{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":35332,"databundleVersionId":3723648,"sourceType":"competition"}],"dockerImageVersionId":30213,"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":"2022-08-10T10:51:14.680666Z","iopub.execute_input":"2022-08-10T10:51:14.681436Z","iopub.status.idle":"2022-08-10T10:51:14.709939Z","shell.execute_reply.started":"2022-08-10T10:51:14.681316Z","shell.execute_reply":"2022-08-10T10:51:14.709116Z"},"trusted":true},"outputs":[{"name":"stdout","text":"/kaggle/input/amex-default-prediction/sample_submission.csv\n/kaggle/input/amex-default-prediction/train_data.csv\n/kaggle/input/amex-default-prediction/test_data.csv\n/kaggle/input/amex-default-prediction/train_labels.csv\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"#!apt-get remove swig","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:51:34.640863Z","iopub.execute_input":"2022-08-10T10:51:34.641269Z","iopub.status.idle":"2022-08-10T10:51:37.629009Z","shell.execute_reply.started":"2022-08-10T10:51:34.641235Z","shell.execute_reply":"2022-08-10T10:51:37.627833Z"},"trusted":true},"outputs":[{"name":"stdout","text":"Reading package lists... Done\nBuilding dependency tree \nReading state information... Done\nPackage 'swig' is not installed, so not removed\n0 upgraded, 0 newly installed, 0 to remove and 29 not upgraded.\n","output_type":"stream"}],"execution_count":2},{"cell_type":"code","source":"#!apt-get install swig3.0 build-essential -y","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:51:51.605895Z","iopub.execute_input":"2022-08-10T10:51:51.606659Z","iopub.status.idle":"2022-08-10T10:51:57.263447Z","shell.execute_reply.started":"2022-08-10T10:51:51.606613Z","shell.execute_reply":"2022-08-10T10:51:57.262255Z"},"trusted":true},"outputs":[{"name":"stdout","text":"Reading package lists... Done\nBuilding dependency tree \nReading state information... Done\nbuild-essential is already the newest version (12.8ubuntu1.1).\nSuggested packages:\n swig3.0-examples swig3.0-doc\nThe following NEW packages will be installed:\n swig3.0\n0 upgraded, 1 newly installed, 0 to remove and 29 not upgraded.\nNeed to get 1109 kB of archives.\nAfter this operation, 5555 kB of additional disk space will be used.\nGet:1 http://archive.ubuntu.com/ubuntu focal/universe amd64 swig3.0 amd64 3.0.12-2.2ubuntu1 [1109 kB]\nFetched 1109 kB in 0s (4648 kB/s)\nSelecting previously unselected package swig3.0.\n(Reading database ... 106350 files and directories currently installed.)\nPreparing to unpack .../swig3.0_3.0.12-2.2ubuntu1_amd64.deb ...\nUnpacking swig3.0 (3.0.12-2.2ubuntu1) ...\nSetting up swig3.0 (3.0.12-2.2ubuntu1) ...\nProcessing triggers for man-db (2.9.1-1) ...\n","output_type":"stream"}],"execution_count":3},{"cell_type":"code","source":"#!ln -s /usr/bin/swig3.0 /usr/bin/swig","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:52:22.146122Z","iopub.execute_input":"2022-08-10T10:52:22.146531Z","iopub.status.idle":"2022-08-10T10:52:23.183947Z","shell.execute_reply.started":"2022-08-10T10:52:22.146497Z","shell.execute_reply":"2022-08-10T10:52:23.182539Z"},"trusted":true},"outputs":[{"name":"stdout","text":"ln: failed to create symbolic link '/usr/bin/swig': File exists\n","output_type":"stream"}],"execution_count":5},{"cell_type":"code","source":"#!apt-get install build-essential","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:52:33.960651Z","iopub.execute_input":"2022-08-10T10:52:33.961075Z","iopub.status.idle":"2022-08-10T10:52:36.538986Z","shell.execute_reply.started":"2022-08-10T10:52:33.961037Z","shell.execute_reply":"2022-08-10T10:52:36.537669Z"},"trusted":true},"outputs":[{"name":"stdout","text":"Reading package lists... Done\nBuilding dependency tree \nReading state information... Done\nbuild-essential is already the newest version (12.8ubuntu1.1).\n0 upgraded, 0 newly installed, 0 to remove and 29 not upgraded.\n","output_type":"stream"}],"execution_count":6},{"cell_type":"code","source":"#!pip install --upgrade setuptools","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:52:57.300794Z","iopub.execute_input":"2022-08-10T10:52:57.30124Z","iopub.status.idle":"2022-08-10T10:53:22.692229Z","shell.execute_reply.started":"2022-08-10T10:52:57.301201Z","shell.execute_reply":"2022-08-10T10:53:22.691217Z"},"trusted":true},"outputs":[{"name":"stdout","text":"Requirement already satisfied: setuptools in /opt/conda/lib/python3.7/site-packages (59.8.0)\nCollecting setuptools\n Downloading setuptools-63.4.2-py3-none-any.whl (1.2 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m0m\n\u001b[?25hInstalling collected packages: setuptools\n Attempting uninstall: setuptools\n Found existing installation: setuptools 59.8.0\n Uninstalling setuptools-59.8.0:\n Successfully uninstalled setuptools-59.8.0\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\nbeatrix-jupyterlab 3.1.7 requires google-cloud-bigquery-storage, which is not installed.\ncloud-tpu-client 0.10 requires google-api-python-client==1.8.0, but you have google-api-python-client 1.12.11 which is incompatible.\nallennlp 2.10.0 requires protobuf==3.20.0, but you have protobuf 3.19.4 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed setuptools-63.4.2\n\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n\u001b[0m","output_type":"stream"}],"execution_count":7},{"cell_type":"code","source":"#!pip install auto-sklearn","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:53:42.121051Z","iopub.execute_input":"2022-08-10T10:53:42.121514Z","iopub.status.idle":"2022-08-10T10:54:17.431543Z","shell.execute_reply.started":"2022-08-10T10:53:42.121477Z","shell.execute_reply":"2022-08-10T10:54:17.430351Z"},"trusted":true},"outputs":[{"name":"stdout","text":"Collecting auto-sklearn\n Downloading auto-sklearn-0.14.7.tar.gz (6.4 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.4/6.4 MB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0m\n\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hRequirement already satisfied: setuptools in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (63.4.2)\nRequirement already satisfied: typing_extensions in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (4.1.1)\nCollecting distro\n Downloading distro-1.7.0-py3-none-any.whl (20 kB)\nRequirement already satisfied: numpy>=1.9.0 in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (1.21.6)\nRequirement already satisfied: scipy>=1.7.0 in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (1.7.3)\nRequirement already satisfied: joblib in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (1.0.1)\nCollecting scikit-learn<0.25.0,>=0.24.0\n Downloading scikit_learn-0.24.2-cp37-cp37m-manylinux2010_x86_64.whl (22.3 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m22.3/22.3 MB\u001b[0m \u001b[31m24.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hRequirement already satisfied: dask>=2021.12 in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (2022.2.0)\nRequirement already satisfied: distributed>=2012.12 in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (2022.2.0)\nRequirement already satisfied: pyyaml in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (6.0)\nRequirement already satisfied: pandas>=1.0 in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (1.3.5)\nCollecting liac-arff\n Downloading liac-arff-2.5.0.tar.gz (13 kB)\n Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hRequirement already satisfied: threadpoolctl in /opt/conda/lib/python3.7/site-packages (from auto-sklearn) (3.1.0)\nCollecting ConfigSpace<0.5,>=0.4.21\n Downloading ConfigSpace-0.4.21-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.3 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.3/4.3 MB\u001b[0m \u001b[31m34.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m:00:01\u001b[0m\n\u001b[?25hCollecting pynisher<0.7,>=0.6.3\n Downloading pynisher-0.6.4.tar.gz (11 kB)\n Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hCollecting pyrfr<0.9,>=0.8.1\n Downloading pyrfr-0.8.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.4 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.4/4.4 MB\u001b[0m \u001b[31m35.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m:00:01\u001b[0m\n\u001b[?25hCollecting smac<1.3,>=1.2\n Downloading smac-1.2.tar.gz (260 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m260.9/260.9 kB\u001b[0m \u001b[31m20.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hRequirement already satisfied: cython in /opt/conda/lib/python3.7/site-packages (from ConfigSpace<0.5,>=0.4.21->auto-sklearn) (0.29.30)\nRequirement already satisfied: pyparsing in /opt/conda/lib/python3.7/site-packages (from ConfigSpace<0.5,>=0.4.21->auto-sklearn) (3.0.9)\nRequirement already satisfied: fsspec>=0.6.0 in /opt/conda/lib/python3.7/site-packages (from dask>=2021.12->auto-sklearn) (2022.5.0)\nRequirement already satisfied: toolz>=0.8.2 in /opt/conda/lib/python3.7/site-packages (from dask>=2021.12->auto-sklearn) (0.11.2)\nRequirement already satisfied: partd>=0.3.10 in /opt/conda/lib/python3.7/site-packages (from dask>=2021.12->auto-sklearn) (1.2.0)\nRequirement already satisfied: cloudpickle>=1.1.1 in /opt/conda/lib/python3.7/site-packages (from dask>=2021.12->auto-sklearn) (2.1.0)\nRequirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.7/site-packages (from dask>=2021.12->auto-sklearn) (21.3)\nRequirement already satisfied: tblib>=1.6.0 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (1.7.0)\nRequirement already satisfied: psutil>=5.0 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (5.9.1)\nRequirement already satisfied: sortedcontainers!=2.0.0,!=2.0.1 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (2.4.0)\nRequirement already satisfied: msgpack>=0.6.0 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (1.0.4)\nRequirement already satisfied: jinja2 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (3.1.2)\nRequirement already satisfied: zict>=0.1.3 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (2.2.0)\nRequirement already satisfied: click>=6.6 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (8.0.4)\nRequirement already satisfied: tornado>=5 in /opt/conda/lib/python3.7/site-packages (from distributed>=2012.12->auto-sklearn) (6.1)\nRequirement already satisfied: python-dateutil>=2.7.3 in /opt/conda/lib/python3.7/site-packages (from pandas>=1.0->auto-sklearn) (2.8.2)\nRequirement already satisfied: pytz>=2017.3 in /opt/conda/lib/python3.7/site-packages (from pandas>=1.0->auto-sklearn) (2022.1)\nCollecting emcee>=3.0.0\n Downloading emcee-3.1.2-py2.py3-none-any.whl (46 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.2/46.2 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25hRequirement already satisfied: importlib-metadata in /opt/conda/lib/python3.7/site-packages (from click>=6.6->distributed>=2012.12->auto-sklearn) (4.12.0)\nRequirement already satisfied: locket in /opt/conda/lib/python3.7/site-packages (from partd>=0.3.10->dask>=2021.12->auto-sklearn) (1.0.0)\nRequirement already satisfied: six>=1.5 in /opt/conda/lib/python3.7/site-packages (from python-dateutil>=2.7.3->pandas>=1.0->auto-sklearn) (1.16.0)\nRequirement already satisfied: heapdict in /opt/conda/lib/python3.7/site-packages (from zict>=0.1.3->distributed>=2012.12->auto-sklearn) (1.0.1)\nRequirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.7/site-packages (from jinja2->distributed>=2012.12->auto-sklearn) (2.0.1)\nRequirement already satisfied: zipp>=0.5 in /opt/conda/lib/python3.7/site-packages (from importlib-metadata->click>=6.6->distributed>=2012.12->auto-sklearn) (3.8.0)\nBuilding wheels for collected packages: auto-sklearn, pynisher, smac, liac-arff\n Building wheel for auto-sklearn (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for auto-sklearn: filename=auto_sklearn-0.14.7-py3-none-any.whl size=6602870 sha256=eafa491efb49d3d1c38e81267a5c5222ad6587744810b8c64e99c2e361e8b696\n Stored in directory: /root/.cache/pip/wheels/ba/43/5c/2fbe6fd19e3af314cbc4aa808378068d8ddd6792064f4a2448\n Building wheel for pynisher (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for pynisher: filename=pynisher-0.6.4-py3-none-any.whl size=7027 sha256=48cdc16f6a89019871d2224f052c06b33b4f887556f2a552a50c413881e0ae3b\n Stored in directory: /root/.cache/pip/wheels/42/71/95/7555ec3253e1ba8add72ae5febf1b015d297f3b73ba296d6f6\n Building wheel for smac (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for smac: filename=smac-1.2-py3-none-any.whl size=215919 sha256=8072225d2325d65821868e8643f3aa34841999ca02885d84ab94e6f20c5fe022\n Stored in directory: /root/.cache/pip/wheels/ad/95/67/6afc6b04d3715070c853d0a9d7c7b1fb822def38671dfbbb9f\n Building wheel for liac-arff (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for liac-arff: filename=liac_arff-2.5.0-py3-none-any.whl size=11716 sha256=ec26964156794176ebc2062315fe29b235d497a1b732b3a4b7594b2a3e648783\n Stored in directory: /root/.cache/pip/wheels/1f/0f/15/332ca86cbebf25ddf98518caaf887945fbe1712b97a0f2493b\nSuccessfully built auto-sklearn pynisher smac liac-arff\nInstalling collected packages: pyrfr, pynisher, liac-arff, emcee, distro, scikit-learn, ConfigSpace, smac, auto-sklearn\n Attempting uninstall: scikit-learn\n Found existing installation: scikit-learn 1.0.2\n Uninstalling scikit-learn-1.0.2:\n Successfully uninstalled scikit-learn-1.0.2\n\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\nyellowbrick 1.4 requires scikit-learn>=1.0.0, but you have scikit-learn 0.24.2 which is incompatible.\npdpbox 0.2.1 requires matplotlib==3.1.1, but you have matplotlib 3.5.2 which is incompatible.\nmlxtend 0.20.0 requires scikit-learn>=1.0.2, but you have scikit-learn 0.24.2 which is incompatible.\nimbalanced-learn 0.9.0 requires scikit-learn>=1.0.1, but you have scikit-learn 0.24.2 which is incompatible.\ngplearn 0.4.2 requires scikit-learn>=1.0.2, but you have scikit-learn 0.24.2 which is incompatible.\nallennlp 2.10.0 requires protobuf==3.20.0, but you have protobuf 3.19.4 which is incompatible.\nallennlp 2.10.0 requires scikit-learn>=1.0.1, but you have scikit-learn 0.24.2 which is incompatible.\u001b[0m\u001b[31m\n\u001b[0mSuccessfully installed ConfigSpace-0.4.21 auto-sklearn-0.14.7 distro-1.7.0 emcee-3.1.2 liac-arff-2.5.0 pynisher-0.6.4 pyrfr-0.8.3 scikit-learn-0.24.2 smac-1.2\n\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n\u001b[0m","output_type":"stream"}],"execution_count":8},{"cell_type":"code","source":"import autosklearn.classification","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:57:10.800711Z","iopub.execute_input":"2022-08-10T10:57:10.801168Z","iopub.status.idle":"2022-08-10T10:57:11.885212Z","shell.execute_reply.started":"2022-08-10T10:57:10.801121Z","shell.execute_reply":"2022-08-10T10:57:11.883957Z"},"trusted":true},"outputs":[],"execution_count":9},{"cell_type":"code","source":"import dask.dataframe as dd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom dask.diagnostics import ProgressBar\nimport warnings \nwarnings.filterwarnings('ignore')","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:57:46.219721Z","iopub.execute_input":"2022-08-10T10:57:46.220158Z","iopub.status.idle":"2022-08-10T10:57:46.768579Z","shell.execute_reply.started":"2022-08-10T10:57:46.22012Z","shell.execute_reply":"2022-08-10T10:57:46.767545Z"},"trusted":true},"outputs":[],"execution_count":10},{"cell_type":"markdown","source":"### Importing all the necessary file","metadata":{}},{"cell_type":"code","source":"train=dd.read_csv('/kaggle/input/amex-default-prediction/train_data.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:58:23.980747Z","iopub.execute_input":"2022-08-10T10:58:23.981723Z","iopub.status.idle":"2022-08-10T10:58:24.214563Z","shell.execute_reply.started":"2022-08-10T10:58:23.98168Z","shell.execute_reply":"2022-08-10T10:58:24.213422Z"},"trusted":true},"outputs":[],"execution_count":11},{"cell_type":"code","source":"train1 = train.drop_duplicates(subset=['customer_ID'], keep='last').compute()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T10:58:36.400868Z","iopub.execute_input":"2022-08-10T10:58:36.401781Z","iopub.status.idle":"2022-08-10T11:01:12.395436Z","shell.execute_reply.started":"2022-08-10T10:58:36.401727Z","shell.execute_reply":"2022-08-10T11:01:12.394377Z"},"trusted":true},"outputs":[],"execution_count":12},{"cell_type":"code","source":"train1['customer_ID'].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:24.642017Z","iopub.execute_input":"2022-08-10T11:01:24.642454Z","iopub.status.idle":"2022-08-10T11:01:24.844245Z","shell.execute_reply.started":"2022-08-10T11:01:24.642418Z","shell.execute_reply":"2022-08-10T11:01:24.842974Z"},"trusted":true},"outputs":[{"execution_count":13,"output_type":"execute_result","data":{"text/plain":"458913"},"metadata":{}}],"execution_count":13},{"cell_type":"markdown","source":"### Reading and Sorting data by dropping any duplicates that exists","metadata":{}},{"cell_type":"code","source":"df = train1.filter(['customer_ID','S_2','P_2','D_39','B_1','R_1','S_3',\n 'D_41','D_43','D_44','B_4','D_45','B_5','R_2','D_46',\n 'D_47','D_48','B_6','B_7','B_8','D_51','B_9','R_3',\n 'D_52','P_3','S_5','S_6','D_54','B_12','R_5','D_58',\n 'B_14','D_59','D_60','D_61','B_15','S_11','D_62','D_63',\n 'D_64','D_65','B_16','B_18','B_19','D_68','S_12','R_6','S_13',\n 'B_21','D_69','B_22','D_70','D_71','D_72','S_15','B_23','P_4',\n 'D_75','B_24','R_7','B_25','B_26','D_78','D_79','S_16','D_80',\n 'R_10','R_11','B_27','D_81','S_17','R_12','R_13','D_83','R_14',\n 'R_15','D_84','R_16','B_30','S_18','D_86','R_17','R_18','S_19',\n 'R_19','B_32','S_20','R_20','R_21','D_89','R_22','R_23','D_91',\n 'D_92','D_93','D_94','R_24','R_25','D_96','S_22','S_23','S_25',\n 'S_26','D_102','D_103','B_36','R_27','D_109','D_112','S_27',\n 'D_113','D_114','D_115','D_116','D_117','D_120','D_121','D_122',\n 'D_123','D_124','D_125','D_126','D_127','D_128','B_41','D_130',\n 'D_133','R_28','D_139','D_140','D_144','D_145','B_3', 'B_20'], axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:27.819977Z","iopub.execute_input":"2022-08-10T11:01:27.820438Z","iopub.status.idle":"2022-08-10T11:01:28.00657Z","shell.execute_reply.started":"2022-08-10T11:01:27.8204Z","shell.execute_reply":"2022-08-10T11:01:28.005379Z"},"trusted":true},"outputs":[],"execution_count":14},{"cell_type":"code","source":"df.shape","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:31.700068Z","iopub.execute_input":"2022-08-10T11:01:31.700483Z","iopub.status.idle":"2022-08-10T11:01:31.708264Z","shell.execute_reply.started":"2022-08-10T11:01:31.700451Z","shell.execute_reply":"2022-08-10T11:01:31.707055Z"},"trusted":true},"outputs":[{"execution_count":15,"output_type":"execute_result","data":{"text/plain":"(458913, 134)"},"metadata":{}}],"execution_count":15},{"cell_type":"code","source":"train_label=dd.read_csv('/kaggle/input/amex-default-prediction/train_labels.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:35.34007Z","iopub.execute_input":"2022-08-10T11:01:35.340512Z","iopub.status.idle":"2022-08-10T11:01:35.367085Z","shell.execute_reply.started":"2022-08-10T11:01:35.340478Z","shell.execute_reply":"2022-08-10T11:01:35.366112Z"},"trusted":true},"outputs":[],"execution_count":16},{"cell_type":"code","source":"train_label1 = train_label.drop_duplicates(subset=['customer_ID'], keep='last').compute()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:38.479842Z","iopub.execute_input":"2022-08-10T11:01:38.480861Z","iopub.status.idle":"2022-08-10T11:01:39.719364Z","shell.execute_reply.started":"2022-08-10T11:01:38.480811Z","shell.execute_reply":"2022-08-10T11:01:39.717943Z"},"trusted":true},"outputs":[],"execution_count":17},{"cell_type":"code","source":"train_label1['customer_ID'].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:43.239853Z","iopub.execute_input":"2022-08-10T11:01:43.240284Z","iopub.status.idle":"2022-08-10T11:01:43.433177Z","shell.execute_reply.started":"2022-08-10T11:01:43.240247Z","shell.execute_reply":"2022-08-10T11:01:43.432107Z"},"trusted":true},"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"458913"},"metadata":{}}],"execution_count":18},{"cell_type":"code","source":"tdf = pd.merge(df,train_label1, on='customer_ID')","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:46.239684Z","iopub.execute_input":"2022-08-10T11:01:46.240386Z","iopub.status.idle":"2022-08-10T11:01:47.742172Z","shell.execute_reply.started":"2022-08-10T11:01:46.240343Z","shell.execute_reply":"2022-08-10T11:01:47.740804Z"},"trusted":true},"outputs":[],"execution_count":19},{"cell_type":"code","source":"tdf['customer_ID'].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:01:50.419961Z","iopub.execute_input":"2022-08-10T11:01:50.421171Z","iopub.status.idle":"2022-08-10T11:01:50.62264Z","shell.execute_reply.started":"2022-08-10T11:01:50.421123Z","shell.execute_reply":"2022-08-10T11:01:50.621341Z"},"trusted":true},"outputs":[{"execution_count":20,"output_type":"execute_result","data":{"text/plain":"458913"},"metadata":{}}],"execution_count":20},{"cell_type":"markdown","source":"### Trying to reduce the memory usage","metadata":{}},{"cell_type":"code","source":"def reduce_mem_usage(gdt, verbose=True):\n numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']\n start_mem = gdt.memory_usage().sum()/1024**2\n for col in gdt.columns:\n col_type = gdt[col].dtypes\n if col_type in numerics:\n c_min = gdt[col].min()\n c_max = gdt[col].max()\n if str(col_type)[:3] == 'int':\n if c_min >np.iinfo(np.int8).min and c_max np.iinfo(np.int16).min and c_max np.iinfo(np.int32).min and c_max np.iinfo(np.int64).min and c_max np.finfo(np.float32).min and c_max \n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
customer_IDS_2P_2D_39B_1R_1S_3D_41D_43D_44...D_130D_133R_28D_139D_140D_144D_145B_3B_20target
00000099d6bd597052cdcda90ffabf56573fe9d7c79be5f...2018-03-130.9347450.0091190.0093820.0061040.1350210.001604NaN0.003258...0.0041860.0062100.0027150.0071860.0042340.0029700.0085330.0071740.0076300
100000fd6641609c6ece5454664794f0340ad84dddce9a2...2018-03-250.8805190.1781260.0346840.0069110.1655090.0055520.0606460.008781...0.0022020.0029960.0017010.0029800.0074790.0031690.0085140.0050680.0043190
200001b22f846c82c51f6e3958ccd81970162bae8b007e8...2018-03-120.8808750.0097040.0042840.006450NaN0.003796NaN0.000628...0.0026540.0098810.0076910.0073830.0066230.0008340.0034440.0071960.0028350
3000041bdba6ecadd89a52d11886e8eaaec9325906c9723...2018-03-290.6217760.0010830.0125640.0078290.2877660.0045320.0461040.007792...0.0000600.0017890.0051400.0027040.0061840.0055600.0029830.0099370.0085570
400007889e4fcd2614b6cbe7f8f3d2e5c728eca32d9eb8a...2018-03-300.8719000.0055730.0076790.001247NaN0.0002310.0446710.002436...1.0061190.0050450.0037060.0029740.0041620.0069440.0009050.0055280.0088070
..................................................................
458908ffff41c8a52833b56430603969b9ca48d208e7c192c6a4...2018-03-310.8442290.4475850.0285150.0019280.1287070.0034820.1130530.002280...0.0066990.0020720.0045890.0079170.0015200.0030090.0048430.0058930.0005250
458909ffff518bb2075e4816ee3fe9f3b152c57fc0e6f01bf7fd...2018-03-220.8312790.0336700.2923600.006953NaN0.0057910.1345400.132158...1.0051341.1287250.0048840.0043930.0061850.0092300.0064350.2330781.0011170
458910ffff9984b999fccb2b6127635ed0736dda94e544e67e02...2018-03-070.8005220.2670180.0205630.0009570.0666480.0074240.0497780.001022...0.0039070.0045130.0089240.0060350.0028690.0003400.0021480.0063140.0060320
458911ffffa5c46bc8de74f5a4554e74e239c8dee6b9baf38814...2018-03-230.7541290.0086190.0158380.0009930.4088490.0033920.0461250.133062...1.0010440.0004790.0068281.0098940.0044780.0025020.1855270.0500480.1804081
458912fffff1d38b785cef84adeace64f8f83db3a0c31e8d92ea...2018-03-140.9821750.0024740.0000770.0008090.1191650.0032870.0134550.006794...0.0006330.0063120.0054290.0073160.0028880.0031840.0019140.0140920.0067430
\n

458913 rows × 135 columns

\n"},"metadata":{}}],"execution_count":22},{"cell_type":"code","source":"tdf['customer_ID'].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:02:54.220692Z","iopub.execute_input":"2022-08-10T11:02:54.221129Z","iopub.status.idle":"2022-08-10T11:02:54.425043Z","shell.execute_reply.started":"2022-08-10T11:02:54.221092Z","shell.execute_reply":"2022-08-10T11:02:54.423732Z"},"trusted":true},"outputs":[{"execution_count":23,"output_type":"execute_result","data":{"text/plain":"458913"},"metadata":{}}],"execution_count":23},{"cell_type":"markdown","source":"### Outliers detection and Capping function","metadata":{}},{"cell_type":"code","source":"def iqr_capping(sdf,cols,factor):\n for col in cols:\n q1 = sdf[col].quantile(0.25)\n q3 = sdf[col].quantile(0.75)\n iqr = q3-q1\n upper_whisker = q3+(factor*iqr)\n lower_whisker = q1-(factor*iqr)\n sdf[col] = np.where(sdf[col]>upper_whisker,upper_whisker,np.where(sdf[col]\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
customer_IDP_2D_39B_1R_1S_3D_41D_43D_44B_4...B_41D_130D_133R_28D_139D_140D_144D_145B_3B_20
800000469ba478561f23a92a868bd366de6f6527a684c9a...0.5689300.1213850.0107790.0069230.1494130.0003960.0073980.0067870.124780...0.0067890.0049020.0062730.0088160.0059120.0012500.0036900.0032190.0035760.004525
2100001bf2e77ff879fab36aa4fac689b9ba411dae63ae39...0.8411770.1264750.0165620.0097150.1121950.006192NaN0.0042340.014831...0.0073400.0012520.0027670.0087890.0043440.0008660.0002470.0077800.0113860.000821
340000210045da4f81e5f122c6bde5c2a617d03eef67f82c...0.6975220.0027240.0014840.0026200.1661650.0048880.1053030.0033810.417713...0.0070621.0038900.0020450.0018521.0012460.0088940.4578190.0920410.0159380.001193
4700003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c...0.5131860.3248280.1495110.0022780.1812000.0058130.2116150.2586270.244689...0.0024270.0094380.0093770.0036221.0082460.0037530.5009240.1830200.4985161.007409
6000004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9...0.2544780.7680160.5636030.5031540.1683170.0094800.0718840.3758390.235517...0.0045320.0033400.0079400.0092320.0066230.0011400.0015580.0005250.8308571.004656
..................................................................
21473ffff952c631f2c911b8a2a8ca56ea6e656309a83d2f64c...0.6469150.0038730.0113090.0038100.1629210.0089440.0347030.0005000.041485...0.0074321.0093250.0098440.0098430.0030150.0068510.0032780.0052940.0289060.009576
21486ffffcf5df59e5e0bba2a5ac4578a34e2b5aa64a1546cd3...0.4713030.0018560.0841630.5088540.8571360.0004620.7603300.2540730.207625...0.0058220.0099050.0019850.0011970.0076840.0033750.0054320.0099810.0705240.241864
21499ffffd61f098cc056dbd7d2a21380c4804bbfe60856f475...0.2064250.0010370.0199520.0095980.3211340.0777580.3290280.5081910.211724...0.0077361.0089230.2748850.0004140.0023040.0016400.0048490.0021200.0142890.009973
21512ffffddef1fc3643ea179c93245b68dca0f36941cd83977...0.5706700.0342020.0497760.0027500.2308470.0018690.1429360.3761460.689184...0.0079671.0098110.7509310.0014440.0053530.0000860.0074820.0069600.0998911.009550
21520fffffa7cf7e453e1acc6a1426475d5cb9400859f82ff61...0.4545460.0044000.0003460.008738NaN0.000936NaN0.0043130.007904...0.0053830.0046910.0000600.0002800.0034000.0095880.0064420.0031420.0034940.004350
\n

924621 rows × 128 columns

\n"},"metadata":{}}],"execution_count":38},{"cell_type":"code","source":"pred_df['customer_ID'].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:28.160701Z","iopub.execute_input":"2022-08-10T11:13:28.161425Z","iopub.status.idle":"2022-08-10T11:13:28.571583Z","shell.execute_reply.started":"2022-08-10T11:13:28.16138Z","shell.execute_reply":"2022-08-10T11:13:28.570648Z"},"trusted":true},"outputs":[{"execution_count":39,"output_type":"execute_result","data":{"text/plain":"924621"},"metadata":{}}],"execution_count":39},{"cell_type":"code","source":"for col in pred_df[cat_col].columns:\n var = pred_df[col].value_counts()\n cat = pred_df[col].value_counts().index.tolist()\n \n freq = []\n for i in var:\n freq.append(i/pred_df[col].count())\n print(cat)\n print(freq)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:32.180282Z","iopub.execute_input":"2022-08-10T11:13:32.180697Z","iopub.status.idle":"2022-08-10T11:13:32.848831Z","shell.execute_reply.started":"2022-08-10T11:13:32.180664Z","shell.execute_reply":"2022-08-10T11:13:32.84753Z"},"trusted":true},"outputs":[{"name":"stdout","text":"[-1.0, 4.0, 3.0, 2.0, 5.0, 6.0, 1.0]\n[0.2892465097625283, 0.21830249569470353, 0.20418949694965752, 0.10864221471282047, 0.08937608183313629, 0.07197420017342385, 0.018269000873730033]\n['CO', 'CR', 'CL', 'XZ', 'XM', 'XL']\n[0.7407370154906713, 0.1584043624360684, 0.08066223890653576, 0.012053587361740649, 0.005323262179855313, 0.002819533625128566]\n['O', 'U', 'R']\n[0.5356802315114255, 0.2695021037400564, 0.19481766474851805]\n[6.0, 5.0, 4.0, 3.0, 2.0, 1.0]\n[0.5011454810854307, 0.23858813775920182, 0.09840718832329721, 0.09451687520296684, 0.04334540327916821, 0.02399691434993533]\n","output_type":"stream"}],"execution_count":40},{"cell_type":"code","source":"pred_df['D_117'].replace([-1.0, 4.0, 3.0, 2.0, 5.0, 6.0, 1.0],[0.28924, 0.21830,0.2041, 0.1086, 0.0893, 0.0719,0.01826 ], inplace=True)\npred_df['D_117'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:36.566067Z","iopub.execute_input":"2022-08-10T11:13:36.567335Z","iopub.status.idle":"2022-08-10T11:13:36.615038Z","shell.execute_reply.started":"2022-08-10T11:13:36.567277Z","shell.execute_reply":"2022-08-10T11:13:36.6138Z"},"trusted":true},"outputs":[{"execution_count":41,"output_type":"execute_result","data":{"text/plain":"0.28924 262521\n0.21830 198132\n0.20410 185323\n0.10860 98604\n0.08930 81118\n0.07190 65324\n0.01826 16581\nName: D_117, dtype: int64"},"metadata":{}}],"execution_count":41},{"cell_type":"code","source":"pred_df['D_63'].replace(['CO', 'CR', 'CL', 'XZ', 'XM', 'XL'],[0.7407, 0.1584,0.0806, 0.01205,0.00532,0.00281], inplace=True)\npred_df['D_63'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:40.020239Z","iopub.execute_input":"2022-08-10T11:13:40.020646Z","iopub.status.idle":"2022-08-10T11:13:40.387828Z","shell.execute_reply.started":"2022-08-10T11:13:40.020612Z","shell.execute_reply":"2022-08-10T11:13:40.387029Z"},"trusted":true},"outputs":[{"execution_count":42,"output_type":"execute_result","data":{"text/plain":"0.74070 684901\n0.15840 146464\n0.08060 74582\n0.01205 11145\n0.00532 4922\n0.00281 2607\nName: D_63, dtype: int64"},"metadata":{}}],"execution_count":42},{"cell_type":"code","source":"pred_df['D_64'].replace(['O', 'U', 'R'],[0.5356, 0.26950,0.1948], inplace=True)\npred_df['D_64'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:44.160125Z","iopub.execute_input":"2022-08-10T11:13:44.160561Z","iopub.status.idle":"2022-08-10T11:13:44.422431Z","shell.execute_reply.started":"2022-08-10T11:13:44.160528Z","shell.execute_reply":"2022-08-10T11:13:44.421229Z"},"trusted":true},"outputs":[{"execution_count":43,"output_type":"execute_result","data":{"text/plain":"0.5356 482019\n0.2695 242505\n0.1948 175302\nName: D_64, dtype: int64"},"metadata":{}}],"execution_count":43},{"cell_type":"code","source":"pred_df['D_68'].replace([6.0, 5.0, 4.0, 3.0, 2.0, 1.0],[0.5011, 0.2385,0.0984,0.09451,0.04334,0.02399], inplace=True)\npred_df['D_68'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:47.579982Z","iopub.execute_input":"2022-08-10T11:13:47.581379Z","iopub.status.idle":"2022-08-10T11:13:47.628385Z","shell.execute_reply.started":"2022-08-10T11:13:47.581308Z","shell.execute_reply":"2022-08-10T11:13:47.627143Z"},"trusted":true},"outputs":[{"execution_count":44,"output_type":"execute_result","data":{"text/plain":"0.50110 452154\n0.23850 215264\n0.09840 88787\n0.09451 85277\n0.04334 39108\n0.02399 21651\nName: D_68, dtype: int64"},"metadata":{}}],"execution_count":44},{"cell_type":"code","source":"from sklearn.feature_selection import SelectKBest, f_classif\nfrom imblearn.ensemble import RUSBoostClassifier\nimport lightgbm as lgb\nimport catboost\nfrom catboost import *\nfrom sklearn.ensemble import StackingClassifier\nfrom sklearn.linear_model import LogisticRegression","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:50.840398Z","iopub.execute_input":"2022-08-10T11:13:50.840817Z","iopub.status.idle":"2022-08-10T11:13:51.437914Z","shell.execute_reply.started":"2022-08-10T11:13:50.840785Z","shell.execute_reply":"2022-08-10T11:13:51.436958Z"},"trusted":true},"outputs":[{"output_type":"display_data","data":{"text/plain":"","text/html":"\n"},"metadata":{}}],"execution_count":45},{"cell_type":"code","source":"for col in pred_df.columns:\n pred_df[col][pred_df[col].isnull()] = pred_df[col].dropna().sample(pred_df[col].isnull().sum()).values","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:13:56.040245Z","iopub.execute_input":"2022-08-10T11:13:56.041162Z","iopub.status.idle":"2022-08-10T11:14:01.547781Z","shell.execute_reply.started":"2022-08-10T11:13:56.041118Z","shell.execute_reply":"2022-08-10T11:14:01.546502Z"},"trusted":true},"outputs":[],"execution_count":46},{"cell_type":"code","source":"num_col1 = []\nfor nocol in pred_df.columns:\n if (is_numeric_dtype(pred_df[nocol]) == True):\n num_col1.append(nocol)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:14:06.220317Z","iopub.execute_input":"2022-08-10T11:14:06.220724Z","iopub.status.idle":"2022-08-10T11:14:06.227628Z","shell.execute_reply.started":"2022-08-10T11:14:06.220691Z","shell.execute_reply":"2022-08-10T11:14:06.226412Z"},"trusted":true},"outputs":[],"execution_count":47},{"cell_type":"code","source":"iqr_capping(pred_df,num_col1,1.5)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T11:14:09.280101Z","iopub.execute_input":"2022-08-10T11:14:09.280702Z","iopub.status.idle":"2022-08-10T11:14:14.447078Z","shell.execute_reply.started":"2022-08-10T11:14:09.28065Z","shell.execute_reply":"2022-08-10T11:14:14.446054Z"},"trusted":true},"outputs":[],"execution_count":48},{"cell_type":"code","source":"x = tdf.drop(['customer_ID', 'S_2', 'target'], axis=1)\ny = tdf.target","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:12:57.263948Z","iopub.execute_input":"2022-08-10T13:12:57.26449Z","iopub.status.idle":"2022-08-10T13:12:57.993964Z","shell.execute_reply.started":"2022-08-10T13:12:57.264449Z","shell.execute_reply":"2022-08-10T13:12:57.992561Z"},"trusted":true},"outputs":[],"execution_count":84},{"cell_type":"code","source":"x1 = x.iloc[:75000, :]\ny1 = y.iloc[ :75000]","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:13:00.462934Z","iopub.execute_input":"2022-08-10T13:13:00.463392Z","iopub.status.idle":"2022-08-10T13:13:00.469407Z","shell.execute_reply.started":"2022-08-10T13:13:00.463354Z","shell.execute_reply":"2022-08-10T13:13:00.468227Z"},"trusted":true},"outputs":[],"execution_count":85},{"cell_type":"code","source":"x_test = pred_df.drop(['customer_ID'], axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:13:09.663701Z","iopub.execute_input":"2022-08-10T13:13:09.664144Z","iopub.status.idle":"2022-08-10T13:13:11.352074Z","shell.execute_reply.started":"2022-08-10T13:13:09.664108Z","shell.execute_reply":"2022-08-10T13:13:11.351078Z"},"trusted":true},"outputs":[],"execution_count":86},{"cell_type":"code","source":"from autosklearn.classification import AutoSklearnClassifier","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:13:18.023043Z","iopub.execute_input":"2022-08-10T13:13:18.023468Z","iopub.status.idle":"2022-08-10T13:13:18.029415Z","shell.execute_reply.started":"2022-08-10T13:13:18.023432Z","shell.execute_reply":"2022-08-10T13:13:18.028056Z"},"trusted":true},"outputs":[],"execution_count":87},{"cell_type":"code","source":"model = AutoSklearnClassifier(\n time_left_for_this_task= 4500,\n per_run_time_limit=450,\n ensemble_size=1,\n initial_configurations_via_metalearning=0,\n n_jobs=-1,\n \n)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:13:39.463763Z","iopub.execute_input":"2022-08-10T13:13:39.464174Z","iopub.status.idle":"2022-08-10T13:13:39.470318Z","shell.execute_reply.started":"2022-08-10T13:13:39.464138Z","shell.execute_reply":"2022-08-10T13:13:39.468829Z"},"trusted":true},"outputs":[],"execution_count":89},{"cell_type":"code","source":"model.fit(x1,y1)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:13:43.302846Z","iopub.execute_input":"2022-08-10T13:13:43.304168Z","iopub.status.idle":"2022-08-10T14:28:48.873299Z","shell.execute_reply.started":"2022-08-10T13:13:43.304109Z","shell.execute_reply":"2022-08-10T14:28:48.872079Z"},"trusted":true},"outputs":[{"execution_count":90,"output_type":"execute_result","data":{"text/plain":"AutoSklearnClassifier(ensemble_size=1,\n initial_configurations_via_metalearning=0, n_jobs=-1,\n per_run_time_limit=450, time_left_for_this_task=4500)"},"metadata":{}}],"execution_count":90},{"cell_type":"code","source":"print(model.sprint_statistics())","metadata":{"execution":{"iopub.status.busy":"2022-08-10T14:29:17.529413Z","iopub.execute_input":"2022-08-10T14:29:17.529853Z","iopub.status.idle":"2022-08-10T14:29:17.568886Z","shell.execute_reply.started":"2022-08-10T14:29:17.529807Z","shell.execute_reply":"2022-08-10T14:29:17.567534Z"},"trusted":true},"outputs":[{"name":"stdout","text":"auto-sklearn results:\n Dataset name: 423ea102-18ae-11ed-8011-0242ac130202\n Metric: accuracy\n Best validation score: 0.892889\n Number of target algorithm runs: 168\n Number of successful target algorithm runs: 130\n Number of crashed target algorithm runs: 1\n Number of target algorithms that exceeded the time limit: 18\n Number of target algorithms that exceeded the memory limit: 19\n\n","output_type":"stream"}],"execution_count":91},{"cell_type":"code","source":"print(model.show_models())","metadata":{"execution":{"iopub.status.busy":"2022-08-10T14:29:38.449503Z","iopub.execute_input":"2022-08-10T14:29:38.449982Z","iopub.status.idle":"2022-08-10T14:29:38.462968Z","shell.execute_reply.started":"2022-08-10T14:29:38.449942Z","shell.execute_reply":"2022-08-10T14:29:38.461325Z"},"trusted":true},"outputs":[{"name":"stdout","text":"{132: {'model_id': 132, 'rank': 1, 'cost': 0.10711111111111116, 'ensemble_weight': 1.0, 'data_preprocessor': , 'balancing': Balancing(random_state=1), 'feature_preprocessor': , 'classifier': , 'sklearn_classifier': HistGradientBoostingClassifier(early_stopping=True,\n l2_regularization=0.012865179750450133,\n learning_rate=0.06665575744691808, max_iter=512,\n max_leaf_nodes=205, min_samples_leaf=35,\n n_iter_no_change=14, random_state=1,\n validation_fraction=None, warm_start=True)}}\n","output_type":"stream"}],"execution_count":92},{"cell_type":"code","source":"y_pred = model.predict_proba(x_test)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T12:57:18.730067Z","iopub.execute_input":"2022-08-10T12:57:18.73051Z","iopub.status.idle":"2022-08-10T12:58:52.239474Z","shell.execute_reply.started":"2022-08-10T12:57:18.730469Z","shell.execute_reply":"2022-08-10T12:58:52.238073Z"},"trusted":true},"outputs":[],"execution_count":64},{"cell_type":"code","source":"y_predict_final=y_pred[:,1]","metadata":{"execution":{"iopub.status.busy":"2022-08-10T12:59:16.930272Z","iopub.execute_input":"2022-08-10T12:59:16.930745Z","iopub.status.idle":"2022-08-10T12:59:16.937848Z","shell.execute_reply.started":"2022-08-10T12:59:16.930699Z","shell.execute_reply":"2022-08-10T12:59:16.936374Z"},"trusted":true},"outputs":[],"execution_count":65},{"cell_type":"code","source":"sub = pd.DataFrame({\"customer_ID\": pred_df.customer_ID,\"prediction\":y_predict_final})","metadata":{"execution":{"iopub.status.busy":"2022-08-10T12:59:34.105892Z","iopub.execute_input":"2022-08-10T12:59:34.106367Z","iopub.status.idle":"2022-08-10T12:59:34.356684Z","shell.execute_reply.started":"2022-08-10T12:59:34.106327Z","shell.execute_reply":"2022-08-10T12:59:34.355177Z"},"trusted":true},"outputs":[],"execution_count":66},{"cell_type":"code","source":"sub.shape","metadata":{"execution":{"iopub.status.busy":"2022-08-10T12:59:47.850095Z","iopub.execute_input":"2022-08-10T12:59:47.850518Z","iopub.status.idle":"2022-08-10T12:59:47.859376Z","shell.execute_reply.started":"2022-08-10T12:59:47.850481Z","shell.execute_reply":"2022-08-10T12:59:47.857948Z"},"trusted":true},"outputs":[{"execution_count":67,"output_type":"execute_result","data":{"text/plain":"(924621, 2)"},"metadata":{}}],"execution_count":67},{"cell_type":"code","source":"sub.sort_index()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:00:02.970888Z","iopub.execute_input":"2022-08-10T13:00:02.971361Z","iopub.status.idle":"2022-08-10T13:00:03.174436Z","shell.execute_reply.started":"2022-08-10T13:00:02.971321Z","shell.execute_reply":"2022-08-10T13:00:03.173146Z"},"trusted":true},"outputs":[{"execution_count":68,"output_type":"execute_result","data":{"text/plain":" customer_ID prediction\n0 afae257b34acdc2682fcf9073661758c1743da9c856400... 9.999321e-01\n0 2ca2879526a7c161c7da0c0ce8af6d00e3d99f7aee5c44... 1.228740e-08\n0 ab537b7577dcda3a9d04864d9664c1935d363b19d186e1... 1.337793e-07\n0 ac4a456b5fb5eb09a52327ef56069f1bf6f3b748ac721e... 1.000000e+00\n0 ad468caed24856124cdad84e4724c280ffe7772a32dc98... 9.984941e-01\n... ... ...\n21554 1e9e0e1fda9978da8d0b34c1fa1230e191bb3a09a24c22... 1.497932e-08\n21556 d8390f2d7249c6eadc5b9a5310d161533ff183e60462fd... 6.212402e-07\n21556 45cfdcfc55e465c31d4c6f6874ba8774a9375d21773591... 1.000346e-05\n21557 0ab989c4c2b5d7fa870d66a48f457ab33fe6f7287dd99d... 4.979367e-06\n21565 e26665612bf187dd12db6949bc9e4a22835bc97cd66d82... 1.587884e-06\n\n[924621 rows x 2 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
customer_IDprediction
0afae257b34acdc2682fcf9073661758c1743da9c856400...9.999321e-01
02ca2879526a7c161c7da0c0ce8af6d00e3d99f7aee5c44...1.228740e-08
0ab537b7577dcda3a9d04864d9664c1935d363b19d186e1...1.337793e-07
0ac4a456b5fb5eb09a52327ef56069f1bf6f3b748ac721e...1.000000e+00
0ad468caed24856124cdad84e4724c280ffe7772a32dc98...9.984941e-01
.........
215541e9e0e1fda9978da8d0b34c1fa1230e191bb3a09a24c22...1.497932e-08
21556d8390f2d7249c6eadc5b9a5310d161533ff183e60462fd...6.212402e-07
2155645cfdcfc55e465c31d4c6f6874ba8774a9375d21773591...1.000346e-05
215570ab989c4c2b5d7fa870d66a48f457ab33fe6f7287dd99d...4.979367e-06
21565e26665612bf187dd12db6949bc9e4a22835bc97cd66d82...1.587884e-06
\n

924621 rows × 2 columns

\n
"},"metadata":{}}],"execution_count":68},{"cell_type":"code","source":"sub.reset_index()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:00:19.050198Z","iopub.execute_input":"2022-08-10T13:00:19.050666Z","iopub.status.idle":"2022-08-10T13:00:19.089129Z","shell.execute_reply.started":"2022-08-10T13:00:19.050623Z","shell.execute_reply":"2022-08-10T13:00:19.087979Z"},"trusted":true},"outputs":[{"execution_count":69,"output_type":"execute_result","data":{"text/plain":" index customer_ID prediction\n0 8 00000469ba478561f23a92a868bd366de6f6527a684c9a... 1.699341e-06\n1 21 00001bf2e77ff879fab36aa4fac689b9ba411dae63ae39... 1.691277e-09\n2 34 0000210045da4f81e5f122c6bde5c2a617d03eef67f82c... 4.799687e-06\n3 47 00003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c... 3.434423e-02\n4 60 00004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9... 9.993012e-01\n... ... ... ...\n924616 21473 ffff952c631f2c911b8a2a8ca56ea6e656309a83d2f64c... 1.953075e-05\n924617 21486 ffffcf5df59e5e0bba2a5ac4578a34e2b5aa64a1546cd3... 8.551885e-01\n924618 21499 ffffd61f098cc056dbd7d2a21380c4804bbfe60856f475... 8.912962e-01\n924619 21512 ffffddef1fc3643ea179c93245b68dca0f36941cd83977... 1.131058e-01\n924620 21520 fffffa7cf7e453e1acc6a1426475d5cb9400859f82ff61... 1.898916e-04\n\n[924621 rows x 3 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
indexcustomer_IDprediction
0800000469ba478561f23a92a868bd366de6f6527a684c9a...1.699341e-06
12100001bf2e77ff879fab36aa4fac689b9ba411dae63ae39...1.691277e-09
2340000210045da4f81e5f122c6bde5c2a617d03eef67f82c...4.799687e-06
34700003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c...3.434423e-02
46000004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9...9.993012e-01
............
92461621473ffff952c631f2c911b8a2a8ca56ea6e656309a83d2f64c...1.953075e-05
92461721486ffffcf5df59e5e0bba2a5ac4578a34e2b5aa64a1546cd3...8.551885e-01
92461821499ffffd61f098cc056dbd7d2a21380c4804bbfe60856f475...8.912962e-01
92461921512ffffddef1fc3643ea179c93245b68dca0f36941cd83977...1.131058e-01
92462021520fffffa7cf7e453e1acc6a1426475d5cb9400859f82ff61...1.898916e-04
\n

924621 rows × 3 columns

\n
"},"metadata":{}}],"execution_count":69},{"cell_type":"code","source":"sub1 = sub.filter(['customer_ID','prediction'], axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:00:35.023403Z","iopub.execute_input":"2022-08-10T13:00:35.023846Z","iopub.status.idle":"2022-08-10T13:00:35.059664Z","shell.execute_reply.started":"2022-08-10T13:00:35.023808Z","shell.execute_reply":"2022-08-10T13:00:35.058551Z"},"trusted":true},"outputs":[],"execution_count":70},{"cell_type":"code","source":"sub1.head(10)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:00:48.982787Z","iopub.execute_input":"2022-08-10T13:00:48.983249Z","iopub.status.idle":"2022-08-10T13:00:48.997175Z","shell.execute_reply.started":"2022-08-10T13:00:48.983209Z","shell.execute_reply":"2022-08-10T13:00:48.995891Z"},"trusted":true},"outputs":[{"execution_count":71,"output_type":"execute_result","data":{"text/plain":" customer_ID prediction\n8 00000469ba478561f23a92a868bd366de6f6527a684c9a... 1.699341e-06\n21 00001bf2e77ff879fab36aa4fac689b9ba411dae63ae39... 1.691277e-09\n34 0000210045da4f81e5f122c6bde5c2a617d03eef67f82c... 4.799687e-06\n47 00003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c... 3.434423e-02\n60 00004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9... 9.993012e-01\n73 00004ffe6e01e1b688170bbd108da8351bc4c316eacfef... 2.227487e-09\n86 00007cfcce97abfa0b4fa0647986157281d01d3ab90de9... 9.998905e-01\n99 000089cc2a30dad8e6ba39126f9d86df6088c9f975093a... 9.415289e-02\n112 00008f50a1dd76fa211ba36a2b0d5a1b201e4134a5fd53... 9.762077e-01\n125 0000b48a4f27dc1d61e78d081678e811620300b88eb3ab... 1.592235e-08","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
customer_IDprediction
800000469ba478561f23a92a868bd366de6f6527a684c9a...1.699341e-06
2100001bf2e77ff879fab36aa4fac689b9ba411dae63ae39...1.691277e-09
340000210045da4f81e5f122c6bde5c2a617d03eef67f82c...4.799687e-06
4700003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c...3.434423e-02
6000004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9...9.993012e-01
7300004ffe6e01e1b688170bbd108da8351bc4c316eacfef...2.227487e-09
8600007cfcce97abfa0b4fa0647986157281d01d3ab90de9...9.998905e-01
99000089cc2a30dad8e6ba39126f9d86df6088c9f975093a...9.415289e-02
11200008f50a1dd76fa211ba36a2b0d5a1b201e4134a5fd53...9.762077e-01
1250000b48a4f27dc1d61e78d081678e811620300b88eb3ab...1.592235e-08
\n
"},"metadata":{}}],"execution_count":71},{"cell_type":"code","source":"sub1.nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:01:02.06415Z","iopub.execute_input":"2022-08-10T13:01:02.064578Z","iopub.status.idle":"2022-08-10T13:01:02.642739Z","shell.execute_reply.started":"2022-08-10T13:01:02.064542Z","shell.execute_reply":"2022-08-10T13:01:02.641586Z"},"trusted":true},"outputs":[{"execution_count":72,"output_type":"execute_result","data":{"text/plain":"customer_ID 924621\nprediction 924620\ndtype: int64"},"metadata":{}}],"execution_count":72},{"cell_type":"code","source":"sub1.round({'prediction':5})","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:06:52.903353Z","iopub.execute_input":"2022-08-10T13:06:52.903957Z","iopub.status.idle":"2022-08-10T13:06:52.949834Z","shell.execute_reply.started":"2022-08-10T13:06:52.903898Z","shell.execute_reply":"2022-08-10T13:06:52.948751Z"},"trusted":true},"outputs":[{"execution_count":79,"output_type":"execute_result","data":{"text/plain":" customer_ID prediction\n8 00000469ba478561f23a92a868bd366de6f6527a684c9a... 0.00000\n21 00001bf2e77ff879fab36aa4fac689b9ba411dae63ae39... 0.00000\n34 0000210045da4f81e5f122c6bde5c2a617d03eef67f82c... 0.00000\n47 00003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c... 0.03434\n60 00004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9... 0.99930\n... ... ...\n21473 ffff952c631f2c911b8a2a8ca56ea6e656309a83d2f64c... 0.00002\n21486 ffffcf5df59e5e0bba2a5ac4578a34e2b5aa64a1546cd3... 0.85519\n21499 ffffd61f098cc056dbd7d2a21380c4804bbfe60856f475... 0.89130\n21512 ffffddef1fc3643ea179c93245b68dca0f36941cd83977... 0.11311\n21520 fffffa7cf7e453e1acc6a1426475d5cb9400859f82ff61... 0.00019\n\n[924621 rows x 2 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
customer_IDprediction
800000469ba478561f23a92a868bd366de6f6527a684c9a...0.00000
2100001bf2e77ff879fab36aa4fac689b9ba411dae63ae39...0.00000
340000210045da4f81e5f122c6bde5c2a617d03eef67f82c...0.00000
4700003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c...0.03434
6000004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9...0.99930
.........
21473ffff952c631f2c911b8a2a8ca56ea6e656309a83d2f64c...0.00002
21486ffffcf5df59e5e0bba2a5ac4578a34e2b5aa64a1546cd3...0.85519
21499ffffd61f098cc056dbd7d2a21380c4804bbfe60856f475...0.89130
21512ffffddef1fc3643ea179c93245b68dca0f36941cd83977...0.11311
21520fffffa7cf7e453e1acc6a1426475d5cb9400859f82ff61...0.00019
\n

924621 rows × 2 columns

\n
"},"metadata":{}}],"execution_count":79},{"cell_type":"code","source":"sub1.to_csv('submission88.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:07:19.462816Z","iopub.execute_input":"2022-08-10T13:07:19.463279Z","iopub.status.idle":"2022-08-10T13:07:23.092363Z","shell.execute_reply.started":"2022-08-10T13:07:19.463237Z","shell.execute_reply":"2022-08-10T13:07:23.090769Z"},"trusted":true},"outputs":[],"execution_count":80},{"cell_type":"code","source":"fd = pd.read_csv('submission88.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:07:27.74287Z","iopub.execute_input":"2022-08-10T13:07:27.744111Z","iopub.status.idle":"2022-08-10T13:07:29.027444Z","shell.execute_reply.started":"2022-08-10T13:07:27.74406Z","shell.execute_reply":"2022-08-10T13:07:29.026405Z"},"trusted":true},"outputs":[],"execution_count":81},{"cell_type":"code","source":"fd.nunique()","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:07:32.06249Z","iopub.execute_input":"2022-08-10T13:07:32.062916Z","iopub.status.idle":"2022-08-10T13:07:32.57327Z","shell.execute_reply.started":"2022-08-10T13:07:32.062879Z","shell.execute_reply":"2022-08-10T13:07:32.571738Z"},"trusted":true},"outputs":[{"execution_count":82,"output_type":"execute_result","data":{"text/plain":"customer_ID 924621\nprediction 924620\ndtype: int64"},"metadata":{}}],"execution_count":82},{"cell_type":"code","source":"fd.head(15)","metadata":{"execution":{"iopub.status.busy":"2022-08-10T13:07:36.262614Z","iopub.execute_input":"2022-08-10T13:07:36.263083Z","iopub.status.idle":"2022-08-10T13:07:36.278697Z","shell.execute_reply.started":"2022-08-10T13:07:36.26304Z","shell.execute_reply":"2022-08-10T13:07:36.27675Z"},"trusted":true},"outputs":[{"execution_count":83,"output_type":"execute_result","data":{"text/plain":" customer_ID prediction\n0 00000469ba478561f23a92a868bd366de6f6527a684c9a... 1.699341e-06\n1 00001bf2e77ff879fab36aa4fac689b9ba411dae63ae39... 1.691277e-09\n2 0000210045da4f81e5f122c6bde5c2a617d03eef67f82c... 4.799687e-06\n3 00003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c... 3.434423e-02\n4 00004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9... 9.993012e-01\n5 00004ffe6e01e1b688170bbd108da8351bc4c316eacfef... 2.227487e-09\n6 00007cfcce97abfa0b4fa0647986157281d01d3ab90de9... 9.998905e-01\n7 000089cc2a30dad8e6ba39126f9d86df6088c9f975093a... 9.415289e-02\n8 00008f50a1dd76fa211ba36a2b0d5a1b201e4134a5fd53... 9.762077e-01\n9 0000b48a4f27dc1d61e78d081678e811620300b88eb3ab... 1.592235e-08\n10 0000bccc55cf039a23d49832234f224085716d85bed7d2... 7.987277e-03\n11 0000c7144ae91777aeeb02a7e02bdbfe7edb127b69fa53... 3.682644e-05\n12 0000f63151bd00e2ebad53ff5fb207fed9139a89f50711... 1.520301e-06\n13 00010121860f74c1641baa1478a329eb81f2cf4608e32b... 3.138446e-08\n14 000115113b3bd18d3db243e9f5277c99fc6f9a6f20db04... 8.610286e-08","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
customer_IDprediction
000000469ba478561f23a92a868bd366de6f6527a684c9a...1.699341e-06
100001bf2e77ff879fab36aa4fac689b9ba411dae63ae39...1.691277e-09
20000210045da4f81e5f122c6bde5c2a617d03eef67f82c...4.799687e-06
300003b41e58ede33b8daf61ab56d9952f17c9ad1c3976c...3.434423e-02
400004b22eaeeeb0ec976890c1d9bfc14fd9427e98c4ee9...9.993012e-01
500004ffe6e01e1b688170bbd108da8351bc4c316eacfef...2.227487e-09
600007cfcce97abfa0b4fa0647986157281d01d3ab90de9...9.998905e-01
7000089cc2a30dad8e6ba39126f9d86df6088c9f975093a...9.415289e-02
800008f50a1dd76fa211ba36a2b0d5a1b201e4134a5fd53...9.762077e-01
90000b48a4f27dc1d61e78d081678e811620300b88eb3ab...1.592235e-08
100000bccc55cf039a23d49832234f224085716d85bed7d2...7.987277e-03
110000c7144ae91777aeeb02a7e02bdbfe7edb127b69fa53...3.682644e-05
120000f63151bd00e2ebad53ff5fb207fed9139a89f50711...1.520301e-06
1300010121860f74c1641baa1478a329eb81f2cf4608e32b...3.138446e-08
14000115113b3bd18d3db243e9f5277c99fc6f9a6f20db04...8.610286e-08
\n
"},"metadata":{}}],"execution_count":83},{"cell_type":"code","source":"","metadata":{},"outputs":[],"execution_count":null}]}