diff --git a/LOAD_MODEL_INSTRUCTIONS.md b/LOAD_MODEL_INSTRUCTIONS.md new file mode 100644 index 0000000..e69de29 diff --git a/Matt_Playground.ipynb b/Matt_Playground.ipynb deleted file mode 100644 index e064e4c..0000000 --- a/Matt_Playground.ipynb +++ /dev/null @@ -1,211 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "##### The cell below is for you to keep track of the libraries used and install those libraries quickly\n", - "##### Ensure that the proper library names are used and the syntax of `%pip install PACKAGE_NAME` is followed" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "%pip install pandas \n", - "%pip install matplotlib\n", - "# add commented pip installation lines for packages used as shown above for ease of testing\n", - "# the line should be of the format %pip install PACKAGE_NAME " - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## **DO NOT CHANGE** the filepath variable\n", - "##### Instead, create a folder named 'data' in your current working directory and \n", - "##### have the .parquet file inside that. A relative path *must* be used when loading data into pandas" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14656\\4089170275.py:2: DeprecationWarning: \n", - "Pyarrow will become a required dependency of pandas in the next major release of pandas (pandas 3.0),\n", - "(to allow more performant data types, such as the Arrow string type, and better interoperability with other libraries)\n", - "but was not found to be installed on your system.\n", - "If this would cause problems for you,\n", - "please provide us feedback at https://github.com/pandas-dev/pandas/issues/54466\n", - " \n", - " import pandas as pd\n" - ] - } - ], - "source": [ - "# Dependencies\n", - "import pandas as pd\n", - "\n", - "# Filepath\n", - "filepath = \"./data/catB_train.csv\" " - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### **ALL** Code for machine learning and dataset analysis should be entered below. \n", - "##### Ensure that your code is clear and readable.\n", - "##### Comments and Markdown notes are advised to direct attention to pieces of code you deem useful." - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [], - "source": [ - "# read the parquet file into a pandas dataframe\n", - "df = pd.read_csv(filepath)\n", - "df.head()\n", - "# show the whole row of the dataframe which has alot of columns\n", - "pd.set_option('display.max_columns', None)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Column Analysis\n", - "- APE, Sum Insured, Prepaid Premiums\n", - "- Purchase and Lapse Metrics" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Number of APE columns: 37 \n", - "Number of Sum Insured columns: 36 \n", - "Number of Prepaid Premium Columns: 37\n", - "Number of Lapse Ape columns: 25 \n", - "Number of N Months Last Bought columns: 33 \n", - "Number of N Months Since Lapse Columns: 25 \n", - "Number of F Ever Bought Columns: 32\n" - ] - } - ], - "source": [ - "# Retrieves columns which starts with [whatever]\n", - "def find_xxx_columns(df, column_to_find):\n", - " return [col for col in df.columns if col.startswith(column_to_find)]\n", - "\n", - "# retrieve columns\n", - "ape_columns = find_xxx_columns(df, \"ape_\")\n", - "sumins_columns = find_xxx_columns(df, \"sumins_\")\n", - "prempaid_columns = find_xxx_columns(df, \"prempaid_\")\n", - "# print results\n", - "print(\"Number of APE columns: \", len(ape_columns),\"\\nNumber of Sum Insured columns: \", len(sumins_columns), \"\\nNumber of Prepaid Premium Columns: \", len(prempaid_columns))\n", - "\n", - "# retrieve columns\n", - "lapse_ape_columns = find_xxx_columns(df, \"lapse_ape_\")\n", - "n_months_last_bought_columns = find_xxx_columns(df, \"n_months_last_bought\")\n", - "n_months_since_lapse = find_xxx_columns(df, \"n_months_since_lapse_\")\n", - "f_ever_bought_columns = find_xxx_columns(df, \"f_ever_bought\")\n", - "# print results\n", - "print(\"Number of Lapse Ape columns: \", len(lapse_ape_columns),\"\\nNumber of N Months Last Bought columns: \", len(n_months_last_bought_columns), \"\\nNumber of N Months Since Lapse Columns: \", len(n_months_since_lapse), \"\\nNumber of F Ever Bought Columns: \", len(f_ever_bought_columns))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## The cell below is **NOT** to be removed\n", - "##### The function is to be amended so that it accepts the given input (dataframe) and returns the required output (list). \n", - "##### It is recommended to test the function out prior to submission\n", - "-------------------------------------------------------------------------------------------------------------------------------\n", - "##### The hidden_data parsed into the function below will have the same layout columns wise as the dataset *SENT* to you\n", - "##### Thus, ensure that steps taken to modify the initial dataset to fit into the model are also carried out in the function below" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "def testing_hidden_data(hidden_data: pd.DataFrame) -> list:\n", - " '''DO NOT REMOVE THIS FUNCTION.\n", - "\n", - "The function accepts a dataframe as input and return an iterable (list)\n", - "of binary classes as output.\n", - "\n", - "The function should be coded to test on hidden data\n", - "and should include any preprocessing functions needed for your model to perform. \n", - " \n", - "All relevant code MUST be included in this function.'''\n", - " result = [] \n", - " return result" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "##### Cell to check testing_hidden_data function" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# This cell should output a list of predictions.\n", - "test_df = pd.read_parquet(filepath)\n", - "test_df = test_df.drop(columns=[\"f_purchase_lh\"])\n", - "print(testing_hidden_data(test_df))" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Please have the filename renamed and ensure that it can be run with the requirements above being met. All the best!" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.9.0" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} diff --git a/NUS_DATATHON_SINGLIFE_Team AwkBBQ.ipynb b/NUS_DATATHON_SINGLIFE_278.ipynb similarity index 65% rename from NUS_DATATHON_SINGLIFE_Team AwkBBQ.ipynb rename to NUS_DATATHON_SINGLIFE_278.ipynb index 58d0df4..4d31ea7 100644 --- a/NUS_DATATHON_SINGLIFE_Team AwkBBQ.ipynb +++ b/NUS_DATATHON_SINGLIFE_278.ipynb @@ -10,19 +10,16 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 181, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Collecting xgboost\n", - " Downloading xgboost-2.0.3-py3-none-win_amd64.whl (99.8 MB)\n", + "Requirement already satisfied: xgboost in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (2.0.3)\n", "Requirement already satisfied: numpy in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from xgboost) (1.26.3)\n", "Requirement already satisfied: scipy in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from xgboost) (1.12.0)\n", - "Installing collected packages: xgboost\n", - "Successfully installed xgboost-2.0.3\n", "Note: you may need to restart the kernel to use updated packages.\n" ] }, @@ -39,10 +36,101 @@ "output_type": "stream", "text": [ "Requirement already satisfied: scikit-learn in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (1.4.0)\n", - "Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from scikit-learn) (3.2.0)\n", - "Requirement already satisfied: scipy>=1.6.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from scikit-learn) (1.12.0)\n", "Requirement already satisfied: joblib>=1.2.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from scikit-learn) (1.3.2)\n", + "Requirement already satisfied: scipy>=1.6.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from scikit-learn) (1.12.0)\n", "Requirement already satisfied: numpy<2.0,>=1.19.5 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from scikit-learn) (1.26.3)\n", + "Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from scikit-learn) (3.2.0)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: You are using pip version 20.2.3; however, version 23.3.2 is available.\n", + "You should consider upgrading via the 'c:\\Users\\Matthew Chuang\\Documents\\Github\\NUS-SDS-Datathon-Singlife\\venv\\Scripts\\python.exe -m pip install --upgrade pip' command.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pandas in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (2.2.0)\n", + "Requirement already satisfied: numpy<2,>=1.22.4; python_version < \"3.11\" in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas) (1.26.3)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas) (2023.3.post1)\n", + "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas) (2023.4)\n", + "Requirement already satisfied: six>=1.5 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: You are using pip version 20.2.3; however, version 23.3.2 is available.\n", + "You should consider upgrading via the 'c:\\Users\\Matthew Chuang\\Documents\\Github\\NUS-SDS-Datathon-Singlife\\venv\\Scripts\\python.exe -m pip install --upgrade pip' command.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: matplotlib in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (3.8.2)\n", + "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (1.2.0)\n", + "Requirement already satisfied: pillow>=8 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (10.2.0)\n", + "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (3.1.1)\n", + "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (1.4.5)\n", + "Requirement already satisfied: importlib-resources>=3.2.0; python_version < \"3.10\" in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (6.1.1)\n", + "Requirement already satisfied: cycler>=0.10 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (0.12.1)\n", + "Requirement already satisfied: numpy<2,>=1.21 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (1.26.3)\n", + "Requirement already satisfied: packaging>=20.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (23.2)\n", + "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (4.47.2)\n", + "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from matplotlib) (2.8.2)\n", + "Requirement already satisfied: zipp>=3.1.0; python_version < \"3.10\" in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from importlib-resources>=3.2.0; python_version < \"3.10\"->matplotlib) (3.17.0)\n", + "Requirement already satisfied: six>=1.5 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from python-dateutil>=2.7->matplotlib) (1.16.0)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: You are using pip version 20.2.3; however, version 23.3.2 is available.\n", + "You should consider upgrading via the 'c:\\Users\\Matthew Chuang\\Documents\\Github\\NUS-SDS-Datathon-Singlife\\venv\\Scripts\\python.exe -m pip install --upgrade pip' command.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: pyarrow in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (15.0.0)\n", + "Requirement already satisfied: numpy<2,>=1.16.6 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pyarrow) (1.26.3)\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "WARNING: You are using pip version 20.2.3; however, version 23.3.2 is available.\n", + "You should consider upgrading via the 'c:\\Users\\Matthew Chuang\\Documents\\Github\\NUS-SDS-Datathon-Singlife\\venv\\Scripts\\python.exe -m pip install --upgrade pip' command.\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Requirement already satisfied: fastparquet in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (2023.10.1)\n", + "Requirement already satisfied: numpy>=1.20.3 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from fastparquet) (1.26.3)\n", + "Requirement already satisfied: pandas>=1.5.0 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from fastparquet) (2.2.0)\n", + "Requirement already satisfied: cramjam>=2.3 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from fastparquet) (2.8.1)\n", + "Requirement already satisfied: fsspec in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from fastparquet) (2023.12.2)\n", + "Requirement already satisfied: packaging in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from fastparquet) (23.2)\n", + "Requirement already satisfied: pytz>=2020.1 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas>=1.5.0->fastparquet) (2023.3.post1)\n", + "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas>=1.5.0->fastparquet) (2023.4)\n", + "Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from pandas>=1.5.0->fastparquet) (2.8.2)\n", + "Requirement already satisfied: six>=1.5 in c:\\users\\matthew chuang\\documents\\github\\nus-sds-datathon-singlife\\venv\\lib\\site-packages (from python-dateutil>=2.8.2->pandas>=1.5.0->fastparquet) (1.16.0)\n", "Note: you may need to restart the kernel to use updated packages.\n" ] }, @@ -60,7 +148,9 @@ "%pip install xgboost\n", "%pip install scikit-learn\n", "%pip install pandas \n", - "%pip install matplotlib" + "%pip install matplotlib\n", + "%pip install pyarrow\n", + "%pip install fastparquet" ] }, { @@ -74,7 +164,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 182, "metadata": {}, "outputs": [], "source": [ @@ -82,6 +172,8 @@ "import pandas as pd\n", "from datetime import datetime\n", "from sklearn.preprocessing import LabelEncoder\n", + "import pyarrow\n", + "import fastparquet\n", "\n", "# Filepath\n", "filepath = \"./data/catB_train.csv\" " @@ -98,7 +190,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 183, "metadata": {}, "outputs": [ { @@ -2234,96 +2326,2695 @@ "3 0.0 0 0 0 0 \n", "4 348.0 0 0 0 0 \n", "\n", - " f_hold_c4bda5 f_hold_ltc f_hold_507c37 f_hold_gi sumins_839f8a \\\n", - "0 0 1 0 0 0 \n", - "1 0 0 0 0 0 \n", - "2 0 0 0 0 0 \n", - "3 0 0 0 0 0 \n", - "4 0 0 1 0 0 \n", + " f_hold_c4bda5 f_hold_ltc f_hold_507c37 f_hold_gi sumins_839f8a \\\n", + "0 0 1 0 0 0 \n", + "1 0 0 0 0 0 \n", + "2 0 0 0 0 0 \n", + "3 0 0 0 0 0 \n", + "4 0 0 1 0 0 \n", + "\n", + " sumins_e22a6a sumins_d0adeb sumins_c4bda5 sumins_ltc sumins_507c37 \\\n", + "0 0 0 0.0 700 0.0 \n", + "1 0 0 0.0 0 0.0 \n", + "2 0 0 0.0 0 0.0 \n", + "3 0 0 0.0 0 0.0 \n", + "4 0 0 0.0 0 400000.0 \n", + "\n", + " sumins_gi prempaid_839f8a prempaid_e22a6a prempaid_d0adeb \\\n", + "0 0 0.0 16854.0 0 \n", + "1 0 0.0 0.0 0 \n", + "2 0 0.0 0.0 0 \n", + "3 0 0.0 0.0 0 \n", + "4 0 0.0 0.0 0 \n", + "\n", + " prempaid_c4bda5 prempaid_ltc prempaid_507c37 prempaid_gi \\\n", + "0 0.0 29203.0 0.0 0 \n", + "1 0.0 0.0 0.0 0 \n", + "2 0.0 0.0 0.0 0 \n", + "3 0.0 0.0 0.0 0 \n", + "4 0.0 0.0 18444.0 0 \n", + "\n", + " lapse_ape_ltc_1280bf lapse_ape_grp_6fc3e6 lapse_ape_grp_de05ae \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_inv_dcd836 lapse_ape_grp_945b5a lapse_ape_grp_6a5788 \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_ltc_43b9d5 lapse_ape_grp_9cdedf lapse_ape_lh_d0adeb \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_grp_1581d7 lapse_ape_grp_22decf lapse_ape_lh_507c37 \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_lh_839f8a lapse_ape_inv_e9f316 lapse_ape_grp_caa6ff \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_grp_fd3bfb lapse_ape_lh_e22a6a lapse_ape_grp_70e1dd \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 601.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_grp_e04c3a lapse_ape_grp_fe5fb8 lapse_ape_grp_94baec \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_grp_e91421 lapse_ape_lh_f852af lapse_ape_lh_947b15 \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_32c74c n_months_since_lapse_ltc_1280bf \\\n", + "0 0.0 9999.0 \n", + "1 0.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_6fc3e6 n_months_since_lapse_grp_de05ae \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_inv_dcd836 n_months_since_lapse_grp_945b5a \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_6a5788 n_months_since_lapse_ltc_43b9d5 \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_9cdedf n_months_since_lapse_lh_d0adeb \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_1581d7 n_months_since_lapse_grp_22decf \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_lh_507c37 n_months_since_lapse_lh_839f8a \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_inv_e9f316 n_months_since_lapse_grp_caa6ff \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_fd3bfb n_months_since_lapse_lh_e22a6a \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 53.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_70e1dd n_months_since_lapse_grp_e04c3a \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_fe5fb8 n_months_since_lapse_grp_94baec \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_grp_e91421 n_months_since_lapse_lh_f852af \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " n_months_since_lapse_lh_947b15 n_months_since_lapse_32c74c \\\n", + "0 9999.0 9999.0 \n", + "1 9999.0 9999.0 \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " f_ever_bought_839f8a f_ever_bought_e22a6a f_ever_bought_d0adeb \\\n", + "0 0 1 0 \n", + "1 0 1 0 \n", + "2 0 0 0 \n", + "3 0 0 0 \n", + "4 0 0 0 \n", + "\n", + " f_ever_bought_c4bda5 f_ever_bought_ltc f_ever_bought_507c37 \\\n", + "0 0 1 0 \n", + "1 0 0 0 \n", + "2 0 0 0 \n", + "3 0 0 0 \n", + "4 0 0 1 \n", + "\n", + " f_ever_bought_gi n_months_last_bought_839f8a n_months_last_bought_e22a6a \\\n", + "0 0 9999 1 \n", + "1 0 9999 140 \n", + "2 0 9999 9999 \n", + "3 0 9999 9999 \n", + "4 0 9999 9999 \n", + "\n", + " n_months_last_bought_d0adeb n_months_last_bought_c4bda5 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_ltc n_months_last_bought_507c37 \\\n", + "0 6 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 62 \n", + "\n", + " n_months_last_bought_gi f_ever_bought_ltc_1280bf \\\n", + "0 9999 0 \n", + "1 9999 0 \n", + "2 9999 0 \n", + "3 9999 0 \n", + "4 9999 0 \n", + "\n", + " f_ever_bought_grp_6fc3e6 f_ever_bought_grp_de05ae \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_inv_dcd836 f_ever_bought_grp_945b5a \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_grp_6a5788 f_ever_bought_ltc_43b9d5 \\\n", + "0 0 1 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_grp_9cdedf f_ever_bought_lh_d0adeb \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_grp_1581d7 f_ever_bought_grp_22decf \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_lh_507c37 f_ever_bought_lh_839f8a f_ever_bought_inv_e9f316 \\\n", + "0 0 0 0 \n", + "1 0 0 0 \n", + "2 0 0 0 \n", + "3 0 0 0 \n", + "4 1 0 0 \n", + "\n", + " f_ever_bought_grp_caa6ff f_ever_bought_grp_fd3bfb \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_lh_e22a6a f_ever_bought_grp_70e1dd \\\n", + "0 1 0 \n", + "1 1 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_grp_e04c3a f_ever_bought_grp_fe5fb8 \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_grp_94baec f_ever_bought_grp_e91421 \\\n", + "0 0 0 \n", + "1 0 0 \n", + "2 0 0 \n", + "3 0 0 \n", + "4 0 0 \n", + "\n", + " f_ever_bought_lh_f852af f_ever_bought_lh_947b15 f_ever_bought_32c74c \\\n", + "0 0 0 0 \n", + "1 0 0 0 \n", + "2 0 0 0 \n", + "3 0 0 0 \n", + "4 0 0 0 \n", + "\n", + " n_months_last_bought_ltc_1280bf n_months_last_bought_grp_6fc3e6 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_grp_de05ae n_months_last_bought_inv_dcd836 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_grp_945b5a n_months_last_bought_grp_6a5788 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_ltc_43b9d5 n_months_last_bought_grp_9cdedf \\\n", + "0 6 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_lh_d0adeb n_months_last_bought_grp_1581d7 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_grp_22decf n_months_last_bought_lh_507c37 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 62 \n", + "\n", + " n_months_last_bought_lh_839f8a n_months_last_bought_inv_e9f316 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_grp_caa6ff n_months_last_bought_grp_fd3bfb \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_lh_e22a6a n_months_last_bought_grp_70e1dd \\\n", + "0 1 9999 \n", + "1 140 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_grp_e04c3a n_months_last_bought_grp_fe5fb8 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_grp_94baec n_months_last_bought_grp_e91421 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_lh_f852af n_months_last_bought_lh_947b15 \\\n", + "0 9999 9999 \n", + "1 9999 9999 \n", + "2 9999 9999 \n", + "3 9999 9999 \n", + "4 9999 9999 \n", + "\n", + " n_months_last_bought_32c74c f_elx f_mindef_mha f_retail \\\n", + "0 9999 0 0 1 \n", + "1 9999 0 0 1 \n", + "2 9999 0 0 1 \n", + "3 9999 0 0 1 \n", + "4 9999 0 0 1 \n", + "\n", + " flg_affconnect_show_interest_ever flg_affconnect_ready_to_buy_ever \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " flg_affconnect_lapse_ever affcon_visit_days n_months_since_visit_affcon \\\n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " clmcon_visit_days recency_clmcon recency_clmcon_regis hlthclaim_amt \\\n", + "0 NaN NaN NaN NaN \n", + "1 NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN \n", + "4 NaN NaN NaN NaN \n", + "\n", + " recency_hlthclaim hlthclaim_cnt_success recency_hlthclaim_success \\\n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " hlthclaim_cnt_unsuccess recency_hlthclaim_unsuccess \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " flg_hlthclaim_839f8a_ever recency_hlthclaim_839f8a \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " flg_hlthclaim_14cb37_ever recency_hlthclaim_14cb37 giclaim_amt \\\n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " recency_giclaim giclaim_cnt_success recency_giclaim_success \\\n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " giclaim_cnt_unsuccess recency_giclaim_unsuccess flg_gi_claim_29d435_ever \\\n", + "0 NaN NaN NaN \n", + "1 NaN NaN NaN \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " flg_gi_claim_058815_ever flg_gi_claim_42e115_ever \\\n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN \n", + "\n", + " flg_gi_claim_856320_ever f_purchase_lh \n", + "0 NaN NaN \n", + "1 NaN NaN \n", + "2 NaN NaN \n", + "3 NaN NaN \n", + "4 NaN NaN " + ] + }, + "execution_count": 183, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# read data\n", + "df = pd.read_csv(filepath)\n", + "\n", + "# display first five rows\n", + "pd.set_option('display.max_columns', None)\n", + "df.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Clean data group \"General Client Information\"\n", + "- Dropped cols \"Unnamed 0\", \"clntnum\" overfitting\n", + "- Dropped cols \"ctrcycode_desc\", \"clttype\" zero variance when certain blank rows are removed\n", + "- Dropped blanks rows from \"race_desc\", \"cltdob_fix\"\n", + "- Generation of feature \"age\", removal of original \"cltdob_fix\"" + ] + }, + { + "cell_type": "code", + "execution_count": 184, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Initial Number of Cols: 305 \n", + "Initial Number of Rows: 17992\n", + "Rows dropped: 3997\n", + "New Number of Cols: 301 \n", + "New Number of Rows: 13995\n" + ] + }, + { + "data": { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
flg_substandardflg_is_borderline_standardflg_is_revised_termflg_is_rental_flatflg_has_health_claimflg_has_life_claimflg_gi_claimflg_is_proposalflg_with_preauthorisationflg_is_returned_mailis_consent_to_mailis_consent_to_emailis_consent_to_callis_consent_to_smsis_valid_dmis_valid_emailis_housewife_retireeis_sg_pris_class_1_2is_dependent_in_at_least_1_policyf_ever_declined_lahh_20pop_20hh_sizehh_size_estannual_income_estn_months_last_bought_productsflg_latest_being_lapseflg_latest_being_cancelrecency_lapserecency_canceltot_inforce_polstot_cancel_polsape_gi_42e115ape_ltc_1280bfape_grp_6fc3e6ape_grp_de05aeape_inv_dcd836ape_grp_945b5aape_grp_6a5788ape_ltc_43b9d5ape_grp_9cdedfape_lh_d0adebape_grp_1581d7ape_grp_22decfape_lh_507c37ape_lh_839f8aape_inv_e9f316ape_gi_a10d1bape_gi_29d435ape_grp_caa6ffape_grp_fd3bfbape_lh_e22a6aape_grp_70e1ddape_grp_e04c3aape_grp_fe5fb8ape_gi_856320ape_grp_94baecape_gi_058815ape_grp_e91421ape_lh_f852afape_lh_947b15ape_32c74csumins_gi_42e115sumins_ltc_1280bfsumins_grp_6fc3e6sumins_grp_de05aesumins_inv_dcd836sumins_grp_945b5asumins_grp_6a5788sumins_ltc_43b9d5sumins_grp_9cdedfsumins_lh_d0adebsumins_grp_1581d7sumins_grp_22decfsumins_lh_507c37sumins_inv_e9f316sumins_gi_a10d1bsumins_gi_29d435sumins_grp_caa6ffsumins_grp_fd3bfbsumins_lh_e22a6asumins_grp_70e1ddsumins_grp_e04c3asumins_grp_fe5fb8sumins_gi_856320sumins_grp_94baecsumins_gi_058815sumins_grp_e91421sumins_lh_f852afsumins_lh_947b15sumins_32c74cprempaid_gi_42e115prempaid_ltc_1280bfprempaid_grp_6fc3e6prempaid_grp_de05aeprempaid_inv_dcd836prempaid_grp_945b5aprempaid_grp_6a5788prempaid_ltc_43b9d5prempaid_grp_9cdedfprempaid_lh_d0adebprempaid_grp_1581d7prempaid_grp_22decfprempaid_lh_507c37prempaid_lh_839f8aprempaid_inv_e9f316prempaid_gi_a10d1bprempaid_gi_29d435prempaid_grp_caa6ffprempaid_grp_fd3bfbprempaid_lh_e22a6aprempaid_grp_70e1ddprempaid_grp_e04c3aprempaid_grp_fe5fb8prempaid_gi_856320prempaid_grp_94baecprempaid_gi_058815prempaid_grp_e91421prempaid_lh_f852afprempaid_lh_947b15prempaid_32c74cape_839f8aape_e22a6aape_d0adebape_c4bda5ape_ltcape_507c37ape_gif_hold_839f8af_hold_e22a6af_hold_d0adebf_hold_c4bda5f_hold_ltcf_hold_507c37f_hold_gisumins_839f8asumins_e22a6asumins_d0adebsumins_c4bda5sumins_ltcsumins_507c37sumins_giprempaid_839f8aprempaid_e22a6aprempaid_d0adebprempaid_c4bda5prempaid_ltcprempaid_507c37prempaid_gilapse_ape_ltc_1280bflapse_ape_grp_6fc3e6lapse_ape_grp_de05aelapse_ape_inv_dcd836lapse_ape_grp_945b5alapse_ape_grp_6a5788lapse_ape_ltc_43b9d5lapse_ape_grp_9cdedflapse_ape_lh_d0adeblapse_ape_grp_1581d7lapse_ape_grp_22decflapse_ape_lh_507c37lapse_ape_lh_839f8alapse_ape_inv_e9f316lapse_ape_grp_caa6fflapse_ape_grp_fd3bfblapse_ape_lh_e22a6alapse_ape_grp_70e1ddlapse_ape_grp_e04c3alapse_ape_grp_fe5fb8lapse_ape_grp_94baeclapse_ape_grp_e91421lapse_ape_lh_f852aflapse_ape_lh_947b15lapse_ape_32c74cn_months_since_lapse_ltc_1280bfn_months_since_lapse_grp_6fc3e6n_months_since_lapse_grp_de05aen_months_since_lapse_inv_dcd836n_months_since_lapse_grp_945b5an_months_since_lapse_grp_6a5788n_months_since_lapse_ltc_43b9d5n_months_since_lapse_grp_9cdedfn_months_since_lapse_lh_d0adebn_months_since_lapse_grp_1581d7n_months_since_lapse_grp_22decfn_months_since_lapse_lh_507c37n_months_since_lapse_lh_839f8an_months_since_lapse_inv_e9f316n_months_since_lapse_grp_caa6ffn_months_since_lapse_grp_fd3bfbn_months_since_lapse_lh_e22a6an_months_since_lapse_grp_70e1ddn_months_since_lapse_grp_e04c3an_months_since_lapse_grp_fe5fb8n_months_since_lapse_grp_94baecn_months_since_lapse_grp_e91421n_months_since_lapse_lh_f852afn_months_since_lapse_lh_947b15n_months_since_lapse_32c74cf_ever_bought_839f8af_ever_bought_e22a6af_ever_bought_d0adebf_ever_bought_c4bda5f_ever_bought_ltcf_ever_bought_507c37f_ever_bought_gin_months_last_bought_839f8an_months_last_bought_e22a6an_months_last_bought_d0adebn_months_last_bought_c4bda5n_months_last_bought_ltcn_months_last_bought_507c37n_months_last_bought_gif_ever_bought_ltc_1280bff_ever_bought_grp_6fc3e6f_ever_bought_grp_de05aef_ever_bought_inv_dcd836f_ever_bought_grp_945b5af_ever_bought_grp_6a5788f_ever_bought_ltc_43b9d5f_ever_bought_grp_9cdedff_ever_bought_lh_d0adebf_ever_bought_grp_1581d7f_ever_bought_grp_22decff_ever_bought_lh_507c37f_ever_bought_lh_839f8af_ever_bought_inv_e9f316f_ever_bought_grp_caa6fff_ever_bought_grp_fd3bfbf_ever_bought_lh_e22a6af_ever_bought_grp_70e1ddf_ever_bought_grp_e04c3af_ever_bought_grp_fe5fb8f_ever_bought_grp_94baecf_ever_bought_grp_e91421f_ever_bought_lh_f852aff_ever_bought_lh_947b15f_ever_bought_32c74cn_months_last_bought_ltc_1280bfn_months_last_bought_grp_6fc3e6n_months_last_bought_grp_de05aen_months_last_bought_inv_dcd836n_months_last_bought_grp_945b5an_months_last_bought_grp_6a5788n_months_last_bought_ltc_43b9d5n_months_last_bought_grp_9cdedfn_months_last_bought_lh_d0adebn_months_last_bought_grp_1581d7n_months_last_bought_grp_22decfn_months_last_bought_lh_507c37n_months_last_bought_lh_839f8an_months_last_bought_inv_e9f316n_months_last_bought_grp_caa6ffn_months_last_bought_grp_fd3bfbn_months_last_bought_lh_e22a6an_months_last_bought_grp_70e1ddn_months_last_bought_grp_e04c3an_months_last_bought_grp_fe5fb8n_months_last_bought_grp_94baecn_months_last_bought_grp_e91421n_months_last_bought_lh_f852afn_months_last_bought_lh_947b15n_months_last_bought_32c74cf_elxf_mindef_mhaf_retailflg_affconnect_show_interest_everflg_affconnect_ready_to_buy_everflg_affconnect_lapse_everaffcon_visit_daysn_months_since_visit_affconclmcon_visit_daysrecency_clmconrecency_clmcon_regishlthclaim_amtrecency_hlthclaimhlthclaim_cnt_successrecency_hlthclaim_successhlthclaim_cnt_unsuccessrecency_hlthclaim_unsuccessflg_hlthclaim_839f8a_everrecency_hlthclaim_839f8aflg_hlthclaim_14cb37_everrecency_hlthclaim_14cb37giclaim_amtrecency_giclaimgiclaim_cnt_successrecency_giclaim_successgiclaim_cnt_unsuccessrecency_giclaim_unsuccessflg_gi_claim_29d435_everflg_gi_claim_058815_everflg_gi_claim_42e115_everflg_gi_claim_856320_everf_purchase_lhageyears_since_first_interactionstat_flag_encodedcltsex_encodedrace_desc_encoded
00.00.00.00.00.00.00.00.00.00.00.00.00.00.01.01.00.01.01.00.0NaN144.0202.01.4027781C.60K-100K10029.0NaN3NaN000.00.000.00.05510.000.00.00.000.0000.00.03180.00.00.000.000.00.00.000000000700000000.0000000.0000000000000.00.000.00.0292030.000.00.00.000.0000.00.0168540.00.00.000.000.00.00.000.0318.000.0551.00.0001001000000.07000.000.016854.000.029203.00.000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.00100100999919999999969999999900000010000000001000000009999999999999999999999996999999999999999999999999999999999999199999999999999999999999999999999001NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN496000
10.00.00.00.00.00.00.00.00.00.00.00.00.00.01.00.00.01.00.00.0NaN153.0480.03.1372553D.30K-60K4500140.0NaN1NaN000.00.000.00.000.000.00.00.000.0000.00.000.00.00.000.000.00.00.0000000000000000.0000000.0000000000000.00.000.00.000.000.00.00.000.0000.00.000.00.00.000.000.00.00.000.00.000.00.00.0000000000000.000.000.00.000.00.00.000.00.00.00.00.00.00.00.00.00.00.00.00.00.00.00.0601.00.00.00.00.00.00.00.00.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.09999.053.09999.09999.09999.09999.09999.09999.09999.09999.001000009999140999999999999999999990000000000000000100000000999999999999999999999999999999999999999999999999999999999999999914099999999999999999999999999999999001NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN4417010
20.00.00.00.00.00.00.00.00.00.01.01.00.00.01.01.00.01.01.00.0NaN62.0179.02.8870973A.ABOVE200K4700NaNNaN1NaN000.00.000.00.000.000.00.00.000.0000.00.000.00.00.000.000.00.00.0000000000000000.0000000.0000000000000.00.000.00.000.000.00.00.000.0000.00.000.00.00.000.000.00.00.000.00.000.00.00.0000000000000.000.000.00.000.00.00.00NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN0000000999999999999999999999999999900000000000000000000000009999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999001NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN484013
30.00.00.00.00.00.00.00.00.00.00.00.00.00.01.01.00.01.01.00.0NaN1.04.04.0000004B.100K-200K2200NaNNaN1NaN000.00.000.00.000.000.00.00.000.0000.00.000.00.00.000.000.00.00.0000000000000000.0000000.0000000000000.00.000.00.000.000.00.00.000.0000.00.000.00.00.000.000.00.00.000.00.000.00.00.0000000000000.000.000.00.000.00.00.00NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN0000000999999999999999999999999999900000000000000000000000009999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999999001NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN472000
40.00.00.00.00.00.00.00.00.00.01.01.00.01.01.01.00.01.01.00.0NaN114.0478.04.192982>4E.BELOW30K6200NaNNaN1NaN000.00.000.00.000.000.00.0348.000.0000.00.000.00.00.000.000.00.00.000000000000004000000.0000000.0000000000000.00.000.00.000.000.00.018444.000.0000.00.000.00.00.000.000.00.00.000.00.000.00.0348.0000000100000.00400000.000.00.000.00.018444.00NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN000001099999999999999999999629999000000000001000000000000099999999999999999999999999999999999999999999629999999999999999999999999999999999999999999999999999001NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN286000
\n", + "
" + ], + "text/plain": [ + " flg_substandard flg_is_borderline_standard flg_is_revised_term \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 0.0 0.0 0.0 \n", + "3 0.0 0.0 0.0 \n", + "4 0.0 0.0 0.0 \n", + "\n", + " flg_is_rental_flat flg_has_health_claim flg_has_life_claim flg_gi_claim \\\n", + "0 0.0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 0.0 \n", + "2 0.0 0.0 0.0 0.0 \n", + "3 0.0 0.0 0.0 0.0 \n", + "4 0.0 0.0 0.0 0.0 \n", + "\n", + " flg_is_proposal flg_with_preauthorisation flg_is_returned_mail \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 0.0 0.0 0.0 \n", + "3 0.0 0.0 0.0 \n", + "4 0.0 0.0 0.0 \n", + "\n", + " is_consent_to_mail is_consent_to_email is_consent_to_call \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 1.0 1.0 0.0 \n", + "3 0.0 0.0 0.0 \n", + "4 1.0 1.0 0.0 \n", + "\n", + " is_consent_to_sms is_valid_dm is_valid_email is_housewife_retiree \\\n", + "0 0.0 1.0 1.0 0.0 \n", + "1 0.0 1.0 0.0 0.0 \n", + "2 0.0 1.0 1.0 0.0 \n", + "3 0.0 1.0 1.0 0.0 \n", + "4 1.0 1.0 1.0 0.0 \n", + "\n", + " is_sg_pr is_class_1_2 is_dependent_in_at_least_1_policy \\\n", + "0 1.0 1.0 0.0 \n", + "1 1.0 0.0 0.0 \n", + "2 1.0 1.0 0.0 \n", + "3 1.0 1.0 0.0 \n", + "4 1.0 1.0 0.0 \n", + "\n", + " f_ever_declined_la hh_20 pop_20 hh_size hh_size_est annual_income_est \\\n", + "0 NaN 144.0 202.0 1.402778 1 C.60K-100K \n", + "1 NaN 153.0 480.0 3.137255 3 D.30K-60K \n", + "2 NaN 62.0 179.0 2.887097 3 A.ABOVE200K \n", + "3 NaN 1.0 4.0 4.000000 4 B.100K-200K \n", + "4 NaN 114.0 478.0 4.192982 >4 E.BELOW30K \n", + "\n", + " n_months_last_bought_products flg_latest_being_lapse \\\n", + "0 1 0 \n", + "1 45 0 \n", + "2 47 0 \n", + "3 22 0 \n", + "4 62 0 \n", + "\n", + " flg_latest_being_cancel recency_lapse recency_cancel tot_inforce_pols \\\n", + "0 0 29.0 NaN 3 \n", + "1 0 140.0 NaN 1 \n", + "2 0 NaN NaN 1 \n", + "3 0 NaN NaN 1 \n", + "4 0 NaN NaN 1 \n", + "\n", + " tot_cancel_pols ape_gi_42e115 ape_ltc_1280bf ape_grp_6fc3e6 \\\n", + "0 NaN 0 0 0.0 \n", + "1 NaN 0 0 0.0 \n", + "2 NaN 0 0 0.0 \n", + "3 NaN 0 0 0.0 \n", + "4 NaN 0 0 0.0 \n", + "\n", + " ape_grp_de05ae ape_inv_dcd836 ape_grp_945b5a ape_grp_6a5788 \\\n", + "0 0.0 0 0.0 0.0 \n", + "1 0.0 0 0.0 0.0 \n", + "2 0.0 0 0.0 0.0 \n", + "3 0.0 0 0.0 0.0 \n", + "4 0.0 0 0.0 0.0 \n", + "\n", + " ape_ltc_43b9d5 ape_grp_9cdedf ape_lh_d0adeb ape_grp_1581d7 \\\n", + "0 551 0.0 0 0.0 \n", + "1 0 0.0 0 0.0 \n", + "2 0 0.0 0 0.0 \n", + "3 0 0.0 0 0.0 \n", + "4 0 0.0 0 0.0 \n", + "\n", + " ape_grp_22decf ape_lh_507c37 ape_lh_839f8a ape_inv_e9f316 \\\n", + "0 0.0 0.0 0 0.0 \n", + "1 0.0 0.0 0 0.0 \n", + "2 0.0 0.0 0 0.0 \n", + "3 0.0 0.0 0 0.0 \n", + "4 0.0 348.0 0 0.0 \n", + "\n", + " ape_gi_a10d1b ape_gi_29d435 ape_grp_caa6ff ape_grp_fd3bfb \\\n", + "0 0 0 0.0 0.0 \n", + "1 0 0 0.0 0.0 \n", + "2 0 0 0.0 0.0 \n", + "3 0 0 0.0 0.0 \n", + "4 0 0 0.0 0.0 \n", + "\n", + " ape_lh_e22a6a ape_grp_70e1dd ape_grp_e04c3a ape_grp_fe5fb8 \\\n", + "0 318 0.0 0.0 0.0 \n", + "1 0 0.0 0.0 0.0 \n", + "2 0 0.0 0.0 0.0 \n", + "3 0 0.0 0.0 0.0 \n", + "4 0 0.0 0.0 0.0 \n", + "\n", + " ape_gi_856320 ape_grp_94baec ape_gi_058815 ape_grp_e91421 \\\n", + "0 0 0.0 0 0.0 \n", + "1 0 0.0 0 0.0 \n", + "2 0 0.0 0 0.0 \n", + "3 0 0.0 0 0.0 \n", + "4 0 0.0 0 0.0 \n", + "\n", + " ape_lh_f852af ape_lh_947b15 ape_32c74c sumins_gi_42e115 \\\n", + "0 0.0 0.0 0 0 \n", + "1 0.0 0.0 0 0 \n", + "2 0.0 0.0 0 0 \n", + "3 0.0 0.0 0 0 \n", + "4 0.0 0.0 0 0 \n", + "\n", + " sumins_ltc_1280bf sumins_grp_6fc3e6 sumins_grp_de05ae sumins_inv_dcd836 \\\n", + "0 0 0 0 0 \n", + "1 0 0 0 0 \n", + "2 0 0 0 0 \n", + "3 0 0 0 0 \n", + "4 0 0 0 0 \n", + "\n", + " sumins_grp_945b5a sumins_grp_6a5788 sumins_ltc_43b9d5 sumins_grp_9cdedf \\\n", + "0 0 0 700 0 \n", + "1 0 0 0 0 \n", + "2 0 0 0 0 \n", + "3 0 0 0 0 \n", + "4 0 0 0 0 \n", + "\n", + " sumins_lh_d0adeb sumins_grp_1581d7 sumins_grp_22decf sumins_lh_507c37 \\\n", + "0 0 0 0 0 \n", + "1 0 0 0 0 \n", + "2 0 0 0 0 \n", + "3 0 0 0 0 \n", + "4 0 0 0 400000 \n", + "\n", + " sumins_inv_e9f316 sumins_gi_a10d1b sumins_gi_29d435 sumins_grp_caa6ff \\\n", + "0 0.0 0 0 0 \n", + "1 0.0 0 0 0 \n", + "2 0.0 0 0 0 \n", + "3 0.0 0 0 0 \n", + "4 0.0 0 0 0 \n", + "\n", + " sumins_grp_fd3bfb sumins_lh_e22a6a sumins_grp_70e1dd sumins_grp_e04c3a \\\n", + "0 0 0 0.0 0 \n", + "1 0 0 0.0 0 \n", + "2 0 0 0.0 0 \n", + "3 0 0 0.0 0 \n", + "4 0 0 0.0 0 \n", + "\n", + " sumins_grp_fe5fb8 sumins_gi_856320 sumins_grp_94baec sumins_gi_058815 \\\n", + "0 0 0 0 0 \n", + "1 0 0 0 0 \n", + "2 0 0 0 0 \n", + "3 0 0 0 0 \n", + "4 0 0 0 0 \n", + "\n", + " sumins_grp_e91421 sumins_lh_f852af sumins_lh_947b15 sumins_32c74c \\\n", + "0 0 0 0 0 \n", + "1 0 0 0 0 \n", + "2 0 0 0 0 \n", + "3 0 0 0 0 \n", + "4 0 0 0 0 \n", + "\n", + " prempaid_gi_42e115 prempaid_ltc_1280bf prempaid_grp_6fc3e6 \\\n", + "0 0 0 0.0 \n", + "1 0 0 0.0 \n", + "2 0 0 0.0 \n", + "3 0 0 0.0 \n", + "4 0 0 0.0 \n", + "\n", + " prempaid_grp_de05ae prempaid_inv_dcd836 prempaid_grp_945b5a \\\n", + "0 0.0 0 0.0 \n", + "1 0.0 0 0.0 \n", + "2 0.0 0 0.0 \n", + "3 0.0 0 0.0 \n", + "4 0.0 0 0.0 \n", + "\n", + " prempaid_grp_6a5788 prempaid_ltc_43b9d5 prempaid_grp_9cdedf \\\n", + "0 0.0 29203 0.0 \n", + "1 0.0 0 0.0 \n", + "2 0.0 0 0.0 \n", + "3 0.0 0 0.0 \n", + "4 0.0 0 0.0 \n", + "\n", + " prempaid_lh_d0adeb prempaid_grp_1581d7 prempaid_grp_22decf \\\n", + "0 0 0.0 0.0 \n", + "1 0 0.0 0.0 \n", + "2 0 0.0 0.0 \n", + "3 0 0.0 0.0 \n", + "4 0 0.0 0.0 \n", + "\n", + " prempaid_lh_507c37 prempaid_lh_839f8a prempaid_inv_e9f316 \\\n", + "0 0.0 0 0.0 \n", + "1 0.0 0 0.0 \n", + "2 0.0 0 0.0 \n", + "3 0.0 0 0.0 \n", + "4 18444.0 0 0.0 \n", + "\n", + " prempaid_gi_a10d1b prempaid_gi_29d435 prempaid_grp_caa6ff \\\n", + "0 0 0 0.0 \n", + "1 0 0 0.0 \n", + "2 0 0 0.0 \n", + "3 0 0 0.0 \n", + "4 0 0 0.0 \n", + "\n", + " prempaid_grp_fd3bfb prempaid_lh_e22a6a prempaid_grp_70e1dd \\\n", + "0 0.0 16854 0.0 \n", + "1 0.0 0 0.0 \n", + "2 0.0 0 0.0 \n", + "3 0.0 0 0.0 \n", + "4 0.0 0 0.0 \n", + "\n", + " prempaid_grp_e04c3a prempaid_grp_fe5fb8 prempaid_gi_856320 \\\n", + "0 0.0 0.0 0 \n", + "1 0.0 0.0 0 \n", + "2 0.0 0.0 0 \n", + "3 0.0 0.0 0 \n", + "4 0.0 0.0 0 \n", + "\n", + " prempaid_grp_94baec prempaid_gi_058815 prempaid_grp_e91421 \\\n", + "0 0.0 0 0.0 \n", + "1 0.0 0 0.0 \n", + "2 0.0 0 0.0 \n", + "3 0.0 0 0.0 \n", + "4 0.0 0 0.0 \n", + "\n", + " prempaid_lh_f852af prempaid_lh_947b15 prempaid_32c74c ape_839f8a \\\n", + "0 0.0 0.0 0 0.0 \n", + "1 0.0 0.0 0 0.0 \n", + "2 0.0 0.0 0 0.0 \n", + "3 0.0 0.0 0 0.0 \n", + "4 0.0 0.0 0 0.0 \n", + "\n", + " ape_e22a6a ape_d0adeb ape_c4bda5 ape_ltc ape_507c37 ape_gi \\\n", + "0 318.0 0 0.0 551.0 0.0 0 \n", + "1 0.0 0 0.0 0.0 0.0 0 \n", + "2 0.0 0 0.0 0.0 0.0 0 \n", + "3 0.0 0 0.0 0.0 0.0 0 \n", + "4 0.0 0 0.0 0.0 348.0 0 \n", + "\n", + " f_hold_839f8a f_hold_e22a6a f_hold_d0adeb f_hold_c4bda5 f_hold_ltc \\\n", + "0 0 1 0 0 1 \n", + "1 0 0 0 0 0 \n", + "2 0 0 0 0 0 \n", + "3 0 0 0 0 0 \n", + "4 0 0 0 0 0 \n", + "\n", + " f_hold_507c37 f_hold_gi sumins_839f8a sumins_e22a6a sumins_d0adeb \\\n", + "0 0 0 0 0 0 \n", + "1 0 0 0 0 0 \n", + "2 0 0 0 0 0 \n", + "3 0 0 0 0 0 \n", + "4 1 0 0 0 0 \n", "\n", - " sumins_e22a6a sumins_d0adeb sumins_c4bda5 sumins_ltc sumins_507c37 \\\n", - "0 0 0 0.0 700 0.0 \n", - "1 0 0 0.0 0 0.0 \n", - "2 0 0 0.0 0 0.0 \n", - "3 0 0 0.0 0 0.0 \n", - "4 0 0 0.0 0 400000.0 \n", + " sumins_c4bda5 sumins_ltc sumins_507c37 sumins_gi prempaid_839f8a \\\n", + "0 0.0 700 0.0 0 0.0 \n", + "1 0.0 0 0.0 0 0.0 \n", + "2 0.0 0 0.0 0 0.0 \n", + "3 0.0 0 0.0 0 0.0 \n", + "4 0.0 0 400000.0 0 0.0 \n", "\n", - " sumins_gi prempaid_839f8a prempaid_e22a6a prempaid_d0adeb \\\n", - "0 0 0.0 16854.0 0 \n", - "1 0 0.0 0.0 0 \n", - "2 0 0.0 0.0 0 \n", - "3 0 0.0 0.0 0 \n", - "4 0 0.0 0.0 0 \n", + " prempaid_e22a6a prempaid_d0adeb prempaid_c4bda5 prempaid_ltc \\\n", + "0 16854.0 0 0.0 29203.0 \n", + "1 0.0 0 0.0 0.0 \n", + "2 0.0 0 0.0 0.0 \n", + "3 0.0 0 0.0 0.0 \n", + "4 0.0 0 0.0 0.0 \n", "\n", - " prempaid_c4bda5 prempaid_ltc prempaid_507c37 prempaid_gi \\\n", - "0 0.0 29203.0 0.0 0 \n", - "1 0.0 0.0 0.0 0 \n", - "2 0.0 0.0 0.0 0 \n", - "3 0.0 0.0 0.0 0 \n", - "4 0.0 0.0 18444.0 0 \n", + " prempaid_507c37 prempaid_gi lapse_ape_ltc_1280bf lapse_ape_grp_6fc3e6 \\\n", + "0 0.0 0 0.0 0.0 \n", + "1 0.0 0 0.0 0.0 \n", + "2 0.0 0 NaN NaN \n", + "3 0.0 0 NaN NaN \n", + "4 18444.0 0 NaN NaN \n", "\n", - " lapse_ape_ltc_1280bf lapse_ape_grp_6fc3e6 lapse_ape_grp_de05ae \\\n", + " lapse_ape_grp_de05ae lapse_ape_inv_dcd836 lapse_ape_grp_945b5a \\\n", "0 0.0 0.0 0.0 \n", "1 0.0 0.0 0.0 \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", "\n", - " lapse_ape_inv_dcd836 lapse_ape_grp_945b5a lapse_ape_grp_6a5788 \\\n", + " lapse_ape_grp_6a5788 lapse_ape_ltc_43b9d5 lapse_ape_grp_9cdedf \\\n", "0 0.0 0.0 0.0 \n", "1 0.0 0.0 0.0 \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", "\n", - " lapse_ape_ltc_43b9d5 lapse_ape_grp_9cdedf lapse_ape_lh_d0adeb \\\n", - "0 0.0 0.0 0.0 \n", - "1 0.0 0.0 0.0 \n", - "2 NaN NaN NaN \n", - "3 NaN NaN NaN \n", - "4 NaN NaN NaN \n", - "\n", - " lapse_ape_grp_1581d7 lapse_ape_grp_22decf lapse_ape_lh_507c37 \\\n", - "0 0.0 0.0 0.0 \n", - "1 0.0 0.0 0.0 \n", - "2 NaN NaN NaN \n", - "3 NaN NaN NaN \n", - "4 NaN NaN NaN \n", - "\n", - " lapse_ape_lh_839f8a lapse_ape_inv_e9f316 lapse_ape_grp_caa6ff \\\n", + " lapse_ape_lh_d0adeb lapse_ape_grp_1581d7 lapse_ape_grp_22decf \\\n", "0 0.0 0.0 0.0 \n", "1 0.0 0.0 0.0 \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", "\n", - " lapse_ape_grp_fd3bfb lapse_ape_lh_e22a6a lapse_ape_grp_70e1dd \\\n", - "0 0.0 0.0 0.0 \n", - "1 0.0 601.0 0.0 \n", - "2 NaN NaN NaN \n", - "3 NaN NaN NaN \n", - "4 NaN NaN NaN \n", + " lapse_ape_lh_507c37 lapse_ape_lh_839f8a lapse_ape_inv_e9f316 \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", "\n", - " lapse_ape_grp_e04c3a lapse_ape_grp_fe5fb8 lapse_ape_grp_94baec \\\n", + " lapse_ape_grp_caa6ff lapse_ape_grp_fd3bfb lapse_ape_lh_e22a6a \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 601.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", + "\n", + " lapse_ape_grp_70e1dd lapse_ape_grp_e04c3a lapse_ape_grp_fe5fb8 \\\n", "0 0.0 0.0 0.0 \n", "1 0.0 0.0 0.0 \n", "2 NaN NaN NaN \n", "3 NaN NaN NaN \n", "4 NaN NaN NaN \n", "\n", - " lapse_ape_grp_e91421 lapse_ape_lh_f852af lapse_ape_lh_947b15 \\\n", - "0 0.0 0.0 0.0 \n", - "1 0.0 0.0 0.0 \n", - "2 NaN NaN NaN \n", - "3 NaN NaN NaN \n", - "4 NaN NaN NaN \n", + " lapse_ape_grp_94baec lapse_ape_grp_e91421 lapse_ape_lh_f852af \\\n", + "0 0.0 0.0 0.0 \n", + "1 0.0 0.0 0.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", "\n", - " lapse_ape_32c74c n_months_since_lapse_ltc_1280bf \\\n", - "0 0.0 9999.0 \n", - "1 0.0 9999.0 \n", - "2 NaN NaN \n", - "3 NaN NaN \n", - "4 NaN NaN \n", + " lapse_ape_lh_947b15 lapse_ape_32c74c n_months_since_lapse_ltc_1280bf \\\n", + "0 0.0 0.0 9999.0 \n", + "1 0.0 0.0 9999.0 \n", + "2 NaN NaN NaN \n", + "3 NaN NaN NaN \n", + "4 NaN NaN NaN \n", "\n", " n_months_since_lapse_grp_6fc3e6 n_months_since_lapse_grp_de05ae \\\n", "0 9999.0 9999.0 \n", @@ -2689,72 +5380,34 @@ "3 NaN NaN \n", "4 NaN NaN \n", "\n", - " flg_gi_claim_856320_ever f_purchase_lh \n", - "0 NaN NaN \n", - "1 NaN NaN \n", - "2 NaN NaN \n", - "3 NaN NaN \n", - "4 NaN NaN " + " flg_gi_claim_856320_ever f_purchase_lh age \\\n", + "0 NaN NaN 49 \n", + "1 NaN NaN 44 \n", + "2 NaN NaN 48 \n", + "3 NaN NaN 47 \n", + "4 NaN NaN 28 \n", + "\n", + " years_since_first_interaction stat_flag_encoded cltsex_encoded \\\n", + "0 6 0 0 \n", + "1 17 0 1 \n", + "2 4 0 1 \n", + "3 2 0 0 \n", + "4 6 0 0 \n", + "\n", + " race_desc_encoded \n", + "0 0 \n", + "1 0 \n", + "2 3 \n", + "3 0 \n", + "4 0 " ] }, - "execution_count": 36, + "execution_count": 184, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# read data\n", - "df = pd.read_csv(filepath)\n", - "\n", - "# display first five rows\n", - "pd.set_option('display.max_columns', None)\n", - "df.head()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Clean data group \"General Client Information\"\n", - "- Dropped cols \"Unnamed 0\", \"clntnum\" overfitting\n", - "- Dropped cols \"ctrcycode_desc\", \"clttype\" zero variance when certain blank rows are removed\n", - "- Dropped blanks rows from \"race_desc\", \"cltdob_fix\"\n", - "- Generation of feature \"age\", removal of original \"cltdob_fix\"" - ] - }, - { - "cell_type": "code", - "execution_count": 37, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Initial Number of Cols: 305 \n", - "Initial Number of Rows: 17992\n", - "Rows dropped: 3997\n", - "New Number of Cols: 301 \n", - "New Number of Rows: 13995\n" - ] - } - ], - "source": [ - "# inital rows and col\n", - "print(\"Initial Number of Cols: \",len(df.columns), \"\\nInitial Number of Rows: \",len(df))\n", - "\n", - "# drop cols\n", - "df.drop(columns=['Unnamed: 0', 'clntnum', 'ctrycode_desc', 'clttype'], inplace=True)\n", - "\n", - "# drop rows\n", - "rows_before = df.shape[0]\n", - "df.dropna(subset=['race_desc','cltdob_fix'], inplace=True)\n", - "rows_dropped = rows_before - df.shape[0]\n", - "print(\"Rows dropped: \", rows_dropped)\n", - "\n", - "# transformation for cltdob_fix\n", - "df['cltdob_fix'] = pd.to_datetime(df['cltdob_fix'], errors='coerce')\n", - "\n", "def calculate_age(row):\n", " ''' Function to calculate age '''\n", " current_date = datetime.now() # current date time\n", @@ -2764,24 +5417,39 @@ " age = current_date.year - birth_date.year - ((current_date.month, current_date.day) < (birth_date.month, birth_date.day))\n", " return age\n", "\n", - "df['age'] = df.apply(calculate_age, axis=1) # create data column age using cltdob_fix\n", - "df.drop(['cltdob_fix'], axis=1, inplace=True) # drop original col cltdob_fix\n", + "def clean_general_client_info(df):\n", + " # drop cols\n", + " df.drop(columns=['Unnamed: 0', 'clntnum', 'ctrycode_desc', 'clttype'], inplace=True)\n", + " # drop rows\n", + " rows_before = df.shape[0]\n", + " df.dropna(subset=['race_desc','cltdob_fix'], inplace=True)\n", + " rows_dropped = rows_before - df.shape[0]\n", + " print(\"Rows dropped: \", rows_dropped)\n", + " # transformation for cltdob_fix\n", + " df['cltdob_fix'] = pd.to_datetime(df['cltdob_fix'], errors='coerce')\n", + " df['age'] = df.apply(calculate_age, axis=1) # create data column age using cltdob_fix\n", + " df.drop(['cltdob_fix'], axis=1, inplace=True) # drop original col cltdob_fix\n", "\n", - "# transformation for min_occ_date \n", - "df['min_occ_date'] = pd.to_datetime(df['min_occ_date'])\n", - "today = pd.Timestamp(datetime.today().date())\n", - "df['years_since_first_interaction'] = (today - df['min_occ_date']) / pd.Timedelta(days=365.25)\n", - "df['years_since_first_interaction'] = df['years_since_first_interaction'].round().astype(int)\n", + " # transformation for min_occ_date \n", + " df['min_occ_date'] = pd.to_datetime(df['min_occ_date'])\n", + " today = pd.Timestamp(datetime.today().date())\n", + " df['years_since_first_interaction'] = (today - df['min_occ_date']) / pd.Timedelta(days=365.25)\n", + " df['years_since_first_interaction'] = df['years_since_first_interaction'].round().astype(int)\n", "\n", - "# Drop the 'min_occ_date' column\n", - "df.drop('min_occ_date', axis=1, inplace=True)\n", + " # Drop the 'min_occ_date' column\n", + " df.drop('min_occ_date', axis=1, inplace=True)\n", "\n", - "label_encoder = LabelEncoder()\n", - "df['stat_flag_encoded'] = label_encoder.fit_transform(df['stat_flag'])\n", - "df['cltsex_encoded'] = label_encoder.fit_transform(df['cltsex_fix'])\n", - "df['race_desc_encoded'] = label_encoder.fit_transform(df['race_desc'])\n", - "df.drop(columns=['stat_flag', 'cltsex_fix', 'race_desc'], inplace=True)\n", + " label_encoder = LabelEncoder()\n", + " df['stat_flag_encoded'] = label_encoder.fit_transform(df['stat_flag'])\n", + " df['cltsex_encoded'] = label_encoder.fit_transform(df['cltsex_fix'])\n", + " df['race_desc_encoded'] = label_encoder.fit_transform(df['race_desc'])\n", + " df.drop(columns=['stat_flag', 'cltsex_fix', 'race_desc'], inplace=True)\n", "\n", + " return df\n", + "\n", + "# inital rows and col\n", + "print(\"Initial Number of Cols: \",len(df.columns), \"\\nInitial Number of Rows: \",len(df))\n", + "df = clean_general_client_info(df)\n", "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", "# final row and cols\n", "df.head() # print df \n" @@ -2797,7 +5465,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 185, "metadata": {}, "outputs": [ { @@ -2811,13 +5479,17 @@ } ], "source": [ - "# drop rows\n", - "rows_before = df.shape[0]\n", - "df.dropna(subset=['flg_substandard'], inplace=True)\n", - "rows_dropped = rows_before - df.shape[0]\n", - "print(\"Rows dropped: \", rows_dropped)\n", - "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", - "\n" + "def clean_client_risk_and_status_indicators(df):\n", + " # drop rows\n", + " rows_before = df.shape[0]\n", + " df.dropna(subset=['flg_substandard'], inplace=True)\n", + " rows_dropped = rows_before - df.shape[0]\n", + " print(\"Rows dropped: \", rows_dropped)\n", + " \n", + " return df\n", + " \n", + "df = clean_client_risk_and_status_indicators(df)\n", + "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))" ] }, { @@ -2832,7 +5504,7 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 186, "metadata": {}, "outputs": [ { @@ -5392,27 +8064,31 @@ "4 0 3.0 " ] }, - "execution_count": 39, + "execution_count": 186, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# Count affected rows during operation\n", - "affected_email_rows = df[(df['is_valid_email'] == False) & (df['is_consent_to_email'] == True)].shape[0]\n", - "affected_mail_rows = df[(df['is_valid_dm'] == False) & (df['is_consent_to_mail'] == True)].shape[0]\n", + "def clean_client_consent_and_communication_preferences(df):\n", + " # Count affected rows during operation\n", + " affected_email_rows = df[(df['is_valid_email'] == False) & (df['is_consent_to_email'] == True)].shape[0]\n", + " affected_mail_rows = df[(df['is_valid_dm'] == False) & (df['is_consent_to_mail'] == True)].shape[0]\n", "\n", - "# If consent is given, but email/mail is not valid, set consent is not given\n", - "df.loc[df['is_valid_email'] == False, 'is_consent_to_email'] = 0\n", - "df.loc[df['is_valid_dm'] == False, 'is_consent_to_mail'] = 0\n", + " # If consent is given, but email/mail is not valid, set consent is not given\n", + " df.loc[df['is_valid_email'] == False, 'is_consent_to_email'] = 0\n", + " df.loc[df['is_valid_dm'] == False, 'is_consent_to_mail'] = 0\n", "\n", - "# Print the number of affected rows\n", - "print(\"Number of affected email rows: \",affected_email_rows, \"\\nNumber of affected mail rows: \",affected_mail_rows)\n", + " # Print the number of affected rows\n", + " print(\"Number of affected email rows: \",affected_email_rows, \"\\nNumber of affected mail rows: \",affected_mail_rows)\n", "\n", - "# aggregation sum of communication methods\n", - "df['methods_of_communications'] = df['is_consent_to_mail'] + df['is_consent_to_email'] + df['is_consent_to_call'] + df['is_consent_to_sms']\n", - "df.drop(columns=['is_consent_to_mail', 'is_consent_to_mail', 'is_consent_to_call', 'is_valid_email', 'is_valid_dm'], inplace=True)\n", + " # aggregation sum of communication methods\n", + " df['methods_of_communications'] = df['is_consent_to_mail'] + df['is_consent_to_email'] + df['is_consent_to_call'] + df['is_consent_to_sms']\n", + " df.drop(columns=['is_consent_to_mail', 'is_consent_to_mail', 'is_consent_to_call', 'is_valid_email', 'is_valid_dm'], inplace=True)\n", + " \n", + " return df\n", "\n", + "df = clean_client_consent_and_communication_preferences(df)\n", "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", "df.head()" ] @@ -5429,7 +8105,7 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 187, "metadata": {}, "outputs": [ { @@ -7975,39 +10651,40 @@ "4 0 3.0 " ] }, - "execution_count": 40, + "execution_count": 187, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# drop rows\n", - "rows_before = df.shape[0]\n", - "df.dropna(subset=['hh_20'], inplace=True)\n", - "rows_dropped = rows_before - df.shape[0]\n", - "print(\"Rows dropped: \", rows_dropped)\n", - "\n", - "# drop col\n", - "df.drop(columns=['is_dependent_in_at_least_1_policy'], inplace=True)\n", - "\n", - "# Count affected rows\n", - "affected_income_rows = df[(df['hh_size_est'] == '>4')].shape[0]\n", - "# replace value '>4' within hh_size_est\" with int value\n", - "df['hh_size_est'] = df['hh_size_est'].replace('>4', 5)\n", - "df['hh_size_est'] = df['hh_size_est'].astype(int)\n", - "\n", - "# mappings for income\n", - "annual_income_dict = {\n", - " 'A.ABOVE200K': 1,\n", - " 'B.100K-200K': 2,\n", - " 'C.60K-100K': 3,\n", - " 'D.30K-60K': 4,\n", - " 'E.BELOW30K': 5\n", - "}\n", + "def clean_demographic_and_household_information(df):\n", + " # drop rows\n", + " rows_before = df.shape[0]\n", + " df.dropna(subset=['hh_20'], inplace=True)\n", + " rows_dropped = rows_before - df.shape[0]\n", + " print(\"Rows dropped: \", rows_dropped)\n", + " # drop col\n", + " df.drop(columns=['is_dependent_in_at_least_1_policy'], inplace=True)\n", + " # Count affected rows\n", + " affected_income_rows = df[(df['hh_size_est'] == '>4')].shape[0]\n", + " # replace value '>4' within hh_size_est\" with int value\n", + " df['hh_size_est'] = df['hh_size_est'].replace('>4', 5)\n", + " df['hh_size_est'] = df['hh_size_est'].astype(int)\n", + " # mappings for income\n", + " annual_income_dict = {\n", + " 'A.ABOVE200K': 1,\n", + " 'B.100K-200K': 2,\n", + " 'C.60K-100K': 3,\n", + " 'D.30K-60K': 4,\n", + " 'E.BELOW30K': 5\n", + " }\n", + " # map values\n", + " df['annual_income_est'] = df['annual_income_est'].map(annual_income_dict)\n", + " \n", + " return df\n", "\n", - "# map values\n", - "df['annual_income_est'] = df['annual_income_est'].map(annual_income_dict)\n", "\n", + "df = clean_demographic_and_household_information(df)\n", "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", "df.head()" ] @@ -8023,7 +10700,7 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 188, "metadata": {}, "outputs": [ { @@ -10556,21 +13233,23 @@ "4 0 3.0 " ] }, - "execution_count": 41, + "execution_count": 188, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.drop(columns=['recency_lapse', 'recency_cancel'], inplace=True)\n", - "\n", - "df = df[df['n_months_last_bought_products'] >= 0]\n", + "def clean_policy_and_claim_history(df):\n", + " df.drop(columns=['recency_lapse', 'recency_cancel'], inplace=True)\n", + " df = df[df['n_months_last_bought_products'] >= 0]\n", + " # Fill missing values with zeros using .loc[]\n", + " df.loc[:, 'tot_inforce_pols'] = df['tot_inforce_pols'].fillna(0)\n", + " df.loc[:, 'tot_cancel_pols'] = df['tot_cancel_pols'].fillna(0)\n", + " df.loc[:, 'f_ever_declined_la'] = df['f_ever_declined_la'].fillna(0)\n", "\n", - "# Fill missing values in 'tot_inforce_pols', 'tot_cancel_pols', and 'f_ever_declined_la' with zeros\n", - "df['tot_inforce_pols'] = df['tot_inforce_pols'].fillna(0)\n", - "df['tot_cancel_pols'] = df['tot_cancel_pols'].fillna(0)\n", - "df['f_ever_declined_la'] = df['f_ever_declined_la'].fillna(0)\n", + " return df\n", "\n", + "df = clean_policy_and_claim_history(df)\n", "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", "df.head()" ] @@ -10587,7 +13266,7 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 189, "metadata": {}, "outputs": [ { @@ -12098,30 +14777,34 @@ "4 9095.636364 0.00 " ] }, - "execution_count": 42, + "execution_count": 189, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "f_ever_bought_columns = df.filter(regex=r'^f_ever_bought_')\n", - "df['total_products_bought'] = f_ever_bought_columns.sum(axis=1)\n", - "df.drop(columns=f_ever_bought_columns.columns, inplace=True)\n", + "def clean_purchase_and_lapse_metrics_for_specific_products(df):\n", + " f_ever_bought_columns = df.filter(regex=r'^f_ever_bought_')\n", + " df['total_products_bought'] = f_ever_bought_columns.sum(axis=1)\n", + " df.drop(columns=f_ever_bought_columns.columns, inplace=True)\n", "\n", - "n_months_last_bought_columns = df.filter(regex=r'^n_months_last_bought_')\n", - "df['avg_months_last_bought'] = n_months_last_bought_columns.mean(axis=1, skipna=True)\n", - "df.drop(columns=n_months_last_bought_columns.columns, inplace=True)\n", + " n_months_last_bought_columns = df.filter(regex=r'^n_months_last_bought_')\n", + " df['avg_months_last_bought'] = n_months_last_bought_columns.mean(axis=1, skipna=True)\n", + " df.drop(columns=n_months_last_bought_columns.columns, inplace=True)\n", "\n", - "n_months_since_lapse_columns = df.filter(regex=r'^n_months_since_lapse_')\n", - "df.loc[:, n_months_since_lapse_columns.columns] = n_months_since_lapse_columns.fillna(0)\n", - "df['avg_months_since_lapse'] = n_months_since_lapse_columns.mean(axis=1, skipna=True)\n", - "df.drop(columns=n_months_since_lapse_columns.columns, inplace=True)\n", - "df['avg_months_since_lapse'] = df['avg_months_since_lapse'].fillna(0)\n", + " n_months_since_lapse_columns = df.filter(regex=r'^n_months_since_lapse_')\n", + " df.loc[:, n_months_since_lapse_columns.columns] = n_months_since_lapse_columns.fillna(0)\n", + " df['avg_months_since_lapse'] = n_months_since_lapse_columns.mean(axis=1, skipna=True)\n", + " df.drop(columns=n_months_since_lapse_columns.columns, inplace=True)\n", + " df['avg_months_since_lapse'] = df['avg_months_since_lapse'].fillna(0)\n", "\n", - "lapse_ape_columns = df.filter(regex=r'^lapse_ape_')\n", - "df.drop(columns=lapse_ape_columns.columns, inplace=True)\n", + " lapse_ape_columns = df.filter(regex=r'^lapse_ape_')\n", + " df.drop(columns=lapse_ape_columns.columns, inplace=True)\n", "\n", - "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", + " return df\n", + "\n", + "df = clean_purchase_and_lapse_metrics_for_specific_products(df)\n", + "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))# \n", "df.head()" ] }, @@ -12137,7 +14820,7 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 190, "metadata": {}, "outputs": [ { @@ -12152,7 +14835,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_24864\\2180672440.py:28: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\1106607189.py:29: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.\n", " df[columns_to_update] = df[columns_to_update].applymap(lambda x: x + 1 if not pd.isna(x) else 0)\n" ] }, @@ -13524,41 +16207,45 @@ "4 9095.636364 0.00 " ] }, - "execution_count": 43, + "execution_count": 190, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# drop columns\n", - "columns_to_drop = [\n", - " 'giclaim_cnt_success',\n", - " 'recency_giclaim_success', \n", - " 'giclaim_cnt_unsuccess', \n", - " 'recency_giclaim_unsuccess', \n", - " 'flg_gi_claim_29d435_ever', \n", - " 'flg_gi_claim_058815_ever', \n", - " 'flg_gi_claim_42e115_ever', \n", - " 'flg_gi_claim_856320_ever', \n", - " 'flg_affconnect_show_interest_ever', \n", - " 'flg_affconnect_ready_to_buy_ever', \n", - " 'flg_affconnect_lapse_ever', \n", - " 'affcon_visit_days', \n", - " 'n_months_since_visit_affcon', \n", - " 'hlthclaim_amt', \n", - " 'recency_hlthclaim'\n", - "]\n", + "def clean_other_flags_and_metrics(df):\n", + " # drop columns\n", + " columns_to_drop = [\n", + " 'giclaim_cnt_success',\n", + " 'recency_giclaim_success', \n", + " 'giclaim_cnt_unsuccess', \n", + " 'recency_giclaim_unsuccess', \n", + " 'flg_gi_claim_29d435_ever', \n", + " 'flg_gi_claim_058815_ever', \n", + " 'flg_gi_claim_42e115_ever', \n", + " 'flg_gi_claim_856320_ever', \n", + " 'flg_affconnect_show_interest_ever', \n", + " 'flg_affconnect_ready_to_buy_ever', \n", + " 'flg_affconnect_lapse_ever', \n", + " 'affcon_visit_days', \n", + " 'n_months_since_visit_affcon', \n", + " 'hlthclaim_amt', \n", + " 'recency_hlthclaim'\n", + " ]\n", "\n", - "df.drop(columns=columns_to_drop, inplace=True)\n", + " df.drop(columns=columns_to_drop, inplace=True)\n", "\n", - "# Replace blanks with 0 if other columns also indicate they have not visited\n", - "columns_to_replace = ['clmcon_visit_days', 'recency_clmcon', 'recency_clmcon_regis', 'hlthclaim_cnt_success', 'hlthclaim_cnt_unsuccess', 'giclaim_amt', 'recency_giclaim', 'flg_hlthclaim_839f8a_ever', 'flg_hlthclaim_14cb37_ever']\n", - "df[columns_to_replace] = df[columns_to_replace].fillna(0)\n", + " # Replace blanks with 0 if other columns also indicate they have not visited\n", + " columns_to_replace = ['clmcon_visit_days', 'recency_clmcon', 'recency_clmcon_regis', 'hlthclaim_cnt_success', 'hlthclaim_cnt_unsuccess', 'giclaim_amt', 'recency_giclaim', 'flg_hlthclaim_839f8a_ever', 'flg_hlthclaim_14cb37_ever']\n", + " df[columns_to_replace] = df[columns_to_replace].fillna(0)\n", "\n", - "# Increment non-blank rows by 1 and fill blanks with 0\n", - "columns_to_update = ['recency_hlthclaim_14cb37', 'recency_hlthclaim_839f8a', 'recency_hlthclaim_unsuccess', 'recency_hlthclaim_success']\n", - "df[columns_to_update] = df[columns_to_update].applymap(lambda x: x + 1 if not pd.isna(x) else 0)\n", + " # Increment non-blank rows by 1 and fill blanks with 0\n", + " columns_to_update = ['recency_hlthclaim_14cb37', 'recency_hlthclaim_839f8a', 'recency_hlthclaim_unsuccess', 'recency_hlthclaim_success']\n", + " df[columns_to_update] = df[columns_to_update].applymap(lambda x: x + 1 if not pd.isna(x) else 0)\n", "\n", + " return df\n", + "\n", + "df = clean_other_flags_and_metrics(df)\n", "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", "df.head()" ] @@ -13574,7 +16261,7 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 191, "metadata": {}, "outputs": [ { @@ -14115,67 +16802,51 @@ "4 0.00 696.0 800000.0 36888.0 " ] }, - "execution_count": 44, + "execution_count": 191, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "columns_to_drop = ['sumins_grp_94baec', 'prempaid_inv_dcd836', 'prempaid_lh_d0adeb',\n", - " 'prempaid_gi_a10d1b', 'prempaid_gi_29d435', 'prempaid_gi_856320',\n", - " 'prempaid_gi_058815', 'prempaid_32c74c', 'ape_gi', 'sumins_gi',\n", - " 'prempaid_d0adeb', 'prempaid_gi', 'sumins_d0adeb', 'sumins_e22a6a',\n", - " 'ape_d0adeb', 'prempaid_gi_42e115', 'prempaid_ltc_1280bf', 'sumins_32c74c',\n", - " 'sumins_gi_058815', 'ape_ltc_1280bf', 'ape_gi_42e115', 'ape_inv_dcd836',\n", - " 'ape_lh_d0adeb', 'ape_gi_a10d1b', 'ape_gi_29d435', 'ape_gi_856320',\n", - " 'ape_gi_058815', 'ape_32c74c', 'sumins_gi_42e115', 'sumins_ltc_1280bf',\n", - " 'sumins_inv_dcd836', 'sumins_lh_d0adeb', 'sumins_grp_22decf',\n", - " 'sumins_gi_a10d1b', 'sumins_gi_29d435', 'sumins_lh_e22a6a', 'sumins_grp_e04c3a',\n", - " 'sumins_gi_856320'] #empty\n", - "# Drop the specified columns from the DataFrame\n", - "df.drop(columns=columns_to_drop, inplace=True)\n", + "def clean_anomyized_insurance_product_metrics(df):\n", + " columns_to_drop = ['sumins_grp_94baec', 'prempaid_inv_dcd836', 'prempaid_lh_d0adeb',\n", + " 'prempaid_gi_a10d1b', 'prempaid_gi_29d435', 'prempaid_gi_856320',\n", + " 'prempaid_gi_058815', 'prempaid_32c74c', 'ape_gi', 'sumins_gi',\n", + " 'prempaid_d0adeb', 'prempaid_gi', 'sumins_d0adeb', 'sumins_e22a6a',\n", + " 'ape_d0adeb', 'prempaid_gi_42e115', 'prempaid_ltc_1280bf', 'sumins_32c74c',\n", + " 'sumins_gi_058815', 'ape_ltc_1280bf', 'ape_gi_42e115', 'ape_inv_dcd836',\n", + " 'ape_lh_d0adeb', 'ape_gi_a10d1b', 'ape_gi_29d435', 'ape_gi_856320',\n", + " 'ape_gi_058815', 'ape_32c74c', 'sumins_gi_42e115', 'sumins_ltc_1280bf',\n", + " 'sumins_inv_dcd836', 'sumins_lh_d0adeb', 'sumins_grp_22decf',\n", + " 'sumins_gi_a10d1b', 'sumins_gi_29d435', 'sumins_lh_e22a6a', 'sumins_grp_e04c3a',\n", + " 'sumins_gi_856320'] #empty\n", + " # Drop the specified columns from the DataFrame\n", + " df.drop(columns=columns_to_drop, inplace=True)\n", + "\n", + " ape_columns = df.filter(regex=r'^ape_(?!lapse_).*')\n", + " # Sum values along columns to create the new \"total_ape\" column\n", + " df['total_ape'] = ape_columns.sum(axis=1)\n", + " df.drop(columns=ape_columns.columns, inplace=True)\n", "\n", - "ape_columns = df.filter(regex=r'^ape_(?!lapse_).*')\n", - "# Sum values along columns to create the new \"total_ape\" column\n", - "df['total_ape'] = ape_columns.sum(axis=1)\n", - "df.drop(columns=ape_columns.columns, inplace=True)\n", + " sumins_col = df.filter(like='sumins_')\n", + " df['total_sumins'] = sumins_col.sum(axis=1)\n", + " df.drop(columns=sumins_col.columns, inplace=True)\n", "\n", - "sumins_col = df.filter(like='sumins_')\n", - "df['total_sumins'] = sumins_col.sum(axis=1)\n", - "df.drop(columns=sumins_col.columns, inplace=True)\n", "\n", + " prempaid_col = df.filter(like='prempaid_')\n", + " df['total_prempaid'] = prempaid_col.sum(axis=1)\n", + " df.drop(columns=prempaid_col.columns, inplace=True)\n", "\n", - "prempaid_col = df.filter(like='prempaid_')\n", - "df['total_prempaid'] = prempaid_col.sum(axis=1)\n", - "df.drop(columns=prempaid_col.columns, inplace=True)\n", + " return df\n", "\n", + "df = clean_anomyized_insurance_product_metrics(df)\n", "print(\"New Number of Cols: \", len(df.columns), \"\\nNew Number of Rows: \", len(df))\n", "df.head()" ] }, { "cell_type": "code", - "execution_count": 45, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "['f_purchase_lh']\n" - ] - } - ], - "source": [ - "columns_with_nan = df.columns[df.isna().any()].tolist()\n", - "\n", - "# 'columns_with_nan' will now contain a list of column names that have NaN values.\n", - "print(columns_with_nan)" - ] - }, - { - "cell_type": "code", - "execution_count": 46, + "execution_count": 192, "metadata": {}, "outputs": [ { @@ -14183,66 +16854,66 @@ "output_type": "stream", "text": [ " Feature Importance\n", - "55 avg_months_last_bought 0.080286\n", - "18 hh_size 0.071309\n", - "17 pop_20 0.067006\n", - "48 age 0.063895\n", - "16 hh_20 0.062591\n", - "49 years_since_first_interaction 0.061585\n", - "57 total_ape 0.057104\n", - "59 total_prempaid 0.053992\n", - "58 total_sumins 0.049928\n", - "56 avg_months_since_lapse 0.036529\n", - "23 tot_inforce_pols 0.031307\n", - "54 total_products_bought 0.031129\n", - "20 annual_income_est 0.025972\n", - "19 hh_size_est 0.025822\n", - "53 methods_of_communications 0.022084\n", - "46 giclaim_amt 0.014427\n", - "52 race_desc_encoded 0.014102\n", - "14 is_class_1_2 0.011970\n", - "10 is_consent_to_email 0.011805\n", - "51 cltsex_encoded 0.011664\n", - "21 flg_latest_being_lapse 0.010445\n", - "47 recency_giclaim 0.010415\n", - "15 f_ever_declined_la 0.009609\n", - "39 recency_hlthclaim_success 0.009472\n", - "6 flg_gi_claim 0.009357\n", - "24 tot_cancel_pols 0.008824\n", - "45 recency_hlthclaim_14cb37 0.008670\n", - "11 is_consent_to_sms 0.008279\n", - "29 f_hold_ltc 0.007614\n", - "30 f_hold_507c37 0.007582\n", - "25 f_hold_839f8a 0.007242\n", - "12 is_housewife_retiree 0.006847\n", - "38 hlthclaim_cnt_success 0.006822\n", - "26 f_hold_e22a6a 0.006783\n", - "7 flg_is_proposal 0.006353\n", - "41 recency_hlthclaim_unsuccess 0.005975\n", - "0 flg_substandard 0.005845\n", - "34 f_retail 0.005634\n", - "37 recency_clmcon_regis 0.005587\n", - "33 f_mindef_mha 0.005537\n", - "32 f_elx 0.005406\n", - "35 clmcon_visit_days 0.004649\n", - "1 flg_is_borderline_standard 0.003954\n", - "50 stat_flag_encoded 0.003664\n", - "43 recency_hlthclaim_839f8a 0.003308\n", - "40 hlthclaim_cnt_unsuccess 0.003220\n", - "36 recency_clmcon 0.002869\n", - "44 flg_hlthclaim_14cb37_ever 0.002816\n", - "22 flg_latest_being_cancel 0.002426\n", - "4 flg_has_health_claim 0.001968\n", - "13 is_sg_pr 0.001762\n", - "42 flg_hlthclaim_839f8a_ever 0.001710\n", - "8 flg_with_preauthorisation 0.001100\n", - "5 flg_has_life_claim 0.001010\n", - "3 flg_is_rental_flat 0.000975\n", - "9 flg_is_returned_mail 0.000957\n", - "28 f_hold_c4bda5 0.000796\n", - "2 flg_is_revised_term 0.000012\n", - "31 f_hold_gi 0.000000\n", - "27 f_hold_d0adeb 0.000000\n" + "55 avg_months_last_bought 0.078786\n", + "18 hh_size 0.070723\n", + "17 pop_20 0.067589\n", + "48 age 0.064721\n", + "16 hh_20 0.062973\n", + "49 years_since_first_interaction 0.062707\n", + "57 total_ape 0.055734\n", + "59 total_prempaid 0.053294\n", + "58 total_sumins 0.049809\n", + "56 avg_months_since_lapse 0.036461\n", + "23 tot_inforce_pols 0.031785\n", + "54 total_products_bought 0.030920\n", + "19 hh_size_est 0.026682\n", + "20 annual_income_est 0.025734\n", + "53 methods_of_communications 0.021670\n", + "52 race_desc_encoded 0.014157\n", + "46 giclaim_amt 0.013867\n", + "14 is_class_1_2 0.012111\n", + "10 is_consent_to_email 0.011943\n", + "51 cltsex_encoded 0.011644\n", + "47 recency_giclaim 0.010816\n", + "21 flg_latest_being_lapse 0.010499\n", + "15 f_ever_declined_la 0.009644\n", + "6 flg_gi_claim 0.009371\n", + "39 recency_hlthclaim_success 0.009315\n", + "24 tot_cancel_pols 0.008687\n", + "45 recency_hlthclaim_14cb37 0.008665\n", + "11 is_consent_to_sms 0.008562\n", + "29 f_hold_ltc 0.007689\n", + "25 f_hold_839f8a 0.007617\n", + "30 f_hold_507c37 0.007267\n", + "12 is_housewife_retiree 0.007058\n", + "38 hlthclaim_cnt_success 0.006678\n", + "26 f_hold_e22a6a 0.006582\n", + "41 recency_hlthclaim_unsuccess 0.006094\n", + "7 flg_is_proposal 0.006084\n", + "37 recency_clmcon_regis 0.005849\n", + "32 f_elx 0.005817\n", + "0 flg_substandard 0.005806\n", + "34 f_retail 0.005777\n", + "33 f_mindef_mha 0.005534\n", + "35 clmcon_visit_days 0.004781\n", + "1 flg_is_borderline_standard 0.004162\n", + "50 stat_flag_encoded 0.003548\n", + "40 hlthclaim_cnt_unsuccess 0.003408\n", + "43 recency_hlthclaim_839f8a 0.002984\n", + "44 flg_hlthclaim_14cb37_ever 0.002964\n", + "36 recency_clmcon 0.002675\n", + "22 flg_latest_being_cancel 0.002250\n", + "13 is_sg_pr 0.001911\n", + "4 flg_has_health_claim 0.001831\n", + "42 flg_hlthclaim_839f8a_ever 0.001544\n", + "3 flg_is_rental_flat 0.001201\n", + "8 flg_with_preauthorisation 0.001190\n", + "5 flg_has_life_claim 0.001075\n", + "28 f_hold_c4bda5 0.000989\n", + "9 flg_is_returned_mail 0.000730\n", + "2 flg_is_revised_term 0.000034\n", + "27 f_hold_d0adeb 0.000000\n", + "31 f_hold_gi 0.000000\n" ] } ], @@ -14277,7 +16948,7 @@ }, { "cell_type": "code", - "execution_count": 47, + "execution_count": 193, "metadata": {}, "outputs": [ { @@ -14285,71 +16956,71 @@ "output_type": "stream", "text": [ " Feature Importance\n", - "6 flg_gi_claim 0.052723\n", - "54 total_products_bought 0.045372\n", - "34 f_retail 0.043386\n", - "44 flg_hlthclaim_14cb37_ever 0.038044\n", - "12 is_housewife_retiree 0.036429\n", - "33 f_mindef_mha 0.030221\n", - "36 recency_clmcon 0.028146\n", - "50 stat_flag_encoded 0.027481\n", - "22 flg_latest_being_cancel 0.026735\n", - "56 avg_months_since_lapse 0.023651\n", - "14 is_class_1_2 0.022932\n", - "7 flg_is_proposal 0.021310\n", - "10 is_consent_to_email 0.020641\n", - "23 tot_inforce_pols 0.019814\n", - "15 f_ever_declined_la 0.019731\n", - "38 hlthclaim_cnt_success 0.019251\n", - "53 methods_of_communications 0.019132\n", - "55 avg_months_last_bought 0.017731\n", - "0 flg_substandard 0.017620\n", - "11 is_consent_to_sms 0.017614\n", - "29 f_hold_ltc 0.017463\n", - "1 flg_is_borderline_standard 0.017303\n", - "57 total_ape 0.017186\n", - "21 flg_latest_being_lapse 0.016897\n", - "52 race_desc_encoded 0.016880\n", - "20 annual_income_est 0.016586\n", - "25 f_hold_839f8a 0.015985\n", - "43 recency_hlthclaim_839f8a 0.015817\n", - "59 total_prempaid 0.015402\n", - "51 cltsex_encoded 0.015284\n", - "47 recency_giclaim 0.015261\n", - "58 total_sumins 0.015107\n", - "17 pop_20 0.014888\n", - "49 years_since_first_interaction 0.014556\n", - "48 age 0.014502\n", - "26 f_hold_e22a6a 0.014495\n", - "46 giclaim_amt 0.014465\n", - "37 recency_clmcon_regis 0.014458\n", - "24 tot_cancel_pols 0.014231\n", - "16 hh_20 0.014194\n", - "32 f_elx 0.014158\n", - "45 recency_hlthclaim_14cb37 0.013842\n", - "39 recency_hlthclaim_success 0.013817\n", - "18 hh_size 0.013348\n", - "30 f_hold_507c37 0.012998\n", - "40 hlthclaim_cnt_unsuccess 0.011669\n", - "35 clmcon_visit_days 0.010640\n", - "28 f_hold_c4bda5 0.010490\n", - "13 is_sg_pr 0.009811\n", - "4 flg_has_health_claim 0.009410\n", - "41 recency_hlthclaim_unsuccess 0.007717\n", - "3 flg_is_rental_flat 0.005493\n", - "19 hh_size_est 0.005212\n", - "8 flg_with_preauthorisation 0.002470\n", + "6 flg_gi_claim 0.085160\n", + "34 f_retail 0.043891\n", + "54 total_products_bought 0.042849\n", + "22 flg_latest_being_cancel 0.041727\n", + "12 is_housewife_retiree 0.038667\n", + "0 flg_substandard 0.024829\n", + "56 avg_months_since_lapse 0.024291\n", + "50 stat_flag_encoded 0.024191\n", + "21 flg_latest_being_lapse 0.021145\n", + "14 is_class_1_2 0.020813\n", + "23 tot_inforce_pols 0.019301\n", + "52 race_desc_encoded 0.019216\n", + "55 avg_months_last_bought 0.018838\n", + "32 f_elx 0.018563\n", + "7 flg_is_proposal 0.018423\n", + "33 f_mindef_mha 0.018369\n", + "30 f_hold_507c37 0.018312\n", + "36 recency_clmcon 0.018211\n", + "11 is_consent_to_sms 0.018139\n", + "15 f_ever_declined_la 0.017991\n", + "51 cltsex_encoded 0.017636\n", + "53 methods_of_communications 0.017090\n", + "24 tot_cancel_pols 0.017077\n", + "25 f_hold_839f8a 0.016878\n", + "57 total_ape 0.016231\n", + "48 age 0.016064\n", + "29 f_hold_ltc 0.015677\n", + "47 recency_giclaim 0.015562\n", + "17 pop_20 0.015375\n", + "20 annual_income_est 0.015206\n", + "10 is_consent_to_email 0.015205\n", + "35 clmcon_visit_days 0.015122\n", + "49 years_since_first_interaction 0.015080\n", + "46 giclaim_amt 0.014901\n", + "59 total_prempaid 0.014819\n", + "26 f_hold_e22a6a 0.014815\n", + "58 total_sumins 0.014692\n", + "40 hlthclaim_cnt_unsuccess 0.014666\n", + "16 hh_20 0.014403\n", + "45 recency_hlthclaim_14cb37 0.014379\n", + "4 flg_has_health_claim 0.014157\n", + "38 hlthclaim_cnt_success 0.013979\n", + "43 recency_hlthclaim_839f8a 0.013824\n", + "37 recency_clmcon_regis 0.013767\n", + "18 hh_size 0.013755\n", + "39 recency_hlthclaim_success 0.012655\n", + "3 flg_is_rental_flat 0.010413\n", + "13 is_sg_pr 0.009121\n", + "41 recency_hlthclaim_unsuccess 0.008367\n", + "8 flg_with_preauthorisation 0.007595\n", + "28 f_hold_c4bda5 0.007243\n", + "44 flg_hlthclaim_14cb37_ever 0.005734\n", + "1 flg_is_borderline_standard 0.005587\n", "27 f_hold_d0adeb 0.000000\n", - "42 flg_hlthclaim_839f8a_ever 0.000000\n", - "9 flg_is_returned_mail 0.000000\n", "5 flg_has_life_claim 0.000000\n", + "31 f_hold_gi 0.000000\n", "2 flg_is_revised_term 0.000000\n", - "31 f_hold_gi 0.000000\n" + "19 hh_size_est 0.000000\n", + "42 flg_hlthclaim_839f8a_ever 0.000000\n", + "9 flg_is_returned_mail 0.000000\n" ] }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -14397,7 +17068,7 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 194, "metadata": {}, "outputs": [ { @@ -14469,22 +17140,160 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 195, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Rows dropped: 3997\n", + "Rows dropped: 359\n", + "Number of affected email rows: 482 \n", + "Number of affected mail rows: 483\n", + "Rows dropped: 454\n", + "[0 0 0 ... 0 0 0]\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:3: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['total_products_bought'] = f_ever_bought_columns.sum(axis=1)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:4: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=f_ever_bought_columns.columns, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:7: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['avg_months_last_bought'] = n_months_last_bought_columns.mean(axis=1, skipna=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:8: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=n_months_last_bought_columns.columns, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:12: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['avg_months_since_lapse'] = n_months_since_lapse_columns.mean(axis=1, skipna=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:13: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=n_months_since_lapse_columns.columns, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:14: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['avg_months_since_lapse'] = df['avg_months_since_lapse'].fillna(0)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\2022624574.py:17: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=lapse_ape_columns.columns, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\1106607189.py:21: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=columns_to_drop, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\1106607189.py:25: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df[columns_to_replace] = df[columns_to_replace].fillna(0)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\1106607189.py:29: FutureWarning: DataFrame.applymap has been deprecated. Use DataFrame.map instead.\n", + " df[columns_to_update] = df[columns_to_update].applymap(lambda x: x + 1 if not pd.isna(x) else 0)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\1106607189.py:29: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df[columns_to_update] = df[columns_to_update].applymap(lambda x: x + 1 if not pd.isna(x) else 0)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:14: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=columns_to_drop, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:18: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['total_ape'] = ape_columns.sum(axis=1)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:19: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=ape_columns.columns, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['total_sumins'] = sumins_col.sum(axis=1)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=sumins_col.columns, inplace=True)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:27: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df['total_prempaid'] = prempaid_col.sum(axis=1)\n", + "C:\\Users\\Matthew Chuang\\AppData\\Local\\Temp\\ipykernel_14428\\4234705292.py:28: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " df.drop(columns=prempaid_col.columns, inplace=True)\n" + ] + } + ], "source": [ "def testing_hidden_data(hidden_data: pd.DataFrame) -> list:\n", " '''DO NOT REMOVE THIS FUNCTION.\n", "\n", - "The function accepts a dataframe as input and return an iterable (list)\n", - "of binary classes as output.\n", + " The function accepts a dataframe as input and return an iterable (list)\n", + " of binary classes as output.\n", "\n", - "The function should be coded to test on hidden data\n", - "and should include any preprocessing functions needed for your model to perform. \n", + " The function should be coded to test on hidden data\n", + " and should include any preprocessing functions needed for your model to perform. \n", + " \n", + " All relevant code MUST be included in this function.''' \n", " \n", - "All relevant code MUST be included in this function.'''\n", - " result = [] \n", - " return result" + " # data preprocessing\n", + " hidden_data = clean_general_client_info(hidden_data)\n", + " hidden_data = clean_client_risk_and_status_indicators(hidden_data)\n", + " hidden_data = clean_client_consent_and_communication_preferences(hidden_data)\n", + " hidden_data = clean_demographic_and_household_information(hidden_data)\n", + " hidden_data = clean_policy_and_claim_history(hidden_data)\n", + " hidden_data = clean_purchase_and_lapse_metrics_for_specific_products(hidden_data)\n", + " hidden_data = clean_other_flags_and_metrics(hidden_data)\n", + " hidden_data = clean_anomyized_insurance_product_metrics(hidden_data)\n", + " \n", + " # Predict on the test data\n", + " result = xgb_model.predict(hidden_data)\n", + " return result\n", + "\n", + "# This cell should output a list of predictions.\n", + "test_df = pd.read_csv(filepath)\n", + "test_df = test_df.drop(columns=[\"f_purchase_lh\"])\n", + "result = testing_hidden_data(test_df)\n", + "print(result)" ] }, { @@ -14494,32 +17303,6 @@ "##### Cell to check testing_hidden_data function" ] }, - { - "cell_type": "code", - "execution_count": 50, - "metadata": {}, - "outputs": [ - { - "ename": "ImportError", - "evalue": "Unable to find a usable engine; tried using: 'pyarrow', 'fastparquet'.\nA suitable version of pyarrow or fastparquet is required for parquet support.\nTrying to import the above resulted in these errors:\n - Missing optional dependency 'pyarrow'. pyarrow is required for parquet support. Use pip or conda to install pyarrow.\n - Missing optional dependency 'fastparquet'. fastparquet is required for parquet support. Use pip or conda to install fastparquet.", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mImportError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[1;32mIn[50], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m# This cell should output a list of predictions.\u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m test_df \u001b[38;5;241m=\u001b[39m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mread_parquet\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilepath\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 3\u001b[0m test_df \u001b[38;5;241m=\u001b[39m test_df\u001b[38;5;241m.\u001b[39mdrop(columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mf_purchase_lh\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28mprint\u001b[39m(testing_hidden_data(test_df))\n", - "File \u001b[1;32mc:\\Users\\Matthew Chuang\\Documents\\Github\\NUS-SDS-Datathon-Singlife\\venv\\lib\\site-packages\\pandas\\io\\parquet.py:651\u001b[0m, in \u001b[0;36mread_parquet\u001b[1;34m(path, engine, columns, storage_options, use_nullable_dtypes, dtype_backend, filesystem, filters, **kwargs)\u001b[0m\n\u001b[0;32m 498\u001b[0m \u001b[38;5;129m@doc\u001b[39m(storage_options\u001b[38;5;241m=\u001b[39m_shared_docs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mstorage_options\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[0;32m 499\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mread_parquet\u001b[39m(\n\u001b[0;32m 500\u001b[0m path: FilePath \u001b[38;5;241m|\u001b[39m ReadBuffer[\u001b[38;5;28mbytes\u001b[39m],\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 508\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m 509\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m DataFrame:\n\u001b[0;32m 510\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 511\u001b[0m \u001b[38;5;124;03m Load a parquet object from the file path, returning a DataFrame.\u001b[39;00m\n\u001b[0;32m 512\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 648\u001b[0m \u001b[38;5;124;03m 1 4 9\u001b[39;00m\n\u001b[0;32m 649\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m--> 651\u001b[0m impl \u001b[38;5;241m=\u001b[39m \u001b[43mget_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mengine\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 653\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_nullable_dtypes \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default:\n\u001b[0;32m 654\u001b[0m msg \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m 655\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe argument \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124muse_nullable_dtypes\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is deprecated and will be removed \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 656\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124min a future version.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 657\u001b[0m )\n", - "File \u001b[1;32mc:\\Users\\Matthew Chuang\\Documents\\Github\\NUS-SDS-Datathon-Singlife\\venv\\lib\\site-packages\\pandas\\io\\parquet.py:67\u001b[0m, in \u001b[0;36mget_engine\u001b[1;34m(engine)\u001b[0m\n\u001b[0;32m 64\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[0;32m 65\u001b[0m error_msgs \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m - \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mstr\u001b[39m(err)\n\u001b[1;32m---> 67\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\n\u001b[0;32m 68\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnable to find a usable engine; \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 69\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtried using: \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpyarrow\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mfastparquet\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 70\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mA suitable version of \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 71\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow or fastparquet is required for parquet \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 72\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msupport.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 73\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTrying to import the above resulted in these errors:\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 74\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00merror_msgs\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 75\u001b[0m )\n\u001b[0;32m 77\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m engine \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyarrow\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[0;32m 78\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m PyArrowImpl()\n", - "\u001b[1;31mImportError\u001b[0m: Unable to find a usable engine; tried using: 'pyarrow', 'fastparquet'.\nA suitable version of pyarrow or fastparquet is required for parquet support.\nTrying to import the above resulted in these errors:\n - Missing optional dependency 'pyarrow'. pyarrow is required for parquet support. Use pip or conda to install pyarrow.\n - Missing optional dependency 'fastparquet'. fastparquet is required for parquet support. Use pip or conda to install fastparquet." - ] - } - ], - "source": [ - "# This cell should output a list of predictions.\n", - "test_df = pd.read_parquet(filepath)\n", - "test_df = test_df.drop(columns=[\"f_purchase_lh\"])\n", - "print(testing_hidden_data(test_df))" - ] - }, { "cell_type": "markdown", "metadata": {}, diff --git a/clean_data.ipynb b/clean_data.ipynb deleted file mode 100644 index c8fe713..0000000 --- a/clean_data.ipynb +++ /dev/null @@ -1,292 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 46, - "metadata": { - "id": "nc19dQGg14fD" - }, - "outputs": [], - "source": [ - "import pandas as pd\n", - "import numpy as np\n", - "from datetime import datetime\n", - "from sklearn.preprocessing import LabelEncoder" - ] - }, - { - "cell_type": "code", - "execution_count": 47, - "metadata": { - "id": "u6PDr47fORg6" - }, - "outputs": [], - "source": [ - "# Load the CSV file into a DataFrame\n", - "df = pd.read_csv(r'C:\\Users\\nicholassng\\OneDrive - Singapore Institute Of Technology\\Desktop\\datathon\\data.csv')" - ] - }, - { - "cell_type": "code", - "execution_count": 48, - "metadata": { - "id": "1n2gU_orO7Do" - }, - "outputs": [], - "source": [ - "\n", - "columns_to_drop = ['sumins_grp_94baec', 'prempaid_inv_dcd836', 'prempaid_lh_d0adeb',\n", - " 'prempaid_gi_a10d1b', 'prempaid_gi_29d435', 'prempaid_gi_856320',\n", - " 'prempaid_gi_058815', 'prempaid_32c74c', 'ape_gi', 'sumins_gi',\n", - " 'prempaid_d0adeb', 'prempaid_gi', 'sumins_d0adeb', 'sumins_e22a6a',\n", - " 'ape_d0adeb', 'prempaid_gi_42e115', 'prempaid_ltc_1280bf', 'sumins_32c74c',\n", - " 'sumins_gi_058815', 'ape_ltc_1280bf', 'ape_gi_42e115', 'ape_inv_dcd836',\n", - " 'ape_lh_d0adeb', 'ape_gi_a10d1b', 'ape_gi_29d435', 'ape_gi_856320',\n", - " 'ape_gi_058815', 'ape_32c74c', 'sumins_gi_42e115', 'sumins_ltc_1280bf',\n", - " 'sumins_inv_dcd836', 'sumins_lh_d0adeb', 'sumins_grp_22decf',\n", - " 'sumins_gi_a10d1b', 'sumins_gi_29d435', 'sumins_lh_e22a6a', 'sumins_grp_e04c3a',\n", - " 'sumins_gi_856320'] #empty\n", - "# Drop the specified columns from the DataFrame\n", - "df.drop(columns=columns_to_drop, inplace=True)\n", - "\n", - "\n", - "df.dropna(subset=['flg_substandard'], inplace=True) #drop empty\n", - "df.dropna(subset=['hh_size_est'], inplace=True) #drop empty\n", - "df.dropna(subset=['race_desc'], inplace=True) #drop empty\n", - "df = df[(df['pop_20'] != '') & (df['pop_20'] != 0)] #drop blank and 0\n", - "df = df[~df['ctrycode_desc'].isin([\"unknown country code\", \"\"])] # drop blanks and unknown country code\n", - "df = df.filter(regex=r'^(?!f_hold)') #remove f_hold columns " - ] - }, - { - "cell_type": "code", - "execution_count": 49, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "UGJqGFQuO9zQ", - "outputId": "3423067d-c4e2-4be2-bf43-68fb98698bc8" - }, - "outputs": [], - "source": [ - "df['is_consent'] = (df['is_consent_to_mail'] + df['is_consent_to_email'] +\n", - " df['is_consent_to_call'] + df['is_consent_to_sms']) > 2\n", - "\n", - "# Convert boolean values to 1s and 0s\n", - "df['is_consent'] = df['is_consent'].astype(int)" - ] - }, - { - "cell_type": "code", - "execution_count": 50, - "metadata": { - "id": "HwJAwOC0sW6j" - }, - "outputs": [], - "source": [ - "df['is_valid'] = (df['is_valid_dm'] + df['is_valid_email']) > 1\n", - "\n", - "# Convert boolean values to 1s and 0s\n", - "df['is_valid'] = df['is_valid'].astype(int)" - ] - }, - { - "cell_type": "code", - "execution_count": 51, - "metadata": { - "id": "b0vL2Z8ltTsX" - }, - "outputs": [], - "source": [ - "# replace '>4' as 5\n", - "df['hh_size_est'] = df['hh_size_est'].replace('>4', 5)\n", - "\n", - "# Convert the column to integer type\n", - "df['hh_size_est'] = df['hh_size_est'].astype(int)" - ] - }, - { - "cell_type": "code", - "execution_count": 52, - "metadata": { - "id": "LgJaxeDD1l5i" - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "C:\\Users\\nicholassng\\AppData\\Local\\Temp\\ipykernel_8376\\3979558514.py:13: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", - "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", - "\n", - "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", - "\n", - "\n", - " df['annual_income_est'].fillna(6, inplace=True)\n" - ] - } - ], - "source": [ - "income_mapping = {\n", - " 'A.ABOVE200K': 1,\n", - " 'B.100K-200K': 2,\n", - " 'C.60K-100K': 3,\n", - " 'D.30K-60K': 4,\n", - " 'E.BELOW30K': 5\n", - "}\n", - "\n", - "# Map the 'annual_income_est' column using the defined mapping\n", - "df['annual_income_est'] = df['annual_income_est'].map(income_mapping)\n", - "\n", - "# Replace NaN values with 6\n", - "df['annual_income_est'].fillna(6, inplace=True)\n", - "\n", - "# Convert the column to integer type\n", - "df['annual_income_est'] = df['annual_income_est'].astype(int)" - ] - }, - { - "cell_type": "code", - "execution_count": 53, - "metadata": { - "id": "39lg4wKy37Hu" - }, - "outputs": [], - "source": [ - "ape_columns = df.filter(regex=r'^ape_(?!lapse_).*')\n", - "# Sum values along columns to create the new \"total_ape\" column\n", - "df['total_ape'] = ape_columns.sum(axis=1)" - ] - }, - { - "cell_type": "code", - "execution_count": 54, - "metadata": { - "id": "uD7Wok864VGv" - }, - "outputs": [], - "source": [ - "sumins_col = df.filter(like='sumins_')\n", - "df['total_sumins'] = sumins_col.sum(axis=1)" - ] - }, - { - "cell_type": "code", - "execution_count": 55, - "metadata": { - "id": "4OQqyNeG43Bj" - }, - "outputs": [], - "source": [ - "prempaid_col = df.filter(like='prempaid_')\n", - "df['total_prempaid'] = prempaid_col.sum(axis=1)" - ] - }, - { - "cell_type": "code", - "execution_count": 56, - "metadata": { - "id": "DYEOEWoX5Dg8" - }, - "outputs": [], - "source": [ - "# Drop rows with 'None' values in the 'cltdob_fix' column\n", - "df = df[df['cltdob_fix'] != 'None']\n", - "\n", - "# Split the \"cltdob_fix\" column into year, month, and day components\n", - "df['cltdob_fix'] = pd.to_datetime(df['cltdob_fix'], errors='coerce') # Convert to datetime and handle invalid dates\n", - "\n", - "# Calculate the current date\n", - "current_date = datetime.now()\n", - "\n", - "# Define a function to calculate age\n", - "def calculate_age(row):\n", - " if pd.isnull(row['cltdob_fix']):\n", - " return pd.NA\n", - " birth_date = row['cltdob_fix']\n", - " age = current_date.year - birth_date.year - ((current_date.month, current_date.day) < (birth_date.month, birth_date.day))\n", - " return age\n", - "\n", - "# Apply the function to calculate age and create the 'age' column\n", - "df['age'] = df.apply(calculate_age, axis=1)\n", - "\n", - "# Drop the intermediate columns 'year', 'month', and 'day' if not needed\n", - "df.drop(['cltdob_fix'], axis=1, inplace=True)" - ] - }, - { - "cell_type": "code", - "execution_count": 57, - "metadata": { - "id": "iMNSKudD9fbT" - }, - "outputs": [], - "source": [ - "label_encoder = LabelEncoder()\n", - "df['stat_flag_encoded'] = label_encoder.fit_transform(df['stat_flag'])" - ] - }, - { - "cell_type": "code", - "execution_count": 58, - "metadata": { - "id": "oTddyqhm_sdN" - }, - "outputs": [], - "source": [ - "# Encode the 'cltsex_fix' column\n", - "df['cltsex_encoded'] = label_encoder.fit_transform(df['cltsex_fix'])" - ] - }, - { - "cell_type": "code", - "execution_count": 59, - "metadata": {}, - "outputs": [], - "source": [ - "# Replace all blank values in 'f_ever_declined_la' with '0'\n", - "df['f_ever_declined_la'] = df['f_ever_declined_la'].fillna('0')" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 60, - "metadata": {}, - "outputs": [], - "source": [ - "# df of cleaned data" - ] - } - ], - "metadata": { - "colab": { - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.10.6" - } - }, - "nbformat": 4, - "nbformat_minor": 0 -}