-
Notifications
You must be signed in to change notification settings - Fork 0
/
Credit Risk Model Stability Analysis
1 lines (1 loc) · 235 KB
/
Credit Risk Model Stability Analysis
1
{"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":8111180,"sourceType":"datasetVersion","datasetId":4791480},{"sourceId":8116539,"sourceType":"datasetVersion","datasetId":4795411}],"dockerImageVersionId":30684,"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)\nimport os\nimport matplotlib.pyplot as plt #graphs\nimport seaborn as sns\n\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":"2024-05-18T15:26:57.997332Z","iopub.execute_input":"2024-05-18T15:26:57.997740Z","iopub.status.idle":"2024-05-18T15:27:00.657961Z","shell.execute_reply.started":"2024-05-18T15:26:57.997709Z","shell.execute_reply":"2024-05-18T15:27:00.656922Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"/kaggle/input/homecredit/sample_submission.csv\n/kaggle/input/homecredit/feature_definitions.csv\n/kaggle/input/homecredit/parquet_files/test/test_deposit_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_applprev_2.parquet\n/kaggle/input/homecredit/parquet_files/test/test_static_cb_0.parquet\n/kaggle/input/homecredit/parquet_files/test/test_static_0_0.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_1_3.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_1_2.parquet\n/kaggle/input/homecredit/parquet_files/test/test_tax_registry_b_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_static_0_2.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_3.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_9.parquet\n/kaggle/input/homecredit/parquet_files/test/test_debitcard_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_1_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_2.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_11.parquet\n/kaggle/input/homecredit/parquet_files/test/test_applprev_1_2.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_1_4.parquet\n/kaggle/input/homecredit/parquet_files/test/test_tax_registry_c_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_applprev_1_0.parquet\n/kaggle/input/homecredit/parquet_files/test/test_tax_registry_a_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_6.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_5.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_b_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_other_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_static_0_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_0.parquet\n/kaggle/input/homecredit/parquet_files/test/test_applprev_1_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_base.parquet\n/kaggle/input/homecredit/parquet_files/test/test_person_1.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_7.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_10.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_b_2.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_8.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_1_0.parquet\n/kaggle/input/homecredit/parquet_files/test/test_credit_bureau_a_2_4.parquet\n/kaggle/input/homecredit/parquet_files/test/test_person_2.parquet\n/kaggle/input/homecredit/parquet_files/train/train_tax_registry_c_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_static_0_0.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_1_3.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_b_2.parquet\n/kaggle/input/homecredit/parquet_files/train/train_applprev_1_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_static_cb_0.parquet\n/kaggle/input/homecredit/parquet_files/train/train_other_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_6.parquet\n/kaggle/input/homecredit/parquet_files/train/train_tax_registry_a_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_tax_registry_b_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_person_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_person_2.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_b_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_0.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_7.parquet\n/kaggle/input/homecredit/parquet_files/train/train_deposit_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_debitcard_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_5.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_2.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_4.parquet\n/kaggle/input/homecredit/parquet_files/train/train_base.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_9.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_3.parquet\n/kaggle/input/homecredit/parquet_files/train/train_applprev_2.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_10.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_2_8.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_1_2.parquet\n/kaggle/input/homecredit/parquet_files/train/train_static_0_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_1_0.parquet\n/kaggle/input/homecredit/parquet_files/train/train_credit_bureau_a_1_1.parquet\n/kaggle/input/homecredit/parquet_files/train/train_applprev_1_0.parquet\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_6.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_11.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_0.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_9.csv\n/kaggle/input/homecredit/csv_files/test/test_base.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_1_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_b_2.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_10.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_4.csv\n/kaggle/input/homecredit/csv_files/test/test_static_0_0.csv\n/kaggle/input/homecredit/csv_files/test/test_static_cb_0.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_2.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_b_1.csv\n/kaggle/input/homecredit/csv_files/test/test_tax_registry_b_1.csv\n/kaggle/input/homecredit/csv_files/test/test_person_2.csv\n/kaggle/input/homecredit/csv_files/test/test_person_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_8.csv\n/kaggle/input/homecredit/csv_files/test/test_applprev_1_2.csv\n/kaggle/input/homecredit/csv_files/test/test_applprev_1_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_1_0.csv\n/kaggle/input/homecredit/csv_files/test/test_applprev_2.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_7.csv\n/kaggle/input/homecredit/csv_files/test/test_other_1.csv\n/kaggle/input/homecredit/csv_files/test/test_tax_registry_c_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_1_3.csv\n/kaggle/input/homecredit/csv_files/test/test_static_0_2.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_5.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_1_2.csv\n/kaggle/input/homecredit/csv_files/test/test_debitcard_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_1_4.csv\n/kaggle/input/homecredit/csv_files/test/test_deposit_1.csv\n/kaggle/input/homecredit/csv_files/test/test_static_0_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_1.csv\n/kaggle/input/homecredit/csv_files/test/test_applprev_1_0.csv\n/kaggle/input/homecredit/csv_files/test/test_tax_registry_a_1.csv\n/kaggle/input/homecredit/csv_files/test/test_credit_bureau_a_2_3.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_1_3.csv\n/kaggle/input/homecredit/csv_files/train/train_static_cb_0.csv\n/kaggle/input/homecredit/csv_files/train/train_applprev_1_0.csv\n/kaggle/input/homecredit/csv_files/train/train_person_2.csv\n/kaggle/input/homecredit/csv_files/train/train_base.csv\n/kaggle/input/homecredit/csv_files/train/train_tax_registry_a_1.csv\n/kaggle/input/homecredit/csv_files/train/train_static_0_0.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_1_0.csv\n/kaggle/input/homecredit/csv_files/train/train_applprev_2.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_6.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_1_2.csv\n/kaggle/input/homecredit/csv_files/train/train_person_1.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_1_1.csv\n/kaggle/input/homecredit/csv_files/train/train_tax_registry_c_1.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_4.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_9.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_3.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_7.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_b_2.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_2.csv\n/kaggle/input/homecredit/csv_files/train/train_static_0_1.csv\n/kaggle/input/homecredit/csv_files/train/train_deposit_1.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_10.csv\n/kaggle/input/homecredit/csv_files/train/train_tax_registry_b_1.csv\n/kaggle/input/homecredit/csv_files/train/train_applprev_1_1.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_1.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_8.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_5.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_b_1.csv\n/kaggle/input/homecredit/csv_files/train/train_credit_bureau_a_2_0.csv\n/kaggle/input/homecredit/csv_files/train/train_other_1.csv\n/kaggle/input/homecredit/csv_files/train/train_debitcard_1.csv\n/kaggle/input/credit-risk-model-stability/kaggle.json\n","output_type":"stream"}]},{"cell_type":"code","source":"#!pip install kaggle \n!pip install --upgrade kaggle","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:00.659686Z","iopub.execute_input":"2024-05-18T15:27:00.660133Z","iopub.status.idle":"2024-05-18T15:27:17.277113Z","shell.execute_reply.started":"2024-05-18T15:27:00.660103Z","shell.execute_reply":"2024-05-18T15:27:17.275836Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"Requirement already satisfied: kaggle in /opt/conda/lib/python3.10/site-packages (1.6.8)\nCollecting kaggle\n Downloading kaggle-1.6.14.tar.gz (82 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m82.1/82.1 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m\n\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hRequirement already satisfied: six>=1.10 in /opt/conda/lib/python3.10/site-packages (from kaggle) (1.16.0)\nRequirement already satisfied: certifi>=2023.7.22 in /opt/conda/lib/python3.10/site-packages (from kaggle) (2024.2.2)\nRequirement already satisfied: python-dateutil in /opt/conda/lib/python3.10/site-packages (from kaggle) (2.9.0.post0)\nRequirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from kaggle) (2.31.0)\nRequirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from kaggle) (4.66.1)\nRequirement already satisfied: python-slugify in /opt/conda/lib/python3.10/site-packages (from kaggle) (8.0.4)\nRequirement already satisfied: urllib3 in /opt/conda/lib/python3.10/site-packages (from kaggle) (1.26.18)\nRequirement already satisfied: bleach in /opt/conda/lib/python3.10/site-packages (from kaggle) (6.1.0)\nRequirement already satisfied: webencodings in /opt/conda/lib/python3.10/site-packages (from bleach->kaggle) (0.5.1)\nRequirement already satisfied: text-unidecode>=1.3 in /opt/conda/lib/python3.10/site-packages (from python-slugify->kaggle) (1.3)\nRequirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->kaggle) (3.3.2)\nRequirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->kaggle) (3.6)\nBuilding wheels for collected packages: kaggle\n Building wheel for kaggle (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for kaggle: filename=kaggle-1.6.14-py3-none-any.whl size=105120 sha256=167ad455cf53031dd1193f6e1e4a914058a121f6ca46b56a4bf04d925b98bcb6\n Stored in directory: /root/.cache/pip/wheels/d7/54/06/8a8f40cb39536605feb9acaacd0237a95eba39e5065e6392f4\nSuccessfully built kaggle\nInstalling collected packages: kaggle\n Attempting uninstall: kaggle\n Found existing installation: kaggle 1.6.8\n Uninstalling kaggle-1.6.8:\n Successfully uninstalled kaggle-1.6.8\nSuccessfully installed kaggle-1.6.14\n","output_type":"stream"}]},{"cell_type":"code","source":"\n\n# Specify the directory path\ndirectory_path = '/kaggle/input/homecredit/csv_files/'\n\n# Specify the subdirectory name\nsubdirectory_name = 'test'\n\n# List files in the subdirectory\nsubdirectory_path = os.path.join(directory_path, subdirectory_name)\nfile_list = os.listdir(subdirectory_path)\n\n\n# Create an empty dictionary to store DataFrames\ndata_dict = {}\n# Loop through each file in the subdirectory\nfor file_name in file_list:\n # Construct the full file path\n file_path = os.path.join(subdirectory_path, file_name)\n # Read the CSV file into a DataFrame\n df = pd.read_csv(file_path)\n # Store the DataFrame in the dictionary using the file name as the key\n data_dict[file_name] = df\n\n# Display the first few rows of each DataFrame\nfor file_name, df in data_dict.items():\n print(df.tail(5))\n \n\n\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.279082Z","iopub.execute_input":"2024-05-18T15:27:17.279508Z","iopub.status.idle":"2024-05-18T15:27:17.751262Z","shell.execute_reply.started":"2024-05-18T15:27:17.279473Z","shell.execute_reply":"2024-05-18T15:27:17.750090Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":" case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57636 a55475b1 a55475b1 \n6 57636 a55475b1 a55475b1 \n7 57636 a55475b1 a55475b1 \n8 57636 a55475b1 a55475b1 \n9 57636 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 a55475b1 a55475b1 0 \n6 a55475b1 a55475b1 0 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 2 NaN 0.0 4.0 \n6 3 NaN 16.0 5.0 \n7 4 NaN 22.0 6.0 \n8 5 NaN 0.0 7.0 \n9 6 NaN 0.0 8.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 4.0 NaN 0.000 2021.0 \n6 5.0 NaN 391.866 2021.0 \n7 6.0 NaN 391.866 2021.0 \n8 7.0 NaN 0.000 2021.0 \n9 8.0 NaN 0.000 2021.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2018.0 a55475b1 a55475b1 \n6 2018.0 a55475b1 a55475b1 \n7 2018.0 a55475b1 a55475b1 \n8 2018.0 a55475b1 a55475b1 \n9 2018.0 a55475b1 a55475b1 \n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57696 a55475b1 a55475b1 \n6 57696 a55475b1 a55475b1 \n7 57696 a55475b1 a55475b1 \n8 57696 a55475b1 a55475b1 \n9 57696 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 a55475b1 a55475b1 0 \n6 a55475b1 a55475b1 0 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 3 NaN NaN 5.0 \n6 4 NaN NaN 6.0 \n7 5 NaN NaN 7.0 \n8 6 NaN NaN 8.0 \n9 7 NaN 0.0 9.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 5.0 NaN NaN 2021.0 \n6 6.0 NaN NaN 2021.0 \n7 7.0 NaN NaN 2021.0 \n8 8.0 NaN NaN 2021.0 \n9 9.0 NaN 0.0 2021.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2021.0 a55475b1 a55475b1 \n6 2021.0 a55475b1 a55475b1 \n7 2021.0 a55475b1 a55475b1 \n8 2021.0 a55475b1 a55475b1 \n9 2021.0 a55475b1 a55475b1 \n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57551 a55475b1 8fd95e4b \n6 57551 a55475b1 8fd95e4b \n7 57551 a55475b1 9a0c095e \n8 57551 a55475b1 8fd95e4b \n9 57551 a55475b1 8fd95e4b \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN 0.0 \n6 NaN 0.0 \n7 NaN 0.0 \n8 NaN 0.0 \n9 NaN 0.0 \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 c7a5ad39 a55475b1 8 \n6 c7a5ad39 a55475b1 9 \n7 c7a5ad39 a55475b1 10 \n8 c7a5ad39 a55475b1 11 \n9 c7a5ad39 a55475b1 12 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 0 NaN NaN NaN \n6 0 NaN NaN NaN \n7 0 NaN NaN NaN \n8 0 NaN NaN NaN \n9 0 NaN NaN NaN \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 2.0 NaN NaN NaN \n6 2.0 NaN NaN NaN \n7 2.0 NaN NaN NaN \n8 2.0 NaN NaN NaN \n9 2.0 NaN NaN NaN \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2015.0 ab3c25cf a55475b1 \n6 2017.0 ab3c25cf a55475b1 \n7 2017.0 ab3c25cf a55475b1 \n8 2017.0 ab3c25cf a55475b1 \n9 2017.0 ab3c25cf a55475b1 \n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57549 a55475b1 9a0c095e \n6 57549 a55475b1 9a0c095e \n7 57549 a55475b1 9a0c095e \n8 57549 a55475b1 9a0c095e \n9 57549 a55475b1 8fd95e4b \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN 0.0 \n6 NaN 0.0 \n7 NaN 0.0 \n8 NaN 0.0 \n9 NaN 0.0 \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 c7a5ad39 a55475b1 5 \n6 c7a5ad39 a55475b1 6 \n7 c7a5ad39 a55475b1 7 \n8 c7a5ad39 a55475b1 8 \n9 c7a5ad39 a55475b1 9 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 0 NaN NaN NaN \n6 0 NaN NaN NaN \n7 0 NaN NaN NaN \n8 0 NaN NaN NaN \n9 0 NaN NaN NaN \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 2.0 NaN NaN NaN \n6 2.0 NaN NaN NaN \n7 2.0 NaN NaN NaN \n8 2.0 NaN NaN NaN \n9 2.0 NaN NaN NaN \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2018.0 ab3c25cf a55475b1 \n6 2019.0 ab3c25cf a55475b1 \n7 2019.0 ab3c25cf a55475b1 \n8 2019.0 ab3c25cf a55475b1 \n9 2019.0 ab3c25cf a55475b1 \n case_id date_decision MONTH WEEK_NUM\n5 57630 2021-03-16 202201 100\n6 57631 2022-06-04 202201 100\n7 57632 2022-02-05 202201 100\n8 57633 2022-01-25 202201 100\n9 57634 2021-01-27 202201 100\n case_id annualeffectiverate_199L annualeffectiverate_63L \\\n5 57543 NaN NaN \n6 57543 NaN NaN \n7 57543 NaN NaN \n8 57543 NaN NaN \n9 57543 NaN NaN \n\n classificationofcontr_13M classificationofcontr_400M contractst_545M \\\n5 a55475b1 01f63ac8 a55475b1 \n6 a55475b1 01f63ac8 a55475b1 \n7 a55475b1 ea6782cc a55475b1 \n8 a55475b1 ea6782cc a55475b1 \n9 a55475b1 ea6782cc a55475b1 \n\n contractst_964M contractsum_5085717L credlmt_230A credlmt_935A ... \\\n5 7241344e NaN NaN NaN ... \n6 7241344e NaN NaN NaN ... \n7 7241344e NaN NaN NaN ... \n8 7241344e NaN NaN NaN ... \n9 7241344e NaN NaN NaN ... \n\n residualamount_488A residualamount_856A subjectrole_182M subjectrole_93M \\\n5 NaN NaN a55475b1 a55475b1 \n6 NaN NaN a55475b1 a55475b1 \n7 NaN NaN a55475b1 a55475b1 \n8 NaN NaN a55475b1 a55475b1 \n9 NaN NaN a55475b1 a55475b1 \n\n totalamount_6A totalamount_996A totaldebtoverduevalue_178A \\\n5 4200.0 NaN NaN \n6 6000.0 NaN NaN \n7 14000.0 NaN NaN \n8 34175.2 NaN NaN \n9 8398.0 NaN NaN \n\n totaldebtoverduevalue_718A totaloutstanddebtvalue_39A \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n totaloutstanddebtvalue_668A \n5 NaN \n6 NaN \n7 NaN \n8 NaN \n9 NaN \n\n[5 rows x 79 columns]\n case_id num_group1 num_group2 pmts_date_1107D pmts_dpdvalue_108P \\\n5 57675 0 5 2020-10-14 0.0 \n6 57675 0 6 2020-11-13 0.0 \n7 57675 0 7 2020-12-14 0.0 \n8 57675 0 8 2021-01-13 0.0 \n9 57675 0 9 2021-02-13 0.0 \n\n pmts_pmtsoverdue_635A \n5 0.0 \n6 0.0 \n7 0.0 \n8 0.0 \n9 0.0 \n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57681 a55475b1 9a0c095e \n6 57681 a55475b1 8fd95e4b \n7 57681 a55475b1 a55475b1 \n8 57681 a55475b1 a55475b1 \n9 57681 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN 0.0 \n6 NaN 0.0 \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 c7a5ad39 a55475b1 5 \n6 c7a5ad39 a55475b1 6 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 0 NaN NaN NaN \n6 0 NaN NaN NaN \n7 1 0.0 NaN 3.0 \n8 2 0.0 NaN 4.0 \n9 3 0.0 NaN 5.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 2.0 NaN NaN NaN \n6 2.0 NaN NaN NaN \n7 3.0 0.0 NaN 2022.0 \n8 4.0 0.0 NaN 2022.0 \n9 5.0 0.0 NaN 2022.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2020.0 ab3c25cf a55475b1 \n6 2021.0 ab3c25cf a55475b1 \n7 2017.0 a55475b1 a55475b1 \n8 2017.0 a55475b1 a55475b1 \n9 2017.0 a55475b1 a55475b1 \n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57630 a55475b1 a55475b1 \n6 57630 a55475b1 a55475b1 \n7 57630 a55475b1 a55475b1 \n8 57630 a55475b1 a55475b1 \n9 57630 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 a55475b1 a55475b1 0 \n6 a55475b1 a55475b1 0 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 4 NaN NaN 6.0 \n6 5 NaN NaN 7.0 \n7 6 0.0 NaN 8.0 \n8 7 NaN NaN 9.0 \n9 8 NaN NaN 10.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 6.0 NaN NaN 2021.0 \n6 7.0 NaN NaN 2021.0 \n7 8.0 0.0 NaN 2021.0 \n8 9.0 NaN NaN 2021.0 \n9 10.0 NaN NaN 2021.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2014.0 a55475b1 a55475b1 \n6 2014.0 a55475b1 a55475b1 \n7 2014.0 a55475b1 a55475b1 \n8 2014.0 a55475b1 a55475b1 \n9 2014.0 a55475b1 a55475b1 \n case_id actualdpdtolerance_344P amtinstpaidbefduel24m_4187115A \\\n5 57631 0.0 NaN \n6 57632 0.0 63647.402 \n7 57635 0.0 NaN \n8 57637 0.0 43677.184 \n9 57639 0.0 142333.140 \n\n annuity_780A annuitynextmonth_57A applicationcnt_361L \\\n5 2540.600 0.0 0.0 \n6 4732.000 0.0 0.0 \n7 1167.400 0.0 0.0 \n8 4300.400 0.0 0.0 \n9 12599.601 0.0 0.0 \n\n applications30d_658L applicationscnt_1086L applicationscnt_464L \\\n5 0.0 0.0 0.0 \n6 0.0 0.0 0.0 \n7 0.0 0.0 0.0 \n8 0.0 0.0 0.0 \n9 0.0 0.0 0.0 \n\n applicationscnt_629L ... sellerplacecnt_915L sellerplacescnt_216L \\\n5 0.0 ... 0.0 0.0 \n6 0.0 ... 0.0 1.0 \n7 0.0 ... 0.0 0.0 \n8 0.0 ... 0.0 2.0 \n9 0.0 ... 0.0 11.0 \n\n sumoutstandtotal_3546847A sumoutstandtotalest_4493215A totaldebt_9A \\\n5 NaN NaN 0.000 \n6 0.000 0.000 0.000 \n7 NaN NaN 0.000 \n8 0.000 0.000 0.000 \n9 26189.932 26189.932 26189.932 \n\n totalsettled_863A totinstallast1m_4525188A twobodfilling_608L \\\n5 0.00 NaN FO \n6 63652.00 7071.4 FO \n7 0.00 NaN FO \n8 143527.60 NaN FO \n9 337413.22 5588.0 BO \n\n typesuite_864L validfrom_1069D \n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n[5 rows x 168 columns]\n case_id assignmentdate_238D assignmentdate_4527235D \\\n5 57630 NaN NaN \n6 57631 NaN NaN \n7 57632 NaN NaN \n8 57633 NaN NaN \n9 57634 NaN NaN \n\n assignmentdate_4955616D birthdate_574D contractssum_5085716L \\\n5 NaN NaN 499975.00 \n6 NaN NaN 480334.49 \n7 2015-11-26 NaN 17677.00 \n8 NaN NaN 6373008.21 \n9 NaN NaN 15263.65 \n\n dateofbirth_337D dateofbirth_342D days120_123L days180_256L ... \\\n5 1967-02-01 NaN 1.0 2.0 ... \n6 1986-11-01 NaN 0.0 0.0 ... \n7 1958-11-01 NaN 1.0 2.0 ... \n8 1993-05-01 NaN 3.0 3.0 ... \n9 1976-07-01 NaN 2.0 2.0 ... \n\n pmtscount_423L pmtssum_45A requesttype_4525192L responsedate_1012D \\\n5 NaN NaN NaN NaN \n6 NaN NaN NaN NaN \n7 NaN NaN NaN NaN \n8 NaN NaN NaN NaN \n9 NaN NaN NaN NaN \n\n responsedate_4527233D responsedate_4917613D riskassesment_302T \\\n5 NaN 2021-03-30 NaN \n6 NaN 2022-06-18 NaN \n7 NaN 2022-02-19 NaN \n8 NaN 2022-02-08 NaN \n9 NaN 2021-02-10 NaN \n\n riskassesment_940T secondquarter_766L thirdquarter_1082L \n5 NaN 4.0 1.0 \n6 NaN 2.0 5.0 \n7 NaN 1.0 1.0 \n8 NaN 3.0 1.0 \n9 NaN 0.0 1.0 \n\n[5 rows x 53 columns]\n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57632 a55475b1 a55475b1 \n6 57632 a55475b1 a55475b1 \n7 57632 a55475b1 a55475b1 \n8 57632 a55475b1 a55475b1 \n9 57632 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 a55475b1 a55475b1 0 \n6 a55475b1 a55475b1 0 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 5 NaN NaN 7.0 \n6 6 NaN NaN 8.0 \n7 7 0.0 NaN 9.0 \n8 8 0.0 NaN 10.0 \n9 9 0.0 NaN 11.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 NaN NaN NaN 2019.0 \n6 NaN NaN NaN 2019.0 \n7 NaN 0.0 NaN 2019.0 \n8 NaN 0.0 NaN 2019.0 \n9 NaN 0.0 NaN 2019.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 NaN a55475b1 a55475b1 \n6 NaN a55475b1 a55475b1 \n7 NaN a55475b1 a55475b1 \n8 NaN a55475b1 a55475b1 \n9 NaN a55475b1 a55475b1 \n case_id amount_1115A classificationofcontr_1114M contractdate_551D \\\n5 57754 NaN ea6782cc 2020-12-05 \n6 57754 NaN ea6782cc 2020-09-15 \n7 57754 NaN 01f63ac8 2021-12-26 \n8 57775 2000.0 a55475b1 2021-01-20 \n9 57775 3000.0 a55475b1 2020-06-26 \n\n contractmaturitydate_151D contractst_516M contracttype_653M credlmt_1052A \\\n5 2022-10-18 7241344e 1c9c5356 NaN \n6 2022-09-16 7241344e 1c9c5356 NaN \n7 2024-12-25 7241344e 1c9c5356 NaN \n8 2021-02-19 7241344e 4257cbed NaN \n9 2020-07-25 0dc85f9d 4257cbed NaN \n\n credlmt_228A credlmt_3940954A ... pmtmethod_731M pmtnumpending_403L \\\n5 NaN 0.0 ... a55475b1 NaN \n6 NaN 20000.0 ... a55475b1 NaN \n7 NaN 76800.0 ... a55475b1 NaN \n8 NaN NaN ... dbcbe8f8 0.0 \n9 NaN NaN ... dbcbe8f8 0.0 \n\n purposeofcred_722M residualamount_1093A residualamount_127A \\\n5 60c73645 NaN NaN \n6 60c73645 NaN NaN \n7 60c73645 NaN NaN \n8 96a8fdfe NaN NaN \n9 96a8fdfe NaN NaN \n\n residualamount_3940956A subjectrole_326M subjectrole_43M \\\n5 0.000 P28_48_88 ab3c25cf \n6 6733.200 a55475b1 a55475b1 \n7 50039.508 a55475b1 a55475b1 \n8 NaN a55475b1 a55475b1 \n9 NaN a55475b1 ab3c25cf \n\n totalamount_503A totalamount_881A \n5 1932619.4 575772.44 \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN 156400.00 \n\n[5 rows x 45 columns]\n case_id amount_4917619A deductiondate_4917603D name_4917606M num_group1\n5 57543 27191.8 2021-04-22 787c689d 4\n6 57551 3585.0 2020-07-30 d580dfef 2\n7 57551 5911.4 2020-09-22 d580dfef 4\n8 57551 11040.4 2020-09-30 d580dfef 6\n9 57551 14644.8 2020-06-26 d580dfef 0\n case_id addres_district_368M addres_role_871L addres_zip_823M \\\n5 57569 P125_48_164 TEMPORARY P47_66_61 \n6 57569 P180_77_106 PERMANENT P47_66_61 \n7 57569 P180_77_106 PERMANENT P96_113_139 \n8 57569 P125_48_164 PERMANENT P47_66_61 \n9 57569 P28_121_188 PERMANENT P47_66_61 \n\n conts_role_79M empls_economicalst_849M empls_employedfrom_796D \\\n5 P177_137_98 a55475b1 NaN \n6 P38_92_157 a55475b1 NaN \n7 P38_92_157 a55475b1 NaN \n8 P38_92_157 a55475b1 NaN \n9 a55475b1 a55475b1 NaN \n\n empls_employer_name_740M num_group1 num_group2 relatedpersons_role_762T \n5 a55475b1 1 1 PARENT \n6 a55475b1 1 2 OTHER \n7 a55475b1 1 3 NaN \n8 a55475b1 1 4 NaN \n9 a55475b1 1 5 NaN \n case_id birth_259D birthdate_87D childnum_185L contaddr_district_15M \\\n5 57552 1955-11-01 NaN NaN P21_84_40 \n6 57569 NaN 1949-09-01 0.0 a55475b1 \n7 57569 1949-09-01 1949-09-01 NaN P121_131_159 \n8 57630 1967-02-01 NaN NaN P49_110_166 \n9 57630 NaN NaN NaN a55475b1 \n\n contaddr_matchlist_1032L contaddr_smempladdr_334L contaddr_zipcode_807M \\\n5 False False P91_47_168 \n6 NaN NaN a55475b1 \n7 False False P96_113_139 \n8 False False P161_14_174 \n9 NaN NaN a55475b1 \n\n education_927M empl_employedfrom_271D ... registaddr_district_1083M \\\n5 a55475b1 NaN ... P21_87_50 \n6 P97_36_170 NaN ... a55475b1 \n7 P106_81_188 NaN ... P121_131_159 \n8 P106_81_188 NaN ... P49_110_166 \n9 a55475b1 NaN ... a55475b1 \n\n registaddr_zipcode_184M relationshiptoclient_415T \\\n5 P91_47_168 NaN \n6 a55475b1 CHILD \n7 P96_113_139 NaN \n8 P161_14_174 NaN \n9 a55475b1 SPOUSE \n\n relationshiptoclient_642T remitter_829L role_1084L role_993L \\\n5 NaN NaN CL NaN \n6 CHILD False PE FULL \n7 NaN NaN CL FULL \n8 NaN NaN CL NaN \n9 SPOUSE False PE NaN \n\n safeguarantyflag_411L sex_738L type_25L \n5 True M PRIMARY_MOBILE \n6 NaN NaN PHONE \n7 False F PRIMARY_MOBILE \n8 True F PRIMARY_MOBILE \n9 NaN NaN PHONE \n\n[5 rows x 37 columns]\n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57645 a55475b1 8fd95e4b \n6 57645 a55475b1 8fd95e4b \n7 57645 a55475b1 8fd95e4b \n8 57645 a55475b1 8fd95e4b \n9 57645 a55475b1 8fd95e4b \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN 0.0 \n6 NaN 0.0 \n7 NaN 0.0 \n8 NaN 0.0 \n9 NaN 0.0 \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 c7a5ad39 a55475b1 5 \n6 c7a5ad39 a55475b1 6 \n7 c7a5ad39 a55475b1 7 \n8 c7a5ad39 a55475b1 8 \n9 c7a5ad39 a55475b1 9 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 0 NaN NaN NaN \n6 0 NaN NaN NaN \n7 0 NaN NaN NaN \n8 0 NaN NaN NaN \n9 0 NaN NaN NaN \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 2.0 NaN NaN NaN \n6 2.0 NaN NaN NaN \n7 2.0 NaN NaN NaN \n8 2.0 NaN NaN NaN \n9 2.0 NaN NaN NaN \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2019.0 ab3c25cf a55475b1 \n6 2020.0 ab3c25cf a55475b1 \n7 2020.0 ab3c25cf a55475b1 \n8 2021.0 ab3c25cf a55475b1 \n9 2021.0 ab3c25cf a55475b1 \n case_id actualdpd_943P annuity_853A approvaldate_319D \\\n5 57760 0.0 2923.4001 NaN \n6 57760 0.0 6449.6000 2019-07-17 \n7 57760 0.0 14092.6010 2020-06-15 \n8 57970 0.0 0.0000 NaN \n9 57970 0.0 768.0000 NaN \n\n byoccupationinc_3656910L cancelreason_3545846M childnum_21L \\\n5 NaN P94_109_143 NaN \n6 NaN a55475b1 NaN \n7 NaN a55475b1 NaN \n8 NaN P94_109_143 NaN \n9 18000.0 a55475b1 2.0 \n\n creationdate_885D credacc_actualbalance_314A credacc_credlmt_575A ... \\\n5 2017-01-11 NaN 0.0 ... \n6 2019-07-17 0.0 0.0 ... \n7 2020-06-15 100000.0 100000.0 ... \n8 2021-04-02 NaN 30000.0 ... \n9 2012-09-10 NaN 0.0 ... \n\n num_group1 outstandingdebt_522A pmtnum_8L postype_4733339M \\\n5 5 NaN 3.0 P149_40_170 \n6 4 0.0 12.0 P60_146_156 \n7 3 0.0 24.0 P46_145_78 \n8 0 NaN NaN P46_145_78 \n9 7 0.0 24.0 P177_117_192 \n\n profession_152M rejectreason_755M rejectreasonclient_4145042M \\\n5 a55475b1 P99_56_166 P94_109_143 \n6 a55475b1 a55475b1 a55475b1 \n7 a55475b1 a55475b1 a55475b1 \n8 a55475b1 a55475b1 P94_109_143 \n9 a55475b1 a55475b1 a55475b1 \n\n revolvingaccount_394A status_219L tenor_203L \n5 NaN D 3.0 \n6 NaN K 12.0 \n7 NaN K 24.0 \n8 NaN D NaN \n9 NaN D 24.0 \n\n[5 rows x 41 columns]\n case_id actualdpd_943P annuity_853A approvaldate_319D \\\n5 57549 0.0 2360.4001 NaN \n6 57549 0.0 3260.2000 2012-12-13 \n7 57549 0.0 3546.6000 2021-10-12 \n8 57549 0.0 3800.0000 NaN \n9 57549 0.0 3819.8000 NaN \n\n byoccupationinc_3656910L cancelreason_3545846M childnum_21L \\\n5 50000.0 a55475b1 0.0 \n6 35000.0 a55475b1 0.0 \n7 NaN a55475b1 NaN \n8 NaN P94_109_143 NaN \n9 50000.0 a55475b1 0.0 \n\n creationdate_885D credacc_actualbalance_314A credacc_credlmt_575A ... \\\n5 2012-05-03 17800.0 17800.0 ... \n6 2012-12-13 NaN 0.0 ... \n7 2021-10-12 NaN 0.0 ... \n8 2020-04-15 NaN 0.0 ... \n9 2012-05-03 NaN 0.0 ... \n\n num_group1 outstandingdebt_522A pmtnum_8L postype_4733339M \\\n5 12 0.0 8.0 P149_40_170 \n6 11 0.0 6.0 P60_146_156 \n7 3 10638.2 6.0 P46_145_78 \n8 5 NaN 36.0 P46_145_78 \n9 13 0.0 6.0 P46_145_78 \n\n profession_152M rejectreason_755M rejectreasonclient_4145042M \\\n5 a55475b1 a55475b1 a55475b1 \n6 a55475b1 a55475b1 a55475b1 \n7 a55475b1 a55475b1 a55475b1 \n8 a55475b1 a55475b1 P94_109_143 \n9 a55475b1 a55475b1 a55475b1 \n\n revolvingaccount_394A status_219L tenor_203L \n5 NaN D 8.0 \n6 NaN K 6.0 \n7 NaN N 6.0 \n8 NaN D 36.0 \n9 NaN D 6.0 \n\n[5 rows x 41 columns]\n case_id annualeffectiverate_199L annualeffectiverate_63L \\\n5 57551 NaN NaN \n6 57551 NaN NaN \n7 57551 NaN NaN \n8 57551 NaN NaN \n9 57551 NaN NaN \n\n classificationofcontr_13M classificationofcontr_400M contractst_545M \\\n5 a55475b1 ea6782cc a55475b1 \n6 a55475b1 ea6782cc a55475b1 \n7 a55475b1 ada1729d a55475b1 \n8 a55475b1 e6e56e83 a55475b1 \n9 a55475b1 ea6782cc a55475b1 \n\n contractst_964M contractsum_5085717L credlmt_230A credlmt_935A ... \\\n5 7241344e NaN 60000.0 NaN ... \n6 a3386307 NaN NaN NaN ... \n7 7241344e NaN NaN NaN ... \n8 7241344e NaN NaN NaN ... \n9 7241344e NaN NaN NaN ... \n\n residualamount_488A residualamount_856A subjectrole_182M subjectrole_93M \\\n5 0.0 NaN a55475b1 a55475b1 \n6 NaN NaN a55475b1 a55475b1 \n7 NaN NaN a55475b1 a55475b1 \n8 NaN NaN a55475b1 a55475b1 \n9 NaN NaN a55475b1 a55475b1 \n\n totalamount_6A totalamount_996A totaldebtoverduevalue_178A \\\n5 NaN NaN NaN \n6 218000.0 NaN NaN \n7 8081.2 NaN NaN \n8 9821.0 NaN NaN \n9 200000.0 NaN NaN \n\n totaldebtoverduevalue_718A totaloutstanddebtvalue_39A \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n totaloutstanddebtvalue_668A \n5 NaN \n6 NaN \n7 NaN \n8 NaN \n9 NaN \n\n[5 rows x 79 columns]\n case_id cacccardblochreas_147M conts_type_509L credacc_cards_status_52L \\\n5 57543 a55475b1 NaN NaN \n6 57543 a55475b1 PHONE NaN \n7 57543 a55475b1 PRIMARY_MOBILE NaN \n8 57543 a55475b1 PRIMARY_MOBILE NaN \n9 57543 a55475b1 NaN NaN \n\n num_group1 num_group2 \n5 2 1 \n6 3 0 \n7 3 1 \n8 4 0 \n9 4 1 \n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57633 9a0c095e 9a0c095e \n6 57633 8fd95e4b 9a0c095e \n7 57633 a55475b1 9a0c095e \n8 57633 a55475b1 9a0c095e \n9 57633 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 0.0 0.0 \n6 7230000.0 0.0 \n7 NaN 0.0 \n8 NaN 0.0 \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 c7a5ad39 c7a5ad39 6 \n6 c7a5ad39 7b62420e 5 \n7 c7a5ad39 a55475b1 7 \n8 c7a5ad39 a55475b1 8 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 0 NaN NaN 2.0 \n6 0 NaN NaN 2.0 \n7 0 NaN NaN NaN \n8 0 NaN NaN NaN \n9 1 0.0 0.0 3.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 2.0 NaN NaN 2021.0 \n6 2.0 NaN NaN 2021.0 \n7 2.0 NaN NaN NaN \n8 2.0 NaN NaN NaN \n9 3.0 0.0 0.0 2020.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2021.0 ab3c25cf ab3c25cf \n6 2021.0 ab3c25cf ab3c25cf \n7 2021.0 ab3c25cf a55475b1 \n8 2021.0 ab3c25cf a55475b1 \n9 2021.0 a55475b1 a55475b1 \n case_id amtdebitincoming_4809443A amtdebitoutgoing_4809440A \\\n5 57650 0.0 0.0 \n6 57657 17171.4 19970.0 \n7 57664 1803.6 1821.8 \n8 57667 9930.8 9930.8 \n9 57669 57910.8 57908.0 \n\n amtdepositbalance_4809441A amtdepositincoming_4809444A \\\n5 234.60000 0.0 \n6 228.40001 0.0 \n7 231.60000 20742.6 \n8 0.00000 0.0 \n9 0.00000 0.0 \n\n amtdepositoutgoing_4809442A num_group1 \n5 1.4 0 \n6 1.8 0 \n7 1102.8 0 \n8 0.0 0 \n9 0.0 0 \nEmpty DataFrame\nColumns: [case_id, employername_160M, num_group1, pmtamount_36A, processingdate_168D]\nIndex: []\n case_id annualeffectiverate_199L annualeffectiverate_63L \\\n5 57549 NaN NaN \n6 57549 NaN NaN \n7 57549 NaN NaN \n8 57549 NaN NaN \n9 57549 NaN NaN \n\n classificationofcontr_13M classificationofcontr_400M contractst_545M \\\n5 a55475b1 00135d9c a55475b1 \n6 a55475b1 00135d9c a55475b1 \n7 a55475b1 00135d9c a55475b1 \n8 a55475b1 00135d9c a55475b1 \n9 a55475b1 00135d9c a55475b1 \n\n contractst_964M contractsum_5085717L credlmt_230A credlmt_935A ... \\\n5 7241344e NaN NaN NaN ... \n6 7241344e NaN NaN NaN ... \n7 7241344e NaN NaN NaN ... \n8 690c65e6 NaN NaN NaN ... \n9 7241344e NaN NaN NaN ... \n\n residualamount_488A residualamount_856A subjectrole_182M subjectrole_93M \\\n5 NaN NaN a55475b1 a55475b1 \n6 NaN NaN a55475b1 a55475b1 \n7 NaN NaN a55475b1 a55475b1 \n8 NaN NaN a55475b1 a55475b1 \n9 NaN NaN a55475b1 a55475b1 \n\n totalamount_6A totalamount_996A totaldebtoverduevalue_178A \\\n5 15000.0 NaN NaN \n6 20000.0 NaN NaN \n7 10000.0 NaN NaN \n8 12000.0 NaN NaN \n9 32000.0 NaN NaN \n\n totaldebtoverduevalue_718A totaloutstanddebtvalue_39A \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n totaloutstanddebtvalue_668A \n5 NaN \n6 NaN \n7 NaN \n8 NaN \n9 NaN \n\n[5 rows x 79 columns]\n case_id actualdpdtolerance_344P amtinstpaidbefduel24m_4187115A \\\n5 58135 0.0 76881.00 \n6 58177 0.0 NaN \n7 58233 0.0 211970.48 \n8 58237 0.0 NaN \n9 58280 0.0 31105.40 \n\n annuity_780A annuitynextmonth_57A applicationcnt_361L \\\n5 5617.6000 0.0 0.0 \n6 1834.4000 0.0 0.0 \n7 1482.2001 5769.4 0.0 \n8 7974.4000 0.0 0.0 \n9 3149.0000 0.0 0.0 \n\n applications30d_658L applicationscnt_1086L applicationscnt_464L \\\n5 0.0 0.0 0.0 \n6 0.0 0.0 0.0 \n7 3.0 0.0 0.0 \n8 0.0 0.0 0.0 \n9 0.0 0.0 0.0 \n\n applicationscnt_629L ... sellerplacecnt_915L sellerplacescnt_216L \\\n5 0.0 ... 0.0 1.0 \n6 0.0 ... 0.0 1.0 \n7 0.0 ... 0.0 5.0 \n8 0.0 ... 0.0 0.0 \n9 0.0 ... 0.0 4.0 \n\n sumoutstandtotal_3546847A sumoutstandtotalest_4493215A totaldebt_9A \\\n5 3145.6802 3145.6802 0.0 \n6 NaN NaN 0.0 \n7 343310.8000 343310.8000 343310.8 \n8 NaN NaN 0.0 \n9 0.0000 0.0000 0.0 \n\n totalsettled_863A totinstallast1m_4525188A twobodfilling_608L \\\n5 322985.22 4800.0 FO \n6 0.00 NaN FO \n7 801651.06 2765.0 FO \n8 0.00 NaN FO \n9 551731.40 NaN FO \n\n typesuite_864L validfrom_1069D \n5 NaN NaN \n6 NaN NaN \n7 AL NaN \n8 NaN NaN \n9 NaN NaN \n\n[5 rows x 168 columns]\n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57569 a55475b1 a55475b1 \n6 57569 a55475b1 a55475b1 \n7 57569 a55475b1 a55475b1 \n8 57569 a55475b1 a55475b1 \n9 57569 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 a55475b1 a55475b1 0 \n6 a55475b1 a55475b1 0 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 4 NaN 2303.0 NaN \n6 5 NaN 2330.0 NaN \n7 6 NaN 2355.0 NaN \n8 7 NaN 2380.0 NaN \n9 8 NaN 2410.0 NaN \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 6.0 NaN 33346.402 NaN \n6 7.0 NaN 33346.402 NaN \n7 8.0 NaN 33346.402 NaN \n8 9.0 NaN 33346.402 NaN \n9 10.0 NaN 33346.402 NaN \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2019.0 a55475b1 a55475b1 \n6 2019.0 a55475b1 a55475b1 \n7 2019.0 a55475b1 a55475b1 \n8 2019.0 a55475b1 a55475b1 \n9 2019.0 a55475b1 a55475b1 \n case_id annualeffectiverate_199L annualeffectiverate_63L \\\n5 57633 34.5 NaN \n6 57633 34.5 NaN \n7 57633 NaN 56.0 \n8 57633 NaN NaN \n9 57633 NaN NaN \n\n classificationofcontr_13M classificationofcontr_400M contractst_545M \\\n5 a55475b1 ea6782cc a55475b1 \n6 a55475b1 01f63ac8 a55475b1 \n7 ea6782cc ea6782cc 7241344e \n8 ea6782cc ea6782cc 7241344e \n9 a55475b1 a55475b1 a55475b1 \n\n contractst_964M contractsum_5085717L credlmt_230A credlmt_935A ... \\\n5 7241344e NaN NaN NaN ... \n6 7241344e NaN NaN NaN ... \n7 7241344e 488495.00 NaN 184606.61 ... \n8 7241344e 4800829.07 NaN 1280000.00 ... \n9 a55475b1 NaN NaN NaN ... \n\n residualamount_488A residualamount_856A subjectrole_182M subjectrole_93M \\\n5 NaN NaN a55475b1 a55475b1 \n6 NaN NaN a55475b1 a55475b1 \n7 NaN 97699.0 ab3c25cf ab3c25cf \n8 NaN NaN a55475b1 a55475b1 \n9 NaN NaN a55475b1 a55475b1 \n\n totalamount_6A totalamount_996A totaldebtoverduevalue_178A \\\n5 580000.0 NaN NaN \n6 180000.0 NaN NaN \n7 300000.0 NaN 0.0 \n8 540000.0 NaN NaN \n9 NaN NaN NaN \n\n totaldebtoverduevalue_718A totaloutstanddebtvalue_39A \\\n5 NaN NaN \n6 NaN NaN \n7 0.0 2579517.8 \n8 NaN NaN \n9 NaN NaN \n\n totaloutstanddebtvalue_668A \n5 NaN \n6 NaN \n7 0.0 \n8 NaN \n9 NaN \n\n[5 rows x 79 columns]\n case_id last180dayaveragebalance_704A last180dayturnover_1134A \\\n5 57709 NaN NaN \n6 57715 NaN NaN \n7 57715 NaN NaN \n8 57715 NaN NaN \n9 57715 NaN NaN \n\n last30dayturnover_651A num_group1 openingdate_857D \n5 NaN 0 2015-09-14 \n6 NaN 0 2015-02-11 \n7 NaN 1 2015-11-09 \n8 NaN 2 2012-10-25 \n9 NaN 3 2013-03-17 \n case_id annualeffectiverate_199L annualeffectiverate_63L \\\n5 57760 NaN NaN \n6 57760 NaN NaN \n7 57760 NaN NaN \n8 57760 NaN NaN \n9 57760 NaN NaN \n\n classificationofcontr_13M classificationofcontr_400M contractst_545M \\\n5 a55475b1 a55475b1 a55475b1 \n6 a55475b1 a55475b1 a55475b1 \n7 a55475b1 a55475b1 a55475b1 \n8 a55475b1 a55475b1 a55475b1 \n9 a55475b1 a55475b1 a55475b1 \n\n contractst_964M contractsum_5085717L credlmt_230A credlmt_935A ... \\\n5 a55475b1 NaN NaN NaN ... \n6 a55475b1 NaN NaN NaN ... \n7 a55475b1 NaN NaN NaN ... \n8 a55475b1 NaN NaN NaN ... \n9 a55475b1 NaN NaN NaN ... \n\n residualamount_488A residualamount_856A subjectrole_182M subjectrole_93M \\\n5 NaN NaN a55475b1 a55475b1 \n6 NaN NaN a55475b1 a55475b1 \n7 NaN NaN a55475b1 a55475b1 \n8 NaN NaN a55475b1 a55475b1 \n9 NaN NaN a55475b1 a55475b1 \n\n totalamount_6A totalamount_996A totaldebtoverduevalue_178A \\\n5 NaN NaN NaN \n6 NaN NaN NaN \n7 NaN NaN NaN \n8 NaN NaN NaN \n9 NaN NaN NaN \n\n totaldebtoverduevalue_718A totaloutstanddebtvalue_39A \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n totaloutstanddebtvalue_668A \n5 NaN \n6 NaN \n7 NaN \n8 NaN \n9 NaN \n\n[5 rows x 79 columns]\n case_id amount_416A contractenddate_991D num_group1 openingdate_313D\n5 57709 0.0 NaN 0 2015-09-14\n6 57715 0.0 NaN 0 2015-02-11\n7 57715 0.0 NaN 2 2012-10-25\n8 57715 0.0 NaN 4 2014-08-13\n9 57715 1800.0 2016-03-16 3 2013-03-17\n case_id actualdpdtolerance_344P amtinstpaidbefduel24m_4187115A \\\n5 57641 0.0 173284.280 \n6 57644 0.0 319846.940 \n7 57645 0.0 38622.620 \n8 57647 0.0 116063.960 \n9 57650 0.0 4570.166 \n\n annuity_780A annuitynextmonth_57A applicationcnt_361L \\\n5 8126.2 6723.200 0.0 \n6 3772.0 0.000 0.0 \n7 11309.4 0.000 0.0 \n8 3585.0 12024.601 0.0 \n9 8984.4 0.000 0.0 \n\n applications30d_658L applicationscnt_1086L applicationscnt_464L \\\n5 0.0 0.0 0.0 \n6 0.0 0.0 0.0 \n7 1.0 0.0 0.0 \n8 0.0 0.0 0.0 \n9 0.0 0.0 0.0 \n\n applicationscnt_629L ... sellerplacecnt_915L sellerplacescnt_216L \\\n5 0.0 ... 0.0 11.0 \n6 0.0 ... 0.0 3.0 \n7 0.0 ... 0.0 4.0 \n8 0.0 ... 1.0 9.0 \n9 0.0 ... 1.0 5.0 \n\n sumoutstandtotal_3546847A sumoutstandtotalest_4493215A totaldebt_9A \\\n5 147884.8 147884.8 140884.8 \n6 0.0 0.0 0.0 \n7 0.0 0.0 0.0 \n8 181718.4 181718.4 174618.4 \n9 0.0 0.0 0.0 \n\n totalsettled_863A totinstallast1m_4525188A twobodfilling_608L \\\n5 741594.50 13446.4 FO \n6 694330.44 NaN BO \n7 356820.40 NaN FO \n8 512090.47 14070.0 FO \n9 446075.40 NaN FO \n\n typesuite_864L validfrom_1069D \n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 AL NaN \n9 NaN NaN \n\n[5 rows x 168 columns]\n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57631 a55475b1 a55475b1 \n6 57631 a55475b1 a55475b1 \n7 57631 a55475b1 a55475b1 \n8 57631 a55475b1 a55475b1 \n9 57631 a55475b1 a55475b1 \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN NaN \n6 NaN NaN \n7 NaN NaN \n8 NaN NaN \n9 NaN NaN \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 a55475b1 a55475b1 0 \n6 a55475b1 a55475b1 0 \n7 a55475b1 a55475b1 0 \n8 a55475b1 a55475b1 0 \n9 a55475b1 a55475b1 0 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 4 0.0 0.0 6.0 \n6 5 0.0 0.0 7.0 \n7 6 0.0 0.0 8.0 \n8 7 0.0 NaN 9.0 \n9 8 0.0 NaN 10.0 \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 6.0 0.0 0.0 2019.0 \n6 7.0 0.0 0.0 2019.0 \n7 8.0 0.0 0.0 2019.0 \n8 9.0 0.0 NaN 2019.0 \n9 10.0 0.0 NaN 2019.0 \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2018.0 a55475b1 a55475b1 \n6 2018.0 a55475b1 a55475b1 \n7 2018.0 a55475b1 a55475b1 \n8 2018.0 a55475b1 a55475b1 \n9 2018.0 a55475b1 a55475b1 \n case_id actualdpd_943P annuity_853A approvaldate_319D \\\n5 57543 0.0 3414.2000 2016-08-31 \n6 57543 0.0 3725.4001 NaN \n7 57543 0.0 4516.8003 2018-09-20 \n8 57543 0.0 4544.8003 NaN \n9 57543 0.0 5172.0000 2018-12-29 \n\n byoccupationinc_3656910L cancelreason_3545846M childnum_21L \\\n5 NaN a55475b1 NaN \n6 1.0 a55475b1 2.0 \n7 NaN a55475b1 NaN \n8 1.0 a55475b1 2.0 \n9 NaN a55475b1 NaN \n\n creationdate_885D credacc_actualbalance_314A credacc_credlmt_575A ... \\\n5 2016-08-31 NaN 0.0 ... \n6 2015-08-14 NaN 0.0 ... \n7 2018-09-20 NaN 0.0 ... \n8 2015-08-14 NaN 0.0 ... \n9 2018-12-29 NaN 0.0 ... \n\n num_group1 outstandingdebt_522A pmtnum_8L postype_4733339M \\\n5 5 0.0 12.0 P177_117_192 \n6 7 0.0 9.0 P149_40_170 \n7 4 0.0 39.0 P46_145_78 \n8 6 0.0 6.0 P149_40_170 \n9 2 0.0 34.0 P177_117_192 \n\n profession_152M rejectreason_755M rejectreasonclient_4145042M \\\n5 a55475b1 a55475b1 a55475b1 \n6 a55475b1 a55475b1 a55475b1 \n7 a55475b1 a55475b1 a55475b1 \n8 a55475b1 a55475b1 a55475b1 \n9 a55475b1 a55475b1 a55475b1 \n\n revolvingaccount_394A status_219L tenor_203L \n5 NaN K 12.0 \n6 NaN D 9.0 \n7 NaN K 39.0 \n8 NaN D 6.0 \n9 NaN K 34.0 \n\n[5 rows x 41 columns]\n case_id amount_4527230A name_4527232M num_group1 recorddate_4527225D\n5 57675 5061.8003 ff9eb829 5 2022-01-07\n6 57754 2134.0000 31b75bd0 1 2022-06-16\n7 57754 2134.0000 31b75bd0 2 2022-06-16\n8 57754 3807.8000 cc68a90a 4 2022-06-16\n9 57754 3807.8000 cc68a90a 7 2022-06-16\n case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n5 57543 a55475b1 8fd95e4b \n6 57543 a55475b1 8fd95e4b \n7 57543 a55475b1 9a0c095e \n8 57543 a55475b1 9a0c095e \n9 57543 a55475b1 9a0c095e \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n5 NaN 0.0 \n6 NaN 0.0 \n7 NaN 0.0 \n8 NaN 0.0 \n9 NaN 0.0 \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n5 c7a5ad39 a55475b1 5 \n6 c7a5ad39 a55475b1 6 \n7 c7a5ad39 a55475b1 7 \n8 c7a5ad39 a55475b1 8 \n9 c7a5ad39 a55475b1 9 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n5 0 NaN NaN NaN \n6 0 NaN NaN NaN \n7 0 NaN NaN NaN \n8 0 NaN NaN NaN \n9 0 NaN NaN NaN \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n5 2.0 NaN NaN NaN \n6 2.0 NaN NaN NaN \n7 2.0 NaN NaN NaN \n8 2.0 NaN NaN NaN \n9 2.0 NaN NaN NaN \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n5 2017.0 ab3c25cf a55475b1 \n6 2018.0 ab3c25cf a55475b1 \n7 2018.0 ab3c25cf a55475b1 \n8 2018.0 ab3c25cf a55475b1 \n9 2018.0 ab3c25cf a55475b1 \n","output_type":"stream"}]},{"cell_type":"code","source":"# Identify missing values \nmissing_values = df.isnull().sum()\nprint(\"Missing values per column:\")\nprint(missing_values)","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.753746Z","iopub.execute_input":"2024-05-18T15:27:17.754111Z","iopub.status.idle":"2024-05-18T15:27:17.763213Z","shell.execute_reply.started":"2024-05-18T15:27:17.754080Z","shell.execute_reply":"2024-05-18T15:27:17.761888Z"},"trusted":true},"execution_count":4,"outputs":[{"name":"stdout","text":"Missing values per column:\ncase_id 0\ncollater_typofvalofguarant_298M 0\ncollater_typofvalofguarant_407M 0\ncollater_valueofguarantee_1124L 8\ncollater_valueofguarantee_876L 0\ncollaterals_typeofguarante_359M 0\ncollaterals_typeofguarante_669M 0\nnum_group1 0\nnum_group2 0\npmts_dpd_1073P 9\npmts_dpd_303P 10\npmts_month_158T 8\npmts_month_706T 0\npmts_overdue_1140A 9\npmts_overdue_1152A 10\npmts_year_1139T 8\npmts_year_507T 0\nsubjectroles_name_541M 0\nsubjectroles_name_838M 0\ndtype: int64\n","output_type":"stream"}]},{"cell_type":"code","source":"df.info()\ndf.describe()","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.764684Z","iopub.execute_input":"2024-05-18T15:27:17.765071Z","iopub.status.idle":"2024-05-18T15:27:17.839343Z","shell.execute_reply.started":"2024-05-18T15:27:17.765041Z","shell.execute_reply":"2024-05-18T15:27:17.838256Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 10 entries, 0 to 9\nData columns (total 19 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 case_id 10 non-null int64 \n 1 collater_typofvalofguarant_298M 10 non-null object \n 2 collater_typofvalofguarant_407M 10 non-null object \n 3 collater_valueofguarantee_1124L 2 non-null float64\n 4 collater_valueofguarantee_876L 10 non-null float64\n 5 collaterals_typeofguarante_359M 10 non-null object \n 6 collaterals_typeofguarante_669M 10 non-null object \n 7 num_group1 10 non-null int64 \n 8 num_group2 10 non-null int64 \n 9 pmts_dpd_1073P 1 non-null float64\n 10 pmts_dpd_303P 0 non-null float64\n 11 pmts_month_158T 2 non-null float64\n 12 pmts_month_706T 10 non-null float64\n 13 pmts_overdue_1140A 1 non-null float64\n 14 pmts_overdue_1152A 0 non-null float64\n 15 pmts_year_1139T 2 non-null float64\n 16 pmts_year_507T 10 non-null float64\n 17 subjectroles_name_541M 10 non-null object \n 18 subjectroles_name_838M 10 non-null object \ndtypes: float64(10), int64(3), object(6)\nmemory usage: 1.6+ KB\n","output_type":"stream"},{"execution_count":5,"output_type":"execute_result","data":{"text/plain":" case_id collater_valueofguarantee_1124L \\\ncount 10.0 2.0 \nmean 57543.0 0.0 \nstd 0.0 0.0 \nmin 57543.0 0.0 \n25% 57543.0 0.0 \n50% 57543.0 0.0 \n75% 57543.0 0.0 \nmax 57543.0 0.0 \n\n collater_valueofguarantee_876L num_group1 num_group2 pmts_dpd_1073P \\\ncount 10.0 10.00000 10.0 1.0 \nmean 0.0 4.50000 0.0 0.0 \nstd 0.0 3.02765 0.0 NaN \nmin 0.0 0.00000 0.0 0.0 \n25% 0.0 2.25000 0.0 0.0 \n50% 0.0 4.50000 0.0 0.0 \n75% 0.0 6.75000 0.0 0.0 \nmax 0.0 9.00000 0.0 0.0 \n\n pmts_dpd_303P pmts_month_158T pmts_month_706T pmts_overdue_1140A \\\ncount 0.0 2.0 10.0 1.0 \nmean NaN 2.0 2.0 0.0 \nstd NaN 0.0 0.0 NaN \nmin NaN 2.0 2.0 0.0 \n25% NaN 2.0 2.0 0.0 \n50% NaN 2.0 2.0 0.0 \n75% NaN 2.0 2.0 0.0 \nmax NaN 2.0 2.0 0.0 \n\n pmts_overdue_1152A pmts_year_1139T pmts_year_507T \ncount 0.0 2.000000 10.000000 \nmean NaN 2020.500000 2016.000000 \nstd NaN 0.707107 2.309401 \nmin NaN 2020.000000 2011.000000 \n25% NaN 2020.250000 2015.000000 \n50% NaN 2020.500000 2016.500000 \n75% NaN 2020.750000 2018.000000 \nmax NaN 2021.000000 2018.000000 ","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>case_id</th>\n <th>collater_valueofguarantee_1124L</th>\n <th>collater_valueofguarantee_876L</th>\n <th>num_group1</th>\n <th>num_group2</th>\n <th>pmts_dpd_1073P</th>\n <th>pmts_dpd_303P</th>\n <th>pmts_month_158T</th>\n <th>pmts_month_706T</th>\n <th>pmts_overdue_1140A</th>\n <th>pmts_overdue_1152A</th>\n <th>pmts_year_1139T</th>\n <th>pmts_year_507T</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>count</th>\n <td>10.0</td>\n <td>2.0</td>\n <td>10.0</td>\n <td>10.00000</td>\n <td>10.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>2.0</td>\n <td>10.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>2.000000</td>\n <td>10.000000</td>\n </tr>\n <tr>\n <th>mean</th>\n <td>57543.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>4.50000</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2020.500000</td>\n <td>2016.000000</td>\n </tr>\n <tr>\n <th>std</th>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>3.02765</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>0.707107</td>\n <td>2.309401</td>\n </tr>\n <tr>\n <th>min</th>\n <td>57543.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.00000</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2020.000000</td>\n <td>2011.000000</td>\n </tr>\n <tr>\n <th>25%</th>\n <td>57543.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>2.25000</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2020.250000</td>\n <td>2015.000000</td>\n </tr>\n <tr>\n <th>50%</th>\n <td>57543.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>4.50000</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2020.500000</td>\n <td>2016.500000</td>\n </tr>\n <tr>\n <th>75%</th>\n <td>57543.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>6.75000</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2020.750000</td>\n <td>2018.000000</td>\n </tr>\n <tr>\n <th>max</th>\n <td>57543.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>9.00000</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2021.000000</td>\n <td>2018.000000</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.840955Z","iopub.execute_input":"2024-05-18T15:27:17.841871Z","iopub.status.idle":"2024-05-18T15:27:17.864471Z","shell.execute_reply.started":"2024-05-18T15:27:17.841831Z","shell.execute_reply":"2024-05-18T15:27:17.863062Z"},"trusted":true},"execution_count":6,"outputs":[{"execution_count":6,"output_type":"execute_result","data":{"text/plain":" case_id collater_typofvalofguarant_298M collater_typofvalofguarant_407M \\\n0 57543 9a0c095e 9a0c095e \n1 57543 9a0c095e 8fd95e4b \n2 57543 a55475b1 9a0c095e \n3 57543 a55475b1 9a0c095e \n4 57543 a55475b1 9a0c095e \n\n collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n0 0.0 0.0 \n1 0.0 0.0 \n2 NaN 0.0 \n3 NaN 0.0 \n4 NaN 0.0 \n\n collaterals_typeofguarante_359M collaterals_typeofguarante_669M num_group1 \\\n0 c7a5ad39 c7a5ad39 0 \n1 c7a5ad39 c7a5ad39 1 \n2 c7a5ad39 a55475b1 2 \n3 c7a5ad39 a55475b1 3 \n4 c7a5ad39 a55475b1 4 \n\n num_group2 pmts_dpd_1073P pmts_dpd_303P pmts_month_158T \\\n0 0 NaN NaN 2.0 \n1 0 0.0 NaN 2.0 \n2 0 NaN NaN NaN \n3 0 NaN NaN NaN \n4 0 NaN NaN NaN \n\n pmts_month_706T pmts_overdue_1140A pmts_overdue_1152A pmts_year_1139T \\\n0 2.0 NaN NaN 2020.0 \n1 2.0 0.0 NaN 2021.0 \n2 2.0 NaN NaN NaN \n3 2.0 NaN NaN NaN \n4 2.0 NaN NaN NaN \n\n pmts_year_507T subjectroles_name_541M subjectroles_name_838M \n0 2011.0 ab3c25cf ab3c25cf \n1 2015.0 ab3c25cf ab3c25cf \n2 2015.0 ab3c25cf a55475b1 \n3 2014.0 ab3c25cf a55475b1 \n4 2016.0 ab3c25cf a55475b1 ","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>case_id</th>\n <th>collater_typofvalofguarant_298M</th>\n <th>collater_typofvalofguarant_407M</th>\n <th>collater_valueofguarantee_1124L</th>\n <th>collater_valueofguarantee_876L</th>\n <th>collaterals_typeofguarante_359M</th>\n <th>collaterals_typeofguarante_669M</th>\n <th>num_group1</th>\n <th>num_group2</th>\n <th>pmts_dpd_1073P</th>\n <th>pmts_dpd_303P</th>\n <th>pmts_month_158T</th>\n <th>pmts_month_706T</th>\n <th>pmts_overdue_1140A</th>\n <th>pmts_overdue_1152A</th>\n <th>pmts_year_1139T</th>\n <th>pmts_year_507T</th>\n <th>subjectroles_name_541M</th>\n <th>subjectroles_name_838M</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>57543</td>\n <td>9a0c095e</td>\n <td>9a0c095e</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>c7a5ad39</td>\n <td>c7a5ad39</td>\n <td>0</td>\n <td>0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2020.0</td>\n <td>2011.0</td>\n <td>ab3c25cf</td>\n <td>ab3c25cf</td>\n </tr>\n <tr>\n <th>1</th>\n <td>57543</td>\n <td>9a0c095e</td>\n <td>8fd95e4b</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>c7a5ad39</td>\n <td>c7a5ad39</td>\n <td>1</td>\n <td>0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>2.0</td>\n <td>0.0</td>\n <td>NaN</td>\n <td>2021.0</td>\n <td>2015.0</td>\n <td>ab3c25cf</td>\n <td>ab3c25cf</td>\n </tr>\n <tr>\n <th>2</th>\n <td>57543</td>\n <td>a55475b1</td>\n <td>9a0c095e</td>\n <td>NaN</td>\n <td>0.0</td>\n <td>c7a5ad39</td>\n <td>a55475b1</td>\n <td>2</td>\n <td>0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2015.0</td>\n <td>ab3c25cf</td>\n <td>a55475b1</td>\n </tr>\n <tr>\n <th>3</th>\n <td>57543</td>\n <td>a55475b1</td>\n <td>9a0c095e</td>\n <td>NaN</td>\n <td>0.0</td>\n <td>c7a5ad39</td>\n <td>a55475b1</td>\n <td>3</td>\n <td>0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2014.0</td>\n <td>ab3c25cf</td>\n <td>a55475b1</td>\n </tr>\n <tr>\n <th>4</th>\n <td>57543</td>\n <td>a55475b1</td>\n <td>9a0c095e</td>\n <td>NaN</td>\n <td>0.0</td>\n <td>c7a5ad39</td>\n <td>a55475b1</td>\n <td>4</td>\n <td>0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2.0</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>NaN</td>\n <td>2016.0</td>\n <td>ab3c25cf</td>\n <td>a55475b1</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df_cleaned = df.dropna()\n\n# Check if missing values have been handled\nprint(\"Missing values after handling:\")\nprint(df_cleaned.isnull().sum())","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.865781Z","iopub.execute_input":"2024-05-18T15:27:17.866113Z","iopub.status.idle":"2024-05-18T15:27:17.879238Z","shell.execute_reply.started":"2024-05-18T15:27:17.866085Z","shell.execute_reply":"2024-05-18T15:27:17.878095Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"Missing values after handling:\ncase_id 0\ncollater_typofvalofguarant_298M 0\ncollater_typofvalofguarant_407M 0\ncollater_valueofguarantee_1124L 0\ncollater_valueofguarantee_876L 0\ncollaterals_typeofguarante_359M 0\ncollaterals_typeofguarante_669M 0\nnum_group1 0\nnum_group2 0\npmts_dpd_1073P 0\npmts_dpd_303P 0\npmts_month_158T 0\npmts_month_706T 0\npmts_overdue_1140A 0\npmts_overdue_1152A 0\npmts_year_1139T 0\npmts_year_507T 0\nsubjectroles_name_541M 0\nsubjectroles_name_838M 0\ndtype: int64\n","output_type":"stream"}]},{"cell_type":"code","source":"#print(df.describe())\nprint(df.dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.880805Z","iopub.execute_input":"2024-05-18T15:27:17.881240Z","iopub.status.idle":"2024-05-18T15:27:17.892684Z","shell.execute_reply.started":"2024-05-18T15:27:17.881201Z","shell.execute_reply":"2024-05-18T15:27:17.891429Z"},"trusted":true},"execution_count":8,"outputs":[{"name":"stdout","text":"case_id int64\ncollater_typofvalofguarant_298M object\ncollater_typofvalofguarant_407M object\ncollater_valueofguarantee_1124L float64\ncollater_valueofguarantee_876L float64\ncollaterals_typeofguarante_359M object\ncollaterals_typeofguarante_669M object\nnum_group1 int64\nnum_group2 int64\npmts_dpd_1073P float64\npmts_dpd_303P float64\npmts_month_158T float64\npmts_month_706T float64\npmts_overdue_1140A float64\npmts_overdue_1152A float64\npmts_year_1139T float64\npmts_year_507T float64\nsubjectroles_name_541M object\nsubjectroles_name_838M object\ndtype: object\n","output_type":"stream"}]},{"cell_type":"code","source":"#data visualization using a box plot and violin\n\ndata = {\n 'case_id': np.random.randint(1, 1000, 100),\n 'collater_valueofguarantee_1124L': np.random.normal(50000, 10000, 100),\n 'collater_valueofguarantee_876L': np.random.normal(50000, 15000, 100),\n 'num_group1': np.random.gamma(shape=2, scale=2, size=100),\n 'num_group2': np.random.gamma(shape=2, scale=2, size=100),\n 'pmts_month_158T': np.random.poisson(lam=300, size=100),\n 'pmts_month_706T': np.random.poisson(lam=500, size=100),\n 'pmts_year_1139T': np.random.randint(1, 12, 100),\n 'pmts_year_507T': np.random.randint(1, 12, 100)\n}\ndf = pd.DataFrame(data)\n\nplt.figure(figsize=(12, 8))\nsns.boxplot(data=df)\nplt.xticks(rotation=45)\nplt.title('Box Plot of Numerical Variables')\nplt.show()\n\n#plt.figure(figsize=(12, 8))\n#sns.violinplot(data=df)\n#plt.xticks(rotation=45)\n#plt.title('Violin Plot of Numerical Variables')\n#plt.show()\n\n","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:17.894074Z","iopub.execute_input":"2024-05-18T15:27:17.894426Z","iopub.status.idle":"2024-05-18T15:27:18.389487Z","shell.execute_reply.started":"2024-05-18T15:27:17.894397Z","shell.execute_reply":"2024-05-18T15:27:18.388370Z"},"trusted":true},"execution_count":9,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x800 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"# Calculate the interquartile range (IQR)\nQ1 = df['collater_valueofguarantee_1124L'].quantile(0.25)\nQ3 = df['collater_valueofguarantee_1124L'].quantile(0.75)\nIQR = Q3 - Q1\n\n# Define the lower and upper bounds for outliers\nlower_bound = Q1 - 1.5 * IQR\nupper_bound = Q3 + 1.5 * IQR\n\n# Identify outliers\noutliers = df[(df['collater_valueofguarantee_1124L'] < lower_bound) \n | (df['collater_valueofguarantee_1124L'] > upper_bound)]\n\n# Display outliers\nprint(\"Outliers:\")\nprint(outliers)\n\n# Visualize outliers using a box plot\nplt.figure(figsize=(8, 6))\nsns.boxplot(x='collater_valueofguarantee_1124L', data=df)\nplt.title('Box Plot of collater_valueofguarantee_1124L Column')\nplt.xlabel('collater_valueofguarantee_1124L')\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:18.392148Z","iopub.execute_input":"2024-05-18T15:27:18.392502Z","iopub.status.idle":"2024-05-18T15:27:18.596844Z","shell.execute_reply.started":"2024-05-18T15:27:18.392472Z","shell.execute_reply":"2024-05-18T15:27:18.595794Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"Outliers:\n case_id collater_valueofguarantee_1124L collater_valueofguarantee_876L \\\n7 292 21234.010185 44174.364717 \n44 371 23734.424398 68642.074217 \n\n num_group1 num_group2 pmts_month_158T pmts_month_706T pmts_year_1139T \\\n7 7.376335 0.956455 313 516 7 \n44 2.999595 3.529809 291 542 5 \n\n pmts_year_507T \n7 3 \n44 10 \n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 800x600 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"target_variable = df['collater_valueofguarantee_1124L']\n\n# Summary statistics\nprint(\"Summary Statistics of Target Variable:\")\nprint(target_variable.describe())\n\n# Distribution plot\nplt.figure(figsize=(10, 6))\nsns.histplot(target_variable, kde=True, color='skyblue')\nplt.title('Distribution of Target Variable')\nplt.xlabel('Likelihood of Default')\nplt.ylabel('Frequency')\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-05-18T15:27:18.598102Z","iopub.execute_input":"2024-05-18T15:27:18.598419Z","iopub.status.idle":"2024-05-18T15:27:18.953129Z","shell.execute_reply.started":"2024-05-18T15:27:18.598392Z","shell.execute_reply":"2024-05-18T15:27:18.952067Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"Summary Statistics of Target Variable:\ncount 100.000000\nmean 49510.301630\nstd 9844.707097\nmin 21234.010185\n25% 43324.069651\n50% 50345.178657\n75% 56328.748281\nmax 70730.602587\nName: collater_valueofguarantee_1124L, dtype: float64\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/seaborn/_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.\n with pd.option_context('mode.use_inf_as_na', True):\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 1000x600 with 1 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}