK7KUdlb6dG2xMvVqA0tcjMFAYhMs\nltANsbGd9u+cUlIiSAL25vfy9N6nSbkpmrPN9JX6cBwHx3EI45AoqfT6DgQDQKVtoRAWiJOYlJca\n1bYw3vJlIiIic9UDDzzAJZdcQiaT4dJLL+X0008nCAIefvhhrrnmGp555hluvfXWGa+jUChwww03\nYIzhbW9724y/3pDbbruNK664gj/8wz/kz//8z/nJT37Cn/7pn1IsFvnMZz5Ts9dR2K1DY7f/zf86\nz8ATA4QHQ+J8jJN1KOwqEPfGlZvS8iWC/QEkEO2v3JSGB0QQ9oV4GY+kJ8FZ7JDry5HKpWBop94p\ntjEM1zj438HgIL858Bt6S70saVjCK4tewXM9zuk4h/ZcO63ZVo5tPJYkSTDGkPEzpNwUaS9dmQUe\nnP0dkvEy2nBCRESOyFpLnI/xGmcnCu3atYtNmzaxcuVKHnroIdrb24ePXXHFFWzZsoUHHnjgqNQy\nUzd2FwoFcrncuMdKpRLXXXcd73nPe/je974HwEc/+lHiOGbLli1cdtllNDc316QOtTHUmag/ovCb\nAlF/NPx97/Zeov6I4FBAnI8ZeHaAsDsk6U8Ie0LKe8oUnitQ3FWszOwGttKPmwB9EJUibGSJkogD\n7gGKXrFm9drBBt7IRhTKBWIb0z3Qzc93/5w7f3Un9zxzD3f+6k6+/atvc9eTd/HPO/+Z5/Y/V1m6\nLN3IaUtP4+xlZw9/adkxERGZjKgnorijSNQXzcrrf+lLXyKfz3P77bePCrpDOjs7ueqqqyZ8/vXX\nX4/jHB7rs8JsAAAgAElEQVTj7rjjDhzH4eWXX99U7LHHHmPDhg0sXbqUXC5HZ2cnH/3oRwF46aWX\naG9vxxgzfE3HcbjxxhuHn//8889z8cUXs2TJErLZLG9+85u5//77R73unXfeieM4bNu2jSuvvJKO\njg6OP/74Cev/8Y9/zMGDB7nyyitHjf/Jn/wJAwMDNQ36mtmtM+HekGBPZRc0r8mj8FyBYHeAjS3R\nvog4H1N+rQwhkEByKKmEWgu2YF/fGMKtjBECvWAWGYIgoCfTQ+SM+YuhytndIf1BP77rE8URewb2\nVHp2DRwqHOKU1lMY8Acqn8CTGIMhl6p8SiwEhcM+jWpnNRGRhclaW9nmvsXDb3njG5ltYgm6AsJ9\nIU6Dg9vkHvFfBa212NjieLWZJ/zBD35AZ2cn5557blXPN8aMW/PY8X379rFhwwba29u59tpraWlp\nYdeuXdx7770ALF26lFtvvZXLL7+ciy66iIsuugiAM888E4Cnn36a8847j+OOO45rr72WhoYG7rnn\nHjZu3Mi9997Le9/73lGvf+WVV9Le3s4XvvAF8vn8hPU/8cQTAKxbt27U+Lp163AchyeeeIIPfvCD\nVbwzh1PYrSNRf0SwL8Br9gj2BuBA8aUi/hKfqDeCVGVFBkJgKK8GDG/HC1Tm+mMqYbdh8HiJSotD\nUNm9zEu8189hxHWqzJcREb3FXspembSXJu2l8Y1PEAdENgJbWZ0hTmKiOCKIAxwcdvXswmIPC7ba\nWEJEZOGJ+2KC1wLiQoy3yMM4E4fXqDciPBjit/mViaCOynPeSPm1MvFATO7k3LTb5fr7+9m9ezcb\nN26c1nUm42c/+xk9PT388Ic/5JxzzhkeH5q5zeVyvP/97+fyyy/nzDPPPCxgfupTn2LFihU8+uij\neF7lPbriiis477zz+OxnP3tY2G1ra+NHP/rREd+jrq4uXNelra1t1Ljv+yxZsoTXXnut6l/zWAq7\ndSTcG2JDi9/qU9xZpO+Xfdi8JdgTUNhZoPxyGQ5SCbsjjZwcHdojIg0mZ7CRBQeCQsDe7F4iokog\nrnF7T5kycRSzr7iP1kwrBsNvDv6G3rAXbCXABnHASz0vsbewl+MWHUcxKOI7lU0mhmhjCRGRhcda\nS7m7XPlXzAMRUU+E3zr+7O7QrK5xDG6DW/kXz+7yG87uxqWYoCsgKSVE7RH+4uktgdnX1wdAU1PT\ntK4zGS0tLVhrue+++zjjjDOGA+tkHDp0iB//+Mds2bKF3t7eUccuvPBCbrjhBrq6uli+fDlQmVX+\n+Mc/PqkPA8VikVRq/EmpTCZDsVi7lkn17NaJkbO6AEkxofximTAfEvVFlLsqn0gnLQTbZ6E4+Nha\nHBw6+jrIFrLjh91pLoYQEVEOyhSCAv1hP73FXrr7uukt9+IYh6yXJe2lSWxCISgQ2MEXtCO+RERk\nwYn7YqL9Ed5iD+MZynvK2GT8HwpDs7puc+WfJ70WrzK72z/xz8hwf0hSSMBA0BVMe0Jl0aJFQGWG\nd6adf/75XHzxxdx44420tbWxceNG7rjjDoLgyD+0d+zYgbWWz33ucyxdunTU1/XXXw/A3r17Rz1n\nxYoVk6orm81OWEOpVCKbzU7qOpNRtzO7xpg/AT4NLAN+BVxlrX10dquaOeHekCRI8Jq94W1+U0tS\nhIXKH+gkn0CGysebAV5vY5jIBB+ovMjDwZn4Y9I0+3dLSQmn7FCMihS9IgPxAKlCiiROWJxdTMbL\nUI7LvNz3MnEc0+Q3DffwApVA3tRRfQEiIjKvDM/qWouTcjDNhvBAOO7s7tCsro0tNrLEUSXgJkEy\n4exuXIor98I0upi0ITw4eO1pzO42NTVxzDHH8NRTT1V9jQlnoePDQ/s999zDL37xC+6//34efPBB\nNm/ezE033cTPf/7zCVdLgMrmTwCf/vSn2bBhw7jnrF69etT3kw2py5cvJ45j9u/fP6qVIQxDDhw4\nwDHHHDOp60xGXYZdY8wfAV8FLgN+AVwNPGiMOdlau39Wi5sBSTkhGohwPIfoUER5d5noYARpiF6u\nrM4QBzGO45DEyZGD7gRiJ6acLhM78Yz9m4DB4OAQJREDwQDFsAgGCmGBxnQji9KLOLl8MksalrAo\nu4isnyXrV/5ghXFIMSyqhUFEZAEZntUd/JdN45nh2V2vZXTvbhIkJFGCm3MrKw8NchtcbLkSgI0/\nOkQOzer6HX7l5i/HEHQFlWtPo3f33e9+N9/85jd55JFHqrpJbfHixUClJWJophgqS5qNZ/369axf\nv54tW7awdetWPvShD/Hd736XzZs3T/jr6OzsBCp9tBdccMGUa3wjZ599NtZaHnvsMd7xjncMjz/6\n6KMkScLZZ59ds9eq1zaGq4HbrLV3WWufAy4HCsDm2S1rZjhph9xJORrPaiTTmcFr88idkqvcjepV\ndk9LCgnJQAIT3xh5RCYxpMtp3MStrOAwkWm0MyQkGMeQcTM0+A3k/Bztje2c1HoSp7SeQkdjB4tz\ni+lo6mB5Y6VHKIzD4YCrndVERBaWYF9AUkyIeiKCvQHB3oAkSIh74sOWFXMzLg2nNdB4duNhX7lT\nczj+6Fg0NKvr5BxIwMYWt8kdnt2djmuuuYZcLsfHPvaxw1oBAF544QVuueWWCZ+/atUqrLWjdj3L\n5/Pcddddo87r6ek57LlnnXUWAOVyGWB4dnfsuUuXLuXtb387t912G3v27DnsOvv3Vz9/eMEFF9Da\n2so3vvGNUePf+MY3aGho4A/+4A+qvvZYdTeza4zxgXXAF4fGrLXWGPND4C2zVtgMc3OV3qNgT4Bx\nDUlQme0NugOiYlSZzQ1445D6BiInYiA3QORFlN3yjM7seniVtQNNZf3dKIkoJSXCYkgxKpJ20jjG\nIYxCDhYP4rs+xy46FoA4ibWxhIjIAuIv8fGaxo8zbtY9bGwqS4fFffFwy0NSHvED1DDtVobOzk7u\nvvtuPvCBD7BmzZpRO6j99Kc/5fvf/z4f+chHJnz+hRdeyAknnMDmzZv5zGc+g+M4fPvb36a9vZ1X\nXnll+Lw777yTr3/967zvfe9j1apV9Pf3881vfpPm5mbe9a53AZUbwk477TS+973vcdJJJ9Ha2srp\np5/Om970Jv76r/+at771rZxxxhl8/OMfp7Ozk+7ubv793/+d3bt3Dy8hBlPbnCKTybBlyxY++clP\ncskll7Bhwwa2bdvG3XffzRe/+EVaWlqqeFfHV3dhF2ijsihW95jxbuCUo1/O0TPUzkAC4Z6QcG9I\ntC/CWDPtm7f8xGdJ/xIGMgM0Bo0csAdGL1k2VhW9u2bwgmVbxo1cMJXwahNLa7oV4xiiJCLtpWnO\nNrNqySo8xyNKIk5dcioYyAd5Tm07VcuOiYgsENNdGeENr73Er8zqjmPkTqXVes973sOTTz7JV77y\nFe677z5uvfVWUqkUp59+On/xF3/BZZddNnzu2PVzPc/j7//+77nyyiv5/Oc/z7Jly7j66qtpbm5m\n8+bX/yH7/PPP59FHH+V73/se3d3dNDc3c+6553L33Xdz4oknDp93++23c9VVV/Fnf/ZnBEHAF77w\nBd70pjexZs0aHnvsMW644QbuvPNODhw4QHt7O+eccw6f//znR/16pjrRdMUVV5BKpfjqV7/K/fff\nz/HHH8/Xvva1N9xMoxqm3vobjTHLgd3AW6y1j4wY/xLwNmvtYbO7xpi1wPbt27ezdu3ao1fsDIgL\nMVgID4UMPD3Anu/uof+R/spNa/vjqlsMAjfgqWOf4sWlL/Kvq/+Vp1Y8NXqd3fFMIW86OMOzumkv\njTEGz1T6oTJehrM7zsbzPMpRmf+06j+xJLeExnQjBkMxLHJqWyXshnHI2cvOJu2lj/yiIiIybY8/\n/vjQxgDrrLWP1/La9fTzWWprKr/v6nFmdz+V1WLH3pLfARzecDLC0CeikTZt2sSmTZtqWuBMGmpn\ncBtcknKC1+iRbk9jscQHprD02Dg865GO0rSUW3Bih8StsidiHMlgf0WKFK51CW1Y2UrYQGxjdg/s\nrty85jgYY2jwG4iTmDAJKUUl8mGelJtSC4OIyAzaunUrW7duHTU2dv1Vkbmm7sKutTY0xmwHfg+4\nD8BU0s/vARN3egM333xzXX1yLP5HsbJ2oI1JoukHU4PBiz0c4+DgDAfUWjIYfN8nCAMSk+CaSniP\nB3e78K1Pzs/R2dqJ71Z2WcsHec7qOGt4RlgtDCIiM2O8CaARM2wic1Ldhd1BNwF3DIbeoaXHcsAd\ns1nU0RT1RRR3FbFRZTOIpJhM+6YyN3ZZ2reU5v5mnGRm7lArUsQEhjAJSTkpWhpacF2XkxefjO/6\nJDbhhOYT8N3Xe7RSbmp4m2ERERGRkeoy7Fpr7zHGtAE3Umlf+CWwwVq7b3YrO3q8RR6p9hS503I4\nux2CAwHl/vKEm0UcicGQilOUvTLZ8gQ7qNWAiwsWLJZyUqav3IcxhucPPE9rtpWmdBM7D+6kMdU4\nHHjVuiAiIiITqcuwC2Ct/Trw9dmuY7ZEfVFlcezEEB+KcdIOlKq/nh/7HHPwGF5of6GyusORJnar\n7CSIiQlsUOnXBVxT2c3Gczxa0i2sbF3JytaVnNlx5vBMrloXREREZCJ1G3YXOm+RR9Obm4j6IpI4\nIdgXVG7bc4Eq71PzEo/EJGRtlmyQJfCCI6/IMEV28D/PeFgsKS+F7/iVdXeBnJ9T24KIiIhMWr3u\noCZA0pcQ98f4LT7FA8VK60EN2g9SYYpckKushTuR6W5kZgcXp7aVXdHyQZ7ABmT9LI5+24qIiMgk\naWa3TiXlhOIrRaLeiIEXBrAHLPhMq5VhiLEGxzrDm0CMaxqhOiHBdVxcXJqzzfiOz+L0Yta0reF3\njvsdcqlc9RcXERGRBUVht465Obey+8tOh1RHiqQ5IXgpqHpjiSGOdUiFKfzEJ2J6e4OPx8WlwW/A\ndV2WNy3HMx5ZP0vaS+O5+i0rIiIik6fkUKectEOqPUXplRJO2mHRuYsovVIi7A2xPRYSqDqnGshE\nGVJhimKqWJO+XYPBxyftpmlMN3JCywlESYS1llJUqmwLHEdENqLZa9bqCyIiIjIpCrt1Kikn2NgS\n9UW4aRcn51DeXcZpcohLMRSmfk2DIR2nSYdpGsoNpJIUbuwSm3ha3d9Zk8VzPXzHpzHdSFuujY5c\nBxZLS7aFxCYszizm5LaTOavjLJrSTVp9QURERCZFYbdOOelK60KqJQUnQ/43eZJ8goODWWKITFTp\n3y1P/pp+7LNq7yo6DnWQLWV56E0PES+LGUgPEKSCqgKvh0eD30DaT5P1s7SkWli+aDnLm5YDsLxx\nOb7j05prpbO1k8ZUo4KuiIgsOCtWrOCCCy7gW9/61myXMu/otvY6ll6WpvWdrbS9q42m05rwFnt4\njR6plhRuk4tpMVP+uOPHPg1hA83lZprKTWTjLOkkTbU7B7u4+K5PLpWjs7mTNUvXcErrKSxftJxj\nmo5hRcsKVrauZGluqUKuiIjUnZ07d/KJT3yCVatWkc1maW5u5rzzzuOWW26hVHr9rvKZbN8rFovc\ncMMNbNu2bcZeYzzf+MY3uOSSSzjxxBNxHIfNmzfPyOtoZrfOpdpSpNpSJHFCXIyJ1kYE3QHpl9MU\nXi5QDsuQZ0ozvACpOEVHbwf7G/dDAyQNCflMfkq/o7JkyaVzLFu0jKZ0E6d1nMZxi44j7adp8pto\nSDfQubiTlJMiSALCeLrrmYmIiMwdDzzwAJdccgmZTIZLL72U008/nSAIePjhh7nmmmt45plnuPXW\nW2e8jkKhwA033IAxhre97W0z/npDvvzlLzMwMMD69evZs2fPjL2Owu4C4XouTWc04S3xKO4oUn6l\nDNvAeIbyK2XsgK3csDaJPGkwNJWbeFPXmyg3lHF9F5uxLMovoi/bR+zGlNyJ1zgzGFY0r6At00Zr\nQyvnn3A+vudzevvpNKWbKMdlWtItpLzU67O5MQq7IiJSM9ZaImvxjJmVm5537drFpk2bWLlyJQ89\n9BDt7e3Dx6644gq2bNnCAw88cFRqsbYGi/CPo1AokMtNvFzotm3bOP744wFoamqakRpAbQwLQlJO\niAYi3EaXuD/GlixBT4BNLE7awck6mObBloaJVlbIAh1AE/hZnxPDEzmj9wze/OqbOefVc1jRt4LV\nvas5oXgCx7rHsjS1FB+fDBla3BYanUba/DaWpJZwbMOxvPWEt3LhSRfyvjXv43c7f5dzjzuX3zn+\ndziz40wa/AaGlvAN4mD4S0REZLqstewLAp7K5/nVwADP5PPsD4IZC3wT+dKXvkQ+n+f2228fFXSH\ndHZ2ctVVV034/Ouvv354d9GR7rjjDhzH4eWXXx4ee+yxx9iwYQNLly4ll8vR2dnJRz/6UQBeeukl\n2tvbMcYMX9NxHG688cbh5z///PNcfPHFLFmyhGw2y5vf/Gbuv//+Ua9755134jgO27Zt48orr6Sj\no2M4yE7kSMdrRTO7C4CTdsidlBve6CFcHZI6PkXupBz5J/OUd5eJShHFF4qUu8qVloYylfMTKh+J\n0uA6LmaJwW/zaWhowDZY+jv66V/ST8+iHpwBh6amJtzFLoeCQ7yaf5XsoixLGpbQV+qjOdNMb7mX\nRelFdC7upDXbOryygjGGtJfGGEPGy1CKSofN5Ga8jJYcExGRwyTW0hdFFJMExxgWuS5Zd/zZmz1B\nwI5ikZQxpB2H/jimp1Dg5FyOpamjd2/ID37wAzo7Ozn33HOrer6ZYEZ67Pi+ffvYsGED7e3tXHvt\ntbS0tLBr1y7uvfdeAJYuXcqtt97K5ZdfzkUXXcRFF10EwJlnngnA008/zXnnncdxxx3HtddeS0ND\nA/fccw8bN27k3nvv5b3vfe+o17/yyitpb2/nC1/4Avl8vqpfW60p7C4Qbu71P/Rug4vf6tNwWgOp\n9hThgZCgKyB9TJqBJwaICzFxMQYX3KwLIaSOS+E1eKSOSZE7OUd8MCYOYjLZDKbNEEYhA94AJmtI\nZ9OEbkhL1EJ7up2VbSvZX9pPS7qFvcW9tOXaWNG8As/zwFZmb4f+YKbcFGuWrhn3E7YxRjepiYjI\nKLG1vFgssmdwdtYCWddlZSZD25jwGiYJXUFAznFo8ioRKOe69EQRrwUBrb6POyZAJtZyIAw5EIYk\n1rLY91ni+6TGmVWdrP7+fnbv3s3GjRurvsZk/exnP6Onp4cf/vCHnHPOOcPjQzO3uVyO97///Vx+\n+eWceeaZfPCDHxz1/E996lOsWLGCRx99tPJzm0qbxXnnncdnP/vZw8JuW1sbP/rRj+bU5JTC7gLl\n5lyCrgDjG9wGl/SxaYxnCPeHJH0JNrBgwGlywAXHOJiMIb00jd/k4zV4RIciUm0pjl1yLNkwS7A0\nYFdpF67v8qrzKu1OO8c2HkvToiY816M53YzFsji7mFJcwscn5aaIbEST3zQq8IqIiEzG/jCsBFXP\nGw6gPVHES+UyTZ5HekQoLSUJxTim1fdHXSPnOAzEMUGSjJoRttayq1Rid7mMZwzO4Osd9H1OyuWq\nDrx9fX3AzPapDmlpacFay3333ccZZ5wxHFgn49ChQ/z4xz9my5Yt9Pb2jjp24YUXcsMNN9DV1cXy\n5ZXlQo0xfPzjH59TQRcUdhesoT5eL+fhOA52kSXVkSJzQgYM+Mt9HN/BzbokQUJxVxGTGJyMg5MZ\n/MN9AjgNDmtXr8WkDOWwzJP7n8QmliV9S3ip7yUSm1CkSFO6ieVNy1mxeAUntZ3E6UtPH25fGPl/\nERGRqdgXBKSNGRU8m12X7jCkP4pIj5jd9YzBcxxCa0fN4AaDN6qNndXti2O6ymUWjwjSibXsDQKW\nhCHL0umqal60aBFQmeGdaeeffz4XX3wxN954IzfffDNvf/vb2bhxIx/84AdJHaFtY8eOHVhr+dzn\nPsd111132HFjDHv37h0Ou1BZD3iuUdhdoMb28Y5iRrc9ADSc0nDEc73YoyVsoRSVWJVbxfFLj8cO\nPinjZThlySmkvTRpL61gKyIiNZEAzpiQaowBaw9bAj7ruizxPHYHAUsGA2w5SRiIIk7MZA6bqS3E\nMbG1o8adwWB9KIqqDrtNTU0cc8wxPPXUU1U9HyZedzeO48PG7rnnHn7xi19w//338+CDD7J582Zu\nuukmfv7zn7/haglJUnkHP/3pT7Nhw4Zxz1m9evWo77PZ7GR/CUeNwu4CNjbQTvdc9duKiMjR1up5\n7CyVWGTtcAAsxDFpx6FhnJvUTshkKn24UUQURfjGcEw6zbHjBFfHGBgnVCZMvHjRZL373e/mm9/8\nJo888khVN6ktXrwYqLREDM0UQ2VJs/GsX7+e9evXs2XLFrZu3cqHPvQhvvvd77J58+YJg3NnZycA\nvu9zwQUXTLnGuUJLj0lNpdzU8OztyC8FXRERmQltvs9iz2NPEHAwDNkXBAzEMcek0+OG3ZTjcFIu\nxxkNDZze0MAZjY2szuXwxum/bXJdMo5DXxQNj5WThNjaw/p+p+qaa64hl8vxsY99jL179x52/IUX\nXuCWW26Z8PmrVq3CWjtq17N8Ps9dd9016ryenp7DnnvWWWcBUC5XdpQamt0de+7SpUt5+9vfzm23\n3Tbupg/79++fsL65RDO7IiIiMm9lXJeTczkOBAG9UYTnOCwZDMATMcbQOIkbtXKuy4pMhl2lEnvK\nZcxgX+/x6fS0w25nZyd33303H/jAB1izZs2oHdR++tOf8v3vf5+PfOQjEz7/wgsv5IQTTmDz5s18\n5jOfwfn/27v34KrKc4/j3ydADEEMjSSiRwWDaCNBBKrYUxClLVhGBRTxNgc0BUSUcaAVipdA4LRW\nUVs8lWIZBkJrFMYriC09Kmc4KsodpKiIiFyEqKhAAxggz/lj7eTs7Fw3TdjZO7/PzBqy13rXu548\ns0mevPtd70pKYu7cuWRmZrJz587ydgUFBcycOZPBgwfTsWNHDh48yOzZs0lLS2PAgAEApKSkcNFF\nF7FgwQI6depEeno6OTk5dO7cmaeeeorevXvTpUsXRo4cSVZWFkVFRaxYsYLdu3ezbt268mtFu1bx\nq6++yoYNG3B3jh49yoYNG/j1r38NwMCBA8nJyYmqv+qo2BUREZG4dkpSEmelpHBWA/SdmZzMqc2a\ncfD4cdyd1GbNaN2sWb2sOHDttdeyceNGpk+fzqJFi5g1axbJycnk5OTw2GOPMWrUqPK2kevnNm/e\nnJdffpkxY8aQl5dHu3btGDduHGlpaeTm5pa369OnD6tWrWLBggUUFRWRlpZGz549KSwspH379uXt\n5syZw9ixYxk/fjwlJSVMnjyZzp07k52dzerVq8nPz6egoIB9+/aRmZlJt27dyMvLq/D9RJuTF154\nocJI9Pr161m/fj0QPHCivopdO9lPDGmMzKw7sGbNmjV079491uGIiIjEjbVr19KjRw+AHu6+tj77\n1u9nqU407zvN2RURERGRhKViV0REREQSlopdEREREUlYKnZFREREJGGp2BURERGRhKViV0REREQS\nlopdEREREUlYKnZFREREJGGp2BURERGRhKViV0REREQSlopdEREREUlYKnZFREREGrkOHTqQm5sb\n6zDikopdERERkRjZtm0bd955Jx07dqRly5akpaXRq1cvnnzySY4cOVLezswaLIbDhw+Tn5/P8uXL\nG+wakXbt2kV+fj49e/YkPT2djIwMrrrqKt544416v1bzeu9RRERERGq1ZMkShg4dSkpKCsOGDSMn\nJ4eSkhLeeustJkyYwObNm5k1a1aDx3Ho0CHy8/MxM6644ooGvx7AK6+8wvTp0xk0aBC33347x44d\nY/78+fz0pz9l7ty5DB8+vN6upWJXRERE5CTbvn07t9xyC+eddx5vvvkmmZmZ5cfuuusupk2bxpIl\nS05KLO7eIP0eOnSI1NTUKo/17duXHTt2kJ6eXr7vzjvv5JJLLiEvL69ei11NYxAREZEmo+R4Cd8d\n+67KreR4yUmL45FHHqG4uJg5c+ZUKHTLZGVlMXbs2GrPnzJlCklJlcu4efPmkZSUxI4dO8r3rV69\nmv79+5ORkUFqaipZWVn8/Oc/B+Czzz4jMzMTMyvvMykpialTp5af/9FHHzFkyBBOP/10WrZsyaWX\nXsrixYsrXLegoICkpCSWL1/OmDFjOOOMMzjnnHOqjT87O7tCoQuQnJzMgAED2LVrF8XFxdWeGy2N\n7IqIiEhcKzleUuXopJmR3Cy5QrsPvvyAI8eOVGoLkNI8heyM7ArnNJRXX32VrKwsevbseULnm1mV\n83gj93/55Zf079+fzMxMJk2aRJs2bdi+fTsvvvgiABkZGcyaNYvRo0dz/fXXc/311wNw8cUXA/CP\nf/yDXr16cfbZZzNp0iRatWrFwoULGTRoEC+++CIDBw6scP0xY8aQmZnJ5MmTT6hg3bNnD6mpqdWO\nCJ8IFbsiIiISt2oqYCOLV3fnyLEjtGjWolJBW3K8hCPHjlQqmutaSEfj4MGD7N69m0GDBp3Q+dF4\n5513+Pbbb3n99dfp1q1b+f6ykdvU1FRuuOEGRo8ezcUXX8ytt95a4fx7772XDh06sGrVKpo3D8rG\nu+66i169ejFx4sRKxW7btm154403TuiGuq1bt/LSSy9x00031esNeSp2RUREJG5VV8BWV7wCJDdL\nrrJQPXr8aIXX0RTS0Thw4AAArVu3jvrcaLVp0wZ3Z9GiRXTp0qW8YK2Lb775hmXLljFt2jT2799f\n4Vi/fv3Iz89nz549nHnmmUDwB8DIkSNPqFA9fPgwN954I6mpqTz88MNRn18TzdkVERGRuFdWwIZv\n/6rwQrpVcqvyrUWzFtUW0nVx2mmnAcEIb0Pr06cPQ4YMYerUqbRt25ZBgwYxb948Skpqn5+8detW\n3J2HHnqIjIyMCtuUKVMA+OKLLyqc06FDh6hjLC0t5aabbuLDDz/khRdeoF27dlH3URON7IqIiIjU\noGSzZqcAAA6dSURBVKriOXIUOBqtW7fmrLPOYtOmTSfcR3Wjp8ePH6+0b+HChaxcuZLFixezdOlS\ncnNzeeKJJ3j33XdrnBtbWloKwC9/+Uv69+9fZZvzzz+/wuuWLVvW9VsoN2LECF577TUKCwvp06dP\n1OfXRsWuiIiINClVrbpwMldiALjmmmuYPXs277333gndpPa9730PCKZElI0UQ7CkWVUuu+wyLrvs\nMqZNm8azzz7LbbfdxnPPPUdubm61hXNWVhYALVq0oG/fvlHHWBf33XcfBQUFzJgxg6FDhzbINTSN\nQURERJoEMyOleQpHjx+luKS4wnb0+FFSmqc06JPKwk2YMIHU1FRGjBhRaSoAwCeffMKTTz5Z7fkd\nO3bE3Ss89ay4uJj58+dXaPftt99WOrdr164AfPfddwDlo7uRbTMyMrjyyit5+umn2bt3b6V+vvrq\nq2rjq4vp06fz+OOP88ADD3DPPff8S33VRCO7IiIiEvciR2arGqlNbpZMdkZ2tXNtq1thoS59Rysr\nK4vCwkJuvvlmsrOzKzxB7e233+b555/njjvuqPb8fv36ce6555Kbm8t9991HUlISc+fOJTMzk507\nd5a3KygoYObMmQwePJiOHTty8OBBZs+eTVpaGgMGDAAgJSWFiy66iAULFtCpUyfS09PJycmhc+fO\nPPXUU/Tu3ZsuXbowcuRIsrKyKCoqYsWKFezevZt169aVXyuaOcwvvfQSEydO5IILLuDCCy/kmWee\nqfT9ZWRk1Lm/mqjYFRERkbhVNlp75NiRSvNoqxqpjebGtWj7jta1117Lxo0bmT59OosWLWLWrFkk\nJyeTk5PDY489xqhRoyrEEn695s2b8/LLLzNmzBjy8vJo164d48aNIy0tjdzc3PJ2ffr0YdWqVSxY\nsICioiLS0tLo2bMnhYWFtG/fvrzdnDlzGDt2LOPHj6ekpITJkyfTuXNnsrOzWb16Nfn5+RQUFLBv\n3z4yMzPp1q0beXl5lfJVVxs3bsTM+Pjjjxk2bFil48uWLau3Ytca6hFx8cTMugNr1qxZQ/fu3WMd\njoiISNxYu3YtPXr0AOjh7mvrs++6/n5uiLVwT0bfcuKied9pZFdERETiWkMWnSpo459uUBMRERGR\nhKViV0REREQSlopdEREREUlYcVXsmtn9Zva2mRWb2dfVtDnHzJaE2uw1s0fNLK6+z3jx7LPPxjqE\nuKS8RU85OzHKW/SUM5HEE29FYAtgIfDHqg6GitrXCG68uxwYDtwOTD1J8TUp+qVwYpS36ClnJ0Z5\ni55yJpJ44qrYdfd8d58BvF9Nk/7A94Hb3P19d18KPATcbWZaeUJERESkiYmrYrcOLgfed/fw59ct\nBdKAzrEJSURERERiJdGK3XZAUcS+orBjIiIiItKExPyjfTN7GJhYQxMHst19SwOGkQLwwQcfNOAl\nEs/+/ftZu7ZeH5bTJChv0VPOTozyFj3lLHphvztTTsI1RIDo3hMxf1ywmZ0OnF5Ls23ufizsnOHA\n79w9PaKvfOBad+8etq8DsA3o5u4bqonhVuCZE/oGREREBIL7ZQrrs0MzOzcpKemj0tLSBiukJX4l\nJSUdKS0tvdDdd9TULuYju+6+D9hXT92tAO43s7Zh83b7AfuBzTWctxS4DdgOHKmnWERERJqCFKAD\nwe/SeuXuO8zsQqBtffct8a+0tPSr2gpdaAQju9Ews3OAdGAg8AvgitChre5eHFp6bB3wOcHUiDOB\n+cCf3P2hGIQsIiIiIjEUb8XuXGBYFYeucvfloTbnEKzDeyVQDMwDJrl76UkKU0REREQaibgqdkVE\nREREopFoS4+JiIiIiJRTsSsiIiIiCavJF7tmdr+ZvW1mxWb2dTVtzjGzJaE2e83s0dDNcE2Wmd1t\nZp+a2WEze9fMLo11TI2JmfU2s0VmttvMSs3suiraTDWzz83skJn9t5mdH4tYGwMzm2RmK83sgJkV\nmdlLZnZBFe2UszBmNtrMNpjZ/tD2jpldHdFGOauBmf0q9H/0iYj9ylsYM5scylP4tjmijXImjVKT\nLthCWgALCW5qqyRU1L5GsEzb5cBw4HZg6kmKr9Exs5uAx4HJQDdgA7DUzLQ0zP9rBawHxhA8GKUC\nM5sI3AOMAi4juJlyqZkln8wgG5HewH8BPYGfEPy//LuZtSxroJxVaSfByjPdgR7Am8ArZpYNyllt\nQn+kjyL4GRa+X3mr2ibgDIInkrYDepUdUM6kUXN3bcFNesOBr6vY/zPgKNA2bN+dwDdA81jHHaNc\nvQvMCHttwC5gQqxja4wbUApcF7Hvc2Bc2OvTgMPA0FjH2xg2gjU1S4FeylnUudsH3KGc1ZqnU4GP\ngL7AMuCJsGPKW+V8TQbW1nBcOdPWaDeN7NbucuB9//+HVECwcHYa0Dk2IcWOmbUgGEF6o2yfuzvw\nOvDDWMUVT8zsPIJRkfAcHgDeQzks04ZgRPxrUM7qwsySzOxmIBV4Rzmr1VPAYnd/M3yn8lajTqGp\nWZ+Y2V9CS30qZ9LoxfwJanGgHVAUsa8o7FiVjyBOYG2BZlSdkwtPfjhxqR1BIVdVDtud/HAaFzMz\n4PfAW+5eNidQOauGmeUQPD0yBTgIDHb3j8zshyhnVQr9UXAJ8IMqDuu9VrV3CabwfUTwwKYpwPLQ\n+085k0YtIYtdM3uYYB5bdRzIdvctJykkEam7mcBFwI9iHUic+BDoSvBp0xBgvpldUfMpTZeZnU3w\nx9RP3P1orOOJF+4e/ijgTWa2EvgMGErwHhRptBJ1GsNjwPdr2LKBbXXsay/BhPxwZ4Qda2q+Ao5T\ndU6aYj5OxF6Cec7KYQQz+wMwALjS3feEHVLOquHux9x9m7uvc/cHCD5tuhflrDo9gAxgrZkdNbOj\nQB/gXjMrIRiNVN5q4e77gS3A+ei9Jo1cQha77r7P3bfUsh2rY3crgC4RKw30A/YDm6s+JXGFRkLW\nAD8u2xf62PnHwDuxiiueuPunBL8AwnN4GsFKBE02h6FCdyDB4793hB9TzqKSBJyinFXrdaALwTSG\nrqFtNfAXoKu7b0N5q5WZnUpQ6H6u95o0dgk5jSEaoQn26UB7oJmZdQ0d2uruxcDfCYraP4eWVjkT\nmAb8oQl/BPYEMM/M1gArgXEEN8XMi2VQjYmZtSL4RWChXVmh99bX7r6T4GPUB81sK7Cd4D21C3gl\nBuHGnJnNBG4BrgOKzaxshGi/ux8Jfa2cRTCz3wB/BXYArYHbCEYp+4WaKGcRQj/XI9eHLQb2ufsH\noV3KWwQzmw4sJpi68G9APsFKRc+Fmihn0mg1+WKXYL3cYWGv14b+vQpY7u6lZnYNwTq87xCsHTiP\nYBmWJsndF4ZGuqcSfEy1Hujv7l/GNrJG5QcEyxl5aHs8tL8AyHX3R80sFXiaYOWB/wV+5u4lsQi2\nERhNkKf/idh/BzAfQDmrUibBe+pMgk+bNgL9ylYYUM7qrMJa2Mpblc4GCoHTgS+Bt4DL3X0fKGfS\nuFmwapSIiIiISOJJyDm7IiIiIiKgYldEREREEpiKXRERERFJWCp2RURERCRhqdgVERERkYSlYldE\nREREEpaKXRERERFJWCp2RURERCRhqdgVkToxs1Izuy7WcdTEzPqY2XEzOy3WsYiISOOgYlekCTOz\nuaEi9riZlZjZXjP7u5ndYWYW0bwd8NdYxBmFt4Ez3f1AQ17EzHqb2SIz2x0PfwSIiDRlKnZF5K8E\nhWx74GrgTWAGsNjMyn9GuPsX7n40NiHWjbsfc/cvTsKlWgHrgTGAnrkuItKIqdgVke/c/Ut33+Pu\n6939t8BAYABwe1mj8BFMM2sfen2jmS03s0NmttLMOpnZpWa2yswOmtlrZnZ6+MXMbISZbTazw6F/\n7wo7VtbvYDN708yKzWy9mV0e1ubc0Kjq12b2TzN738yuDh3rEzr/tLD2N5jZJjM7Ymafmtn4iHg+\nNbNJZjbHzA6Y2WdmNrKmhLn739w9z91fASJHwEVEpBFRsSsilbj7MmADcH0tTacAU4FuwDGgEPgt\nMBboBZwfOg6Amd0WOmcS8H3gfmCqmf1HRL//CTwKdAW2AIVho8wzgeRQ/znAROCf4eGHXa8HsCAU\nVw4wGZhmZsMirjceWAVcEur/j2bWqZbvXURE4kDzWAcgIo3Wh0CXWtpMd/fXAcxsBkFR2dfd3w3t\nmwMMD2s/BfhFaEQU4DMz6wyMBv4c0e/fQn1MBjYRFM5bgHOA5919c6jt9hriGwe87u6/Cb3eGrre\nfcD8sHZL3H1W6OtHzGwccBXwcS3fv4iINHIa2RWR6hi1z0d9P+zrotC/myL2ZQKYWSrQEZgTmuJw\n0MwOAg8A59XQ755QLJmh108CD5nZW2Y2xcxqKsizCW5aC/c20CniBrz3I9rsDbueiIjEMRW7IlKd\nbODTWtqE37Dm1ewr+zlzaujfEQTTE8q2HOCHdeg3CcDd5xAUx/ND5642s7tribM2kTfehcctIiJx\nTD/MRaQSM+tLMIXh+RqaRbUKQWiVhM+Bju6+LWL7LJp+3X23u//J3YcAjwPV3VD2AfCjiH29gC3u\nrlUURESaAM3ZFZFTzOwMoBlwBvAz4FfAIirOo41U1SoEta1MMBmYYWYHgL8BpwA/ANq4++/r0oeZ\n/Y5gubQtQDrB3NrN4U3Cvn4cWGlmDxLcqPbvwN0Ec4RPmJm1IphDXHatLDPrCnzt7jv/lb5FRKR+\nqdgVkasJRlyPAd8QrMJwj7vPj2gXORJa1chojaOl7j7HzIqBCQSrLRQTzJf9fXizWvptBvwBOBs4\nQFD4jq+qrbuvM7OhBCtCPEgw//dBd/9zVe3r+n0QFOjLQu2coKgGKAByazlXREROItMneSIiIiKS\nqDRnV0REREQSlopdEREREUlYKnZFREREJGGp2BURERGRhKViV0REREQSlopdEREREUlYKnZFRERE\nJGGp2BURERGRhKViV0REREQSlopdEREREUlYKnZFREREJGGp2BURERGRhPV/xIOk6Clqb/gAAAAA\nSUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x115bc6240>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# project training data onto 2-D using principal components\n",
    "# join with clusters labels\n",
    "# plot\n",
    "pca = H2OPrincipalComponentAnalysisEstimator(k=2) # project onto 2 PCs\n",
    "pca.train(x=reals, training_frame=labeled_frame)\n",
    "features = pca.predict(labeled_frame)\n",
    "features_pandas = features.as_data_frame()\n",
    "features_pandas['label'] = labeled_frame[-1].as_data_frame()\n",
    "print(features_pandas.head())\n",
    "plot(features_pandas)\n",
    "\n",
    "# view detailed results at http://ip:port/flow/index.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# shutdown h2o\n",
    "# be careful - this can erase your work\n",
    "# h2o.cluster().shutdown(prompt=True)"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [conda root]",
   "language": "python",
   "name": "conda-root-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}