Update in Part 1

Author: Neha Sharma

samples/04_gis_analysts_data_scientists/predicting_voters_turnout_for_us_election_in_2016_using_automl_part_1.ipynb

@@ -1093,73 +1093,31 @@
       "4_Linear r2 0.651521 trained in 13.02 seconds\n",
       "* Step default_algorithms will try to check up to 4 models\n",
       "5_Default_LightGBM r2 0.773111 trained in 53.69 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "6_Default_Xgboost r2 0.765353 trained in 47.61 seconds\n",
       "7_Default_RandomTrees r2 0.582249 trained in 114.74 seconds\n",
       "8_Default_ExtraTrees r2 0.525917 trained in 41.74 seconds\n",
       "* Step not_so_random will try to check up to 36 models\n",
       "18_LightGBM r2 0.778586 trained in 20.91 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "9_Xgboost r2 0.74601 trained in 69.1 seconds\n",
       "27_RandomTrees r2 0.584312 trained in 89.58 seconds\n",
       "36_ExtraTrees r2 0.509314 trained in 36.97 seconds\n",
       "19_LightGBM r2 0.745846 trained in 17.39 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "10_Xgboost r2 0.741448 trained in 104.41 seconds\n",
       "28_RandomTrees r2 0.518539 trained in 106.18 seconds\n",
       "37_ExtraTrees r2 0.461816 trained in 45.37 seconds\n",
       "20_LightGBM r2 0.772607 trained in 55.96 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "11_Xgboost r2 0.773569 trained in 32.98 seconds\n",
       "29_RandomTrees r2 0.654122 trained in 262.43 seconds\n",
       "38_ExtraTrees r2 0.611619 trained in 62.34 seconds\n",
       "21_LightGBM r2 0.758954 trained in 99.03 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "12_Xgboost r2 0.752604 trained in 28.49 seconds\n",
       "30_RandomTrees r2 0.648906 trained in 135.54 seconds\n",
       "39_ExtraTrees r2 0.592089 trained in 33.39 seconds\n",
       "22_LightGBM r2 0.754357 trained in 17.14 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "13_Xgboost r2 0.775421 trained in 22.68 seconds\n",
       "31_RandomTrees r2 0.675828 trained in 143.16 seconds\n",
       "40_ExtraTrees r2 0.623064 trained in 44.52 seconds\n",
       "23_LightGBM r2 0.774772 trained in 29.47 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "14_Xgboost r2 0.771997 trained in 25.09 seconds\n",
       "32_RandomTrees r2 0.668177 trained in 229.35 seconds\n",
       "Skip mix_encoding because of the time limit.\n",
@@ -1168,132 +1126,42 @@
       "Drop features ['disposab_7', 'random_feature', 'hispanic_1', 'educatio_2', 'disposab_4', 'disposa_10', 'F5yearin_2', 'househol_2', 'disposab_9', 'disposab_1', 'househol_4', 'disposab_6', 'miscellane', 'county_brown', 'county_pulaski', 'county_carbon', 'county_rock', 'county_grundy', 'county_la', 'county_miami', 'county_river', 'county_butte', 'county_richland', 'county_anderson', 'county_pierce', 'county_kent', 'county_henderson', 'county_richmond', 'county_randolph', 'county_caldwell', 'county_green', 'county_garfield', 'county_allen', 'county_sheridan', 'county_sherman', 'county_sullivan', 'county_valley', 'county_wilson', 'county_middlesex', 'county_mitchell', 'county_phillips', 'county_lancaster', 'county_george', 'county_park', 'county_red', 'county_dallas', 'county_charles', 'county_clair', 'county_dodge', 'county_delaware', 'county_dawson', 'county_wood', 'county_putnam', 'county_benton', 'county_perry', 'county_cumberland', 'county_custer', 'county_davis', 'county_decatur', 'county_dekalb', 'county_fayette', 'county_howard', 'county_jasper', 'county_carroll', 'county_orange', 'county_columbia', 'county_newton', 'county_new', 'county_morgan', 'county_montgomery', 'county_monroe', 'county_mineral', 'county_mercer', 'county_mason', 'county_martin', 'county_crawford', 'county_clinton', 'county_marion', 'county_henry', 'county_floyd', 'county_franklin', 'county_fulton', 'county_grand', 'county_clay', 'county_hamilton', 'county_hancock', 'county_hardin', 'county_harrison', 'county_grant', 'county_york', 'county_greene', 'county_essex', 'county_douglas', 'county_carter', 'county_cass', 'county_cherokee', 'county_city', 'county_clark', 'county_clarke', 'county_boone', 'county_marshall', 'county_madison', 'county_washington', 'county_macon', 'county_shelby', 'county_camden', 'county_st', 'county_taylor', 'county_union', 'county_van', 'county_warren', 'county_wayne', 'county_san', 'county_webster', 'county_wheeler', 'county_white', 'county_saline', 'county_russell', 'county_pike', 'county_adams', 'county_polk', 'county_santa', 'county_scott', 'county_calhoun', 'county_jackson', 'county_lyon', 'county_logan', 'county_jefferson', 'county_johnson', 'county_jones', 'county_king', 'county_knox', 'county_lafayette', 'county_butler', 'county_stone', 'county_lake', 'county_lawrence', 'county_lee', 'county_lewis', 'county_lincoln', 'county_linn', 'county_livingston', 'county_lamar', 'county_campbell', 'language_1', 'disposable', 'financia_1', 'househol_3', 'househol_5', 'atrisk_avg']\n",
       "* Step features_selection will try to check up to 4 models\n",
       "18_LightGBM_SelectedFeatures r2 0.780683 trained in 21.84 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "13_Xgboost_SelectedFeatures r2 0.772052 trained in 20.15 seconds\n",
       "31_RandomTrees_SelectedFeatures r2 0.678155 trained in 105.64 seconds\n",
       "* Step hill_climbing_1 will try to check up to 20 models\n",
       "41_LightGBM_SelectedFeatures r2 0.781144 trained in 20.94 seconds\n",
       "42_LightGBM r2 0.777351 trained in 30.22 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "43_Xgboost r2 0.777537 trained in 28.16 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "44_Xgboost r2 0.765904 trained in 25.01 seconds\n",
       "45_LightGBM r2 0.774772 trained in 29.03 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "46_Xgboost r2 0.7798 trained in 31.25 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "47_Xgboost r2 0.762149 trained in 24.15 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "48_Xgboost_SelectedFeatures r2 0.777437 trained in 24.41 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "49_Xgboost_SelectedFeatures r2 0.768074 trained in 19.29 seconds\n",
       "50_RandomTrees_SelectedFeatures r2 0.678834 trained in 85.66 seconds\n",
       "* Step hill_climbing_2 will try to check up to 20 models\n",
       "51_LightGBM_SelectedFeatures r2 0.775765 trained in 19.87 seconds\n",
       "52_LightGBM_SelectedFeatures r2 0.783672 trained in 20.21 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "53_Xgboost r2 0.7781 trained in 28.93 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "54_Xgboost r2 0.778609 trained in 37.46 seconds\n",
       "55_LightGBM r2 0.772547 trained in 20.44 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "56_Xgboost r2 0.777419 trained in 28.31 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "57_Xgboost r2 0.77624 trained in 29.72 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "58_Xgboost_SelectedFeatures r2 0.780774 trained in 22.7 seconds\n",
       "* Step boost_on_errors will try to check up to 1 model\n",
       "52_LightGBM_SelectedFeatures_BoostOnErrors r2 0.775721 trained in 19.58 seconds\n",
       "* Step ensemble will try to check up to 1 model\n",
       "Ensemble r2 0.791472 trained in 8.41 seconds\n",
       "* Step stack will try to check up to 34 models\n",
       "52_LightGBM_SelectedFeatures_Stacked r2 0.777043 trained in 15.96 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "58_Xgboost_SelectedFeatures_Stacked r2 0.76841 trained in 17.74 seconds\n",
       "50_RandomTrees_SelectedFeatures_Stacked r2 0.785301 trained in 184.3 seconds\n",
       "40_ExtraTrees_Stacked r2 0.786661 trained in 54.71 seconds\n",
       "41_LightGBM_SelectedFeatures_Stacked r2 0.777301 trained in 18.16 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "46_Xgboost_Stacked r2 0.765382 trained in 22.91 seconds\n",
       "31_RandomTrees_SelectedFeatures_Stacked r2 0.784903 trained in 156.12 seconds\n",
       "38_ExtraTrees_Stacked r2 0.786768 trained in 59.36 seconds\n",
       "18_LightGBM_SelectedFeatures_Stacked r2 0.777556 trained in 14.95 seconds\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
       "54_Xgboost_Stacked r2 0.768311 trained in 22.51 seconds\n",
       "31_RandomTrees_Stacked not trained. Stop training after the first fold. Time needed to train on the first fold 58.0 seconds. The time estimate for training on all folds is larger than total_time_limit.\n",
       "39_ExtraTrees_Stacked r2 0.787297 trained in 39.47 seconds\n",