added preprocessing files

data_preprocessing_scripts/Data Preprocessing Script.ipynb

@@ -0,0 +1,576 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5619ac0c-7398-4eb5-bdc0-8d338bf4a41f",
+   "metadata": {},
+   "source": [
+    "### Data Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8774cfd1-91b0-4d2d-b0f1-f057a5940cea",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "### Importing Libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b0b6e81d-c547-41ae-8a2b-4f8864cbc8d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings(\"ignore\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "27dd12eb-2975-4b6f-9010-845ae2d23c8f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c49948e7-3018-4cf8-b3bc-0bae7e6a051f",
+   "metadata": {},
+   "source": [
+    "### Data Preprocessing Function"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "02ee5dbe-dc71-4839-a19b-34699133f2be",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_and_clean_data(file_path):\n",
+    "    \"\"\"\n",
+    "    Load and clean the data from the specified CSV file.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - file_path (str): Path to the CSV file containing the data.\n",
+    "\n",
+    "    Returns:\n",
+    "    - DataFrame: Cleaned DataFrame containing selected columns with NaN values dropped.\n",
+    "    \"\"\"\n",
+    "    df = pd.read_csv(file_path)\n",
+    "    df['Date received'] = pd.to_datetime(df['Date received'])\n",
+    "    \n",
+    "    cols_to_consider = ['Product', 'Sub-product', 'Issue', 'Sub-issue', 'Consumer complaint narrative',\n",
+    "                        'Company public response', 'Company', 'State', 'ZIP code', 'Date received']\n",
+    "    \n",
+    "    df_new = df[cols_to_consider]\n",
+    "    \n",
+    "    df_new = df_new.dropna()\n",
+    "    \n",
+    "    return df_new"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "413135b7-1fb8-4cef-876e-99bfd1f148ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def filter_by_years(df, years):\n",
+    "    \"\"\"\n",
+    "    Filter the DataFrame to include only the rows corresponding to specified years.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - df (DataFrame): The DataFrame containing data to filter.\n",
+    "    - years (list of int): List of years to filter by.\n",
+    "\n",
+    "    Returns:\n",
+    "    - DataFrame: Filtered DataFrame containing rows corresponding to specified years.\n",
+    "    \"\"\"\n",
+    "    filtered_df = df[df['Date received'].dt.year.isin(years)].reset_index(drop=True)\n",
+    "    return filtered_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9e3f199f-0ad9-40a3-82f1-065af9efa9f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def map_product_column(df):\n",
+    "    \"\"\"\n",
+    "    Map values in the 'Product' column of the DataFrame to a standardized set of categories.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - df (DataFrame): The DataFrame containing the 'Product' column to map.\n",
+    "\n",
+    "    Returns:\n",
+    "    - DataFrame: DataFrame with the 'Product' column values mapped to standardized categories.\n",
+    "    \"\"\"\n",
+    "\n",
+    "    product_map = {'Credit reporting or other personal consumer reports': 'Credit Reporting',\n",
+    "                   'Credit reporting, credit repair services, or other personal consumer reports': 'Credit Reporting',\n",
+    "                   'Payday loan, title loan, personal loan, or advance loan': 'Loans / Mortgage',\n",
+    "                   'Payday loan, title loan, or personal loan': 'Loans / Mortgage',\n",
+    "                   'Student loan': 'Loans / Mortgage',\n",
+    "                   'Vehicle loan or lease': 'Loans / Mortgage',\n",
+    "                   'Debt collection': 'Debt collection',\n",
+    "                   'Credit card or prepaid card': 'Credit/Prepaid Card',\n",
+    "                   'Credit card': 'Credit/Prepaid Card',\n",
+    "                   'Prepaid card': 'Credit/Prepaid Card',\n",
+    "                   'Mortgage': 'Loans / Mortgage',\n",
+    "                   'Checking or savings account': 'Checking or savings account'  \n",
+    "                  }\n",
+    "    # Map 'Product' column\n",
+    "    df.loc[:,'Product'] = df['Product'].map(product_map)\n",
+    "    \n",
+    "    return df\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "03a2e0a2-75ff-4b33-b081-58e3d5c791c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def clean_narrative(df):\n",
+    "\n",
+    "    \"\"\"\n",
+    "    Clean the consumer complaint narratives in the DataFrame by excluding short and irrelevant complaints.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - df (DataFrame): The input DataFrame containing consumer complaint data.\n",
+    "\n",
+    "    Returns:\n",
+    "    - DataFrame: DataFrame with cleaned consumer complaint narratives.\n",
+    "    \"\"\"\n",
+    "# Compute complaint length\n",
+    "    df['complaint length'] = df['Consumer complaint narrative'].apply(lambda x : len(x))\n",
+    "\n",
+    "    df = df[df['complaint length'] > 20]\n",
+    "    \n",
+    "    complaints_to_exclude = ['See document attached', 'See the attached documents.', 'Incorrect information on my credit report', 'incorrect information on my credit report',\n",
+    "    'please see attached file','Please see documents Attached','Incorrect information on my credit report.', 'Please see attached file', 'see attached',\n",
+    "    'See attached', 'SEE ATTACHED DOCUMENTS', 'See Attached', 'SEE ATTACHMENT', 'SEE ATTACHMENTS', \n",
+    "    'XXXX XXXX XXXX XXXX XXXX XXXX XXXX XXXX XXXX XXXX']\n",
+    "    \n",
+    "    df = df[~df['Consumer complaint narrative'].isin(complaints_to_exclude)]\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "0cb28135-12d8-41fc-94a8-2968e558473b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def filter_by_frequency(df):\n",
+    "    \"\"\"\n",
+    "    Filter the DataFrame based on the frequency of sub-issues and sub-products.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - df (DataFrame): The input DataFrame containing consumer complaint data.\n",
+    "\n",
+    "    Returns:\n",
+    "    - DataFrame: DataFrame filtered based on the frequency of sub-issues and sub-products.\n",
+    "    \"\"\"\n",
+    "    # Select sub-issues with frequency > 500\n",
+    "    sub_issues_to_consider = df['Sub-issue'].value_counts()[df['Sub-issue'].value_counts() > 500].index\n",
+    "\n",
+    "    # Filter DataFrame based on selected sub-issues\n",
+    "    reduced_subissues = df[df['Sub-issue'].isin(sub_issues_to_consider)]\n",
+    "    # Select sub-products with frequency > 100\n",
+    "    sub_products_to_consider = reduced_subissues['Sub-product'].value_counts()[reduced_subissues['Sub-product'].value_counts() > 100].index\n",
+    "\n",
+    "    # Filter DataFrame based on selected sub-products\n",
+    "    final_df = reduced_subissues[reduced_subissues['Sub-product'].isin(sub_products_to_consider)]\n",
+    "\n",
+    "    return final_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e102c902-645e-453e-9a67-07781ba6fc55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def map_issue(df):\n",
+    "    \"\"\"\n",
+    "    Map the issues to more defined and lesser number of issues  in the DataFrame.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - df (DataFrame): The input DataFrame containing consumer complaint data.\n",
+    "\n",
+    "    Returns:\n",
+    "    - DataFrame: DataFrame with the 'Issue' column mapped to appropriate issues.\n",
+    "    \"\"\"\n",
+    "    # Create a dictionary mapping issues to sub-issues\n",
+    "    issues_to_subissues = {}\n",
+    "    for issue in df['Issue'].value_counts().index:\n",
+    "        issues_to_subissues[issue] = list(df[df['Issue'] == issue]['Sub-issue'].value_counts().to_dict().keys())\n",
+    "\n",
+    "    # Separate issues with only one sub-issue and more than one sub-issue\n",
+    "    one_subissue = {key: value for key, value in issues_to_subissues.items() if len(issues_to_subissues[key]) == 1}\n",
+    "    more_than_one_subissue = {key: value for key, value in issues_to_subissues.items() if len(issues_to_subissues[key]) > 1}\n",
+    "\n",
+    "    # Existing issue mapping for issues with more than one sub-issue\n",
+    "    existing_issue_mapping = {issue: issue for issue in more_than_one_subissue}\n",
+    "\n",
+    "    # Issue renaming based on provided mapping\n",
+    "    issue_renaming = {\n",
+    "        'Problem with a lender or other company charging your account': 'Account Operations and Unauthorized Transaction Issues',\n",
+    "        'Opening an account': 'Account Operations and Unauthorized Transaction Issues',\n",
+    "        'Getting a credit card': 'Account Operations and Unauthorized Transaction Issues',\n",
+    "\n",
+    "        'Unable to get your credit report or credit score': 'Credit Report and Monitoring Issues',\n",
+    "        'Credit monitoring or identity theft protection services': 'Credit Report and Monitoring Issues',\n",
+    "        'Identity theft protection or other monitoring services': 'Credit Report and Monitoring Issues',\n",
+    "\n",
+    "        'Problem caused by your funds being low': 'Payment and Funds Management',\n",
+    "        'Problem when making payments': 'Payment and Funds Management',\n",
+    "        'Managing the loan or lease': 'Payment and Funds Management',\n",
+    "\n",
+    "        'False statements or representation': 'Disputes and Misrepresentations',\n",
+    "        'Fees or interest': 'Disputes and Misrepresentations',\n",
+    "        'Other features, terms, or problems': 'Disputes and Misrepresentations',\n",
+    "\n",
+    "        'Took or threatened to take negative or legal action': 'Legal and Threat Actions'\n",
+    "    }\n",
+    "\n",
+    "    # Combine issue renaming and existing issue mapping\n",
+    "    issues_mapping = {**issue_renaming, **existing_issue_mapping}\n",
+    "\n",
+    "    # Map 'Issue' column using the defined mapping dictionary\n",
+    "    df['Issue'] = df['Issue'].apply(lambda x: issues_mapping[x])\n",
+    "\n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b8a50ac3-1a5b-4c78-92bb-da14d38a679c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def split_and_save_data(df,year, test_size=0.25, random_state=42, directory_to_save='./data_splits/'):\n",
+    "    \"\"\"\n",
+    "    Split the input DataFrame into train and test sets, and save them as CSV files with the specified year included in the file names.\n",
+    "\n",
+    "    Parameters:\n",
+    "    - df (DataFrame): The input DataFrame containing consumer complaint data.\n",
+    "    - year (int): The year associated with the data split.\n",
+    "    - test_size (float, optional): The proportion of the dataset to include in the test split. Default is 0.25.\n",
+    "    - random_state (int, optional): The seed used by the random number generator. Default is 42.\n",
+    "    - directory_to_save (str, optional): The directory path to save the data splits. Default is './data_splits/'.\n",
+    "\n",
+    "    Returns:\n",
+    "    - None\n",
+    "    \"\"\"\n",
+    "    # Split the data into train and test sets\n",
+    "    X = df['Consumer complaint narrative']\n",
+    "    y = df[['Product', 'Sub-product', 'Issue', 'Sub-issue']]\n",
+    "    X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y['Product'], test_size=test_size, random_state=random_state)\n",
+    "\n",
+    "    # Concatenate X_train and y_train, and X_test and y_test respectively\n",
+    "    train_df = pd.concat([X_train, y_train], axis=1).reset_index(drop=True)\n",
+    "    test_df = pd.concat([X_test, y_test], axis=1).reset_index(drop=True)\n",
+    "\n",
+    "    # Create directory if it doesn't exist\n",
+    "    if not os.path.exists(directory_to_save):\n",
+    "        os.makedirs(directory_to_save)\n",
+    "        \n",
+    "    # Save train and test data as CSV files with the year included in the file names\n",
+    "    train_df.to_csv(os.path.join(directory_to_save, f'train-data-split_{year}.csv'), index=False)\n",
+    "    test_df.to_csv(os.path.join(directory_to_save, f'test-data-split_{year}.csv'), index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a11fbb2c-548e-4bf8-bb41-abe22a4bd485",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "### Main Cleaning Pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "479d2872-0202-4eac-85d9-ce2b532881dd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def main(file_path, year,year_name):\n",
+    "    # Load and clean the data\n",
+    "    df_cleaned = load_and_clean_data(file_path)\n",
+    "    \n",
+    "    # Filter the data by years\n",
+    "    df_filtered = filter_by_years(df_cleaned, year)\n",
+    "    \n",
+    "    # Map the 'Product' column\n",
+    "    df_mapped = map_product_column(df_filtered)\n",
+    "    \n",
+    "    # Clean the customer narratives in the data\n",
+    "    df_clean_narrative = clean_narrative(df_mapped)\n",
+    "\n",
+    "    # Clean the data by frequency\n",
+    "    df_freq = filter_by_frequency(df_clean_narrative)\n",
+    "\n",
+    "    #Mapping the Issues and filtering Sub Issues\n",
+    "    df_final = map_issue_to_subissue(df_freq)\n",
+    "    \n",
+    "    # Split and save the data\n",
+    "    split_and_save_data(df_final,year_name)\n",
+    "    return df_final"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "60c6f92a-de2b-4c8a-817e-fb49a68f87ba",
+   "metadata": {},
+   "source": [
+    "### Calling the data preprocessing script"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "76932edd-4de8-47e1-a1a1-3cc4b07d6850",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_path = 'complaints.csv'\n",
+    "years_to_include = [2023]\n",
+    "year_name=2023\n",
+    "df_final=main(file_path, years_to_include,year_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "b55f4b09-6c89-470b-a4f0-60c0148534ec",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(247517, 11)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "ed38bd8a-2004-435a-87b2-2bcc43dbd565",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Credit Reporting               211695\n",
+       "Checking or savings account     12285\n",
+       "Credit/Prepaid Card             11975\n",
+       "Debt collection                  9380\n",
+       "Loans / Mortgage                 2182\n",
+       "Name: Product, dtype: int64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final.Product.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "dab29296-8a5b-44c3-8c6e-7b60e062343f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Credit reporting                              210735\n",
+       "General-purpose credit card or charge card     10668\n",
+       "Checking account                               10409\n",
+       "Other debt                                      3041\n",
+       "I do not know                                   2316\n",
+       "Credit card debt                                1652\n",
+       "Federal student loan servicing                  1344\n",
+       "Store credit card                               1307\n",
+       "Medical debt                                    1053\n",
+       "Savings account                                  989\n",
+       "Other personal consumer report                   960\n",
+       "Loan                                             732\n",
+       "Other banking product or service                 725\n",
+       "Auto debt                                        581\n",
+       "Telecommunications debt                          419\n",
+       "Rental debt                                      179\n",
+       "CD (Certificate of Deposit)                      162\n",
+       "Mortgage debt                                    139\n",
+       "Conventional home mortgage                       106\n",
+       "Name: Sub-product, dtype: int64"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final['Sub-product'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "10127c9e-ea4a-49ce-a5f2-76991abde850",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Incorrect information on your report                                                87200\n",
+       "Improper use of your report                                                         61868\n",
+       "Problem with a credit reporting company's investigation into an existing problem    45371\n",
+       "Problem with a company's investigation into an existing problem                     20985\n",
+       "Managing an account                                                                  7367\n",
+       "Attempts to collect debt not owed                                                    5453\n",
+       "Problem with a purchase shown on your statement                                      3253\n",
+       "Account Operations and Unauthorized Transaction Issues                               2450\n",
+       "Written notification about debt                                                      2404\n",
+       "Disputes and Misrepresentations                                                      2311\n",
+       "Payment and Funds Management                                                         2259\n",
+       "Closing an account                                                                   1975\n",
+       "Credit Report and Monitoring Issues                                                  1630\n",
+       "Dealing with your lender or servicer                                                 1293\n",
+       "Closing your account                                                                  813\n",
+       "Legal and Threat Actions                                                              662\n",
+       "Problem with a company's investigation into an existing issue                         223\n",
+       "Name: Issue, dtype: int64"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final['Issue'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "e774f715-6d3d-4035-9f28-753801490d13",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Information belongs to someone else                                                      57850\n",
+       "Reporting company used your report improperly                                            48732\n",
+       "Their investigation did not fix an error on your report                                  45395\n",
+       "Credit inquiries on your report that you don't recognize                                 13136\n",
+       "Account status incorrect                                                                 10208\n",
+       "Account information incorrect                                                             9267\n",
+       "Was not notified of investigation status or results                                       9200\n",
+       "Investigation took more than 30 days                                                      8928\n",
+       "Personal information incorrect                                                            5900\n",
+       "Debt is not yours                                                                         2785\n",
+       "Deposits and withdrawals                                                                  2626\n",
+       "Credit card company isn't resolving a dispute about a purchase on your statement          2289\n",
+       "Didn't receive enough information to verify debt                                          1777\n",
+       "Debt was result of identity theft                                                         1727\n",
+       "Old information reappears or never goes away                                              1714\n",
+       "Difficulty submitting a dispute or getting information about a dispute over the phone     1704\n",
+       "Company closed your account                                                               1517\n",
+       "Problem using a debit or ATM card                                                         1503\n",
+       "Public record information inaccurate                                                      1384\n",
+       "Transaction was not authorized                                                            1378\n",
+       "Problem with personal statement of dispute                                                1352\n",
+       "Other problem getting your report or credit score                                         1109\n",
+       "Card was charged for something you did not purchase with the card                          964\n",
+       "Banking errors                                                                             958\n",
+       "Funds not handled or disbursed as instructed                                               955\n",
+       "Overdrafts and overdraft fees                                                              951\n",
+       "Debt was paid                                                                              941\n",
+       "Information is missing that should be on the report                                        877\n",
+       "Attempted to collect wrong amount                                                          861\n",
+       "Problem during payment process                                                             840\n",
+       "Fee problem                                                                                764\n",
+       "Problem with fees                                                                          749\n",
+       "Other problem                                                                              701\n",
+       "Received bad information about your loan                                                   677\n",
+       "Funds not received from closed account                                                     673\n",
+       "Threatened or suggested your credit would be damaged                                       662\n",
+       "Didn't receive notice of right to dispute                                                  627\n",
+       "Trouble with how payments are being handled                                                616\n",
+       "Can't close your account                                                                   598\n",
+       "Problem accessing account                                                                  561\n",
+       "Account opened as a result of fraud                                                        561\n",
+       "Problem canceling credit monitoring or identify theft protection service                   521\n",
+       "Card opened as result of identity theft or fraud                                           511\n",
+       "Billing problem                                                                            468\n",
+       "Name: Sub-issue, dtype: int64"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_final['Sub-issue'].value_counts()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

data_preprocessing_scripts/data_splits/test-data-split_2022.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c203087801339af843b99a42a2187585d4af3445aab36c59c7cd7653b87587e
+size 62357439

data_preprocessing_scripts/data_splits/test-data-split_2023.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a253ea22f1b90530a803e61f1624d3b270ef62c88b89aece879cbe793e64eea
+size 68758811

data_preprocessing_scripts/data_splits/train-data-balanced.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acbfac231d968f341f65ce49dd5369f75fea7ab792e29c6116dfafe113589186
+size 70018604

data_preprocessing_scripts/data_splits/train-data-split_2022.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53dac829454c1da6425cfa6d07ad668e2150d4854b6a470c413bb267f7f0f51d
+size 185727392

data_preprocessing_scripts/data_splits/train-data-split_2023.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0cab77284db3c21e6d186d5a2d46ba27557a3320de250c19784822c73fc443
+size 205853579

data_preprocessing_scripts/issue_data_splits/account_operations_and_unauthorized_transaction_issues_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204e335acf3df6981acc48e8aa845b8f2f1ca356d961f99f3e973aca273599bc
+size 2090623

data_preprocessing_scripts/issue_data_splits/account_operations_and_unauthorized_transaction_issues_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f00513b1d44dbc7190ff68aa135655fdd22fe4b38bbe042a7713e68fc85ed8
+size 1883764

data_preprocessing_scripts/issue_data_splits/account_operations_and_unauthorized_transaction_issues_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e46867c68fee83e0994f36aa6e39be17a2e5e67eb05f17378aedc7bc01350ce
+size 206915

data_preprocessing_scripts/issue_data_splits/attempts_to_collect_debt_not_owed_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126f320e8e8df97c756c507ff4eb5c669f6058c92a3ec25f52c5f7b81599719b
+size 4135658

data_preprocessing_scripts/issue_data_splits/attempts_to_collect_debt_not_owed_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96f4e5342aa61f35cdd4eb42bd81a092fc25bc168f70e1f7be3322b8ea64cc4
+size 3718608

data_preprocessing_scripts/issue_data_splits/attempts_to_collect_debt_not_owed_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:036e70ce151a32c8a6757c2abef7f2547542d4c11c6541c6b6d705bd0063fd85
+size 417106

data_preprocessing_scripts/issue_data_splits/closing_an_account_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dbff3ce91e5c3433d3a0ae1cf543671c4025c2a9c3b9bcb40656975e17852d
+size 1799450

data_preprocessing_scripts/issue_data_splits/closing_an_account_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216a3640f091ef01b069809e4895528912bc2665358971d0eb30eee103892a68
+size 1587242

data_preprocessing_scripts/issue_data_splits/closing_an_account_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704275d826033848072c0d747e2595745185cd385c4a65b4b34cb46b849eb388
+size 212264

data_preprocessing_scripts/issue_data_splits/closing_your_account_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8428ebcc053869342b7343c709c2eef18d1a88973601dd4cead6141034c0ff2
+size 799995

data_preprocessing_scripts/issue_data_splits/closing_your_account_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4de5779cddd84b99a6695dca6e58d36ef93cd5d670fbee821a3b9ff2b39fc8
+size 736684

data_preprocessing_scripts/issue_data_splits/closing_your_account_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e2e7589b709c008ff61ee8a2c5ac805462c4b0028074c5abb0e6c824437903
+size 63367

data_preprocessing_scripts/issue_data_splits/credit_report_and_monitoring_issues_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7029133836244969f80daa7f682a53951e7bfdd1fc304ccb65dcd4f126adc526
+size 2353757

data_preprocessing_scripts/issue_data_splits/credit_report_and_monitoring_issues_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791d59058ebd88fec2f991f66b1e4fd557322179b4435215dcfcbc33f8984429
+size 2115089

data_preprocessing_scripts/issue_data_splits/credit_report_and_monitoring_issues_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53fbdf8fca538f24db0dc091d8f39a155a1e2952fdf2b96a62b9317d7dab7368
+size 238724

data_preprocessing_scripts/issue_data_splits/dealing_with_your_lender_or_servicer_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65c17415c7deba2c51c98fe5a96e563aff73cb9d2354a3c318f9d04ddffe746
+size 1500034

data_preprocessing_scripts/issue_data_splits/dealing_with_your_lender_or_servicer_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235e66bcf2e35fd99d858d301ffd7a2831b1f33c09098cd2fd503a6642a18048
+size 1370056

data_preprocessing_scripts/issue_data_splits/dealing_with_your_lender_or_servicer_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8289ab48f58adcacb8a81078cb8c9e216d61dedb87b907ac5f850ea7244218
+size 130034

data_preprocessing_scripts/issue_data_splits/disputes_and_misrepresentations_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa794e53b61d14225d6c03bc749fb83ad315ac5f485c4bcf946a6e0cc0fb34a
+size 2207971

data_preprocessing_scripts/issue_data_splits/disputes_and_misrepresentations_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00081a0b4c6c429f141df193159b55c550c2f15007970a54c12b10e25166e970
+size 1981586

data_preprocessing_scripts/issue_data_splits/disputes_and_misrepresentations_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66990f81784bae88083bb6cc6fa0582d94c0410050d70c261b5561547d18492d
+size 226441

data_preprocessing_scripts/issue_data_splits/improper_use_of_your_report_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ced2ef476e18679dee486e7b81ad35e6d66a6eb7ad936b92efeb85d30e65c9
+size 51426802

data_preprocessing_scripts/issue_data_splits/improper_use_of_your_report_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2dde33856c2cb76ef0674aa869cd6ccc6b96b548bb283d0c39c010aca0f722a
+size 46289254

data_preprocessing_scripts/issue_data_splits/improper_use_of_your_report_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df20ab17ff8751b8251244684294af3ebc11979b2bc699d7e207abe2bc511942
+size 5137604

data_preprocessing_scripts/issue_data_splits/incorrect_information_on_your_report_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c557f260383639a5248caae11d252de71cd72e88a23e20c7d32c1f65a42232bb
+size 67002391

data_preprocessing_scripts/issue_data_splits/incorrect_information_on_your_report_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a947015eb1b0d8a3958d70e6a86df6dd79436fe4bb42cf7dcae5238f5a1b95
+size 60306312

data_preprocessing_scripts/issue_data_splits/incorrect_information_on_your_report_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db7603a2b5d168bf2a6ee56dfaa5ad909a06e35ad345c5772344d6f77765ce96
+size 6696135

data_preprocessing_scripts/issue_data_splits/legal_and_threat_actions_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f9c755e499c83d36f8c5cb20d813cb5ac0db73d188c32a334ea9a47b6efb52
+size 612393

data_preprocessing_scripts/issue_data_splits/legal_and_threat_actions_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd9fd5013473734be09aac6b9563f2f10fbea3156a72d548e42bbdfef5c891a
+size 543877

data_preprocessing_scripts/issue_data_splits/legal_and_threat_actions_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7623b91317d2f8746f340422183fd089a3b0ace3647bdf3b71692928dbf5e3a9
+size 68572

data_preprocessing_scripts/issue_data_splits/managing_an_account_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46c2f03a742087ee42a05c22444648e56ad25bf551d19e28bd09b06a3425ef7
+size 7169538

data_preprocessing_scripts/issue_data_splits/managing_an_account_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d0d485f89d83edb41c61262e2fe5963bfb9100f6f54ef6b16788dc967326ff
+size 6420679

data_preprocessing_scripts/issue_data_splits/managing_an_account_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9882076a622b2c2bc1399fdb27b4ca396c6d6cd7623da4ac41af0456471261
+size 748915

data_preprocessing_scripts/issue_data_splits/payment_and_funds_management_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15719bc2484dc054a68e9c7d38bc110aedf6fa82962058088f8f2c1dc9d2384f
+size 1854714

data_preprocessing_scripts/issue_data_splits/payment_and_funds_management_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d12880274bfdccc9e99f2b973c5f7bf7239e2e8fdda2e08833d1a68a013c3b0
+size 1680205

data_preprocessing_scripts/issue_data_splits/payment_and_funds_management_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec358880a0bc9e79f74843b91e0607e5ed2930831715a539231a0b28d9158681
+size 174565

data_preprocessing_scripts/issue_data_splits/problem_with_a_company's_investigation_into_an_existing_issue_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51956f542a4924d8e6f5c363210406a4ccfa553f5703bdb61b9c252d3c74198b
+size 320657

data_preprocessing_scripts/issue_data_splits/problem_with_a_company's_investigation_into_an_existing_issue_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1011d1017bebc41a4df1217ee9d99604c9e1aa1e11f4f386fb34896383e8dca
+size 284289

data_preprocessing_scripts/issue_data_splits/problem_with_a_company's_investigation_into_an_existing_issue_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f7f02d80205cf532ebbd6307e849f71eaeab724e0c5c94cf7de9cca4397d32
+size 36424

data_preprocessing_scripts/issue_data_splits/problem_with_a_company's_investigation_into_an_existing_problem_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf2935aed3387bc5bcf55dc3afaf29794eb8f4b084ec843b092da96b2c7590c
+size 15288595

data_preprocessing_scripts/issue_data_splits/problem_with_a_company's_investigation_into_an_existing_problem_train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ae7dd9f926f0cce7be50f1a21327b4bd2d416edd2524b87a1a5617457447ef
+size 13714937

data_preprocessing_scripts/issue_data_splits/problem_with_a_company's_investigation_into_an_existing_problem_val_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff329c35b163e0ff2d3e868cc41a1046f045903ae0fede9cd341655f906b310
+size 1573714

data_preprocessing_scripts/issue_data_splits/problem_with_a_credit_reporting_company's_investigation_into_an_existing_problem_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3324a8147b120f23f086f69a7a3ccea1b893ec6769ee470e3121dfe9bec059a0
+size 35696420