Kaggle_Python3_Bronze_Medal_COVID-19_with_H2OAutoML_Baseline.ipynb

{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Required library"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import json\nimport pandas as pd\nimport numpy as np\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.model_selection import train_test_split\nimport h2o\nfrom h2o.automl import H2OAutoML","execution_count":1,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"h2o.init(max_mem_size='16G')","execution_count":2,"outputs":[{"output_type":"stream","text":"Checking whether there is an H2O instance running at http://localhost:54321 ..... not found.\nAttempting to start a local H2O server...\n  Java Version: openjdk version \"11.0.8\" 2020-07-14; OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu118.04.1); OpenJDK 64-Bit Server VM (build 11.0.8+10-post-Ubuntu-0ubuntu118.04.1, mixed mode, sharing)\n  Starting server from /opt/conda/lib/python3.7/site-packages/h2o/backend/bin/h2o.jar\n  Ice root: /tmp/tmpwbd06uwo\n  JVM stdout: /tmp/tmpwbd06uwo/h2o_unknownUser_started_from_python.out\n  JVM stderr: /tmp/tmpwbd06uwo/h2o_unknownUser_started_from_python.err\n  Server is running at http://127.0.0.1:54321\nConnecting to H2O server at http://127.0.0.1:54321 ... successful.\n","name":"stdout"},{"output_type":"display_data","data":{"text/plain":"--------------------------  ------------------------------------------------------------------\nH2O_cluster_uptime:         02 secs\nH2O_cluster_timezone:       Etc/UTC\nH2O_data_parsing_timezone:  UTC\nH2O_cluster_version:        3.30.1.2\nH2O_cluster_version_age:    17 days\nH2O_cluster_name:           H2O_from_python_unknownUser_221j18\nH2O_cluster_total_nodes:    1\nH2O_cluster_free_memory:    16 Gb\nH2O_cluster_total_cores:    4\nH2O_cluster_allowed_cores:  4\nH2O_cluster_status:         accepting new members, healthy\nH2O_connection_url:         http://127.0.0.1:54321\nH2O_connection_proxy:       {\"http\": null, \"https\": null}\nH2O_internal_security:      False\nH2O_API_Extensions:         Amazon S3, XGBoost, Algos, AutoML, Core V3, TargetEncoder, Core V4\nPython_version:             3.7.6 final\n--------------------------  ------------------------------------------------------------------","text/html":"<div style=\"overflow:auto\"><table style=\"width:50%\"><tr><td>H2O_cluster_uptime:</td>\n<td>02 secs</td></tr>\n<tr><td>H2O_cluster_timezone:</td>\n<td>Etc/UTC</td></tr>\n<tr><td>H2O_data_parsing_timezone:</td>\n<td>UTC</td></tr>\n<tr><td>H2O_cluster_version:</td>\n<td>3.30.1.2</td></tr>\n<tr><td>H2O_cluster_version_age:</td>\n<td>17 days </td></tr>\n<tr><td>H2O_cluster_name:</td>\n<td>H2O_from_python_unknownUser_221j18</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>16 Gb</td></tr>\n<tr><td>H2O_cluster_total_cores:</td>\n<td>4</td></tr>\n<tr><td>H2O_cluster_allowed_cores:</td>\n<td>4</td></tr>\n<tr><td>H2O_cluster_status:</td>\n<td>accepting new members, healthy</td></tr>\n<tr><td>H2O_connection_url:</td>\n<td>http://127.0.0.1:54321</td></tr>\n<tr><td>H2O_connection_proxy:</td>\n<td>{\"http\": null, \"https\": null}</td></tr>\n<tr><td>H2O_internal_security:</td>\n<td>False</td></tr>\n<tr><td>H2O_API_Extensions:</td>\n<td>Amazon S3, XGBoost, Algos, AutoML, Core V3, TargetEncoder, Core V4</td></tr>\n<tr><td>Python_version:</td>\n<td>3.7.6 final</td></tr></table></div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"# Road and check the data"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Read the data\npath = '/kaggle/input/stanford-covid-vaccine'\ntrain_df = pd.read_json(f'{path}/train.json',lines=True)\ntest_df = pd.read_json(f'{path}/test.json', lines=True)\nsample_sub_df = pd.read_csv(f'{path}/sample_submission.csv')","execution_count":3,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":4,"outputs":[{"output_type":"execute_result","execution_count":4,"data":{"text/plain":"   index            id                                           sequence  \\\n0      0  id_001f94081  GGAAAAGCUCUAAUAACAGGAGACUAGGACUACGUAUUUCUAGGUA...   \n1      1  id_0049f53ba  GGAAAAAGCGCGCGCGGUUAGCGCGCGCUUUUGCGCGCGCUGUACC...   \n2      2  id_006f36f57  GGAAAGUGCUCAGAUAAGCUAAGCUCGAAUAGCAAUCGAAUAGAAU...   \n3      3  id_0082d463b  GGAAAAGCGCGCGCGCGCGCGCGAAAAAGCGCGCGCGCGCGCGCGC...   \n4      4  id_0087940f4  GGAAAAUAUAUAAUAUAUUAUAUAAAUAUAUUAUAGAAGUAUAAUA...   \n\n                                           structure  \\\n0  .....((((((.......)))).)).((.....((..((((((......   \n1  .....(((((((((((((((((((((((....)))))))))).)))...   \n2  .....((((.((.....((((.(((.....)))..((((......)...   \n3  ......((((((((((((((((......))))))))))))))))((...   \n4  .....(((((((.((((((((((((.(((((((((....)))))))...   \n\n                                 predicted_loop_type  signal_to_noise  \\\n0  EEEEESSSSSSHHHHHHHSSSSBSSXSSIIIIISSIISSSSSSHHH...            6.894   \n1  EEEEESSSSSSSSSSSSSSSSSSSSSSSHHHHSSSSSSSSSSBSSS...            0.193   \n2  EEEEESSSSISSIIIIISSSSMSSSHHHHHSSSMMSSSSHHHHHHS...            8.800   \n3  EEEEEESSSSSSSSSSSSSSSSHHHHHHSSSSSSSSSSSSSSSSSS...            0.104   \n4  EEEEESSSSSSSBSSSSSSSSSSSSBSSSSSSSSSHHHHSSSSSSS...            0.423   \n\n   SN_filter  seq_length  seq_scored  \\\n0          1         107          68   \n1          0         107          68   \n2          1         107          68   \n3          0         107          68   \n4          0         107          68   \n\n                                    reactivity_error  \\\n0  [0.1359, 0.20700000000000002, 0.1633, 0.1452, ...   \n1  [2.8272, 2.8272, 2.8272, 4.7343, 2.5676, 2.567...   \n2  [0.0931, 0.13290000000000002, 0.11280000000000...   \n3  [3.5229, 6.0748, 3.0374, 3.0374, 3.0374, 3.037...   \n4  [1.665, 2.1728, 2.0041, 1.2405, 0.620200000000...   \n\n                                   deg_error_Mg_pH10  \\\n0  [0.26130000000000003, 0.38420000000000004, 0.1...   \n1  [73705.3985, 73705.3985, 73705.3985, 73705.398...   \n2  [0.1365, 0.2237, 0.1812, 0.1333, 0.1148, 0.160...   \n3  [73705.3985, 73705.3985, 73705.3985, 73705.398...   \n4  [4.2139, 3.9637000000000002, 3.2467, 2.4716, 1...   \n\n                                      deg_error_pH10  \\\n0  [0.2631, 0.28600000000000003, 0.0964, 0.1574, ...   \n1  [10.1986, 9.2418, 5.0933, 5.0933, 5.0933, 5.09...   \n2  [0.17020000000000002, 0.178, 0.111, 0.091, 0.0...   \n3  [11.8007, 12.7566, 5.7733, 5.7733, 5.7733, 5.7...   \n4  [3.0942, 3.015, 2.1212, 2.0552, 0.881500000000...   \n\n                                    deg_error_Mg_50C  \\\n0  [0.1501, 0.275, 0.0947, 0.18660000000000002, 0...   \n1  [16.6174, 13.868, 8.1968, 8.1968, 8.1968, 8.19...   \n2  [0.1033, 0.1464, 0.1126, 0.09620000000000001, ...   \n3  [121286.7181, 121286.7182, 121286.7181, 121286...   \n4  [2.6717, 2.4818, 1.9919, 2.5484999999999998, 1...   \n\n                                       deg_error_50C  \\\n0  [0.2167, 0.34750000000000003, 0.188, 0.2124, 0...   \n1  [15.4857, 7.9596, 13.3957, 5.8777, 5.8777, 5.8...   \n2  [0.14980000000000002, 0.1761, 0.1517, 0.116700...   \n3  [15.3995, 8.1124, 7.7824, 7.7824, 7.7824, 7.78...   \n4  [1.3285, 3.6173, 1.3057, 1.3021, 1.1507, 1.150...   \n\n                                          reactivity  \\\n0  [0.3297, 1.5693000000000001, 1.1227, 0.8686, 0...   \n1  [0.0, 0.0, 0.0, 2.2965, 0.0, 0.0, 0.0, 0.0, 0....   \n2  [0.44820000000000004, 1.4822, 1.1819, 0.743400...   \n3  [0.0, 2.2399, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0....   \n4  [0.8267, 2.6577, 2.8481, 0.40090000000000003, ...   \n\n                                         deg_Mg_pH10  \\\n0  [0.7556, 2.983, 0.2526, 1.3789, 0.637600000000...   \n1  [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...   \n2  [0.2504, 1.4021, 0.9804, 0.49670000000000003, ...   \n3  [0.0, -0.5083, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0...   \n4  [2.1058, 3.138, 2.5437000000000003, 1.0932, 0....   \n\n                                            deg_pH10  \\\n0  [2.3375, 3.5060000000000002, 0.3008, 1.0108, 0...   \n1  [4.947, 4.4523, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...   \n2  [2.243, 2.9361, 1.0553, 0.721, 0.6396000000000...   \n3  [3.4248, 6.8128, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,...   \n4  [4.7366, 4.6243, 1.2068, 1.1538, 0.0, 0.0, 0.7...   \n\n                                          deg_Mg_50C  \\\n0  [0.35810000000000003, 2.9683, 0.2589, 1.4552, ...   \n1  [4.8511, 4.0426, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,...   \n2  [0.5163, 1.6823000000000001, 1.0426, 0.7902, 0...   \n3  [0.0, -0.8365, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0...   \n4  [2.2052, 1.7947000000000002, 0.7457, 3.1233, 0...   \n\n                                             deg_50C  \n0  [0.6382, 3.4773, 0.9988, 1.3228, 0.78770000000...  \n1  [7.6692, 0.0, 10.9561, 0.0, 0.0, 0.0, 0.0, 0.0...  \n2  [0.9501000000000001, 1.7974999999999999, 1.499...  \n3  [7.6692, -1.3223, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0...  \n4  [0.0, 5.1198, -0.3551, -0.3518, 0.0, 0.0, 0.0,...  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>index</th>\n      <th>id</th>\n      <th>sequence</th>\n      <th>structure</th>\n      <th>predicted_loop_type</th>\n      <th>signal_to_noise</th>\n      <th>SN_filter</th>\n      <th>seq_length</th>\n      <th>seq_scored</th>\n      <th>reactivity_error</th>\n      <th>deg_error_Mg_pH10</th>\n      <th>deg_error_pH10</th>\n      <th>deg_error_Mg_50C</th>\n      <th>deg_error_50C</th>\n      <th>reactivity</th>\n      <th>deg_Mg_pH10</th>\n      <th>deg_pH10</th>\n      <th>deg_Mg_50C</th>\n      <th>deg_50C</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>id_001f94081</td>\n      <td>GGAAAAGCUCUAAUAACAGGAGACUAGGACUACGUAUUUCUAGGUA...</td>\n      <td>.....((((((.......)))).)).((.....((..((((((......</td>\n      <td>EEEEESSSSSSHHHHHHHSSSSBSSXSSIIIIISSIISSSSSSHHH...</td>\n      <td>6.894</td>\n      <td>1</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[0.1359, 0.20700000000000002, 0.1633, 0.1452, ...</td>\n      <td>[0.26130000000000003, 0.38420000000000004, 0.1...</td>\n      <td>[0.2631, 0.28600000000000003, 0.0964, 0.1574, ...</td>\n      <td>[0.1501, 0.275, 0.0947, 0.18660000000000002, 0...</td>\n      <td>[0.2167, 0.34750000000000003, 0.188, 0.2124, 0...</td>\n      <td>[0.3297, 1.5693000000000001, 1.1227, 0.8686, 0...</td>\n      <td>[0.7556, 2.983, 0.2526, 1.3789, 0.637600000000...</td>\n      <td>[2.3375, 3.5060000000000002, 0.3008, 1.0108, 0...</td>\n      <td>[0.35810000000000003, 2.9683, 0.2589, 1.4552, ...</td>\n      <td>[0.6382, 3.4773, 0.9988, 1.3228, 0.78770000000...</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>id_0049f53ba</td>\n      <td>GGAAAAAGCGCGCGCGGUUAGCGCGCGCUUUUGCGCGCGCUGUACC...</td>\n      <td>.....(((((((((((((((((((((((....)))))))))).)))...</td>\n      <td>EEEEESSSSSSSSSSSSSSSSSSSSSSSHHHHSSSSSSSSSSBSSS...</td>\n      <td>0.193</td>\n      <td>0</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[2.8272, 2.8272, 2.8272, 4.7343, 2.5676, 2.567...</td>\n      <td>[73705.3985, 73705.3985, 73705.3985, 73705.398...</td>\n      <td>[10.1986, 9.2418, 5.0933, 5.0933, 5.0933, 5.09...</td>\n      <td>[16.6174, 13.868, 8.1968, 8.1968, 8.1968, 8.19...</td>\n      <td>[15.4857, 7.9596, 13.3957, 5.8777, 5.8777, 5.8...</td>\n      <td>[0.0, 0.0, 0.0, 2.2965, 0.0, 0.0, 0.0, 0.0, 0....</td>\n      <td>[0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...</td>\n      <td>[4.947, 4.4523, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...</td>\n      <td>[4.8511, 4.0426, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,...</td>\n      <td>[7.6692, 0.0, 10.9561, 0.0, 0.0, 0.0, 0.0, 0.0...</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>id_006f36f57</td>\n      <td>GGAAAGUGCUCAGAUAAGCUAAGCUCGAAUAGCAAUCGAAUAGAAU...</td>\n      <td>.....((((.((.....((((.(((.....)))..((((......)...</td>\n      <td>EEEEESSSSISSIIIIISSSSMSSSHHHHHSSSMMSSSSHHHHHHS...</td>\n      <td>8.800</td>\n      <td>1</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[0.0931, 0.13290000000000002, 0.11280000000000...</td>\n      <td>[0.1365, 0.2237, 0.1812, 0.1333, 0.1148, 0.160...</td>\n      <td>[0.17020000000000002, 0.178, 0.111, 0.091, 0.0...</td>\n      <td>[0.1033, 0.1464, 0.1126, 0.09620000000000001, ...</td>\n      <td>[0.14980000000000002, 0.1761, 0.1517, 0.116700...</td>\n      <td>[0.44820000000000004, 1.4822, 1.1819, 0.743400...</td>\n      <td>[0.2504, 1.4021, 0.9804, 0.49670000000000003, ...</td>\n      <td>[2.243, 2.9361, 1.0553, 0.721, 0.6396000000000...</td>\n      <td>[0.5163, 1.6823000000000001, 1.0426, 0.7902, 0...</td>\n      <td>[0.9501000000000001, 1.7974999999999999, 1.499...</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>id_0082d463b</td>\n      <td>GGAAAAGCGCGCGCGCGCGCGCGAAAAAGCGCGCGCGCGCGCGCGC...</td>\n      <td>......((((((((((((((((......))))))))))))))))((...</td>\n      <td>EEEEEESSSSSSSSSSSSSSSSHHHHHHSSSSSSSSSSSSSSSSSS...</td>\n      <td>0.104</td>\n      <td>0</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[3.5229, 6.0748, 3.0374, 3.0374, 3.0374, 3.037...</td>\n      <td>[73705.3985, 73705.3985, 73705.3985, 73705.398...</td>\n      <td>[11.8007, 12.7566, 5.7733, 5.7733, 5.7733, 5.7...</td>\n      <td>[121286.7181, 121286.7182, 121286.7181, 121286...</td>\n      <td>[15.3995, 8.1124, 7.7824, 7.7824, 7.7824, 7.78...</td>\n      <td>[0.0, 2.2399, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0....</td>\n      <td>[0.0, -0.5083, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0...</td>\n      <td>[3.4248, 6.8128, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,...</td>\n      <td>[0.0, -0.8365, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0...</td>\n      <td>[7.6692, -1.3223, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0...</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>id_0087940f4</td>\n      <td>GGAAAAUAUAUAAUAUAUUAUAUAAAUAUAUUAUAGAAGUAUAAUA...</td>\n      <td>.....(((((((.((((((((((((.(((((((((....)))))))...</td>\n      <td>EEEEESSSSSSSBSSSSSSSSSSSSBSSSSSSSSSHHHHSSSSSSS...</td>\n      <td>0.423</td>\n      <td>0</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[1.665, 2.1728, 2.0041, 1.2405, 0.620200000000...</td>\n      <td>[4.2139, 3.9637000000000002, 3.2467, 2.4716, 1...</td>\n      <td>[3.0942, 3.015, 2.1212, 2.0552, 0.881500000000...</td>\n      <td>[2.6717, 2.4818, 1.9919, 2.5484999999999998, 1...</td>\n      <td>[1.3285, 3.6173, 1.3057, 1.3021, 1.1507, 1.150...</td>\n      <td>[0.8267, 2.6577, 2.8481, 0.40090000000000003, ...</td>\n      <td>[2.1058, 3.138, 2.5437000000000003, 1.0932, 0....</td>\n      <td>[4.7366, 4.6243, 1.2068, 1.1538, 0.0, 0.0, 0.7...</td>\n      <td>[2.2052, 1.7947000000000002, 0.7457, 3.1233, 0...</td>\n      <td>[0.0, 5.1198, -0.3551, -0.3518, 0.0, 0.0, 0.0,...</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.head()","execution_count":5,"outputs":[{"output_type":"execute_result","execution_count":5,"data":{"text/plain":"   index            id                                           sequence  \\\n0      0  id_00073f8be  GGAAAAGUACGACUUGAGUACGGAAAACGUACCAACUCGAUUAAAA...   \n1      1  id_000ae4237  GGAAACGGGUUCCGCGGAUUGCUGCUAAUAAGAGUAAUCUCUAAAU...   \n2      2  id_00131c573  GGAAAACAAAACGGCCUGGAAGACGAAGGAAUUCGGCGCGAAGGCC...   \n3      3  id_00181fd34  GGAAAGGAUCUCUAUCGAAGGAUAGAGAUCGCUCGCGACGGCACGA...   \n4      4  id_0020473f7  GGAAACCCGCCCGCGCCCGCCCGCGCUGCUGCCGUGCCUCCUCUCC...   \n\n                                           structure  \\\n0  ......((((((((((.(((((.....))))))))((((((((......   \n1  .....((((..((((((...(((((.....((((....)))).......   \n2  ...........((.(((.(.(..((..((..((((...))))..))...   \n3  ......((((((((((....))))))))))((((((..((.(((.....   \n4  .....(((((((((((((((((((((((((((((((((((((((((...   \n\n                                 predicted_loop_type  seq_length  seq_scored  \n0  EEEEEESSSSSSSSSSBSSSSSHHHHHSSSSSSSSSSSSSSSSHHH...         107          68  \n1  EEEEESSSSIISSSSSSIIISSSSSIIIIISSSSHHHHSSSSIIII...         130          91  \n2  EEEEEEEEEEESSISSSISISIISSIISSIISSSSHHHSSSSIISS...         107          68  \n3  EEEEEESSSSSSSSSSHHHHSSSSSSSSSSSSSSSSIISSISSSHH...         107          68  \n4  EEEEESSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS...         130          91  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>index</th>\n      <th>id</th>\n      <th>sequence</th>\n      <th>structure</th>\n      <th>predicted_loop_type</th>\n      <th>seq_length</th>\n      <th>seq_scored</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>id_00073f8be</td>\n      <td>GGAAAAGUACGACUUGAGUACGGAAAACGUACCAACUCGAUUAAAA...</td>\n      <td>......((((((((((.(((((.....))))))))((((((((......</td>\n      <td>EEEEEESSSSSSSSSSBSSSSSHHHHHSSSSSSSSSSSSSSSSHHH...</td>\n      <td>107</td>\n      <td>68</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>id_000ae4237</td>\n      <td>GGAAACGGGUUCCGCGGAUUGCUGCUAAUAAGAGUAAUCUCUAAAU...</td>\n      <td>.....((((..((((((...(((((.....((((....)))).......</td>\n      <td>EEEEESSSSIISSSSSSIIISSSSSIIIIISSSSHHHHSSSSIIII...</td>\n      <td>130</td>\n      <td>91</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>id_00131c573</td>\n      <td>GGAAAACAAAACGGCCUGGAAGACGAAGGAAUUCGGCGCGAAGGCC...</td>\n      <td>...........((.(((.(.(..((..((..((((...))))..))...</td>\n      <td>EEEEEEEEEEESSISSSISISIISSIISSIISSSSHHHSSSSIISS...</td>\n      <td>107</td>\n      <td>68</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>id_00181fd34</td>\n      <td>GGAAAGGAUCUCUAUCGAAGGAUAGAGAUCGCUCGCGACGGCACGA...</td>\n      <td>......((((((((((....))))))))))((((((..((.(((.....</td>\n      <td>EEEEEESSSSSSSSSSHHHHSSSSSSSSSSSSSSSSIISSISSSHH...</td>\n      <td>107</td>\n      <td>68</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>id_0020473f7</td>\n      <td>GGAAACCCGCCCGCGCCCGCCCGCGCUGCUGCCGUGCCUCCUCUCC...</td>\n      <td>.....(((((((((((((((((((((((((((((((((((((((((...</td>\n      <td>EEEEESSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS...</td>\n      <td>130</td>\n      <td>91</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub_df.head()","execution_count":6,"outputs":[{"output_type":"execute_result","execution_count":6,"data":{"text/plain":"        id_seqpos  reactivity  deg_Mg_pH10  deg_pH10  deg_Mg_50C  deg_50C\n0  id_00073f8be_0         0.0          0.0       0.0         0.0      0.0\n1  id_00073f8be_1         0.0          0.0       0.0         0.0      0.0\n2  id_00073f8be_2         0.0          0.0       0.0         0.0      0.0\n3  id_00073f8be_3         0.0          0.0       0.0         0.0      0.0\n4  id_00073f8be_4         0.0          0.0       0.0         0.0      0.0","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id_seqpos</th>\n      <th>reactivity</th>\n      <th>deg_Mg_pH10</th>\n      <th>deg_pH10</th>\n      <th>deg_Mg_50C</th>\n      <th>deg_50C</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>id_00073f8be_0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>id_00073f8be_1</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>id_00073f8be_2</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>id_00073f8be_3</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>id_00073f8be_4</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n      <td>0.0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"# Definition of objective and explanatory variables\n- Quote from\n- https://www.kaggle.com/kaushal2896/openvaccine-xgboost-baseline"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Calculate Means of targets\ntrain_df['reactivity'] = train_df['reactivity'].apply(lambda x: np.mean(x))\ntrain_df['deg_Mg_pH10'] = train_df['deg_Mg_pH10'].apply(lambda x: np.mean(x))\ntrain_df['deg_pH10'] = train_df['deg_pH10'].apply(lambda x: np.mean(x))\ntrain_df['deg_Mg_50C'] = train_df['deg_Mg_50C'].apply(lambda x: np.mean(x))\ntrain_df['deg_50C'] = train_df['deg_50C'].apply(lambda x: np.mean(x))","execution_count":7,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":8,"outputs":[{"output_type":"execute_result","execution_count":8,"data":{"text/plain":"   index            id                                           sequence  \\\n0      0  id_001f94081  GGAAAAGCUCUAAUAACAGGAGACUAGGACUACGUAUUUCUAGGUA...   \n1      1  id_0049f53ba  GGAAAAAGCGCGCGCGGUUAGCGCGCGCUUUUGCGCGCGCUGUACC...   \n2      2  id_006f36f57  GGAAAGUGCUCAGAUAAGCUAAGCUCGAAUAGCAAUCGAAUAGAAU...   \n3      3  id_0082d463b  GGAAAAGCGCGCGCGCGCGCGCGAAAAAGCGCGCGCGCGCGCGCGC...   \n4      4  id_0087940f4  GGAAAAUAUAUAAUAUAUUAUAUAAAUAUAUUAUAGAAGUAUAAUA...   \n\n                                           structure  \\\n0  .....((((((.......)))).)).((.....((..((((((......   \n1  .....(((((((((((((((((((((((....)))))))))).)))...   \n2  .....((((.((.....((((.(((.....)))..((((......)...   \n3  ......((((((((((((((((......))))))))))))))))((...   \n4  .....(((((((.((((((((((((.(((((((((....)))))))...   \n\n                                 predicted_loop_type  signal_to_noise  \\\n0  EEEEESSSSSSHHHHHHHSSSSBSSXSSIIIIISSIISSSSSSHHH...            6.894   \n1  EEEEESSSSSSSSSSSSSSSSSSSSSSSHHHHSSSSSSSSSSBSSS...            0.193   \n2  EEEEESSSSISSIIIIISSSSMSSSHHHHHSSSMMSSSSHHHHHHS...            8.800   \n3  EEEEEESSSSSSSSSSSSSSSSHHHHHHSSSSSSSSSSSSSSSSSS...            0.104   \n4  EEEEESSSSSSSBSSSSSSSSSSSSBSSSSSSSSSHHHHSSSSSSS...            0.423   \n\n   SN_filter  seq_length  seq_scored  \\\n0          1         107          68   \n1          0         107          68   \n2          1         107          68   \n3          0         107          68   \n4          0         107          68   \n\n                                    reactivity_error  \\\n0  [0.1359, 0.20700000000000002, 0.1633, 0.1452, ...   \n1  [2.8272, 2.8272, 2.8272, 4.7343, 2.5676, 2.567...   \n2  [0.0931, 0.13290000000000002, 0.11280000000000...   \n3  [3.5229, 6.0748, 3.0374, 3.0374, 3.0374, 3.037...   \n4  [1.665, 2.1728, 2.0041, 1.2405, 0.620200000000...   \n\n                                   deg_error_Mg_pH10  \\\n0  [0.26130000000000003, 0.38420000000000004, 0.1...   \n1  [73705.3985, 73705.3985, 73705.3985, 73705.398...   \n2  [0.1365, 0.2237, 0.1812, 0.1333, 0.1148, 0.160...   \n3  [73705.3985, 73705.3985, 73705.3985, 73705.398...   \n4  [4.2139, 3.9637000000000002, 3.2467, 2.4716, 1...   \n\n                                      deg_error_pH10  \\\n0  [0.2631, 0.28600000000000003, 0.0964, 0.1574, ...   \n1  [10.1986, 9.2418, 5.0933, 5.0933, 5.0933, 5.09...   \n2  [0.17020000000000002, 0.178, 0.111, 0.091, 0.0...   \n3  [11.8007, 12.7566, 5.7733, 5.7733, 5.7733, 5.7...   \n4  [3.0942, 3.015, 2.1212, 2.0552, 0.881500000000...   \n\n                                    deg_error_Mg_50C  \\\n0  [0.1501, 0.275, 0.0947, 0.18660000000000002, 0...   \n1  [16.6174, 13.868, 8.1968, 8.1968, 8.1968, 8.19...   \n2  [0.1033, 0.1464, 0.1126, 0.09620000000000001, ...   \n3  [121286.7181, 121286.7182, 121286.7181, 121286...   \n4  [2.6717, 2.4818, 1.9919, 2.5484999999999998, 1...   \n\n                                       deg_error_50C  reactivity  deg_Mg_pH10  \\\n0  [0.2167, 0.34750000000000003, 0.188, 0.2124, 0...    0.502631     0.559628   \n1  [15.4857, 7.9596, 13.3957, 5.8777, 5.8777, 5.8...    0.411401     0.698354   \n2  [0.14980000000000002, 0.1761, 0.1517, 0.116700...    0.433966     0.578362   \n3  [15.3995, 8.1124, 7.7824, 7.7824, 7.7824, 7.78...    0.329059     0.826485   \n4  [1.3285, 3.6173, 1.3057, 1.3021, 1.1507, 1.150...    0.282204     0.469587   \n\n   deg_pH10  deg_Mg_50C   deg_50C  \n0  0.503501    0.538540  0.585893  \n1  0.846041    0.930103  0.865125  \n2  0.548174    0.570284  0.575172  \n3  1.051551    1.221297  0.696476  \n4  0.384826    0.393072  0.440115  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>index</th>\n      <th>id</th>\n      <th>sequence</th>\n      <th>structure</th>\n      <th>predicted_loop_type</th>\n      <th>signal_to_noise</th>\n      <th>SN_filter</th>\n      <th>seq_length</th>\n      <th>seq_scored</th>\n      <th>reactivity_error</th>\n      <th>deg_error_Mg_pH10</th>\n      <th>deg_error_pH10</th>\n      <th>deg_error_Mg_50C</th>\n      <th>deg_error_50C</th>\n      <th>reactivity</th>\n      <th>deg_Mg_pH10</th>\n      <th>deg_pH10</th>\n      <th>deg_Mg_50C</th>\n      <th>deg_50C</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>id_001f94081</td>\n      <td>GGAAAAGCUCUAAUAACAGGAGACUAGGACUACGUAUUUCUAGGUA...</td>\n      <td>.....((((((.......)))).)).((.....((..((((((......</td>\n      <td>EEEEESSSSSSHHHHHHHSSSSBSSXSSIIIIISSIISSSSSSHHH...</td>\n      <td>6.894</td>\n      <td>1</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[0.1359, 0.20700000000000002, 0.1633, 0.1452, ...</td>\n      <td>[0.26130000000000003, 0.38420000000000004, 0.1...</td>\n      <td>[0.2631, 0.28600000000000003, 0.0964, 0.1574, ...</td>\n      <td>[0.1501, 0.275, 0.0947, 0.18660000000000002, 0...</td>\n      <td>[0.2167, 0.34750000000000003, 0.188, 0.2124, 0...</td>\n      <td>0.502631</td>\n      <td>0.559628</td>\n      <td>0.503501</td>\n      <td>0.538540</td>\n      <td>0.585893</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>id_0049f53ba</td>\n      <td>GGAAAAAGCGCGCGCGGUUAGCGCGCGCUUUUGCGCGCGCUGUACC...</td>\n      <td>.....(((((((((((((((((((((((....)))))))))).)))...</td>\n      <td>EEEEESSSSSSSSSSSSSSSSSSSSSSSHHHHSSSSSSSSSSBSSS...</td>\n      <td>0.193</td>\n      <td>0</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[2.8272, 2.8272, 2.8272, 4.7343, 2.5676, 2.567...</td>\n      <td>[73705.3985, 73705.3985, 73705.3985, 73705.398...</td>\n      <td>[10.1986, 9.2418, 5.0933, 5.0933, 5.0933, 5.09...</td>\n      <td>[16.6174, 13.868, 8.1968, 8.1968, 8.1968, 8.19...</td>\n      <td>[15.4857, 7.9596, 13.3957, 5.8777, 5.8777, 5.8...</td>\n      <td>0.411401</td>\n      <td>0.698354</td>\n      <td>0.846041</td>\n      <td>0.930103</td>\n      <td>0.865125</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>id_006f36f57</td>\n      <td>GGAAAGUGCUCAGAUAAGCUAAGCUCGAAUAGCAAUCGAAUAGAAU...</td>\n      <td>.....((((.((.....((((.(((.....)))..((((......)...</td>\n      <td>EEEEESSSSISSIIIIISSSSMSSSHHHHHSSSMMSSSSHHHHHHS...</td>\n      <td>8.800</td>\n      <td>1</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[0.0931, 0.13290000000000002, 0.11280000000000...</td>\n      <td>[0.1365, 0.2237, 0.1812, 0.1333, 0.1148, 0.160...</td>\n      <td>[0.17020000000000002, 0.178, 0.111, 0.091, 0.0...</td>\n      <td>[0.1033, 0.1464, 0.1126, 0.09620000000000001, ...</td>\n      <td>[0.14980000000000002, 0.1761, 0.1517, 0.116700...</td>\n      <td>0.433966</td>\n      <td>0.578362</td>\n      <td>0.548174</td>\n      <td>0.570284</td>\n      <td>0.575172</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>id_0082d463b</td>\n      <td>GGAAAAGCGCGCGCGCGCGCGCGAAAAAGCGCGCGCGCGCGCGCGC...</td>\n      <td>......((((((((((((((((......))))))))))))))))((...</td>\n      <td>EEEEEESSSSSSSSSSSSSSSSHHHHHHSSSSSSSSSSSSSSSSSS...</td>\n      <td>0.104</td>\n      <td>0</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[3.5229, 6.0748, 3.0374, 3.0374, 3.0374, 3.037...</td>\n      <td>[73705.3985, 73705.3985, 73705.3985, 73705.398...</td>\n      <td>[11.8007, 12.7566, 5.7733, 5.7733, 5.7733, 5.7...</td>\n      <td>[121286.7181, 121286.7182, 121286.7181, 121286...</td>\n      <td>[15.3995, 8.1124, 7.7824, 7.7824, 7.7824, 7.78...</td>\n      <td>0.329059</td>\n      <td>0.826485</td>\n      <td>1.051551</td>\n      <td>1.221297</td>\n      <td>0.696476</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>id_0087940f4</td>\n      <td>GGAAAAUAUAUAAUAUAUUAUAUAAAUAUAUUAUAGAAGUAUAAUA...</td>\n      <td>.....(((((((.((((((((((((.(((((((((....)))))))...</td>\n      <td>EEEEESSSSSSSBSSSSSSSSSSSSBSSSSSSSSSHHHHSSSSSSS...</td>\n      <td>0.423</td>\n      <td>0</td>\n      <td>107</td>\n      <td>68</td>\n      <td>[1.665, 2.1728, 2.0041, 1.2405, 0.620200000000...</td>\n      <td>[4.2139, 3.9637000000000002, 3.2467, 2.4716, 1...</td>\n      <td>[3.0942, 3.015, 2.1212, 2.0552, 0.881500000000...</td>\n      <td>[2.6717, 2.4818, 1.9919, 2.5484999999999998, 1...</td>\n      <td>[1.3285, 3.6173, 1.3057, 1.3021, 1.1507, 1.150...</td>\n      <td>0.282204</td>\n      <td>0.469587</td>\n      <td>0.384826</td>\n      <td>0.393072</td>\n      <td>0.440115</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Drop unnecessary columns for now\ntrain_df = train_df.drop(['id', 'index', 'reactivity_error', 'deg_error_Mg_pH10', 'deg_error_pH10', 'deg_error_Mg_50C', 'deg_error_50C', 'SN_filter', 'signal_to_noise', 'deg_pH10', 'deg_50C'], axis=1)\ntrain_df.head()","execution_count":9,"outputs":[{"output_type":"execute_result","execution_count":9,"data":{"text/plain":"                                            sequence  \\\n0  GGAAAAGCUCUAAUAACAGGAGACUAGGACUACGUAUUUCUAGGUA...   \n1  GGAAAAAGCGCGCGCGGUUAGCGCGCGCUUUUGCGCGCGCUGUACC...   \n2  GGAAAGUGCUCAGAUAAGCUAAGCUCGAAUAGCAAUCGAAUAGAAU...   \n3  GGAAAAGCGCGCGCGCGCGCGCGAAAAAGCGCGCGCGCGCGCGCGC...   \n4  GGAAAAUAUAUAAUAUAUUAUAUAAAUAUAUUAUAGAAGUAUAAUA...   \n\n                                           structure  \\\n0  .....((((((.......)))).)).((.....((..((((((......   \n1  .....(((((((((((((((((((((((....)))))))))).)))...   \n2  .....((((.((.....((((.(((.....)))..((((......)...   \n3  ......((((((((((((((((......))))))))))))))))((...   \n4  .....(((((((.((((((((((((.(((((((((....)))))))...   \n\n                                 predicted_loop_type  seq_length  seq_scored  \\\n0  EEEEESSSSSSHHHHHHHSSSSBSSXSSIIIIISSIISSSSSSHHH...         107          68   \n1  EEEEESSSSSSSSSSSSSSSSSSSSSSSHHHHSSSSSSSSSSBSSS...         107          68   \n2  EEEEESSSSISSIIIIISSSSMSSSHHHHHSSSMMSSSSHHHHHHS...         107          68   \n3  EEEEEESSSSSSSSSSSSSSSSHHHHHHSSSSSSSSSSSSSSSSSS...         107          68   \n4  EEEEESSSSSSSBSSSSSSSSSSSSBSSSSSSSSSHHHHSSSSSSS...         107          68   \n\n   reactivity  deg_Mg_pH10  deg_Mg_50C  \n0    0.502631     0.559628    0.538540  \n1    0.411401     0.698354    0.930103  \n2    0.433966     0.578362    0.570284  \n3    0.329059     0.826485    1.221297  \n4    0.282204     0.469587    0.393072  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>sequence</th>\n      <th>structure</th>\n      <th>predicted_loop_type</th>\n      <th>seq_length</th>\n      <th>seq_scored</th>\n      <th>reactivity</th>\n      <th>deg_Mg_pH10</th>\n      <th>deg_Mg_50C</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>GGAAAAGCUCUAAUAACAGGAGACUAGGACUACGUAUUUCUAGGUA...</td>\n      <td>.....((((((.......)))).)).((.....((..((((((......</td>\n      <td>EEEEESSSSSSHHHHHHHSSSSBSSXSSIIIIISSIISSSSSSHHH...</td>\n      <td>107</td>\n      <td>68</td>\n      <td>0.502631</td>\n      <td>0.559628</td>\n      <td>0.538540</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>GGAAAAAGCGCGCGCGGUUAGCGCGCGCUUUUGCGCGCGCUGUACC...</td>\n      <td>.....(((((((((((((((((((((((....)))))))))).)))...</td>\n      <td>EEEEESSSSSSSSSSSSSSSSSSSSSSSHHHHSSSSSSSSSSBSSS...</td>\n      <td>107</td>\n      <td>68</td>\n      <td>0.411401</td>\n      <td>0.698354</td>\n      <td>0.930103</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>GGAAAGUGCUCAGAUAAGCUAAGCUCGAAUAGCAAUCGAAUAGAAU...</td>\n      <td>.....((((.((.....((((.(((.....)))..((((......)...</td>\n      <td>EEEEESSSSISSIIIIISSSSMSSSHHHHHSSSMMSSSSHHHHHHS...</td>\n      <td>107</td>\n      <td>68</td>\n      <td>0.433966</td>\n      <td>0.578362</td>\n      <td>0.570284</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>GGAAAAGCGCGCGCGCGCGCGCGAAAAAGCGCGCGCGCGCGCGCGC...</td>\n      <td>......((((((((((((((((......))))))))))))))))((...</td>\n      <td>EEEEEESSSSSSSSSSSSSSSSHHHHHHSSSSSSSSSSSSSSSSSS...</td>\n      <td>107</td>\n      <td>68</td>\n      <td>0.329059</td>\n      <td>0.826485</td>\n      <td>1.221297</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>GGAAAAUAUAUAAUAUAUUAUAUAAAUAUAUUAUAGAAGUAUAAUA...</td>\n      <td>.....(((((((.((((((((((((.(((((((((....)))))))...</td>\n      <td>EEEEESSSSSSSBSSSSSSSSSSSSBSSSSSSSSSHHHHSSSSSSS...</td>\n      <td>107</td>\n      <td>68</td>\n      <td>0.282204</td>\n      <td>0.469587</td>\n      <td>0.393072</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Split data in features and labels\nX_train = train_df.drop(['reactivity', 'deg_Mg_pH10', 'deg_Mg_50C'], axis=1)\nY_train = train_df[['reactivity', 'deg_Mg_pH10', 'deg_Mg_50C']]","execution_count":10,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, Y_train, Y_test = train_test_split(X_train, Y_train, test_size=0.15)","execution_count":11,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def featurize(df):\n    \n    df['total_A_count'] = df['sequence'].apply(lambda s: s.count('A'))\n    df['total_G_count'] = df['sequence'].apply(lambda s: s.count('G'))\n    df['total_U_count'] = df['sequence'].apply(lambda s: s.count('U'))\n    df['total_C_count'] = df['sequence'].apply(lambda s: s.count('C'))\n    \n    df['total_dot_count'] = df['structure'].apply(lambda s: s.count('.'))\n    df['total_ob_count'] = df['structure'].apply(lambda s: s.count('('))\n    df['total_cb_count'] = df['structure'].apply(lambda s: s.count(')'))\n    \n    return df","execution_count":12,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = featurize(X_train)\nX_test = featurize(X_test)","execution_count":13,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = X_train.drop(['sequence', 'structure', 'predicted_loop_type'], axis=1)\nX_test = X_test.drop(['sequence', 'structure', 'predicted_loop_type'], axis=1)","execution_count":14,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":15,"outputs":[{"output_type":"execute_result","execution_count":15,"data":{"text/plain":"      seq_length  seq_scored  total_A_count  total_G_count  total_U_count  \\\n1189         107          68             69              7             25   \n1183         107          68             24             36             17   \n2274         107          68             43             24             20   \n915          107          68             38             24             17   \n2069         107          68             45             30             16   \n\n      total_C_count  total_dot_count  total_ob_count  total_cb_count  \n1189              6               93               7               7  \n1183             30               59              24              24  \n2274             20               59              24              24  \n915              28               51              28              28  \n2069             16               61              23              23  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>seq_length</th>\n      <th>seq_scored</th>\n      <th>total_A_count</th>\n      <th>total_G_count</th>\n      <th>total_U_count</th>\n      <th>total_C_count</th>\n      <th>total_dot_count</th>\n      <th>total_ob_count</th>\n      <th>total_cb_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1189</th>\n      <td>107</td>\n      <td>68</td>\n      <td>69</td>\n      <td>7</td>\n      <td>25</td>\n      <td>6</td>\n      <td>93</td>\n      <td>7</td>\n      <td>7</td>\n    </tr>\n    <tr>\n      <th>1183</th>\n      <td>107</td>\n      <td>68</td>\n      <td>24</td>\n      <td>36</td>\n      <td>17</td>\n      <td>30</td>\n      <td>59</td>\n      <td>24</td>\n      <td>24</td>\n    </tr>\n    <tr>\n      <th>2274</th>\n      <td>107</td>\n      <td>68</td>\n      <td>43</td>\n      <td>24</td>\n      <td>20</td>\n      <td>20</td>\n      <td>59</td>\n      <td>24</td>\n      <td>24</td>\n    </tr>\n    <tr>\n      <th>915</th>\n      <td>107</td>\n      <td>68</td>\n      <td>38</td>\n      <td>24</td>\n      <td>17</td>\n      <td>28</td>\n      <td>51</td>\n      <td>28</td>\n      <td>28</td>\n    </tr>\n    <tr>\n      <th>2069</th>\n      <td>107</td>\n      <td>68</td>\n      <td>45</td>\n      <td>30</td>\n      <td>16</td>\n      <td>16</td>\n      <td>61</td>\n      <td>23</td>\n      <td>23</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test.head()","execution_count":16,"outputs":[{"output_type":"execute_result","execution_count":16,"data":{"text/plain":"      seq_length  seq_scored  total_A_count  total_G_count  total_U_count  \\\n367          107          68             43             23             19   \n1942         107          68             76             16              8   \n1041         107          68             39             38              3   \n2104         107          68             31             34             12   \n1045         107          68             44             24             16   \n\n      total_C_count  total_dot_count  total_ob_count  total_cb_count  \n367              22               55              26              26  \n1942              7               93               7               7  \n1041             27               71              18              18  \n2104             30               49              29              29  \n1045             23               59              24              24  ","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>seq_length</th>\n      <th>seq_scored</th>\n      <th>total_A_count</th>\n      <th>total_G_count</th>\n      <th>total_U_count</th>\n      <th>total_C_count</th>\n      <th>total_dot_count</th>\n      <th>total_ob_count</th>\n      <th>total_cb_count</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>367</th>\n      <td>107</td>\n      <td>68</td>\n      <td>43</td>\n      <td>23</td>\n      <td>19</td>\n      <td>22</td>\n      <td>55</td>\n      <td>26</td>\n      <td>26</td>\n    </tr>\n    <tr>\n      <th>1942</th>\n      <td>107</td>\n      <td>68</td>\n      <td>76</td>\n      <td>16</td>\n      <td>8</td>\n      <td>7</td>\n      <td>93</td>\n      <td>7</td>\n      <td>7</td>\n    </tr>\n    <tr>\n      <th>1041</th>\n      <td>107</td>\n      <td>68</td>\n      <td>39</td>\n      <td>38</td>\n      <td>3</td>\n      <td>27</td>\n      <td>71</td>\n      <td>18</td>\n      <td>18</td>\n    </tr>\n    <tr>\n      <th>2104</th>\n      <td>107</td>\n      <td>68</td>\n      <td>31</td>\n      <td>34</td>\n      <td>12</td>\n      <td>30</td>\n      <td>49</td>\n      <td>29</td>\n      <td>29</td>\n    </tr>\n    <tr>\n      <th>1045</th>\n      <td>107</td>\n      <td>68</td>\n      <td>44</td>\n      <td>24</td>\n      <td>16</td>\n      <td>23</td>\n      <td>59</td>\n      <td>24</td>\n      <td>24</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"scaler = StandardScaler()\nscaler.fit(X_train)\n\nX_train = scaler.transform(X_train)\nX_test = scaler.transform(X_test)","execution_count":17,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# AutoML - train & predict\n- Reference:\n- https://www.kaggle.com/tunguz/ieee-with-h2o-automl\n- https://stackoverflow.com/questions/59366199/is-there-a-way-to-convert-h2oframe-to-pandas-dataframe\n- https://stackoverflow.com/questions/48317921/python-h2o-frame-to-np-array-reshape"},{"metadata":{"trusted":true},"cell_type":"code","source":"htrain = pd.concat([Y_train, pd.DataFrame(X_train)], axis=1)\nhtrain = h2o.H2OFrame(htrain)\nhtrain['reactivity'].asfactor\nhtrain['deg_Mg_pH10'].asfactor\nhtrain['deg_Mg_50C'].asfactor\nhtrain","execution_count":18,"outputs":[{"output_type":"stream","text":"Parse progress: |█████████████████████████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"display_data","data":{"text/html":"<table>\n<thead>\n<tr><th style=\"text-align: right;\">  reactivity</th><th style=\"text-align: right;\">  deg_Mg_pH10</th><th style=\"text-align: right;\">  deg_Mg_50C</th><th style=\"text-align: right;\">  0</th><th style=\"text-align: right;\">  1</th><th style=\"text-align: right;\">         2</th><th style=\"text-align: right;\">        3</th><th style=\"text-align: right;\">         4</th><th style=\"text-align: right;\">        5</th><th style=\"text-align: right;\">         6</th><th style=\"text-align: right;\">         7</th><th style=\"text-align: right;\">         8</th></tr>\n</thead>\n<tbody>\n<tr><td style=\"text-align: right;\">    0.502631</td><td style=\"text-align: right;\">     0.559628</td><td style=\"text-align: right;\">    0.53854 </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 2.5612   </td><td style=\"text-align: right;\">-2.39057 </td><td style=\"text-align: right;\"> 0.935213 </td><td style=\"text-align: right;\">-2.38768 </td><td style=\"text-align: right;\"> 2.11724  </td><td style=\"text-align: right;\">-2.11724  </td><td style=\"text-align: right;\">-2.11724  </td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-1.7442   </td><td style=\"text-align: right;\"> 1.49978 </td><td style=\"text-align: right;\">-0.0154956</td><td style=\"text-align: right;\"> 1.01941 </td><td style=\"text-align: right;\">-0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td></tr>\n<tr><td style=\"text-align: right;\">    0.433966</td><td style=\"text-align: right;\">     0.578362</td><td style=\"text-align: right;\">    0.570284</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 0.0736327</td><td style=\"text-align: right;\">-0.110016</td><td style=\"text-align: right;\"> 0.34102  </td><td style=\"text-align: right;\">-0.400208</td><td style=\"text-align: right;\">-0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-0.404745 </td><td style=\"text-align: right;\">-0.110016</td><td style=\"text-align: right;\">-0.0154956</td><td style=\"text-align: right;\"> 0.73549 </td><td style=\"text-align: right;\">-0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td></tr>\n<tr><td style=\"text-align: right;\">    0.282204</td><td style=\"text-align: right;\">     0.469587</td><td style=\"text-align: right;\">    0.393072</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 0.264984 </td><td style=\"text-align: right;\"> 0.694884</td><td style=\"text-align: right;\">-0.134334 </td><td style=\"text-align: right;\">-0.968057</td><td style=\"text-align: right;\"> 0.0934394</td><td style=\"text-align: right;\">-0.0934394</td><td style=\"text-align: right;\">-0.0934394</td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-0.30907  </td><td style=\"text-align: right;\"> 0.158284</td><td style=\"text-align: right;\">-0.372011 </td><td style=\"text-align: right;\"> 0.73549 </td><td style=\"text-align: right;\">-0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td></tr>\n<tr><td style=\"text-align: right;\">    0.349713</td><td style=\"text-align: right;\">     0.353104</td><td style=\"text-align: right;\">    0.367032</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-1.17015  </td><td style=\"text-align: right;\"> 0.829034</td><td style=\"text-align: right;\"> 0.578697 </td><td style=\"text-align: right;\"> 0.167641</td><td style=\"text-align: right;\">-0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td></tr>\n<tr><td style=\"text-align: right;\">    0.304882</td><td style=\"text-align: right;\">     0.443834</td><td style=\"text-align: right;\">    0.336829</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 0.456335 </td><td style=\"text-align: right;\">-0.914917</td><td style=\"text-align: right;\">-0.372011 </td><td style=\"text-align: right;\"> 0.73549 </td><td style=\"text-align: right;\">-0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td></tr>\n<tr><td style=\"text-align: right;\">    0.220175</td><td style=\"text-align: right;\">     0.310119</td><td style=\"text-align: right;\">    0.313763</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 0.36066  </td><td style=\"text-align: right;\"> 0.560734</td><td style=\"text-align: right;\">-0.372011 </td><td style=\"text-align: right;\">-0.684133</td><td style=\"text-align: right;\"> 0.219927 </td><td style=\"text-align: right;\">-0.219927 </td><td style=\"text-align: right;\">-0.219927 </td></tr>\n<tr><td style=\"text-align: right;\">    0.436157</td><td style=\"text-align: right;\">     0.49866 </td><td style=\"text-align: right;\">    0.381422</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 2.65687  </td><td style=\"text-align: right;\">-2.25642 </td><td style=\"text-align: right;\">-1.20388  </td><td style=\"text-align: right;\">-0.116284</td><td style=\"text-align: right;\"> 2.11724  </td><td style=\"text-align: right;\">-2.11724  </td><td style=\"text-align: right;\">-2.11724  </td></tr>\n</tbody>\n</table>"},"metadata":{}},{"output_type":"execute_result","execution_count":18,"data":{"text/plain":""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"htest = pd.concat([Y_test, pd.DataFrame(X_test)], axis=1)\nhtest = h2o.H2OFrame(htest)\nhtest['reactivity'].asfactor\nhtest['deg_Mg_pH10'].asfactor\nhtest['deg_Mg_50C'].asfactor\nhtest","execution_count":19,"outputs":[{"output_type":"stream","text":"Parse progress: |█████████████████████████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"display_data","data":{"text/html":"<table>\n<thead>\n<tr><th style=\"text-align: right;\">  reactivity</th><th style=\"text-align: right;\">  deg_Mg_pH10</th><th style=\"text-align: right;\">  deg_Mg_50C</th><th style=\"text-align: right;\">  0</th><th style=\"text-align: right;\">  1</th><th style=\"text-align: right;\">         2</th><th style=\"text-align: right;\">        3</th><th style=\"text-align: right;\">         4</th><th style=\"text-align: right;\">         5</th><th style=\"text-align: right;\">         6</th><th style=\"text-align: right;\">         7</th><th style=\"text-align: right;\">         8</th></tr>\n</thead>\n<tbody>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 0.0736327</td><td style=\"text-align: right;\">-0.244166</td><td style=\"text-align: right;\"> 0.222181 </td><td style=\"text-align: right;\">-0.116284 </td><td style=\"text-align: right;\">-0.286022 </td><td style=\"text-align: right;\"> 0.286022 </td><td style=\"text-align: right;\"> 0.286022 </td></tr>\n<tr><td style=\"text-align: right;\">    0.411401</td><td style=\"text-align: right;\">     0.698354</td><td style=\"text-align: right;\">    0.930103</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 3.23093  </td><td style=\"text-align: right;\">-1.18322 </td><td style=\"text-align: right;\">-1.08504  </td><td style=\"text-align: right;\">-2.24572  </td><td style=\"text-align: right;\"> 2.11724  </td><td style=\"text-align: right;\">-2.11724  </td><td style=\"text-align: right;\">-2.11724  </td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-0.30907  </td><td style=\"text-align: right;\"> 1.76808 </td><td style=\"text-align: right;\">-1.67924  </td><td style=\"text-align: right;\"> 0.593527 </td><td style=\"text-align: right;\"> 0.725876 </td><td style=\"text-align: right;\">-0.725876 </td><td style=\"text-align: right;\">-0.725876 </td></tr>\n<tr><td style=\"text-align: right;\">    0.329059</td><td style=\"text-align: right;\">     0.826485</td><td style=\"text-align: right;\">    1.2213  </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-1.07447  </td><td style=\"text-align: right;\"> 1.23148 </td><td style=\"text-align: right;\">-0.609688 </td><td style=\"text-align: right;\"> 1.01941  </td><td style=\"text-align: right;\">-0.665484 </td><td style=\"text-align: right;\"> 0.665484 </td><td style=\"text-align: right;\"> 0.665484 </td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 0.169308 </td><td style=\"text-align: right;\">-0.110016</td><td style=\"text-align: right;\">-0.134334 </td><td style=\"text-align: right;\"> 0.0256785</td><td style=\"text-align: right;\">-0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td></tr>\n<tr><td style=\"text-align: right;\">    0.286488</td><td style=\"text-align: right;\">     0.411699</td><td style=\"text-align: right;\">    0.325238</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 1.22174  </td><td style=\"text-align: right;\">-0.914917</td><td style=\"text-align: right;\">-0.253173 </td><td style=\"text-align: right;\">-0.54217  </td><td style=\"text-align: right;\">-0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td><td style=\"text-align: right;\"> 0.0330479</td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\"> 2.65687  </td><td style=\"text-align: right;\">-0.780767</td><td style=\"text-align: right;\">-0.728527 </td><td style=\"text-align: right;\">-2.24572  </td><td style=\"text-align: right;\"> 2.11724  </td><td style=\"text-align: right;\">-2.11724  </td><td style=\"text-align: right;\">-2.11724  </td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-0.691772 </td><td style=\"text-align: right;\"> 0.158284</td><td style=\"text-align: right;\">-0.0154956</td><td style=\"text-align: right;\"> 0.877452 </td><td style=\"text-align: right;\">-1.42441  </td><td style=\"text-align: right;\"> 1.42441  </td><td style=\"text-align: right;\"> 1.42441  </td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-0.787448 </td><td style=\"text-align: right;\"> 0.829034</td><td style=\"text-align: right;\">-0.609688 </td><td style=\"text-align: right;\"> 1.01941  </td><td style=\"text-align: right;\">-0.665484 </td><td style=\"text-align: right;\"> 0.665484 </td><td style=\"text-align: right;\"> 0.665484 </td></tr>\n<tr><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">   nan       </td><td style=\"text-align: right;\">  nan       </td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">  0</td><td style=\"text-align: right;\">-0.213394 </td><td style=\"text-align: right;\"> 0.158284</td><td style=\"text-align: right;\"> 0.578697 </td><td style=\"text-align: right;\">-0.54217  </td><td style=\"text-align: right;\">-0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td><td style=\"text-align: right;\"> 0.538997 </td></tr>\n</tbody>\n</table>"},"metadata":{}},{"output_type":"execute_result","execution_count":19,"data":{"text/plain":""},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Convert test data to predict\ntest = featurize(test_df.drop(['index', 'id'], axis=1))\ntest = test.drop(['sequence', 'structure', 'predicted_loop_type'], axis=1)\ntest = scaler.transform(test)\ntest = h2o.H2OFrame(test, column_names=['0','1','2','3','4','5','6','7','8'])","execution_count":20,"outputs":[{"output_type":"stream","text":"Parse progress: |█████████████████████████████████████████████████████████| 100%\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train & predict an each\ndef h2o_ML(htrain, htest, test):\n    Y1 = 'reactivity'\n    Y2 = 'deg_Mg_pH10'\n    Y3 = 'deg_Mg_50C'\n    X1 = htrain.columns.remove(Y1)\n    X2 = htrain.columns.remove(Y2)\n    X3 = htrain.columns.remove(Y3)\n    \n    def h2o_train_test(X, Y, htrain, htest, test):       \n        aml = H2OAutoML(max_runtime_secs=(3600 * 2),  # 2 hours for all Y\n                        max_models=30, # None, # no limt\n                        seed=2000,\n                        nfolds=3,\n                        keep_cross_validation_predictions=True\n                       )\n        aml.train(x=X, y=Y, training_frame=htrain, leaderboard_frame=htest)\n        \n        # View the AutoML Leaderboard\n        lb = aml.leaderboard\n        print(lb.head(rows=lb.nrows))  # Print all rows instead of default (10 rows)\n        \n        # predict\n        preds = aml.predict(test).as_data_frame().values\n        preds = pd.DataFrame(preds, columns=[Y])\n        \n        return preds\n        \n    h2o_1 = h2o_train_test(X1, Y1, htrain, htest, test)\n    h2o_2 = h2o_train_test(X2, Y2, htrain, htest, test)\n    h2o_3 = h2o_train_test(X3, Y3, htrain, htest, test)\n    \n    result = pd.concat([h2o_1, h2o_2, h2o_3], axis=1)\n    \n    return result","execution_count":21,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Run functions\nmodel = h2o_ML(htrain, htest, test)\nmodel","execution_count":22,"outputs":[{"output_type":"stream","text":"AutoML progress: |\n22:54:45.344: XGBoost_1_AutoML_20200920_225444 [XGBoost def_1] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_1_AutoML_20200920_225444_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n█\n22:54:46.349: XGBoost_2_AutoML_20200920_225444 [XGBoost def_2] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_2_AutoML_20200920_225444_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n\n22:54:47.354: XGBoost_3_AutoML_20200920_225444 [XGBoost def_3] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_3_AutoML_20200920_225444_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n████████████████\n22:55:11.577: XRT_1_AutoML_20200920_225444 [DRF XRT (Extremely Randomized Trees)] failed: java.lang.AssertionError\n\n███████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"display_data","data":{"text/html":"<table>\n<thead>\n<tr><th>model_id                                           </th><th style=\"text-align: right;\">  mean_residual_deviance</th><th style=\"text-align: right;\">     rmse</th><th style=\"text-align: right;\">       mse</th><th style=\"text-align: right;\">      mae</th><th style=\"text-align: right;\">    rmsle</th></tr>\n</thead>\n<tbody>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_6         </td><td style=\"text-align: right;\">              0.00738631</td><td style=\"text-align: right;\">0.0859436</td><td style=\"text-align: right;\">0.00738631</td><td style=\"text-align: right;\">0.0545764</td><td style=\"text-align: right;\">0.0628694</td></tr>\n<tr><td>GBM_3_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.0074295 </td><td style=\"text-align: right;\">0.0861945</td><td style=\"text-align: right;\">0.0074295 </td><td style=\"text-align: right;\">0.0553048</td><td style=\"text-align: right;\">0.0628458</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_7         </td><td style=\"text-align: right;\">              0.0074473 </td><td style=\"text-align: right;\">0.0862977</td><td style=\"text-align: right;\">0.0074473 </td><td style=\"text-align: right;\">0.0544819</td><td style=\"text-align: right;\">0.0626223</td></tr>\n<tr><td>GBM_2_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.00750497</td><td style=\"text-align: right;\">0.0866312</td><td style=\"text-align: right;\">0.00750497</td><td style=\"text-align: right;\">0.0552353</td><td style=\"text-align: right;\">0.0629706</td></tr>\n<tr><td>GBM_5_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.00752197</td><td style=\"text-align: right;\">0.0867293</td><td style=\"text-align: right;\">0.00752197</td><td style=\"text-align: right;\">0.0546333</td><td style=\"text-align: right;\">0.0636622</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_1         </td><td style=\"text-align: right;\">              0.00755649</td><td style=\"text-align: right;\">0.086928 </td><td style=\"text-align: right;\">0.00755649</td><td style=\"text-align: right;\">0.0544746</td><td style=\"text-align: right;\">0.0632809</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_10        </td><td style=\"text-align: right;\">              0.00756139</td><td style=\"text-align: right;\">0.0869563</td><td style=\"text-align: right;\">0.00756139</td><td style=\"text-align: right;\">0.0589072</td><td style=\"text-align: right;\">0.0619725</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_5         </td><td style=\"text-align: right;\">              0.00759711</td><td style=\"text-align: right;\">0.0871614</td><td style=\"text-align: right;\">0.00759711</td><td style=\"text-align: right;\">0.0562014</td><td style=\"text-align: right;\">0.0641314</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_225444_model_2</td><td style=\"text-align: right;\">              0.0076264 </td><td style=\"text-align: right;\">0.0873292</td><td style=\"text-align: right;\">0.0076264 </td><td style=\"text-align: right;\">0.0553775</td><td style=\"text-align: right;\">0.0646547</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_8         </td><td style=\"text-align: right;\">              0.00764455</td><td style=\"text-align: right;\">0.0874331</td><td style=\"text-align: right;\">0.00764455</td><td style=\"text-align: right;\">0.0550484</td><td style=\"text-align: right;\">0.0637525</td></tr>\n<tr><td>StackedEnsemble_AllModels_AutoML_20200920_225444   </td><td style=\"text-align: right;\">              0.00764816</td><td style=\"text-align: right;\">0.0874538</td><td style=\"text-align: right;\">0.00764816</td><td style=\"text-align: right;\">0.0551301</td><td style=\"text-align: right;\">0.0644199</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_3         </td><td style=\"text-align: right;\">              0.00766154</td><td style=\"text-align: right;\">0.0875302</td><td style=\"text-align: right;\">0.00766154</td><td style=\"text-align: right;\">0.0555981</td><td style=\"text-align: right;\">0.0638928</td></tr>\n<tr><td>StackedEnsemble_BestOfFamily_AutoML_20200920_225444</td><td style=\"text-align: right;\">              0.00766481</td><td style=\"text-align: right;\">0.0875489</td><td style=\"text-align: right;\">0.00766481</td><td style=\"text-align: right;\">0.055488 </td><td style=\"text-align: right;\">0.0647697</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_9         </td><td style=\"text-align: right;\">              0.0076905 </td><td style=\"text-align: right;\">0.0876955</td><td style=\"text-align: right;\">0.0076905 </td><td style=\"text-align: right;\">0.056292 </td><td style=\"text-align: right;\">0.0640183</td></tr>\n<tr><td>GBM_4_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.00770051</td><td style=\"text-align: right;\">0.0877526</td><td style=\"text-align: right;\">0.00770051</td><td style=\"text-align: right;\">0.0574041</td><td style=\"text-align: right;\">0.0643726</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_225444_model_1</td><td style=\"text-align: right;\">              0.00770365</td><td style=\"text-align: right;\">0.0877705</td><td style=\"text-align: right;\">0.00770365</td><td style=\"text-align: right;\">0.05454  </td><td style=\"text-align: right;\">0.0648939</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_2         </td><td style=\"text-align: right;\">              0.00770456</td><td style=\"text-align: right;\">0.0877757</td><td style=\"text-align: right;\">0.00770456</td><td style=\"text-align: right;\">0.0577092</td><td style=\"text-align: right;\">0.0640719</td></tr>\n<tr><td>DeepLearning_1_AutoML_20200920_225444              </td><td style=\"text-align: right;\">              0.00775252</td><td style=\"text-align: right;\">0.0880484</td><td style=\"text-align: right;\">0.00775252</td><td style=\"text-align: right;\">0.0564065</td><td style=\"text-align: right;\">0.0649979</td></tr>\n<tr><td>DRF_1_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.00781553</td><td style=\"text-align: right;\">0.0884055</td><td style=\"text-align: right;\">0.00781553</td><td style=\"text-align: right;\">0.0574413</td><td style=\"text-align: right;\">0.0644877</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_225444_model_1</td><td style=\"text-align: right;\">              0.00782638</td><td style=\"text-align: right;\">0.0884669</td><td style=\"text-align: right;\">0.00782638</td><td style=\"text-align: right;\">0.0547391</td><td style=\"text-align: right;\">0.0657824</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_225444_model_1</td><td style=\"text-align: right;\">              0.00792428</td><td style=\"text-align: right;\">0.0890184</td><td style=\"text-align: right;\">0.00792428</td><td style=\"text-align: right;\">0.0555754</td><td style=\"text-align: right;\">0.0655235</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_225444_model_3</td><td style=\"text-align: right;\">              0.00799934</td><td style=\"text-align: right;\">0.089439 </td><td style=\"text-align: right;\">0.00799934</td><td style=\"text-align: right;\">0.0574452</td><td style=\"text-align: right;\">0.0646713</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_11        </td><td style=\"text-align: right;\">              0.00803284</td><td style=\"text-align: right;\">0.0896261</td><td style=\"text-align: right;\">0.00803284</td><td style=\"text-align: right;\">0.0576694</td><td style=\"text-align: right;\">0.0650569</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_225444_model_3</td><td style=\"text-align: right;\">              0.00803887</td><td style=\"text-align: right;\">0.0896597</td><td style=\"text-align: right;\">0.00803887</td><td style=\"text-align: right;\">0.0563179</td><td style=\"text-align: right;\">0.0663608</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_225444_model_3</td><td style=\"text-align: right;\">              0.00815033</td><td style=\"text-align: right;\">0.0902792</td><td style=\"text-align: right;\">0.00815033</td><td style=\"text-align: right;\">0.0582004</td><td style=\"text-align: right;\">0.0659742</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_225444_model_4</td><td style=\"text-align: right;\">              0.00815715</td><td style=\"text-align: right;\">0.0903169</td><td style=\"text-align: right;\">0.00815715</td><td style=\"text-align: right;\">0.0575587</td><td style=\"text-align: right;\">0.0666404</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_225444_model_4         </td><td style=\"text-align: right;\">              0.00827001</td><td style=\"text-align: right;\">0.0909396</td><td style=\"text-align: right;\">0.00827001</td><td style=\"text-align: right;\">0.0558092</td><td style=\"text-align: right;\">0.0679474</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_225444_model_2</td><td style=\"text-align: right;\">              0.00833137</td><td style=\"text-align: right;\">0.0912763</td><td style=\"text-align: right;\">0.00833137</td><td style=\"text-align: right;\">0.0549251</td><td style=\"text-align: right;\">0.0670811</td></tr>\n<tr><td>GLM_1_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.00843255</td><td style=\"text-align: right;\">0.0918289</td><td style=\"text-align: right;\">0.00843255</td><td style=\"text-align: right;\">0.0563854</td><td style=\"text-align: right;\">0.0673508</td></tr>\n<tr><td>GBM_1_AutoML_20200920_225444                       </td><td style=\"text-align: right;\">              0.00857711</td><td style=\"text-align: right;\">0.0926127</td><td style=\"text-align: right;\">0.00857711</td><td style=\"text-align: right;\">0.0565453</td><td style=\"text-align: right;\">0.0681473</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_225444_model_4</td><td style=\"text-align: right;\">              0.00895459</td><td style=\"text-align: right;\">0.0946287</td><td style=\"text-align: right;\">0.00895459</td><td style=\"text-align: right;\">0.0546409</td><td style=\"text-align: right;\">0.0740477</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_225444_model_2</td><td style=\"text-align: right;\">              0.00900151</td><td style=\"text-align: right;\">0.0948763</td><td style=\"text-align: right;\">0.00900151</td><td style=\"text-align: right;\">0.0589611</td><td style=\"text-align: right;\">0.069424 </td></tr>\n</tbody>\n</table>"},"metadata":{}},{"output_type":"stream","text":"\ngbm prediction progress: |████████████████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"stream","text":"/opt/conda/lib/python3.7/site-packages/h2o/job.py:70: UserWarning: Test/Validation dataset is missing column 'deg_Mg_pH10': substituting in a column of NaN\n  warnings.warn(w)\n/opt/conda/lib/python3.7/site-packages/h2o/job.py:70: UserWarning: Test/Validation dataset is missing column 'deg_Mg_50C': substituting in a column of NaN\n  warnings.warn(w)\n","name":"stderr"},{"output_type":"stream","text":"AutoML progress: |\n23:20:40.821: XGBoost_1_AutoML_20200920_232039 [XGBoost def_1] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_1_AutoML_20200920_232039_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n█\n23:20:41.823: XGBoost_2_AutoML_20200920_232039 [XGBoost def_2] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_2_AutoML_20200920_232039_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n█\n23:20:42.825: XGBoost_3_AutoML_20200920_232039 [XGBoost def_3] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_3_AutoML_20200920_232039_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n██████████████\n23:20:54.907: XRT_1_AutoML_20200920_232039 [DRF XRT (Extremely Randomized Trees)] failed: java.lang.AssertionError\n\n████████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"display_data","data":{"text/html":"<table>\n<thead>\n<tr><th>model_id                                           </th><th style=\"text-align: right;\">  mean_residual_deviance</th><th style=\"text-align: right;\">     rmse</th><th style=\"text-align: right;\">       mse</th><th style=\"text-align: right;\">      mae</th><th style=\"text-align: right;\">    rmsle</th></tr>\n</thead>\n<tbody>\n<tr><td>StackedEnsemble_AllModels_AutoML_20200920_232039   </td><td style=\"text-align: right;\">              0.00637792</td><td style=\"text-align: right;\">0.0798619</td><td style=\"text-align: right;\">0.00637792</td><td style=\"text-align: right;\">0.0522716</td><td style=\"text-align: right;\">0.0537331</td></tr>\n<tr><td>StackedEnsemble_BestOfFamily_AutoML_20200920_232039</td><td style=\"text-align: right;\">              0.00647724</td><td style=\"text-align: right;\">0.0804813</td><td style=\"text-align: right;\">0.00647724</td><td style=\"text-align: right;\">0.0533526</td><td style=\"text-align: right;\">0.0542402</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_232039_model_1</td><td style=\"text-align: right;\">              0.00653524</td><td style=\"text-align: right;\">0.0808408</td><td style=\"text-align: right;\">0.00653524</td><td style=\"text-align: right;\">0.052537 </td><td style=\"text-align: right;\">0.0542802</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_232039_model_1</td><td style=\"text-align: right;\">              0.00676021</td><td style=\"text-align: right;\">0.0822205</td><td style=\"text-align: right;\">0.00676021</td><td style=\"text-align: right;\">0.0544577</td><td style=\"text-align: right;\">0.0558394</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_232039_model_2</td><td style=\"text-align: right;\">              0.00678964</td><td style=\"text-align: right;\">0.0823993</td><td style=\"text-align: right;\">0.00678964</td><td style=\"text-align: right;\">0.0562424</td><td style=\"text-align: right;\">0.0551984</td></tr>\n<tr><td>GBM_1_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00681156</td><td style=\"text-align: right;\">0.0825321</td><td style=\"text-align: right;\">0.00681156</td><td style=\"text-align: right;\">0.0557185</td><td style=\"text-align: right;\">0.0562741</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_232039_model_4</td><td style=\"text-align: right;\">              0.00686594</td><td style=\"text-align: right;\">0.082861 </td><td style=\"text-align: right;\">0.00686594</td><td style=\"text-align: right;\">0.0538982</td><td style=\"text-align: right;\">0.0554044</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_232039_model_1</td><td style=\"text-align: right;\">              0.00688968</td><td style=\"text-align: right;\">0.0830041</td><td style=\"text-align: right;\">0.00688968</td><td style=\"text-align: right;\">0.0556217</td><td style=\"text-align: right;\">0.0563086</td></tr>\n<tr><td>GBM_2_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00691381</td><td style=\"text-align: right;\">0.0831493</td><td style=\"text-align: right;\">0.00691381</td><td style=\"text-align: right;\">0.0556294</td><td style=\"text-align: right;\">0.056145 </td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_6         </td><td style=\"text-align: right;\">              0.00693012</td><td style=\"text-align: right;\">0.0832474</td><td style=\"text-align: right;\">0.00693012</td><td style=\"text-align: right;\">0.055368 </td><td style=\"text-align: right;\">0.0562441</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_7         </td><td style=\"text-align: right;\">              0.00694382</td><td style=\"text-align: right;\">0.0833296</td><td style=\"text-align: right;\">0.00694382</td><td style=\"text-align: right;\">0.0555037</td><td style=\"text-align: right;\">0.0567081</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_3         </td><td style=\"text-align: right;\">              0.00696172</td><td style=\"text-align: right;\">0.0834369</td><td style=\"text-align: right;\">0.00696172</td><td style=\"text-align: right;\">0.0555711</td><td style=\"text-align: right;\">0.0566776</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_9         </td><td style=\"text-align: right;\">              0.00700846</td><td style=\"text-align: right;\">0.0837165</td><td style=\"text-align: right;\">0.00700846</td><td style=\"text-align: right;\">0.0563422</td><td style=\"text-align: right;\">0.0567435</td></tr>\n<tr><td>DeepLearning_1_AutoML_20200920_232039              </td><td style=\"text-align: right;\">              0.00702312</td><td style=\"text-align: right;\">0.0838041</td><td style=\"text-align: right;\">0.00702312</td><td style=\"text-align: right;\">0.0573221</td><td style=\"text-align: right;\">0.0567748</td></tr>\n<tr><td>GBM_5_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00703818</td><td style=\"text-align: right;\">0.0838939</td><td style=\"text-align: right;\">0.00703818</td><td style=\"text-align: right;\">0.0560971</td><td style=\"text-align: right;\">0.0570546</td></tr>\n<tr><td>GBM_3_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00704313</td><td style=\"text-align: right;\">0.0839234</td><td style=\"text-align: right;\">0.00704313</td><td style=\"text-align: right;\">0.0557884</td><td style=\"text-align: right;\">0.0566746</td></tr>\n<tr><td>GLM_1_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00704933</td><td style=\"text-align: right;\">0.0839603</td><td style=\"text-align: right;\">0.00704933</td><td style=\"text-align: right;\">0.0556542</td><td style=\"text-align: right;\">0.056788 </td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_232039_model_3</td><td style=\"text-align: right;\">              0.0070615 </td><td style=\"text-align: right;\">0.0840327</td><td style=\"text-align: right;\">0.0070615 </td><td style=\"text-align: right;\">0.0550984</td><td style=\"text-align: right;\">0.0573249</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_5         </td><td style=\"text-align: right;\">              0.00719904</td><td style=\"text-align: right;\">0.0848471</td><td style=\"text-align: right;\">0.00719904</td><td style=\"text-align: right;\">0.056928 </td><td style=\"text-align: right;\">0.0573538</td></tr>\n<tr><td>DRF_1_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00730684</td><td style=\"text-align: right;\">0.0854801</td><td style=\"text-align: right;\">0.00730684</td><td style=\"text-align: right;\">0.0570398</td><td style=\"text-align: right;\">0.0577082</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_232039_model_2</td><td style=\"text-align: right;\">              0.00731047</td><td style=\"text-align: right;\">0.0855013</td><td style=\"text-align: right;\">0.00731047</td><td style=\"text-align: right;\">0.054658 </td><td style=\"text-align: right;\">0.0568342</td></tr>\n<tr><td>GBM_4_AutoML_20200920_232039                       </td><td style=\"text-align: right;\">              0.00733764</td><td style=\"text-align: right;\">0.08566  </td><td style=\"text-align: right;\">0.00733764</td><td style=\"text-align: right;\">0.0577252</td><td style=\"text-align: right;\">0.0579831</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_11        </td><td style=\"text-align: right;\">              0.00735895</td><td style=\"text-align: right;\">0.0857843</td><td style=\"text-align: right;\">0.00735895</td><td style=\"text-align: right;\">0.0575571</td><td style=\"text-align: right;\">0.0577654</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_2         </td><td style=\"text-align: right;\">              0.00742048</td><td style=\"text-align: right;\">0.0861422</td><td style=\"text-align: right;\">0.00742048</td><td style=\"text-align: right;\">0.0583562</td><td style=\"text-align: right;\">0.0582507</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_1         </td><td style=\"text-align: right;\">              0.00747505</td><td style=\"text-align: right;\">0.0864584</td><td style=\"text-align: right;\">0.00747505</td><td style=\"text-align: right;\">0.05858  </td><td style=\"text-align: right;\">0.05906  </td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_4         </td><td style=\"text-align: right;\">              0.00748317</td><td style=\"text-align: right;\">0.0865053</td><td style=\"text-align: right;\">0.00748317</td><td style=\"text-align: right;\">0.0570416</td><td style=\"text-align: right;\">0.0605439</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_232039_model_2</td><td style=\"text-align: right;\">              0.00768434</td><td style=\"text-align: right;\">0.0876603</td><td style=\"text-align: right;\">0.00768434</td><td style=\"text-align: right;\">0.0565267</td><td style=\"text-align: right;\">0.0601485</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_8         </td><td style=\"text-align: right;\">              0.00803507</td><td style=\"text-align: right;\">0.0896385</td><td style=\"text-align: right;\">0.00803507</td><td style=\"text-align: right;\">0.0605016</td><td style=\"text-align: right;\">0.0609673</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_232039_model_3</td><td style=\"text-align: right;\">              0.00856802</td><td style=\"text-align: right;\">0.0925636</td><td style=\"text-align: right;\">0.00856802</td><td style=\"text-align: right;\">0.0577701</td><td style=\"text-align: right;\">0.0757606</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_232039_model_3</td><td style=\"text-align: right;\">              0.00905336</td><td style=\"text-align: right;\">0.0951491</td><td style=\"text-align: right;\">0.00905336</td><td style=\"text-align: right;\">0.0599224</td><td style=\"text-align: right;\">0.0662729</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_232039_model_10        </td><td style=\"text-align: right;\">              0.00909197</td><td style=\"text-align: right;\">0.0953518</td><td style=\"text-align: right;\">0.00909197</td><td style=\"text-align: right;\">0.0689963</td><td style=\"text-align: right;\">0.0650554</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_232039_model_4</td><td style=\"text-align: right;\">              0.0126662 </td><td style=\"text-align: right;\">0.112544 </td><td style=\"text-align: right;\">0.0126662 </td><td style=\"text-align: right;\">0.0858245</td><td style=\"text-align: right;\">0.0750043</td></tr>\n</tbody>\n</table>"},"metadata":{}},{"output_type":"stream","text":"\nstackedensemble prediction progress: |████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"stream","text":"/opt/conda/lib/python3.7/site-packages/h2o/job.py:70: UserWarning: Test/Validation dataset is missing column 'reactivity': substituting in a column of NaN\n  warnings.warn(w)\n","name":"stderr"},{"output_type":"stream","text":"AutoML progress: |\n23:48:25.202: XGBoost_1_AutoML_20200920_234824 [XGBoost def_1] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_1_AutoML_20200920_234824_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n█\n23:48:26.205: XGBoost_2_AutoML_20200920_234824 [XGBoost def_2] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_2_AutoML_20200920_234824_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n█\n23:48:27.207: XGBoost_3_AutoML_20200920_234824 [XGBoost def_3] failed: water.exceptions.H2OModelBuilderIllegalArgumentException: Illegal argument(s) for XGBoost model: XGBoost_3_AutoML_20200920_234824_cv_1.  Details: ERRR on field: _response_column: Response contains missing values (NAs) - not supported by XGBoost.\n\n\n█████████████\n23:48:38.278: XRT_1_AutoML_20200920_234824 [DRF XRT (Extremely Randomized Trees)] failed: java.lang.AssertionError\n\n█████████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"display_data","data":{"text/html":"<table>\n<thead>\n<tr><th>model_id                                           </th><th style=\"text-align: right;\">  mean_residual_deviance</th><th style=\"text-align: right;\">    rmse</th><th style=\"text-align: right;\">      mse</th><th style=\"text-align: right;\">      mae</th><th style=\"text-align: right;\">    rmsle</th></tr>\n</thead>\n<tbody>\n<tr><td>StackedEnsemble_AllModels_AutoML_20200920_234824   </td><td style=\"text-align: right;\">               0.010006 </td><td style=\"text-align: right;\">0.10003 </td><td style=\"text-align: right;\">0.010006 </td><td style=\"text-align: right;\">0.06154  </td><td style=\"text-align: right;\">0.078252 </td></tr>\n<tr><td>GBM_1_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0101166</td><td style=\"text-align: right;\">0.100581</td><td style=\"text-align: right;\">0.0101166</td><td style=\"text-align: right;\">0.0613664</td><td style=\"text-align: right;\">0.0770673</td></tr>\n<tr><td>StackedEnsemble_BestOfFamily_AutoML_20200920_234824</td><td style=\"text-align: right;\">               0.0101371</td><td style=\"text-align: right;\">0.100683</td><td style=\"text-align: right;\">0.0101371</td><td style=\"text-align: right;\">0.0631146</td><td style=\"text-align: right;\">0.0781736</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_234824_model_3</td><td style=\"text-align: right;\">               0.0103028</td><td style=\"text-align: right;\">0.101502</td><td style=\"text-align: right;\">0.0103028</td><td style=\"text-align: right;\">0.066374 </td><td style=\"text-align: right;\">0.0778297</td></tr>\n<tr><td>GBM_3_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0105303</td><td style=\"text-align: right;\">0.102617</td><td style=\"text-align: right;\">0.0105303</td><td style=\"text-align: right;\">0.0630167</td><td style=\"text-align: right;\">0.0793493</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_234824_model_1</td><td style=\"text-align: right;\">               0.010566 </td><td style=\"text-align: right;\">0.102791</td><td style=\"text-align: right;\">0.010566 </td><td style=\"text-align: right;\">0.0647867</td><td style=\"text-align: right;\">0.0827198</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_7         </td><td style=\"text-align: right;\">               0.0106444</td><td style=\"text-align: right;\">0.103172</td><td style=\"text-align: right;\">0.0106444</td><td style=\"text-align: right;\">0.0617179</td><td style=\"text-align: right;\">0.079731 </td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_3         </td><td style=\"text-align: right;\">               0.0106946</td><td style=\"text-align: right;\">0.103415</td><td style=\"text-align: right;\">0.0106946</td><td style=\"text-align: right;\">0.0614676</td><td style=\"text-align: right;\">0.0795407</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_234824_model_2</td><td style=\"text-align: right;\">               0.0107527</td><td style=\"text-align: right;\">0.103695</td><td style=\"text-align: right;\">0.0107527</td><td style=\"text-align: right;\">0.0685172</td><td style=\"text-align: right;\">0.0765239</td></tr>\n<tr><td>GBM_2_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0107732</td><td style=\"text-align: right;\">0.103794</td><td style=\"text-align: right;\">0.0107732</td><td style=\"text-align: right;\">0.062418 </td><td style=\"text-align: right;\">0.0795746</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_6         </td><td style=\"text-align: right;\">               0.0108052</td><td style=\"text-align: right;\">0.103948</td><td style=\"text-align: right;\">0.0108052</td><td style=\"text-align: right;\">0.0620212</td><td style=\"text-align: right;\">0.079997 </td></tr>\n<tr><td>GBM_4_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0108226</td><td style=\"text-align: right;\">0.104032</td><td style=\"text-align: right;\">0.0108226</td><td style=\"text-align: right;\">0.0639955</td><td style=\"text-align: right;\">0.0795495</td></tr>\n<tr><td>GLM_1_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0108797</td><td style=\"text-align: right;\">0.104306</td><td style=\"text-align: right;\">0.0108797</td><td style=\"text-align: right;\">0.0647426</td><td style=\"text-align: right;\">0.0814098</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_2         </td><td style=\"text-align: right;\">               0.0109122</td><td style=\"text-align: right;\">0.104461</td><td style=\"text-align: right;\">0.0109122</td><td style=\"text-align: right;\">0.0656829</td><td style=\"text-align: right;\">0.0803355</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_5         </td><td style=\"text-align: right;\">               0.0109724</td><td style=\"text-align: right;\">0.104749</td><td style=\"text-align: right;\">0.0109724</td><td style=\"text-align: right;\">0.0635837</td><td style=\"text-align: right;\">0.0804398</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_9         </td><td style=\"text-align: right;\">               0.0110121</td><td style=\"text-align: right;\">0.104938</td><td style=\"text-align: right;\">0.0110121</td><td style=\"text-align: right;\">0.0643262</td><td style=\"text-align: right;\">0.0814016</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_234824_model_1</td><td style=\"text-align: right;\">               0.0111092</td><td style=\"text-align: right;\">0.1054  </td><td style=\"text-align: right;\">0.0111092</td><td style=\"text-align: right;\">0.0613637</td><td style=\"text-align: right;\">0.0829204</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_234824_model_1</td><td style=\"text-align: right;\">               0.0111106</td><td style=\"text-align: right;\">0.105407</td><td style=\"text-align: right;\">0.0111106</td><td style=\"text-align: right;\">0.0631975</td><td style=\"text-align: right;\">0.0829442</td></tr>\n<tr><td>DeepLearning_1_AutoML_20200920_234824              </td><td style=\"text-align: right;\">               0.0111674</td><td style=\"text-align: right;\">0.105676</td><td style=\"text-align: right;\">0.0111674</td><td style=\"text-align: right;\">0.0610485</td><td style=\"text-align: right;\">0.0836552</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_11        </td><td style=\"text-align: right;\">               0.0111774</td><td style=\"text-align: right;\">0.105723</td><td style=\"text-align: right;\">0.0111774</td><td style=\"text-align: right;\">0.0657369</td><td style=\"text-align: right;\">0.0812042</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_234824_model_4</td><td style=\"text-align: right;\">               0.0112784</td><td style=\"text-align: right;\">0.1062  </td><td style=\"text-align: right;\">0.0112784</td><td style=\"text-align: right;\">0.0629212</td><td style=\"text-align: right;\">0.0832523</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_234824_model_3</td><td style=\"text-align: right;\">               0.0113549</td><td style=\"text-align: right;\">0.10656 </td><td style=\"text-align: right;\">0.0113549</td><td style=\"text-align: right;\">0.0658942</td><td style=\"text-align: right;\">0.0812551</td></tr>\n<tr><td>DeepLearning_grid__3_AutoML_20200920_234824_model_2</td><td style=\"text-align: right;\">               0.0113711</td><td style=\"text-align: right;\">0.106635</td><td style=\"text-align: right;\">0.0113711</td><td style=\"text-align: right;\">0.0648853</td><td style=\"text-align: right;\">0.0847521</td></tr>\n<tr><td>DRF_1_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0114376</td><td style=\"text-align: right;\">0.106947</td><td style=\"text-align: right;\">0.0114376</td><td style=\"text-align: right;\">0.0645839</td><td style=\"text-align: right;\">0.0833392</td></tr>\n<tr><td>GBM_5_AutoML_20200920_234824                       </td><td style=\"text-align: right;\">               0.0114407</td><td style=\"text-align: right;\">0.106961</td><td style=\"text-align: right;\">0.0114407</td><td style=\"text-align: right;\">0.0623902</td><td style=\"text-align: right;\">0.0822426</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_234824_model_2</td><td style=\"text-align: right;\">               0.0114927</td><td style=\"text-align: right;\">0.107204</td><td style=\"text-align: right;\">0.0114927</td><td style=\"text-align: right;\">0.0637197</td><td style=\"text-align: right;\">0.0825954</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_4         </td><td style=\"text-align: right;\">               0.0120194</td><td style=\"text-align: right;\">0.109633</td><td style=\"text-align: right;\">0.0120194</td><td style=\"text-align: right;\">0.0625521</td><td style=\"text-align: right;\">0.0843163</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_1         </td><td style=\"text-align: right;\">               0.0128119</td><td style=\"text-align: right;\">0.11319 </td><td style=\"text-align: right;\">0.0128119</td><td style=\"text-align: right;\">0.0647983</td><td style=\"text-align: right;\">0.0882216</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_10        </td><td style=\"text-align: right;\">               0.0128833</td><td style=\"text-align: right;\">0.113505</td><td style=\"text-align: right;\">0.0128833</td><td style=\"text-align: right;\">0.0701721</td><td style=\"text-align: right;\">0.0875504</td></tr>\n<tr><td>GBM_grid__1_AutoML_20200920_234824_model_8         </td><td style=\"text-align: right;\">               0.0133266</td><td style=\"text-align: right;\">0.115441</td><td style=\"text-align: right;\">0.0133266</td><td style=\"text-align: right;\">0.0665975</td><td style=\"text-align: right;\">0.0899724</td></tr>\n<tr><td>DeepLearning_grid__1_AutoML_20200920_234824_model_3</td><td style=\"text-align: right;\">               0.0141652</td><td style=\"text-align: right;\">0.119018</td><td style=\"text-align: right;\">0.0141652</td><td style=\"text-align: right;\">0.0674472</td><td style=\"text-align: right;\">0.0849594</td></tr>\n<tr><td>DeepLearning_grid__2_AutoML_20200920_234824_model_4</td><td style=\"text-align: right;\">               0.0158513</td><td style=\"text-align: right;\">0.125902</td><td style=\"text-align: right;\">0.0158513</td><td style=\"text-align: right;\">0.0883706</td><td style=\"text-align: right;\">0.0986644</td></tr>\n</tbody>\n</table>"},"metadata":{}},{"output_type":"stream","text":"\nstackedensemble prediction progress: |████████████████████████████████████| 100%\n","name":"stdout"},{"output_type":"execute_result","execution_count":22,"data":{"text/plain":"      reactivity  deg_Mg_pH10  deg_Mg_50C\n0       0.396706     0.454717    0.408552\n1       0.400306     0.454101    0.402659\n2       0.397701     0.451536    0.410363\n3       0.399495     0.450908    0.405003\n4       0.417669     0.444551    0.416413\n...          ...          ...         ...\n3629    0.415873     0.457682    0.405266\n3630    0.395881     0.456338    0.402828\n3631    0.410651     0.458140    0.415940\n3632    0.395894     0.452541    0.409513\n3633    0.399154     0.458056    0.405797\n\n[3634 rows x 3 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>reactivity</th>\n      <th>deg_Mg_pH10</th>\n      <th>deg_Mg_50C</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0.396706</td>\n      <td>0.454717</td>\n      <td>0.408552</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>0.400306</td>\n      <td>0.454101</td>\n      <td>0.402659</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>0.397701</td>\n      <td>0.451536</td>\n      <td>0.410363</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>0.399495</td>\n      <td>0.450908</td>\n      <td>0.405003</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>0.417669</td>\n      <td>0.444551</td>\n      <td>0.416413</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>3629</th>\n      <td>0.415873</td>\n      <td>0.457682</td>\n      <td>0.405266</td>\n    </tr>\n    <tr>\n      <th>3630</th>\n      <td>0.395881</td>\n      <td>0.456338</td>\n      <td>0.402828</td>\n    </tr>\n    <tr>\n      <th>3631</th>\n      <td>0.410651</td>\n      <td>0.458140</td>\n      <td>0.415940</td>\n    </tr>\n    <tr>\n      <th>3632</th>\n      <td>0.395894</td>\n      <td>0.452541</td>\n      <td>0.409513</td>\n    </tr>\n    <tr>\n      <th>3633</th>\n      <td>0.399154</td>\n      <td>0.458056</td>\n      <td>0.405797</td>\n    </tr>\n  </tbody>\n</table>\n<p>3634 rows × 3 columns</p>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"h2o.shutdown(prompt=False)","execution_count":23,"outputs":[{"output_type":"stream","text":"/opt/conda/lib/python3.7/site-packages/ipykernel_launcher.py:1: DeprecationWarning: Deprecated, use ``h2o.cluster().shutdown()``.\n  \"\"\"Entry point for launching an IPython kernel.\n","name":"stderr"},{"output_type":"stream","text":"H2O session _sid_8377 closed.\n","name":"stdout"}]},{"metadata":{},"cell_type":"markdown","source":"# Submit\n- Reference:\n- https://www.kaggle.com/kaushal2896/openvaccine-xgboost-baseline"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Create submission csv\nsubmission_df = model.loc[model.index.repeat(list(test_df['seq_length']))].reset_index(drop=True)\nsubmission_df = submission_df.rename(columns={0: 'reactivity', 1: 'deg_Mg_pH10', 2: 'deg_Mg_50C'})\nsubmission_df['id_seqpos'] = sample_sub_df['id_seqpos']\nsubmission_df['deg_pH10'] = 0.0\nsubmission_df['deg_50C'] = 0.0\nsubmission_df = submission_df[['id_seqpos', 'reactivity', 'deg_Mg_pH10', 'deg_pH10', 'deg_Mg_50C', 'deg_50C']]\nsubmission_df","execution_count":24,"outputs":[{"output_type":"execute_result","execution_count":24,"data":{"text/plain":"               id_seqpos  reactivity  deg_Mg_pH10  deg_pH10  deg_Mg_50C  \\\n0         id_00073f8be_0    0.396706     0.454717       0.0    0.408552   \n1         id_00073f8be_1    0.396706     0.454717       0.0    0.408552   \n2         id_00073f8be_2    0.396706     0.454717       0.0    0.408552   \n3         id_00073f8be_3    0.396706     0.454717       0.0    0.408552   \n4         id_00073f8be_4    0.396706     0.454717       0.0    0.408552   \n...                  ...         ...          ...       ...         ...   \n457948  id_ffda94f24_125    0.399154     0.458056       0.0    0.405797   \n457949  id_ffda94f24_126    0.399154     0.458056       0.0    0.405797   \n457950  id_ffda94f24_127    0.399154     0.458056       0.0    0.405797   \n457951  id_ffda94f24_128    0.399154     0.458056       0.0    0.405797   \n457952  id_ffda94f24_129    0.399154     0.458056       0.0    0.405797   \n\n        deg_50C  \n0           0.0  \n1           0.0  \n2           0.0  \n3           0.0  \n4           0.0  \n...         ...  \n457948      0.0  \n457949      0.0  \n457950      0.0  \n457951      0.0  \n457952      0.0  \n\n[457953 rows x 6 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id_seqpos</th>\n      <th>reactivity</th>\n      <th>deg_Mg_pH10</th>\n      <th>deg_pH10</th>\n      <th>deg_Mg_50C</th>\n      <th>deg_50C</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>id_00073f8be_0</td>\n      <td>0.396706</td>\n      <td>0.454717</td>\n      <td>0.0</td>\n      <td>0.408552</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>id_00073f8be_1</td>\n      <td>0.396706</td>\n      <td>0.454717</td>\n      <td>0.0</td>\n      <td>0.408552</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>id_00073f8be_2</td>\n      <td>0.396706</td>\n      <td>0.454717</td>\n      <td>0.0</td>\n      <td>0.408552</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>id_00073f8be_3</td>\n      <td>0.396706</td>\n      <td>0.454717</td>\n      <td>0.0</td>\n      <td>0.408552</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>id_00073f8be_4</td>\n      <td>0.396706</td>\n      <td>0.454717</td>\n      <td>0.0</td>\n      <td>0.408552</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>457948</th>\n      <td>id_ffda94f24_125</td>\n      <td>0.399154</td>\n      <td>0.458056</td>\n      <td>0.0</td>\n      <td>0.405797</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>457949</th>\n      <td>id_ffda94f24_126</td>\n      <td>0.399154</td>\n      <td>0.458056</td>\n      <td>0.0</td>\n      <td>0.405797</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>457950</th>\n      <td>id_ffda94f24_127</td>\n      <td>0.399154</td>\n      <td>0.458056</td>\n      <td>0.0</td>\n      <td>0.405797</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>457951</th>\n      <td>id_ffda94f24_128</td>\n      <td>0.399154</td>\n      <td>0.458056</td>\n      <td>0.0</td>\n      <td>0.405797</td>\n      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>457952</th>\n      <td>id_ffda94f24_129</td>\n      <td>0.399154</td>\n      <td>0.458056</td>\n      <td>0.0</td>\n      <td>0.405797</td>\n      <td>0.0</td>\n    </tr>\n  </tbody>\n</table>\n<p>457953 rows × 6 columns</p>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Save that CSV for submission\nsubmission_df.to_csv('submission.csv', index=False)","execution_count":25,"outputs":[]}],"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.7.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":4}