backend/src/clean_data_json.py

import json
import pandas as pd
from sklearn.preprocessing import StandardScaler

scale = StandardScaler()

x={
    "State": {
        "AK": 0,
        "AL": 1,
        "AR": 2,
        "AZ": 3,
        "CA": 4,
        "CO": 5,
        "CT": 6,
        "DC": 7,
        "DE": 8,
        "FL": 9,
        "GA": 10,
        "HI": 11,
        "IA": 12,
        "ID": 13,
        "IL": 14,
        "IN": 15,
        "KS": 16,
        "KY": 17,
        "LA": 18,
        "MA": 19,
        "MD": 20,
        "ME": 21,
        "MI": 22,
        "MN": 23,
        "MO": 24,
        "MS": 25,
        "MT": 26,
        "NC": 27,
        "ND": 28,
        "NE": 29,
        "NH": 30,
        "NJ": 31,
        "NM": 32,
        "NV": 33,
        "NY": 34,
        "OH": 35,
        "OK": 36,
        "OR": 37,
        "PA": 38,
        "RI": 39,
        "SC": 40,
        "SD": 41,
        "TN": 42,
        "TX": 43,
        "UT": 44,
        "VA": 45,
        "VT": 46,
        "WA": 47,
        "WI": 48,
        "WV": 49,
        "WY": 50
    },
    "BankState": {
        "AK": 0,
        "AL": 1,
        "AR": 2,
        "AZ": 3,
        "CA": 4,
        "CO": 5,
        "CT": 6,
        "DC": 7,
        "DE": 8,
        "EN": 9,
        "FL": 10,
        "GA": 11,
        "GU": 12,
        "HI": 13,
        "IA": 14,
        "ID": 15,
        "IL": 16,
        "IN": 17,
        "KS": 18,
        "KY": 19,
        "LA": 20,
        "MA": 21,
        "MD": 22,
        "ME": 23,
        "MI": 24,
        "MN": 25,
        "MO": 26,
        "MS": 27,
        "MT": 28,
        "NC": 29,
        "ND": 30,
        "NE": 31,
        "NH": 32,
        "NJ": 33,
        "NM": 34,
        "NV": 35,
        "NY": 36,
        "OH": 37,
        "OK": 38,
        "OR": 39,
        "PA": 40,
        "PR": 41,
        "RI": 42,
        "SC": 43,
        "SD": 44,
        "TN": 45,
        "TX": 46,
        "UT": 47,
        "VA": 48,
        "VT": 49,
        "WA": 50,
        "WI": 51,
        "WV": 52,
        "WY": 53
    },
    "Industry": {
        "Accom/Food_serv": 0,
        "Admin_sup/Waste_Mgmt_Rem": 1,
        "Ag/For/Fish/Hunt": 2,
        "Arts/Entertain/Rec": 3,
        "Construction": 4,
        "Educational": 5,
        "Finance/Insurance": 6,
        "Healthcare/Social_assist": 7,
        "Information": 8,
        "Manufacturing": 9,
        "Mgmt_comp": 10,
        "Min/Quar/Oil_Gas_ext": 11,
        "Other_no_pub": 12,
        "Prof/Science/Tech": 13,
        "Public_Admin": 14,
        "RE/Rental/Lease": 15,
        "Retail_trade": 16,
        "Trans/Ware": 17,
        "Unknown": 18,
        "Utilities": 19,
        "Wholesale_trade": 20
    }
}
def clean_data(df):
    df['State'] = df['State'].map(x['State'])
    df['BankState'] = df['BankState'].map(x['BankState'])
    df['Industry'] = df['Industry'].map(x['Industry'])
    return df

# Function to scale data
def scaling(df):
    # Only scale numerical columns
    num_cols = df.select_dtypes(include=['number']).columns
    df[num_cols] = scale.fit_transform(df[num_cols])
    return df