Credit card customer churn prediction

{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":1481789,"sourceType":"datasetVersion","datasetId":869651}],"dockerImageVersionId":30746,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","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\nimport numpy as np # linear algebra\nimport 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\nimport os\nfor 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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-08-16T09:50:50.560808Z","iopub.execute_input":"2024-08-16T09:50:50.561286Z","iopub.status.idle":"2024-08-16T09:50:51.819709Z","shell.execute_reply.started":"2024-08-16T09:50:50.561247Z","shell.execute_reply":"2024-08-16T09:50:51.818357Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"/kaggle/input/credit-card-customer-churn-prediction/Churn_Modelling.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"df=pd.read_csv('/kaggle/input/credit-card-customer-churn-prediction/Churn_Modelling.csv')","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:51:37.523467Z","iopub.execute_input":"2024-08-16T09:51:37.523979Z","iopub.status.idle":"2024-08-16T09:51:37.570491Z","shell.execute_reply.started":"2024-08-16T09:51:37.523946Z","shell.execute_reply":"2024-08-16T09:51:37.569432Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:51:42.202025Z","iopub.execute_input":"2024-08-16T09:51:42.202407Z","iopub.status.idle":"2024-08-16T09:51:42.239760Z","shell.execute_reply.started":"2024-08-16T09:51:42.202375Z","shell.execute_reply":"2024-08-16T09:51:42.238315Z"},"trusted":true},"execution_count":3,"outputs":[{"execution_count":3,"output_type":"execute_result","data":{"text/plain":"      RowNumber  CustomerId    Surname  CreditScore Geography  Gender  Age  \\\n0             1    15634602   Hargrave          619    France  Female   42   \n1             2    15647311       Hill          608     Spain  Female   41   \n2             3    15619304       Onio          502    France  Female   42   \n3             4    15701354       Boni          699    France  Female   39   \n4             5    15737888   Mitchell          850     Spain  Female   43   \n...         ...         ...        ...          ...       ...     ...  ...   \n9995       9996    15606229   Obijiaku          771    France    Male   39   \n9996       9997    15569892  Johnstone          516    France    Male   35   \n9997       9998    15584532        Liu          709    France  Female   36   \n9998       9999    15682355  Sabbatini          772   Germany    Male   42   \n9999      10000    15628319     Walker          792    France  Female   28   \n\n      Tenure    Balance  NumOfProducts  HasCrCard  IsActiveMember  \\\n0          2       0.00              1          1               1   \n1          1   83807.86              1          0               1   \n2          8  159660.80              3          1               0   \n3          1       0.00              2          0               0   \n4          2  125510.82              1          1               1   \n...      ...        ...            ...        ...             ...   \n9995       5       0.00              2          1               0   \n9996      10   57369.61              1          1               1   \n9997       7       0.00              1          0               1   \n9998       3   75075.31              2          1               0   \n9999       4  130142.79              1          1               0   \n\n      EstimatedSalary  Exited  \n0           101348.88       1  \n1           112542.58       0  \n2           113931.57       1  \n3            93826.63       0  \n4            79084.10       0  \n...               ...     ...  \n9995         96270.64       0  \n9996        101699.77       0  \n9997         42085.58       1  \n9998         92888.52       1  \n9999         38190.78       0  \n\n[10000 rows x 14 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>RowNumber</th>\n      <th>CustomerId</th>\n      <th>Surname</th>\n      <th>CreditScore</th>\n      <th>Geography</th>\n      <th>Gender</th>\n      <th>Age</th>\n      <th>Tenure</th>\n      <th>Balance</th>\n      <th>NumOfProducts</th>\n      <th>HasCrCard</th>\n      <th>IsActiveMember</th>\n      <th>EstimatedSalary</th>\n      <th>Exited</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>15634602</td>\n      <td>Hargrave</td>\n      <td>619</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>42</td>\n      <td>2</td>\n      <td>0.00</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>101348.88</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>15647311</td>\n      <td>Hill</td>\n      <td>608</td>\n      <td>Spain</td>\n      <td>Female</td>\n      <td>41</td>\n      <td>1</td>\n      <td>83807.86</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>112542.58</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>15619304</td>\n      <td>Onio</td>\n      <td>502</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>42</td>\n      <td>8</td>\n      <td>159660.80</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113931.57</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>15701354</td>\n      <td>Boni</td>\n      <td>699</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>39</td>\n      <td>1</td>\n      <td>0.00</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0</td>\n      <td>93826.63</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>15737888</td>\n      <td>Mitchell</td>\n      <td>850</td>\n      <td>Spain</td>\n      <td>Female</td>\n      <td>43</td>\n      <td>2</td>\n      <td>125510.82</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>79084.10</td>\n      <td>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      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>9995</th>\n      <td>9996</td>\n      <td>15606229</td>\n      <td>Obijiaku</td>\n      <td>771</td>\n      <td>France</td>\n      <td>Male</td>\n      <td>39</td>\n      <td>5</td>\n      <td>0.00</td>\n      <td>2</td>\n      <td>1</td>\n      <td>0</td>\n      <td>96270.64</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>9996</th>\n      <td>9997</td>\n      <td>15569892</td>\n      <td>Johnstone</td>\n      <td>516</td>\n      <td>France</td>\n      <td>Male</td>\n      <td>35</td>\n      <td>10</td>\n      <td>57369.61</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>101699.77</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>9997</th>\n      <td>9998</td>\n      <td>15584532</td>\n      <td>Liu</td>\n      <td>709</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>36</td>\n      <td>7</td>\n      <td>0.00</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>42085.58</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>9998</th>\n      <td>9999</td>\n      <td>15682355</td>\n      <td>Sabbatini</td>\n      <td>772</td>\n      <td>Germany</td>\n      <td>Male</td>\n      <td>42</td>\n      <td>3</td>\n      <td>75075.31</td>\n      <td>2</td>\n      <td>1</td>\n      <td>0</td>\n      <td>92888.52</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>9999</th>\n      <td>10000</td>\n      <td>15628319</td>\n      <td>Walker</td>\n      <td>792</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>28</td>\n      <td>4</td>\n      <td>130142.79</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>38190.78</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n<p>10000 rows × 14 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df.shape","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:51:49.688422Z","iopub.execute_input":"2024-08-16T09:51:49.688930Z","iopub.status.idle":"2024-08-16T09:51:49.699059Z","shell.execute_reply.started":"2024-08-16T09:51:49.688882Z","shell.execute_reply":"2024-08-16T09:51:49.696789Z"},"trusted":true},"execution_count":4,"outputs":[{"execution_count":4,"output_type":"execute_result","data":{"text/plain":"(10000, 14)"},"metadata":{}}]},{"cell_type":"code","source":"df.info()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:52:07.764579Z","iopub.execute_input":"2024-08-16T09:52:07.764986Z","iopub.status.idle":"2024-08-16T09:52:07.795671Z","shell.execute_reply.started":"2024-08-16T09:52:07.764945Z","shell.execute_reply":"2024-08-16T09:52:07.794066Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 10000 entries, 0 to 9999\nData columns (total 14 columns):\n #   Column           Non-Null Count  Dtype  \n---  ------           --------------  -----  \n 0   RowNumber        10000 non-null  int64  \n 1   CustomerId       10000 non-null  int64  \n 2   Surname          10000 non-null  object \n 3   CreditScore      10000 non-null  int64  \n 4   Geography        10000 non-null  object \n 5   Gender           10000 non-null  object \n 6   Age              10000 non-null  int64  \n 7   Tenure           10000 non-null  int64  \n 8   Balance          10000 non-null  float64\n 9   NumOfProducts    10000 non-null  int64  \n 10  HasCrCard        10000 non-null  int64  \n 11  IsActiveMember   10000 non-null  int64  \n 12  EstimatedSalary  10000 non-null  float64\n 13  Exited           10000 non-null  int64  \ndtypes: float64(2), int64(9), object(3)\nmemory usage: 1.1+ MB\n","output_type":"stream"}]},{"cell_type":"code","source":"df.duplicated().sum()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:53:48.131663Z","iopub.execute_input":"2024-08-16T09:53:48.132111Z","iopub.status.idle":"2024-08-16T09:53:48.151562Z","shell.execute_reply.started":"2024-08-16T09:53:48.132079Z","shell.execute_reply":"2024-08-16T09:53:48.149477Z"},"trusted":true},"execution_count":6,"outputs":[{"execution_count":6,"output_type":"execute_result","data":{"text/plain":"0"},"metadata":{}}]},{"cell_type":"code","source":"df['Exited'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:54:20.310124Z","iopub.execute_input":"2024-08-16T09:54:20.310545Z","iopub.status.idle":"2024-08-16T09:54:20.326130Z","shell.execute_reply.started":"2024-08-16T09:54:20.310493Z","shell.execute_reply":"2024-08-16T09:54:20.324760Z"},"trusted":true},"execution_count":7,"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"Exited\n0    7963\n1    2037\nName: count, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"df['Geography'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:54:52.613955Z","iopub.execute_input":"2024-08-16T09:54:52.614436Z","iopub.status.idle":"2024-08-16T09:54:52.625279Z","shell.execute_reply.started":"2024-08-16T09:54:52.614394Z","shell.execute_reply":"2024-08-16T09:54:52.623987Z"},"trusted":true},"execution_count":8,"outputs":[{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"Geography\nFrance     5014\nGermany    2509\nSpain      2477\nName: count, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"df.drop(columns=['RowNumber','CustomerId','Surname'],inplace=True)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:57:14.821398Z","iopub.execute_input":"2024-08-16T09:57:14.822482Z","iopub.status.idle":"2024-08-16T09:57:14.830907Z","shell.execute_reply.started":"2024-08-16T09:57:14.822444Z","shell.execute_reply":"2024-08-16T09:57:14.829664Z"},"trusted":true},"execution_count":9,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T09:57:19.995971Z","iopub.execute_input":"2024-08-16T09:57:19.996420Z","iopub.status.idle":"2024-08-16T09:57:20.016484Z","shell.execute_reply.started":"2024-08-16T09:57:19.996381Z","shell.execute_reply":"2024-08-16T09:57:20.014968Z"},"trusted":true},"execution_count":10,"outputs":[{"execution_count":10,"output_type":"execute_result","data":{"text/plain":"   CreditScore Geography  Gender  Age  Tenure    Balance  NumOfProducts  \\\n0          619    France  Female   42       2       0.00              1   \n1          608     Spain  Female   41       1   83807.86              1   \n2          502    France  Female   42       8  159660.80              3   \n3          699    France  Female   39       1       0.00              2   \n4          850     Spain  Female   43       2  125510.82              1   \n\n   HasCrCard  IsActiveMember  EstimatedSalary  Exited  \n0          1               1        101348.88       1  \n1          0               1        112542.58       0  \n2          1               0        113931.57       1  \n3          0               0         93826.63       0  \n4          1               1         79084.10       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>CreditScore</th>\n      <th>Geography</th>\n      <th>Gender</th>\n      <th>Age</th>\n      <th>Tenure</th>\n      <th>Balance</th>\n      <th>NumOfProducts</th>\n      <th>HasCrCard</th>\n      <th>IsActiveMember</th>\n      <th>EstimatedSalary</th>\n      <th>Exited</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>619</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>42</td>\n      <td>2</td>\n      <td>0.00</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>101348.88</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>608</td>\n      <td>Spain</td>\n      <td>Female</td>\n      <td>41</td>\n      <td>1</td>\n      <td>83807.86</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>112542.58</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>502</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>42</td>\n      <td>8</td>\n      <td>159660.80</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113931.57</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>699</td>\n      <td>France</td>\n      <td>Female</td>\n      <td>39</td>\n      <td>1</td>\n      <td>0.00</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0</td>\n      <td>93826.63</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>850</td>\n      <td>Spain</td>\n      <td>Female</td>\n      <td>43</td>\n      <td>2</td>\n      <td>125510.82</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>79084.10</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df=pd.get_dummies(df,columns=['Geography','Gender'],drop_first=True)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:05:50.190751Z","iopub.execute_input":"2024-08-16T10:05:50.191151Z","iopub.status.idle":"2024-08-16T10:05:50.210287Z","shell.execute_reply.started":"2024-08-16T10:05:50.191122Z","shell.execute_reply":"2024-08-16T10:05:50.208403Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:05:53.931636Z","iopub.execute_input":"2024-08-16T10:05:53.932091Z","iopub.status.idle":"2024-08-16T10:05:53.959352Z","shell.execute_reply.started":"2024-08-16T10:05:53.932055Z","shell.execute_reply":"2024-08-16T10:05:53.958121Z"},"trusted":true},"execution_count":17,"outputs":[{"execution_count":17,"output_type":"execute_result","data":{"text/plain":"      CreditScore  Age  Tenure    Balance  NumOfProducts  HasCrCard  \\\n0             619   42       2       0.00              1          1   \n1             608   41       1   83807.86              1          0   \n2             502   42       8  159660.80              3          1   \n3             699   39       1       0.00              2          0   \n4             850   43       2  125510.82              1          1   \n...           ...  ...     ...        ...            ...        ...   \n9995          771   39       5       0.00              2          1   \n9996          516   35      10   57369.61              1          1   \n9997          709   36       7       0.00              1          0   \n9998          772   42       3   75075.31              2          1   \n9999          792   28       4  130142.79              1          1   \n\n      IsActiveMember  EstimatedSalary  Exited  Geography_Germany  \\\n0                  1        101348.88       1              False   \n1                  1        112542.58       0              False   \n2                  0        113931.57       1              False   \n3                  0         93826.63       0              False   \n4                  1         79084.10       0              False   \n...              ...              ...     ...                ...   \n9995               0         96270.64       0              False   \n9996               1        101699.77       0              False   \n9997               1         42085.58       1              False   \n9998               0         92888.52       1               True   \n9999               0         38190.78       0              False   \n\n      Geography_Spain  Gender_Male  \n0               False        False  \n1                True        False  \n2               False        False  \n3               False        False  \n4                True        False  \n...               ...          ...  \n9995            False         True  \n9996            False         True  \n9997            False        False  \n9998            False         True  \n9999            False        False  \n\n[10000 rows x 12 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>CreditScore</th>\n      <th>Age</th>\n      <th>Tenure</th>\n      <th>Balance</th>\n      <th>NumOfProducts</th>\n      <th>HasCrCard</th>\n      <th>IsActiveMember</th>\n      <th>EstimatedSalary</th>\n      <th>Exited</th>\n      <th>Geography_Germany</th>\n      <th>Geography_Spain</th>\n      <th>Gender_Male</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>619</td>\n      <td>42</td>\n      <td>2</td>\n      <td>0.00</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>101348.88</td>\n      <td>1</td>\n      <td>False</td>\n      <td>False</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>608</td>\n      <td>41</td>\n      <td>1</td>\n      <td>83807.86</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>112542.58</td>\n      <td>0</td>\n      <td>False</td>\n      <td>True</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>502</td>\n      <td>42</td>\n      <td>8</td>\n      <td>159660.80</td>\n      <td>3</td>\n      <td>1</td>\n      <td>0</td>\n      <td>113931.57</td>\n      <td>1</td>\n      <td>False</td>\n      <td>False</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>699</td>\n      <td>39</td>\n      <td>1</td>\n      <td>0.00</td>\n      <td>2</td>\n      <td>0</td>\n      <td>0</td>\n      <td>93826.63</td>\n      <td>0</td>\n      <td>False</td>\n      <td>False</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>850</td>\n      <td>43</td>\n      <td>2</td>\n      <td>125510.82</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>79084.10</td>\n      <td>0</td>\n      <td>False</td>\n      <td>True</td>\n      <td>False</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      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>9995</th>\n      <td>771</td>\n      <td>39</td>\n      <td>5</td>\n      <td>0.00</td>\n      <td>2</td>\n      <td>1</td>\n      <td>0</td>\n      <td>96270.64</td>\n      <td>0</td>\n      <td>False</td>\n      <td>False</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>9996</th>\n      <td>516</td>\n      <td>35</td>\n      <td>10</td>\n      <td>57369.61</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>101699.77</td>\n      <td>0</td>\n      <td>False</td>\n      <td>False</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>9997</th>\n      <td>709</td>\n      <td>36</td>\n      <td>7</td>\n      <td>0.00</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>42085.58</td>\n      <td>1</td>\n      <td>False</td>\n      <td>False</td>\n      <td>False</td>\n    </tr>\n    <tr>\n      <th>9998</th>\n      <td>772</td>\n      <td>42</td>\n      <td>3</td>\n      <td>75075.31</td>\n      <td>2</td>\n      <td>1</td>\n      <td>0</td>\n      <td>92888.52</td>\n      <td>1</td>\n      <td>True</td>\n      <td>False</td>\n      <td>True</td>\n    </tr>\n    <tr>\n      <th>9999</th>\n      <td>792</td>\n      <td>28</td>\n      <td>4</td>\n      <td>130142.79</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>38190.78</td>\n      <td>0</td>\n      <td>False</td>\n      <td>False</td>\n      <td>False</td>\n    </tr>\n  </tbody>\n</table>\n<p>10000 rows × 12 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"X=df.drop(columns=['Exited'])\ny=df['Exited']\nfrom sklearn.model_selection import train_test_split\nX_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=1)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:10:49.857758Z","iopub.execute_input":"2024-08-16T10:10:49.858294Z","iopub.status.idle":"2024-08-16T10:10:49.881775Z","shell.execute_reply.started":"2024-08-16T10:10:49.858255Z","shell.execute_reply":"2024-08-16T10:10:49.879075Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"code","source":"X_train.shape","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:11:51.824000Z","iopub.execute_input":"2024-08-16T10:11:51.824615Z","iopub.status.idle":"2024-08-16T10:11:51.833843Z","shell.execute_reply.started":"2024-08-16T10:11:51.824572Z","shell.execute_reply":"2024-08-16T10:11:51.832164Z"},"trusted":true},"execution_count":24,"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":"(8000, 11)"},"metadata":{}}]},{"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\nscaler=StandardScaler()\n\nX_train_scaled=scaler.fit_transform(X_train)\nX_test_scaled=scaler.transform(X_test)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:16:36.813382Z","iopub.execute_input":"2024-08-16T10:16:36.813803Z","iopub.status.idle":"2024-08-16T10:16:36.833956Z","shell.execute_reply.started":"2024-08-16T10:16:36.813770Z","shell.execute_reply":"2024-08-16T10:16:36.832051Z"},"trusted":true},"execution_count":28,"outputs":[]},{"cell_type":"code","source":"X_train_scaled","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:16:55.521091Z","iopub.execute_input":"2024-08-16T10:16:55.521491Z","iopub.status.idle":"2024-08-16T10:16:55.530886Z","shell.execute_reply.started":"2024-08-16T10:16:55.521460Z","shell.execute_reply":"2024-08-16T10:16:55.529469Z"},"trusted":true},"execution_count":29,"outputs":[{"execution_count":29,"output_type":"execute_result","data":{"text/plain":"array([[-0.23082038, -0.94449979, -0.70174202, ...,  1.71490137,\n        -0.57273139,  0.91509065],\n       [-0.25150912, -0.94449979, -0.35520275, ..., -0.58312392,\n        -0.57273139, -1.09278791],\n       [-0.3963303 ,  0.77498705,  0.33787579, ...,  1.71490137,\n        -0.57273139, -1.09278791],\n       ...,\n       [ 0.22433188,  0.58393295,  1.3774936 , ..., -0.58312392,\n        -0.57273139, -1.09278791],\n       [ 0.13123255,  0.01077067,  1.03095433, ..., -0.58312392,\n        -0.57273139, -1.09278791],\n       [ 1.1656695 ,  0.29735181,  0.33787579, ...,  1.71490137,\n        -0.57273139,  0.91509065]])"},"metadata":{}}]},{"cell_type":"code","source":"import tensorflow\nfrom tensorflow import keras\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Dense","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:19:12.314312Z","iopub.execute_input":"2024-08-16T10:19:12.314721Z","iopub.status.idle":"2024-08-16T10:19:12.322552Z","shell.execute_reply.started":"2024-08-16T10:19:12.314682Z","shell.execute_reply":"2024-08-16T10:19:12.321031Z"},"trusted":true},"execution_count":31,"outputs":[]},{"cell_type":"code","source":"model=Sequential()\n\nmodel.add(Dense(11,activation='relu',input_dim=11))\nmodel.add(Dense(11,activation='relu'))\nmodel.add(Dense(1,activation='sigmoid'))","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:32:42.304797Z","iopub.execute_input":"2024-08-16T10:32:42.305201Z","iopub.status.idle":"2024-08-16T10:32:42.349809Z","shell.execute_reply.started":"2024-08-16T10:32:42.305169Z","shell.execute_reply":"2024-08-16T10:32:42.348047Z"},"trusted":true},"execution_count":49,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:32:45.118631Z","iopub.execute_input":"2024-08-16T10:32:45.119018Z","iopub.status.idle":"2024-08-16T10:32:45.141919Z","shell.execute_reply.started":"2024-08-16T10:32:45.118987Z","shell.execute_reply":"2024-08-16T10:32:45.140121Z"},"trusted":true},"execution_count":50,"outputs":[{"output_type":"display_data","data":{"text/plain":"\u001b[1mModel: \"sequential_3\"\u001b[0m\n","text/html":"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_3\"</span>\n</pre>\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ dense_7 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m)             │           \u001b[38;5;34m132\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_8 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m11\u001b[0m)             │           \u001b[38;5;34m132\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_9 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m12\u001b[0m │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n","text/html":"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ dense_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">11</span>)             │           <span style=\"color: #00af00; text-decoration-color: #00af00\">132</span> │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">11</span>)             │           <span style=\"color: #00af00; text-decoration-color: #00af00\">132</span> │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │            <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span> │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n</pre>\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m276\u001b[0m (1.08 KB)\n","text/html":"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">276</span> (1.08 KB)\n</pre>\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m276\u001b[0m (1.08 KB)\n","text/html":"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">276</span> (1.08 KB)\n</pre>\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n</pre>\n"},"metadata":{}}]},{"cell_type":"code","source":"model.compile(loss='binary_crossentropy',optimizer='Adam')","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:35:03.266095Z","iopub.execute_input":"2024-08-16T10:35:03.266620Z","iopub.status.idle":"2024-08-16T10:35:03.281094Z","shell.execute_reply.started":"2024-08-16T10:35:03.266578Z","shell.execute_reply":"2024-08-16T10:35:03.279636Z"},"trusted":true},"execution_count":58,"outputs":[]},{"cell_type":"code","source":"history=model.fit(X_train_scaled,y_train,epochs=100,validation_split=0.2)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:39:20.210423Z","iopub.execute_input":"2024-08-16T10:39:20.210838Z","iopub.status.idle":"2024-08-16T10:40:10.128283Z","shell.execute_reply.started":"2024-08-16T10:39:20.210808Z","shell.execute_reply":"2024-08-16T10:40:10.126909Z"},"trusted":true},"execution_count":64,"outputs":[{"name":"stdout","text":"Epoch 1/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3077 - val_loss: 0.3600\nEpoch 2/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3100 - val_loss: 0.3590\nEpoch 3/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3020 - val_loss: 0.3583\nEpoch 4/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3089 - val_loss: 0.3612\nEpoch 5/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3153 - val_loss: 0.3602\nEpoch 6/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3011 - val_loss: 0.3584\nEpoch 7/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3124 - val_loss: 0.3601\nEpoch 8/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3071 - val_loss: 0.3602\nEpoch 9/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3134 - val_loss: 0.3611\nEpoch 10/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3129 - val_loss: 0.3593\nEpoch 11/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3097 - val_loss: 0.3602\nEpoch 12/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3191 - val_loss: 0.3604\nEpoch 13/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3238 - val_loss: 0.3611\nEpoch 14/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3032 - val_loss: 0.3593\nEpoch 15/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3160 - val_loss: 0.3601\nEpoch 16/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3104 - val_loss: 0.3591\nEpoch 17/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3032 - val_loss: 0.3612\nEpoch 18/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3156 - val_loss: 0.3633\nEpoch 19/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3057 - val_loss: 0.3599\nEpoch 20/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3077 - val_loss: 0.3595\nEpoch 21/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3115 - val_loss: 0.3597\nEpoch 22/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3138 - val_loss: 0.3586\nEpoch 23/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.2999 - val_loss: 0.3640\nEpoch 24/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3006 - val_loss: 0.3583\nEpoch 25/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3042 - val_loss: 0.3608\nEpoch 26/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.2937 - val_loss: 0.3602\nEpoch 27/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3040 - val_loss: 0.3630\nEpoch 28/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3112 - val_loss: 0.3610\nEpoch 29/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3173 - val_loss: 0.3637\nEpoch 30/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3054 - val_loss: 0.3597\nEpoch 31/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3147 - val_loss: 0.3594\nEpoch 32/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3082 - val_loss: 0.3615\nEpoch 33/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3127 - val_loss: 0.3605\nEpoch 34/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3068 - val_loss: 0.3609\nEpoch 35/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3212 - val_loss: 0.3625\nEpoch 36/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3115 - val_loss: 0.3598\nEpoch 37/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3052 - val_loss: 0.3619\nEpoch 38/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3155 - val_loss: 0.3584\nEpoch 39/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3064 - val_loss: 0.3585\nEpoch 40/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3164 - val_loss: 0.3634\nEpoch 41/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3100 - val_loss: 0.3621\nEpoch 42/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3086 - val_loss: 0.3624\nEpoch 43/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3107 - val_loss: 0.3591\nEpoch 44/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3134 - val_loss: 0.3620\nEpoch 45/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3101 - val_loss: 0.3619\nEpoch 46/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3102 - val_loss: 0.3609\nEpoch 47/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3098 - val_loss: 0.3620\nEpoch 48/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3169 - val_loss: 0.3622\nEpoch 49/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3032 - val_loss: 0.3614\nEpoch 50/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3238 - val_loss: 0.3590\nEpoch 51/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.2982 - val_loss: 0.3605\nEpoch 52/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3012 - val_loss: 0.3594\nEpoch 53/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3090 - val_loss: 0.3608\nEpoch 54/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.2977 - val_loss: 0.3615\nEpoch 55/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3072 - val_loss: 0.3626\nEpoch 56/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3098 - val_loss: 0.3638\nEpoch 57/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3131 - val_loss: 0.3601\nEpoch 58/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3129 - val_loss: 0.3610\nEpoch 59/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3186 - val_loss: 0.3597\nEpoch 60/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3065 - val_loss: 0.3605\nEpoch 61/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3083 - val_loss: 0.3610\nEpoch 62/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3086 - val_loss: 0.3599\nEpoch 63/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3071 - val_loss: 0.3582\nEpoch 64/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3076 - val_loss: 0.3621\nEpoch 65/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.2972 - val_loss: 0.3612\nEpoch 66/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.2974 - val_loss: 0.3614\nEpoch 67/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3093 - val_loss: 0.3615\nEpoch 68/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3084 - val_loss: 0.3601\nEpoch 69/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3124 - val_loss: 0.3615\nEpoch 70/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3024 - val_loss: 0.3609\nEpoch 71/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3146 - val_loss: 0.3638\nEpoch 72/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.2986 - val_loss: 0.3595\nEpoch 73/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3101 - val_loss: 0.3611\nEpoch 74/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3019 - val_loss: 0.3636\nEpoch 75/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3080 - val_loss: 0.3618\nEpoch 76/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3029 - val_loss: 0.3603\nEpoch 77/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3125 - val_loss: 0.3629\nEpoch 78/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3100 - val_loss: 0.3616\nEpoch 79/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3073 - val_loss: 0.3613\nEpoch 80/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3031 - val_loss: 0.3629\nEpoch 81/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3109 - val_loss: 0.3619\nEpoch 82/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3024 - val_loss: 0.3629\nEpoch 83/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3108 - val_loss: 0.3658\nEpoch 84/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3136 - val_loss: 0.3616\nEpoch 85/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3054 - val_loss: 0.3617\nEpoch 86/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.3175 - val_loss: 0.3620\nEpoch 87/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3037 - val_loss: 0.3632\nEpoch 88/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.2925 - val_loss: 0.3638\nEpoch 89/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3061 - val_loss: 0.3642\nEpoch 90/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3046 - val_loss: 0.3653\nEpoch 91/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3061 - val_loss: 0.3620\nEpoch 92/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3127 - val_loss: 0.3623\nEpoch 93/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3097 - val_loss: 0.3641\nEpoch 94/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 2ms/step - loss: 0.3071 - val_loss: 0.3600\nEpoch 95/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3003 - val_loss: 0.3621\nEpoch 96/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.2943 - val_loss: 0.3625\nEpoch 97/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3143 - val_loss: 0.3624\nEpoch 98/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3053 - val_loss: 0.3613\nEpoch 99/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3203 - val_loss: 0.3629\nEpoch 100/100\n\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.3093 - val_loss: 0.3642\n","output_type":"stream"}]},{"cell_type":"code","source":"model.layers[1].get_weights()","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:36:20.299471Z","iopub.execute_input":"2024-08-16T10:36:20.300578Z","iopub.status.idle":"2024-08-16T10:36:20.314185Z","shell.execute_reply.started":"2024-08-16T10:36:20.300488Z","shell.execute_reply":"2024-08-16T10:36:20.312378Z"},"trusted":true},"execution_count":60,"outputs":[{"execution_count":60,"output_type":"execute_result","data":{"text/plain":"[array([[-0.03858776, -1.036712  ,  0.11884644,  0.07729118,  0.32777578,\n          0.63519144,  0.26811105,  0.67696035,  0.24790213, -0.15478271,\n          0.11784063],\n        [ 0.5908122 , -0.28715274, -0.48749322,  0.32279605,  0.5094614 ,\n         -0.3627616 ,  0.67475843, -0.8495858 ,  0.42019585,  0.11394725,\n          0.7787595 ],\n        [ 0.11071913,  0.4739361 , -0.32016814,  0.03529104, -0.07932729,\n          0.05395971, -0.61746484,  0.5343623 ,  0.52302647, -1.2348486 ,\n         -0.8435831 ],\n        [-1.2395929 ,  0.21868177,  0.19624695,  0.4721767 , -0.4567758 ,\n         -0.01565278,  0.2721727 , -1.2632912 ,  0.7490687 , -0.06503552,\n         -0.02592093],\n        [ 0.602407  , -0.8924459 , -0.577098  , -0.73518354,  0.04995962,\n         -0.7138423 ,  0.5236008 ,  0.50232005,  0.20322266, -0.78110826,\n          0.21751393],\n        [-0.06725077, -0.19835487, -0.23649645,  1.0445428 , -0.40839812,\n          0.35980666,  0.2652028 , -0.48712292,  0.39978215,  0.21199161,\n         -0.8269506 ],\n        [-0.63806945,  0.47840506,  0.14881958,  0.5357165 , -0.6287938 ,\n         -0.29635555, -0.58951366,  0.5951584 , -0.5303762 ,  0.6604994 ,\n          0.11986119],\n        [-0.01657734,  0.08166829,  0.1999365 , -0.2276518 , -1.0490825 ,\n          0.64033693,  0.08958744,  0.68012303,  0.3293335 , -0.39857572,\n         -0.27146953],\n        [ 0.7421306 , -0.01097731,  0.6695651 ,  0.46422392,  0.7513868 ,\n          0.24977766,  0.36928266,  0.32836688,  0.1051584 , -0.24629983,\n          0.09617753],\n        [-0.28878537,  0.07613596,  0.33939758, -0.2992713 ,  0.28714243,\n         -0.14956519, -0.38229388, -0.09044052, -1.1750525 ,  0.40415493,\n          0.02017275],\n        [ 0.46110386,  0.6603985 ,  0.24839209, -1.182988  , -0.2942415 ,\n         -0.231153  , -0.08151922, -0.04869241, -0.32438955,  0.16516286,\n          0.0798097 ]], dtype=float32),\n array([ 0.18607222,  0.17817849,  0.7903422 , -0.12907366,  0.17187302,\n         0.8677374 ,  0.26455104,  0.24916644,  0.26503423,  0.40288967,\n         0.2354055 ], dtype=float32)]"},"metadata":{}}]},{"cell_type":"code","source":"y_log=model.predict(X_test_scaled)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:36:23.795338Z","iopub.execute_input":"2024-08-16T10:36:23.795746Z","iopub.status.idle":"2024-08-16T10:36:24.091060Z","shell.execute_reply.started":"2024-08-16T10:36:23.795713Z","shell.execute_reply":"2024-08-16T10:36:24.089806Z"},"trusted":true},"execution_count":61,"outputs":[{"name":"stdout","text":"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step\n","output_type":"stream"}]},{"cell_type":"code","source":"y_pred=np.where(y_log>0.5,1,0)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:36:26.318602Z","iopub.execute_input":"2024-08-16T10:36:26.318987Z","iopub.status.idle":"2024-08-16T10:36:26.325149Z","shell.execute_reply.started":"2024-08-16T10:36:26.318958Z","shell.execute_reply":"2024-08-16T10:36:26.323406Z"},"trusted":true},"execution_count":62,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\naccuracy_score(y_test,y_pred)","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:36:29.055701Z","iopub.execute_input":"2024-08-16T10:36:29.056109Z","iopub.status.idle":"2024-08-16T10:36:29.067575Z","shell.execute_reply.started":"2024-08-16T10:36:29.056076Z","shell.execute_reply":"2024-08-16T10:36:29.066199Z"},"trusted":true},"execution_count":63,"outputs":[{"execution_count":63,"output_type":"execute_result","data":{"text/plain":"0.8545"},"metadata":{}}]},{"cell_type":"code","source":"import matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:40:32.585621Z","iopub.execute_input":"2024-08-16T10:40:32.586454Z","iopub.status.idle":"2024-08-16T10:40:32.591309Z","shell.execute_reply.started":"2024-08-16T10:40:32.586416Z","shell.execute_reply":"2024-08-16T10:40:32.589792Z"},"trusted":true},"execution_count":65,"outputs":[]},{"cell_type":"code","source":"history.history","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:40:42.464909Z","iopub.execute_input":"2024-08-16T10:40:42.465319Z","iopub.status.idle":"2024-08-16T10:40:42.474771Z","shell.execute_reply.started":"2024-08-16T10:40:42.465286Z","shell.execute_reply":"2024-08-16T10:40:42.473598Z"},"trusted":true},"execution_count":66,"outputs":[{"execution_count":66,"output_type":"execute_result","data":{"text/plain":"{'loss': [0.30956652760505676,\n  0.3095845878124237,\n  0.3101411461830139,\n  0.31002503633499146,\n  0.3094123303890228,\n  0.3095414638519287,\n  0.3097653090953827,\n  0.30939555168151855,\n  0.30966129899024963,\n  0.3089887201786041,\n  0.31012850999832153,\n  0.30976372957229614,\n  0.3090441823005676,\n  0.31044256687164307,\n  0.30918222665786743,\n  0.3095510005950928,\n  0.3095966875553131,\n  0.3085702061653137,\n  0.3093222677707672,\n  0.3095090091228485,\n  0.30914506316185,\n  0.3092975616455078,\n  0.3089619576931,\n  0.3090868890285492,\n  0.30849093198776245,\n  0.3088625371456146,\n  0.3088570237159729,\n  0.3099684715270996,\n  0.30914971232414246,\n  0.30911171436309814,\n  0.3091176748275757,\n  0.30931025743484497,\n  0.3087999224662781,\n  0.30877989530563354,\n  0.3093958795070648,\n  0.30868422985076904,\n  0.30930086970329285,\n  0.30871880054473877,\n  0.30885544419288635,\n  0.3086387515068054,\n  0.308952659368515,\n  0.3081667423248291,\n  0.309264600276947,\n  0.308534175157547,\n  0.3083716034889221,\n  0.3087332844734192,\n  0.30841195583343506,\n  0.3087460398674011,\n  0.30904290080070496,\n  0.30877524614334106,\n  0.3089132606983185,\n  0.3081217110157013,\n  0.3079424798488617,\n  0.3084436058998108,\n  0.3080974519252777,\n  0.30829036235809326,\n  0.3087197542190552,\n  0.3082801401615143,\n  0.30817580223083496,\n  0.3085843026638031,\n  0.30810144543647766,\n  0.30816584825515747,\n  0.3083595633506775,\n  0.30798205733299255,\n  0.30733180046081543,\n  0.3083761930465698,\n  0.3079558312892914,\n  0.30846428871154785,\n  0.3078637719154358,\n  0.3081812560558319,\n  0.30754557251930237,\n  0.308402419090271,\n  0.30816739797592163,\n  0.3076642155647278,\n  0.30848199129104614,\n  0.30725666880607605,\n  0.30742284655570984,\n  0.3075794279575348,\n  0.30760741233825684,\n  0.307628333568573,\n  0.3080425560474396,\n  0.30754852294921875,\n  0.3070678412914276,\n  0.3085118234157562,\n  0.3072095215320587,\n  0.3083871901035309,\n  0.3078516125679016,\n  0.30801886320114136,\n  0.30726301670074463,\n  0.3080972731113434,\n  0.30807510018348694,\n  0.3075014352798462,\n  0.30739784240722656,\n  0.3079899847507477,\n  0.307949036359787,\n  0.3075254261493683,\n  0.3082959055900574,\n  0.3075144588947296,\n  0.3069843649864197,\n  0.3077332377433777],\n 'val_loss': [0.36004334688186646,\n  0.35902121663093567,\n  0.35830092430114746,\n  0.36120444536209106,\n  0.36021095514297485,\n  0.3584010601043701,\n  0.36014947295188904,\n  0.36024364829063416,\n  0.3611057698726654,\n  0.3592773377895355,\n  0.36016830801963806,\n  0.36035072803497314,\n  0.36114558577537537,\n  0.35931339859962463,\n  0.36014214158058167,\n  0.35908588767051697,\n  0.36120426654815674,\n  0.3632582128047943,\n  0.35992631316185,\n  0.35951268672943115,\n  0.35970914363861084,\n  0.3585553765296936,\n  0.36404886841773987,\n  0.3582766652107239,\n  0.36083000898361206,\n  0.3602224290370941,\n  0.3630334138870239,\n  0.36104512214660645,\n  0.36374151706695557,\n  0.3597078323364258,\n  0.3593975901603699,\n  0.3614537715911865,\n  0.3604705333709717,\n  0.360855370759964,\n  0.36249056458473206,\n  0.35975733399391174,\n  0.3619372844696045,\n  0.3583507835865021,\n  0.3585112690925598,\n  0.36335375905036926,\n  0.36206069588661194,\n  0.3623882532119751,\n  0.3590898811817169,\n  0.3620286285877228,\n  0.3618806004524231,\n  0.3608819544315338,\n  0.3619530200958252,\n  0.3621658682823181,\n  0.3613920509815216,\n  0.358967661857605,\n  0.3605221211910248,\n  0.35935860872268677,\n  0.3607766330242157,\n  0.3614751100540161,\n  0.36261704564094543,\n  0.3638436496257782,\n  0.36014530062675476,\n  0.3610178828239441,\n  0.3596732020378113,\n  0.36050474643707275,\n  0.36095812916755676,\n  0.359887033700943,\n  0.3582206070423126,\n  0.36212098598480225,\n  0.36119452118873596,\n  0.3614426851272583,\n  0.36151206493377686,\n  0.36006996035575867,\n  0.361545592546463,\n  0.3608816862106323,\n  0.3638095557689667,\n  0.35954511165618896,\n  0.3611413538455963,\n  0.363638311624527,\n  0.36181995272636414,\n  0.3603155016899109,\n  0.36289089918136597,\n  0.36158180236816406,\n  0.3612617552280426,\n  0.36290568113327026,\n  0.36192816495895386,\n  0.3628796339035034,\n  0.36577117443084717,\n  0.36162838339805603,\n  0.36171868443489075,\n  0.36202698945999146,\n  0.3632090091705322,\n  0.3638245761394501,\n  0.36419200897216797,\n  0.36525267362594604,\n  0.36197951436042786,\n  0.36225372552871704,\n  0.3640654385089874,\n  0.35998889803886414,\n  0.362116277217865,\n  0.36246609687805176,\n  0.3623773157596588,\n  0.36132925748825073,\n  0.3628736436367035,\n  0.3642493188381195]}"},"metadata":{}}]},{"cell_type":"code","source":"plt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])","metadata":{"execution":{"iopub.status.busy":"2024-08-16T10:41:53.638769Z","iopub.execute_input":"2024-08-16T10:41:53.639162Z","iopub.status.idle":"2024-08-16T10:41:53.890053Z","shell.execute_reply.started":"2024-08-16T10:41:53.639130Z","shell.execute_reply":"2024-08-16T10:41:53.888876Z"},"trusted":true},"execution_count":68,"outputs":[{"execution_count":68,"output_type":"execute_result","data":{"text/plain":"[<matplotlib.lines.Line2D at 0x7e879374fd90>]"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}