bacteria-dna-classification.ipynb

{"cells":[{"source":"<a href=\"https://www.kaggle.com/samu2505/bacteria-dna-classification?scriptVersionId=89213065\" target=\"_blank\"><img align=\"left\" alt=\"Kaggle\" title=\"Open in Kaggle\" src=\"https://kaggle.com/static/images/open-in-kaggle.svg\"></a>","metadata":{},"cell_type":"markdown","outputs":[],"execution_count":0},{"cell_type":"code","execution_count":1,"id":"28c166d1","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.execute_input":"2022-03-03T16:42:54.925042Z","iopub.status.busy":"2022-03-03T16:42:54.924327Z","iopub.status.idle":"2022-03-03T16:42:54.930242Z","shell.execute_reply":"2022-03-03T16:42:54.93106Z","shell.execute_reply.started":"2022-03-03T16:24:57.977857Z"},"papermill":{"duration":0.035251,"end_time":"2022-03-03T16:42:54.931494","exception":false,"start_time":"2022-03-03T16:42:54.896243","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["/kaggle/input/tabular-playground-series-feb-2022/sample_submission.csv\n","/kaggle/input/tabular-playground-series-feb-2022/train.csv\n","/kaggle/input/tabular-playground-series-feb-2022/test.csv\n"]}],"source":["# This Python 3 environment comes with many helpful analytics libraries installed\n","# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n","# For example, here's several helpful packages to load\n","\n","import numpy as np # linear algebra\n","import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n","\n","# Input data files are available in the read-only \"../input/\" directory\n","# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n","\n","import os\n","for dirname, _, filenames in os.walk('/kaggle/input'):\n","    for filename in filenames:\n","        print(os.path.join(dirname, filename))\n","\n","# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n","# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"]},{"cell_type":"code","execution_count":2,"id":"71e1fcd5","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:42:54.974556Z","iopub.status.busy":"2022-03-03T16:42:54.97389Z","iopub.status.idle":"2022-03-03T16:43:01.866847Z","shell.execute_reply":"2022-03-03T16:43:01.865924Z","shell.execute_reply.started":"2022-03-03T16:24:58.013782Z"},"papermill":{"duration":6.915096,"end_time":"2022-03-03T16:43:01.866997","exception":false,"start_time":"2022-03-03T16:42:54.951901","status":"completed"},"tags":[]},"outputs":[],"source":["# I'll be starting with tensorflow \n","import tensorflow as tf\n","from tensorflow import keras\n","from tensorflow.keras import layers, datasets\n","\n","from tqdm.auto import tqdm\n","\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","%matplotlib inline"]},{"cell_type":"code","execution_count":3,"id":"8a91de91","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:01.911843Z","iopub.status.busy":"2022-03-03T16:43:01.91119Z","iopub.status.idle":"2022-03-03T16:43:36.967821Z","shell.execute_reply":"2022-03-03T16:43:36.968336Z","shell.execute_reply.started":"2022-03-03T16:25:05.132087Z"},"papermill":{"duration":35.081989,"end_time":"2022-03-03T16:43:36.968518","exception":false,"start_time":"2022-03-03T16:43:01.886529","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["Training data shape:  (200000, 287)\n","Test data shape:  (100000, 286)\n"]}],"source":["train = pd.read_csv(\"../input/tabular-playground-series-feb-2022/train.csv\", index_col=0)\n","test = pd.read_csv(\"../input/tabular-playground-series-feb-2022/test.csv\", index_col=0)\n","\n","print(\"Training data shape: \", train.shape)\n","print(\"Test data shape: \", test.shape)"]},{"cell_type":"code","execution_count":4,"id":"444b8043","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:37.014609Z","iopub.status.busy":"2022-03-03T16:43:37.013734Z","iopub.status.idle":"2022-03-03T16:43:39.82616Z","shell.execute_reply":"2022-03-03T16:43:39.826769Z","shell.execute_reply.started":"2022-03-03T16:25:46.43016Z"},"papermill":{"duration":2.838466,"end_time":"2022-03-03T16:43:39.826948","exception":false,"start_time":"2022-03-03T16:43:36.988482","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["Data types:\n"," [dtype('float64') dtype('O')]\n","\n","Missing data in train set:\n"," 0\n","\n","Missing data in test set:\n"," 0\n","\n","Duplicate values in train set:\n"," 76007\n","\n","Duplicate values in test set:\n"," 26779\n"]}],"source":["# checking available data types\n","print(\"Data types:\\n\", train.dtypes.unique())\n","\n","# checking for missing data\n","print(\"\\nMissing data in train set:\\n\", np.sum(train.isna().sum()))\n","print(\"\\nMissing data in test set:\\n\", np.sum(test.isna().sum()))\n","\n","# checking for duplicate values\n","print(\"\\nDuplicate values in train set:\\n\", train.duplicated().sum())\n","print(\"\\nDuplicate values in test set:\\n\", test.duplicated().sum())"]},{"cell_type":"code","execution_count":5,"id":"0f53eff0","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:39.872617Z","iopub.status.busy":"2022-03-03T16:43:39.871308Z","iopub.status.idle":"2022-03-03T16:43:43.220126Z","shell.execute_reply":"2022-03-03T16:43:43.220618Z","shell.execute_reply.started":"2022-03-03T16:25:49.189851Z"},"papermill":{"duration":3.374028,"end_time":"2022-03-03T16:43:43.220833","exception":false,"start_time":"2022-03-03T16:43:39.846805","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["Shape of new training data:  (123993, 287)\n","Checking number of duplicates in new training data:  0\n"]}],"source":["# Now, have to deal with duplicate values in the dataset\n","train_with_duplicates = train.copy()\n","\n","# drop the duplicate values out of the dataset for both the train and test sets\n","train.drop_duplicates(keep='first', inplace=True)\n","# Dont't temper with the test set.\n","# test.drop_duplicates(keep='first', inplace=True)\n","\n","print(\"Shape of new training data: \", train.shape)\n","print(\"Checking number of duplicates in new training data: \", train.duplicated().sum())"]},{"cell_type":"code","execution_count":6,"id":"d8b08353","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:43.265121Z","iopub.status.busy":"2022-03-03T16:43:43.264163Z","iopub.status.idle":"2022-03-03T16:43:43.269329Z","shell.execute_reply":"2022-03-03T16:43:43.269732Z","shell.execute_reply.started":"2022-03-03T16:25:52.31987Z"},"papermill":{"duration":0.02875,"end_time":"2022-03-03T16:43:43.269918","exception":false,"start_time":"2022-03-03T16:43:43.241168","status":"completed"},"tags":[]},"outputs":[],"source":["# CHECKING FOR THE DISTRIBUTION OF THE TARGETS FOR BOTH CASES\n","def plot(train, title):\n","    plt.figure(figsize=(10, 6))\n","    plt.title(title)\n","    plt.xticks(rotation=30, ha='right')\n","    ax = sns.countplot(x=train['target'], data=train)\n","    print(pd.Series(train['target'], index=train.index).value_counts().sort_index() / len(train) * 100)\n","    plt.show()"]},{"cell_type":"code","execution_count":7,"id":"185beb01","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:43.320559Z","iopub.status.busy":"2022-03-03T16:43:43.319913Z","iopub.status.idle":"2022-03-03T16:43:43.753604Z","shell.execute_reply":"2022-03-03T16:43:43.754126Z","shell.execute_reply.started":"2022-03-03T16:25:52.328733Z"},"papermill":{"duration":0.463113,"end_time":"2022-03-03T16:43:43.754407","exception":false,"start_time":"2022-03-03T16:43:43.291294","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["Bacteroides_fragilis        10.098957\n","Campylobacter_jejuni        10.056213\n","Enterococcus_hirae           9.978789\n","Escherichia_coli             9.917495\n","Escherichia_fergusonii       9.907817\n","Klebsiella_pneumoniae       10.016694\n","Salmonella_enterica          9.992500\n","Staphylococcus_aureus       10.012662\n","Streptococcus_pneumoniae    10.013469\n","Streptococcus_pyogenes      10.005404\n","Name: target, dtype: float64\n"]},{"data":{"image/png":"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\n","text/plain":["<Figure size 720x432 with 1 Axes>"]},"metadata":{"needs_background":"light"},"output_type":"display_data"}],"source":["plot(train, \"Dataset without duplicates\")"]},{"cell_type":"code","execution_count":8,"id":"4d67449a","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:43.803724Z","iopub.status.busy":"2022-03-03T16:43:43.803116Z","iopub.status.idle":"2022-03-03T16:43:44.282943Z","shell.execute_reply":"2022-03-03T16:43:44.283387Z","shell.execute_reply.started":"2022-03-03T16:25:52.834931Z"},"papermill":{"duration":0.507139,"end_time":"2022-03-03T16:43:44.28356","exception":false,"start_time":"2022-03-03T16:43:43.776421","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["Bacteroides_fragilis        10.0695\n","Campylobacter_jejuni        10.0315\n","Enterococcus_hirae           9.9735\n","Escherichia_coli             9.9790\n","Escherichia_fergusonii       9.9685\n","Klebsiella_pneumoniae        9.9235\n","Salmonella_enterica         10.0150\n","Staphylococcus_aureus        9.9645\n","Streptococcus_pneumoniae    10.0370\n","Streptococcus_pyogenes      10.0380\n","Name: target, dtype: float64\n"]},{"data":{"image/png":"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\n","text/plain":["<Figure size 720x432 with 1 Axes>"]},"metadata":{"needs_background":"light"},"output_type":"display_data"}],"source":["plot(train_with_duplicates, \"Dataset with duplicates\")"]},{"cell_type":"code","execution_count":9,"id":"3bca6a2b","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:44.333238Z","iopub.status.busy":"2022-03-03T16:43:44.33258Z","iopub.status.idle":"2022-03-03T16:43:44.342923Z","shell.execute_reply":"2022-03-03T16:43:44.3434Z","shell.execute_reply.started":"2022-03-03T16:25:53.475845Z"},"papermill":{"duration":0.036603,"end_time":"2022-03-03T16:43:44.343595","exception":false,"start_time":"2022-03-03T16:43:44.306992","status":"completed"},"tags":[]},"outputs":[],"source":["# Next, checking for memory usage \n","# print(\"Memory usage(train_with_duplicates): {:5.2f} Mb\".format(train_with_duplicates.memory_usage().sum()/1024**2))\n","# print(\"Memory usage(train): {:5.2f} Mb\".format(train.memory_usage().sum()/1024**2))\n","\n","# Still, the memory usage can be reduced further\n","def reduce_mem_usage(df, verbose=True):\n","    numerics = ['int8', 'int16', 'int32', 'int64', 'float32', 'float64']\n","    initial_mem = df.memory_usage().sum()/1024**2\n","    \n","    for col in df.columns:\n","        col_dtype = df[col].dtypes\n","        \n","        if col_dtype in numerics:\n","            c_min = df[col].min()\n","            c_max = df[col].max()\n","            \n","            if str(col_dtype)[:3] == 'int':  \n","                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n","                    df[col] = df[col].astype(np.int8)\n","                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n","                    df[col] = df[col].astype(np.int16)\n","                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n","                    df[col] = df[col].astype(np.int32)\n","                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n","                    df[col] = df[col].astype(np.int64)\n","                \n","            else:\n","                if c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n","                    df[col] = df[col].astype(np.float32)\n","                else:\n","                    df[col] = df[col].astype(np.float64)\n","                    \n","    end_mem = df.memory_usage().sum()/1024**2\n","    if verbose:\n","        print(\"Mem usage decreased to {:5.2f} Mb, ({:4.2f}%)\".format(end_mem, 100*(initial_mem - end_mem)/initial_mem))\n","    return df"]},{"cell_type":"code","execution_count":10,"id":"d1623d08","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:43:44.393246Z","iopub.status.busy":"2022-03-03T16:43:44.392575Z","iopub.status.idle":"2022-03-03T16:44:07.251267Z","shell.execute_reply":"2022-03-03T16:44:07.250548Z","shell.execute_reply.started":"2022-03-03T16:25:53.492994Z"},"papermill":{"duration":22.884641,"end_time":"2022-03-03T16:44:07.251417","exception":false,"start_time":"2022-03-03T16:43:44.366776","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["New memory usage for train set\n","Mem usage decreased to 141.20 Mb, (48.93%)\n","New memory usage for test set\n","Mem usage decreased to 109.86 Mb, (49.83%)\n"]}],"source":["# Reducing memory usage for the dataset without duplicates\n","print(\"New memory usage for train set\")\n","train = reduce_mem_usage(train)\n","\n","print(\"New memory usage for test set\")\n","test = reduce_mem_usage(test)\n","# Reducing memory usage for the dataset with duplicates\n","# train_with_duplicates = reduce_mem_usage(train_with_duplicates)"]},{"cell_type":"code","execution_count":11,"id":"7a0b9d81","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:07.304887Z","iopub.status.busy":"2022-03-03T16:44:07.303898Z","iopub.status.idle":"2022-03-03T16:44:07.309965Z","shell.execute_reply":"2022-03-03T16:44:07.31052Z","shell.execute_reply.started":"2022-03-03T16:26:17.646376Z"},"papermill":{"duration":0.033647,"end_time":"2022-03-03T16:44:07.310686","exception":false,"start_time":"2022-03-03T16:44:07.277039","status":"completed"},"tags":[]},"outputs":[{"name":"stdout","output_type":"stream","text":["# of features:  286\n"]}],"source":["# Now, we can separate the features from the targets\n","features = train.columns[:-1]\n","target = 'target'\n","\n","print(\"# of features: \", len(features))"]},{"cell_type":"code","execution_count":12,"id":"39aba9b5","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:07.362611Z","iopub.status.busy":"2022-03-03T16:44:07.361673Z","iopub.status.idle":"2022-03-03T16:44:07.511492Z","shell.execute_reply":"2022-03-03T16:44:07.510865Z","shell.execute_reply.started":"2022-03-03T16:26:17.65806Z"},"papermill":{"duration":0.176649,"end_time":"2022-03-03T16:44:07.51163","exception":false,"start_time":"2022-03-03T16:44:07.334981","status":"completed"},"tags":[]},"outputs":[],"source":["# Target encoding, that is turn the bacteria into numeric labels\n","from sklearn.preprocessing import LabelEncoder\n","encoder = LabelEncoder()\n","train[target] = encoder.fit_transform(train[target])\n","\n","# sample_weight = train.value_counts().values"]},{"cell_type":"code","execution_count":13,"id":"51f7e8bf","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:07.563531Z","iopub.status.busy":"2022-03-03T16:44:07.562915Z","iopub.status.idle":"2022-03-03T16:44:08.908732Z","shell.execute_reply":"2022-03-03T16:44:08.908223Z","shell.execute_reply.started":"2022-03-03T16:26:17.837997Z"},"papermill":{"duration":1.372908,"end_time":"2022-03-03T16:44:08.908923","exception":false,"start_time":"2022-03-03T16:44:07.536015","status":"completed"},"tags":[]},"outputs":[],"source":["# Preprocess the features\n","from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler\n","scaler = StandardScaler()\n","scaled_data = scaler.fit_transform(train_with_duplicates[features])\n","scaled_data = pd.DataFrame(scaled_data, columns=features)"]},{"cell_type":"code","execution_count":14,"id":"e803a752","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:08.960197Z","iopub.status.busy":"2022-03-03T16:44:08.9596Z","iopub.status.idle":"2022-03-03T16:44:09.560583Z","shell.execute_reply":"2022-03-03T16:44:09.559928Z","shell.execute_reply.started":"2022-03-03T16:26:19.630592Z"},"papermill":{"duration":0.627596,"end_time":"2022-03-03T16:44:09.560728","exception":false,"start_time":"2022-03-03T16:44:08.933132","status":"completed"},"tags":[]},"outputs":[],"source":["test = scaler.fit_transform(test)"]},{"cell_type":"code","execution_count":15,"id":"91268d5e","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:09.616562Z","iopub.status.busy":"2022-03-03T16:44:09.615929Z","iopub.status.idle":"2022-03-03T16:44:09.639093Z","shell.execute_reply":"2022-03-03T16:44:09.638583Z","shell.execute_reply.started":"2022-03-03T16:26:20.235135Z"},"papermill":{"duration":0.054211,"end_time":"2022-03-03T16:44:09.639239","exception":false,"start_time":"2022-03-03T16:44:09.585028","status":"completed"},"tags":[]},"outputs":[{"data":{"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>A0T0G0C10</th>\n","      <th>A0T0G1C9</th>\n","      <th>A0T0G2C8</th>\n","      <th>A0T0G3C7</th>\n","      <th>A0T0G4C6</th>\n","      <th>A0T0G5C5</th>\n","      <th>A0T0G6C4</th>\n","      <th>A0T0G7C3</th>\n","      <th>A0T0G8C2</th>\n","      <th>A0T0G9C1</th>\n","      <th>...</th>\n","      <th>A8T0G0C2</th>\n","      <th>A8T0G1C1</th>\n","      <th>A8T0G2C0</th>\n","      <th>A8T1G0C1</th>\n","      <th>A8T1G1C0</th>\n","      <th>A8T2G0C0</th>\n","      <th>A9T0G0C1</th>\n","      <th>A9T0G1C0</th>\n","      <th>A9T1G0C0</th>\n","      <th>A10T0G0C0</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>-0.018438</td>\n","      <td>-0.049055</td>\n","      <td>-0.099841</td>\n","      <td>-0.240396</td>\n","      <td>-0.300284</td>\n","      <td>-0.305733</td>\n","      <td>-0.276749</td>\n","      <td>-0.238137</td>\n","      <td>-0.142872</td>\n","      <td>-0.024116</td>\n","      <td>...</td>\n","      <td>-0.250392</td>\n","      <td>-0.388083</td>\n","      <td>-0.323410</td>\n","      <td>-0.444488</td>\n","      <td>-0.436241</td>\n","      <td>-0.356999</td>\n","      <td>-0.152918</td>\n","      <td>-0.181456</td>\n","      <td>-0.186407</td>\n","      <td>-0.057325</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>-0.018438</td>\n","      <td>-0.049055</td>\n","      <td>-0.099841</td>\n","      <td>2.055508</td>\n","      <td>-0.300284</td>\n","      <td>0.844497</td>\n","      <td>-0.276749</td>\n","      <td>-0.238137</td>\n","      <td>-0.142872</td>\n","      <td>-0.024116</td>\n","      <td>...</td>\n","      <td>-0.250392</td>\n","      <td>-0.388083</td>\n","      <td>-0.323410</td>\n","      <td>0.363383</td>\n","      <td>0.218321</td>\n","      <td>-0.356999</td>\n","      <td>-0.152918</td>\n","      <td>-0.181456</td>\n","      <td>-0.186407</td>\n","      <td>-0.057325</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>-0.018438</td>\n","      <td>0.011693</td>\n","      <td>0.074608</td>\n","      <td>0.317508</td>\n","      <td>0.384633</td>\n","      <td>0.280884</td>\n","      <td>0.294624</td>\n","      <td>0.304069</td>\n","      <td>0.268421</td>\n","      <td>0.011929</td>\n","      <td>...</td>\n","      <td>-0.130892</td>\n","      <td>-0.235909</td>\n","      <td>-0.223794</td>\n","      <td>-0.309574</td>\n","      <td>-0.310565</td>\n","      <td>-0.259742</td>\n","      <td>-0.109998</td>\n","      <td>-0.148583</td>\n","      <td>-0.143687</td>\n","      <td>0.040232</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>-0.006884</td>\n","      <td>-0.018681</td>\n","      <td>0.092053</td>\n","      <td>0.583833</td>\n","      <td>0.712456</td>\n","      <td>0.570742</td>\n","      <td>0.491960</td>\n","      <td>0.467411</td>\n","      <td>0.231031</td>\n","      <td>0.011929</td>\n","      <td>...</td>\n","      <td>-0.094339</td>\n","      <td>-0.175934</td>\n","      <td>-0.166871</td>\n","      <td>-0.229594</td>\n","      <td>-0.247727</td>\n","      <td>-0.191240</td>\n","      <td>-0.086392</td>\n","      <td>-0.135799</td>\n","      <td>-0.103912</td>\n","      <td>-0.057325</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>-0.018438</td>\n","      <td>-0.049055</td>\n","      <td>-0.099841</td>\n","      <td>-0.240396</td>\n","      <td>-0.300284</td>\n","      <td>-0.305733</td>\n","      <td>-0.276749</td>\n","      <td>-0.238137</td>\n","      <td>-0.142872</td>\n","      <td>-0.024116</td>\n","      <td>...</td>\n","      <td>-0.250392</td>\n","      <td>-0.388083</td>\n","      <td>-0.323410</td>\n","      <td>-0.444488</td>\n","      <td>-0.436241</td>\n","      <td>-0.356999</td>\n","      <td>-0.152918</td>\n","      <td>-0.181456</td>\n","      <td>-0.186407</td>\n","      <td>-0.057325</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>5 rows × 286 columns</p>\n","</div>"],"text/plain":["   A0T0G0C10  A0T0G1C9  A0T0G2C8  A0T0G3C7  A0T0G4C6  A0T0G5C5  A0T0G6C4  \\\n","0  -0.018438 -0.049055 -0.099841 -0.240396 -0.300284 -0.305733 -0.276749   \n","1  -0.018438 -0.049055 -0.099841  2.055508 -0.300284  0.844497 -0.276749   \n","2  -0.018438  0.011693  0.074608  0.317508  0.384633  0.280884  0.294624   \n","3  -0.006884 -0.018681  0.092053  0.583833  0.712456  0.570742  0.491960   \n","4  -0.018438 -0.049055 -0.099841 -0.240396 -0.300284 -0.305733 -0.276749   \n","\n","   A0T0G7C3  A0T0G8C2  A0T0G9C1  ...  A8T0G0C2  A8T0G1C1  A8T0G2C0  A8T1G0C1  \\\n","0 -0.238137 -0.142872 -0.024116  ... -0.250392 -0.388083 -0.323410 -0.444488   \n","1 -0.238137 -0.142872 -0.024116  ... -0.250392 -0.388083 -0.323410  0.363383   \n","2  0.304069  0.268421  0.011929  ... -0.130892 -0.235909 -0.223794 -0.309574   \n","3  0.467411  0.231031  0.011929  ... -0.094339 -0.175934 -0.166871 -0.229594   \n","4 -0.238137 -0.142872 -0.024116  ... -0.250392 -0.388083 -0.323410 -0.444488   \n","\n","   A8T1G1C0  A8T2G0C0  A9T0G0C1  A9T0G1C0  A9T1G0C0  A10T0G0C0  \n","0 -0.436241 -0.356999 -0.152918 -0.181456 -0.186407  -0.057325  \n","1  0.218321 -0.356999 -0.152918 -0.181456 -0.186407  -0.057325  \n","2 -0.310565 -0.259742 -0.109998 -0.148583 -0.143687   0.040232  \n","3 -0.247727 -0.191240 -0.086392 -0.135799 -0.103912  -0.057325  \n","4 -0.436241 -0.356999 -0.152918 -0.181456 -0.186407  -0.057325  \n","\n","[5 rows x 286 columns]"]},"execution_count":15,"metadata":{},"output_type":"execute_result"}],"source":["scaled_data.head()"]},{"cell_type":"code","execution_count":16,"id":"f3987a36","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:09.693322Z","iopub.status.busy":"2022-03-03T16:44:09.692695Z","iopub.status.idle":"2022-03-03T16:44:09.922244Z","shell.execute_reply":"2022-03-03T16:44:09.921671Z","shell.execute_reply.started":"2022-03-03T16:26:20.27126Z"},"papermill":{"duration":0.257192,"end_time":"2022-03-03T16:44:09.922399","exception":false,"start_time":"2022-03-03T16:44:09.665207","status":"completed"},"tags":[]},"outputs":[],"source":["from sklearn.model_selection import StratifiedKFold\n","from sklearn.ensemble import ExtraTreesClassifier\n","from sklearn.metrics import accuracy_score"]},{"cell_type":"code","execution_count":17,"id":"f38bc28a","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:09.975522Z","iopub.status.busy":"2022-03-03T16:44:09.974934Z","iopub.status.idle":"2022-03-03T16:44:09.980386Z","shell.execute_reply":"2022-03-03T16:44:09.981067Z","shell.execute_reply.started":"2022-03-03T16:26:20.538559Z"},"papermill":{"duration":0.033937,"end_time":"2022-03-03T16:44:09.981242","exception":false,"start_time":"2022-03-03T16:44:09.947305","status":"completed"},"tags":[]},"outputs":[],"source":["scaled_data['target'] = train_with_duplicates[target]"]},{"cell_type":"code","execution_count":18,"id":"85ca0201","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:10.034533Z","iopub.status.busy":"2022-03-03T16:44:10.033934Z","iopub.status.idle":"2022-03-03T16:44:10.043077Z","shell.execute_reply":"2022-03-03T16:44:10.043519Z","shell.execute_reply.started":"2022-03-03T16:26:20.549296Z"},"papermill":{"duration":0.037578,"end_time":"2022-03-03T16:44:10.043695","exception":false,"start_time":"2022-03-03T16:44:10.006117","status":"completed"},"tags":[]},"outputs":[],"source":["def ExtraTreesModel(N_ESTIMATORS=1000):\n","    model = ExtraTreesClassifier(\n","        n_estimators=N_ESTIMATORS,\n","        n_jobs=-1,\n","        verbose=0,\n","        random_state=1221\n","    )\n","    return model\n","\n","def DNN():\n","    inputs = keras.Input(shape=X.shape[1])\n","    x = layers.Dense(512, activation='relu')(inputs)\n","    x = layers.Dense(256, activation='relu')(x)\n","    x = layers.Dense(256, activation='relu')(x)\n","    x = layers.Dropout(0.2)(x)\n","    x = layers.Dense(128, activation='relu')(x)\n","    x = layers.Dense(128, activation='relu')(x)\n","    x = layers.Dense(64, activation='relu')(x)\n","    x = layers.Dropout(0.2)(x)\n","    x = layers.Dense(64, activation='relu')(x)\n","    x = layers.Dense(32, activation='relu')(x)\n","    x = layers.Dense(32, activation='relu')(x)\n","    outputs = layers.Dense(10, activation='softmax')(x)\n","    model = keras.Model(inputs, outputs)\n","    return model"]},{"cell_type":"code","execution_count":19,"id":"67eb1d39","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:10.096704Z","iopub.status.busy":"2022-03-03T16:44:10.096042Z","iopub.status.idle":"2022-03-03T16:44:10.134512Z","shell.execute_reply":"2022-03-03T16:44:10.135015Z","shell.execute_reply.started":"2022-03-03T16:26:20.562761Z"},"papermill":{"duration":0.066696,"end_time":"2022-03-03T16:44:10.135189","exception":false,"start_time":"2022-03-03T16:44:10.068493","status":"completed"},"tags":[]},"outputs":[],"source":["scaled_data[target] = encoder.fit_transform(scaled_data[target])"]},{"cell_type":"code","execution_count":20,"id":"57bc8097","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:10.187434Z","iopub.status.busy":"2022-03-03T16:44:10.186831Z","iopub.status.idle":"2022-03-03T16:44:10.19044Z","shell.execute_reply":"2022-03-03T16:44:10.190942Z","shell.execute_reply.started":"2022-03-03T16:26:20.636071Z"},"papermill":{"duration":0.031377,"end_time":"2022-03-03T16:44:10.191106","exception":false,"start_time":"2022-03-03T16:44:10.159729","status":"completed"},"tags":[]},"outputs":[],"source":["# N_SPLITS = 10\n","# X, y = scaled_data[features], scaled_data[target]\n","# folds = StratifiedKFold(n_splits=N_SPLITS, shuffle=True, random_state=1334)\n","# dnn_preds = []\n","# for fold, (train_id, valid_id) in enumerate(tqdm(folds.split(X, y), total=N_SPLITS)):\n","#     x_tr = X.iloc[train_id]\n","#     y_tr = y.iloc[train_id]\n","#     x_val = X.iloc[valid_id]\n","#     y_val = y.iloc[valid_id]\n","#     y_tr = keras.utils.to_categorical(y_tr)\n","#     y_val = keras.utils.to_categorical(y_val)\n","#     model = DNN()\n","#     callbacks = [\n","#         keras.callbacks.EarlyStopping(\n","#             monitor='val_loss', patience=10, verbose=1\n","#         )\n","#     ]\n","#     model.compile(optimizer='adam',\n","#                  loss='categorical_crossentropy',\n","#                  metrics=['accuracy'])\n","#     model.fit(x_tr, y_tr, validation_data=(x_val, y_val), batch_size=128, epochs=50, callbacks=callbacks, verbose=0)\n","#     print(f\"Fold {fold} Evaluation: {model.evaluate(x_val, y_val)}\")\n","#     dnn_preds.append(model.predict(test))"]},{"cell_type":"code","execution_count":21,"id":"18418c0d","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:10.243339Z","iopub.status.busy":"2022-03-03T16:44:10.242692Z","iopub.status.idle":"2022-03-03T16:44:10.250382Z","shell.execute_reply":"2022-03-03T16:44:10.250831Z","shell.execute_reply.started":"2022-03-03T16:26:20.64227Z"},"papermill":{"duration":0.035298,"end_time":"2022-03-03T16:44:10.251007","exception":false,"start_time":"2022-03-03T16:44:10.215709","status":"completed"},"tags":[]},"outputs":[],"source":["def training_loop(data, model_name = \"etc\", N_SPLITS=10):\n","    X = data[features]\n","    # hard coded (:\n","    y = train_with_duplicates[target]\n","    sample_weight = data.value_counts().values\n","    folds = StratifiedKFold(n_splits=N_SPLITS, shuffle=True, random_state=1223)\n","    scores = []\n","    predictions = []\n","\n","    for fold, (train_id, valid_id) in enumerate(tqdm(folds.split(X, y), total=N_SPLITS)):\n","        X_train = X.iloc[train_id]\n","        y_train = y.iloc[train_id]\n","        X_valid = X.iloc[valid_id]\n","        y_valid = y.iloc[valid_id]\n","\n","        if model_name == \"etc\":\n","            # etc stands for ExtraTreeClassifier\n","            # Training\n","            model = ExtraTreesModel()\n","            if len(sample_weight) == 0:\n","                model.fit(X_train, y_train)\n","            else:\n","#                  sample_weight_train = sample_weight[train_id]\n","                model.fit(X_train, y_train)\n","            \n","#             validation\n","            valid_pred = model.predict(X_valid)\n","            valid_score = 0\n","            if len(sample_weight) == 0:\n","                valid_score = accuracy_score(valid_pred, y_valid)\n","            else:\n","#                 sample_weight_valid = sample_weight[valid_id]\n","                valid_score = accuracy_score(valid_pred, y_valid)\n","                scores.append(valid_score)\n","            print(f\"Fold {fold+1} \\tAccuracy: {valid_score:.4f}\")\n","        \n","        predictions.append(model.predict_proba(test))\n","    \n","    return {\"model\": model, \"logits\": predictions}"]},{"cell_type":"code","execution_count":22,"id":"860bb3c1","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:44:10.303631Z","iopub.status.busy":"2022-03-03T16:44:10.302985Z","iopub.status.idle":"2022-03-03T16:57:27.608075Z","shell.execute_reply":"2022-03-03T16:57:27.60868Z","shell.execute_reply.started":"2022-03-03T16:26:20.655158Z"},"papermill":{"duration":797.333273,"end_time":"2022-03-03T16:57:27.609095","exception":false,"start_time":"2022-03-03T16:44:10.275822","status":"completed"},"tags":[]},"outputs":[{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"c2567ddb1b0b4259bd95288fad404a7c","version_major":2,"version_minor":0},"text/plain":["  0%|          | 0/3 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["Fold 1 \tAccuracy: 0.9935\n","Fold 2 \tAccuracy: 0.9937\n","Fold 3 \tAccuracy: 0.9934\n"]}],"source":["etc_model = training_loop(data=scaled_data, N_SPLITS=3)"]},{"cell_type":"code","execution_count":23,"id":"7760fab1","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:57:27.671498Z","iopub.status.busy":"2022-03-03T16:57:27.670381Z","iopub.status.idle":"2022-03-03T16:57:27.805625Z","shell.execute_reply":"2022-03-03T16:57:27.805036Z","shell.execute_reply.started":"2022-03-03T16:41:01.171478Z"},"papermill":{"duration":0.17058,"end_time":"2022-03-03T16:57:27.805808","exception":false,"start_time":"2022-03-03T16:57:27.635228","status":"completed"},"tags":[]},"outputs":[],"source":["# Neural network outputs are probabilistic. \n","# Doing the same for the ExtraTreeClassifier\n","# dnn_probas = dnn_model.predict(test)\n","# etc_probas = etc_model.predict_proba(test)\n","model = etc_model['model']\n","logits = etc_model['logits']\n","\n","logits = sum(logits)/len(logits)\n","# dnn_preds = sum(dnn_preds)/len(dnn_preds)\n","\n","# preds = 0.9*logits + 0.1*dnn_preds\n","\n","predictions = pd.DataFrame({'predictions': np.argmax(logits, axis=1)})\n","predictions.to_csv('Predictions.csv')"]},{"cell_type":"code","execution_count":24,"id":"b4780805","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:57:27.86848Z","iopub.status.busy":"2022-03-03T16:57:27.863567Z","iopub.status.idle":"2022-03-03T16:57:27.899727Z","shell.execute_reply":"2022-03-03T16:57:27.899203Z","shell.execute_reply.started":"2022-03-03T16:41:01.419997Z"},"papermill":{"duration":0.067771,"end_time":"2022-03-03T16:57:27.899892","exception":false,"start_time":"2022-03-03T16:57:27.832121","status":"completed"},"tags":[]},"outputs":[{"data":{"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>predictions</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>4</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>6</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>2</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>6</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>7</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   predictions\n","0            4\n","1            6\n","2            2\n","3            6\n","4            7"]},"execution_count":24,"metadata":{},"output_type":"execute_result"}],"source":["predictions = pd.read_csv(\"Predictions.csv\", index_col=0)\n","predictions.head()"]},{"cell_type":"code","execution_count":25,"id":"ecb00f99","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:57:27.958988Z","iopub.status.busy":"2022-03-03T16:57:27.958318Z","iopub.status.idle":"2022-03-03T16:57:27.970426Z","shell.execute_reply":"2022-03-03T16:57:27.970913Z","shell.execute_reply.started":"2022-03-03T16:41:01.471784Z"},"papermill":{"duration":0.04405,"end_time":"2022-03-03T16:57:27.971093","exception":false,"start_time":"2022-03-03T16:57:27.927043","status":"completed"},"tags":[]},"outputs":[{"name":"stderr","output_type":"stream","text":["/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py:72: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n","  return f(**kwargs)\n"]},{"data":{"text/plain":["array(['Escherichia_fergusonii', 'Salmonella_enterica',\n","       'Enterococcus_hirae', ..., 'Bacteroides_fragilis',\n","       'Bacteroides_fragilis', 'Streptococcus_pyogenes'], dtype=object)"]},"execution_count":25,"metadata":{},"output_type":"execute_result"}],"source":["# convert the numbers into the respective names of the bacteria\n","labels = encoder.inverse_transform(predictions)\n","labels"]},{"cell_type":"code","execution_count":26,"id":"1568ad22","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:57:28.030886Z","iopub.status.busy":"2022-03-03T16:57:28.030254Z","iopub.status.idle":"2022-03-03T16:57:28.128242Z","shell.execute_reply":"2022-03-03T16:57:28.127662Z","shell.execute_reply.started":"2022-03-03T16:41:01.491977Z"},"papermill":{"duration":0.130483,"end_time":"2022-03-03T16:57:28.128385","exception":false,"start_time":"2022-03-03T16:57:27.997902","status":"completed"},"tags":[]},"outputs":[],"source":["sample = pd.read_csv(\"../input/tabular-playground-series-feb-2022/sample_submission.csv\")"]},{"cell_type":"code","execution_count":27,"id":"16a89113","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:57:28.215463Z","iopub.status.busy":"2022-03-03T16:57:28.214485Z","iopub.status.idle":"2022-03-03T16:57:28.327377Z","shell.execute_reply":"2022-03-03T16:57:28.327909Z","shell.execute_reply.started":"2022-03-03T16:41:01.594616Z"},"papermill":{"duration":0.172812,"end_time":"2022-03-03T16:57:28.328101","exception":false,"start_time":"2022-03-03T16:57:28.155289","status":"completed"},"tags":[]},"outputs":[],"source":["sample['target'] = labels\n","sample.to_csv(\"submission.csv\", index=False)"]},{"cell_type":"code","execution_count":28,"id":"a11af7c8","metadata":{"execution":{"iopub.execute_input":"2022-03-03T16:57:28.387545Z","iopub.status.busy":"2022-03-03T16:57:28.38649Z","iopub.status.idle":"2022-03-03T16:57:28.42596Z","shell.execute_reply":"2022-03-03T16:57:28.426394Z","shell.execute_reply.started":"2022-03-03T16:41:01.875398Z"},"papermill":{"duration":0.071434,"end_time":"2022-03-03T16:57:28.426568","exception":false,"start_time":"2022-03-03T16:57:28.355134","status":"completed"},"tags":[]},"outputs":[{"data":{"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>row_id</th>\n","      <th>target</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>200000</td>\n","      <td>Escherichia_fergusonii</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>200001</td>\n","      <td>Salmonella_enterica</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>200002</td>\n","      <td>Enterococcus_hirae</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>200003</td>\n","      <td>Salmonella_enterica</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>200004</td>\n","      <td>Staphylococcus_aureus</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   row_id                  target\n","0  200000  Escherichia_fergusonii\n","1  200001     Salmonella_enterica\n","2  200002      Enterococcus_hirae\n","3  200003     Salmonella_enterica\n","4  200004   Staphylococcus_aureus"]},"execution_count":28,"metadata":{},"output_type":"execute_result"}],"source":["pd.read_csv(\"submission.csv\").head()"]},{"cell_type":"code","execution_count":null,"id":"61af7c3d","metadata":{"papermill":{"duration":0.027261,"end_time":"2022-03-03T16:57:28.481107","exception":false,"start_time":"2022-03-03T16:57:28.453846","status":"completed"},"tags":[]},"outputs":[],"source":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.7.12"},"papermill":{"default_parameters":{},"duration":885.968523,"end_time":"2022-03-03T16:57:32.074519","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2022-03-03T16:42:46.105996","version":"2.3.3"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"32093293ad444c9c938da3f96c0c66d8":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_4c673f016cb84555afe1d2ae2e3b0dcd","placeholder":"​","style":"IPY_MODEL_5d0345dda022470a8f6a3a39855a432c","value":"100%"}},"3d817575e2764c4a8ffd3052038f9905":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"4c673f016cb84555afe1d2ae2e3b0dcd":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"57f72497f6c34eb2bdf927e72ea2dee4":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"5d0345dda022470a8f6a3a39855a432c":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"6955d8f1cbb5427cb22784114cfa5749":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"71e471f258a24a148db037e63cfe948a":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"8c55c055fa0a406aba20a9613f3b3351":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_57f72497f6c34eb2bdf927e72ea2dee4","max":3.0,"min":0.0,"orientation":"horizontal","style":"IPY_MODEL_d225b1d32fbe46c0ac617a115fdee47d","value":3.0}},"c2567ddb1b0b4259bd95288fad404a7c":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_32093293ad444c9c938da3f96c0c66d8","IPY_MODEL_8c55c055fa0a406aba20a9613f3b3351","IPY_MODEL_ed0abbc05187413da9790d2dc8aeb64c"],"layout":"IPY_MODEL_6955d8f1cbb5427cb22784114cfa5749"}},"d225b1d32fbe46c0ac617a115fdee47d":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"ed0abbc05187413da9790d2dc8aeb64c":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_3d817575e2764c4a8ffd3052038f9905","placeholder":"​","style":"IPY_MODEL_71e471f258a24a148db037e63cfe948a","value":" 3/3 [13:12&lt;00:00, 265.38s/it]"}}},"version_major":2,"version_minor":0}}},"nbformat":4,"nbformat_minor":5}