blocks-transformer/block.py

import logging
import pandas as pd
import math
import json

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
)
logger = logging.getLogger(__name__)

# with open('C:/Users/abinisha/flowx/kiwi-blocks/sequence-2/fraud_v1_pre_processing/category_orders_train.json', 'r') as f:
#     category_orders = json.load(f)

def __main__(user_age: int,persona_entity_confidence_score: float,persona_selfie_similarity_score_right: float,
             persona_selfie_similarity_score_left: float,persona_hesitation_percentage: float,
             persona_hesitation_count: float,device_id_age_max: int,selfie_consistency_score_avg: float,
             device_consistency: int,selfie_consistency_score: float,global_fs_ls: int,inquiry_frequency: int,
             confidence_score_min: float,contract_date_fs_sub: int,browser_os: str,user_city_ip_match: int,
             device_id_age_avg: float,persona_distraction_events: float,sub_fs_ls: int,device_id_age_min: int,
             confidence_score_max: float,persona_phone_risk_score: float,ip_address_risk_level: str,
             login_frequency: float,suspect_score: int,confidence_score: float,name_consistency: int,
             ip_location_consistency: int) ->dict:

    dtypes = {
        'user_age': 'int',
        'persona_entity_confidence_score': 'float',
        'persona_selfie_similarity_score_right': 'float',
        'persona_selfie_similarity_score_left': 'float',
        'persona_hesitation_percentage': 'float',
        'persona_hesitation_count': 'float',
        'device_id_age_max': 'int',
        'selfie_consistency_score_avg': 'float',
        'device_consistency': 'int',
        'selfie_consistency_score': 'float',
        'global_fs_ls': 'int',
        'inquiry_frequency': 'int',
        'confidence_score_min': 'float',
        'contract_date_fs_sub': 'int',
        'browser_os': 'string',
        'user_city_ip_match': 'int',
        'device_id_age_avg': 'float',
        'persona_distraction_events': 'float',
        'sub_fs_ls': 'int',
        'device_id_age_min': 'int',
        'confidence_score_max': 'float',
        'persona_phone_risk_score': 'float',
        'ip_address_risk_level': 'string',
        'login_frequency': 'float',
        'suspect_score': 'int',
        'confidence_score': 'float',
        'name_consistency': 'int',
        'ip_location_consistency': 'int'
    }

    input_data = {"user_age" : user_age,"persona_entity_confidence_score" : persona_entity_confidence_score,
        "persona_selfie_similarity_score_right" : persona_selfie_similarity_score_right,
        "persona_selfie_similarity_score_left" : persona_selfie_similarity_score_left,
        "persona_hesitation_percentage" : persona_hesitation_percentage,
        "persona_hesitation_count" : persona_hesitation_count,"device_id_age_max" : device_id_age_max,
        "selfie_consistency_score_avg" : selfie_consistency_score_avg,"device_consistency" : device_consistency,
        "selfie_consistency_score" : selfie_consistency_score,"global_fs_ls" : global_fs_ls,
        "inquiry_frequency" : inquiry_frequency,"confidence_score_min" : confidence_score_min,
        "contract_date_fs_sub" : contract_date_fs_sub,"browser_os" : browser_os,
        "user_city_ip_match" : user_city_ip_match,"device_id_age_avg" : device_id_age_avg,
        "persona_distraction_events" : persona_distraction_events,"sub_fs_ls" : sub_fs_ls,
        "device_id_age_min" : device_id_age_min,"confidence_score_max" : confidence_score_max,
        "persona_phone_risk_score" : persona_phone_risk_score,"ip_address_risk_level" : ip_address_risk_level,
        "login_frequency" : login_frequency,"suspect_score" : suspect_score,"confidence_score" : confidence_score,
        "name_consistency" : name_consistency,"ip_location_consistency" : ip_location_consistency}

    df = pd.DataFrame(input_data, index=[False])

    for column, dtype in dtypes.items():
        if dtype == 'int' or dtype == 'float':
            df[column] = pd.to_numeric(df[column], errors='coerce')
        else:
            df[column] = df[column].astype(str).str.lower()
            
    output_data = df.iloc[0].where(pd.notnull(df.iloc[0]), None).to_dict()

    logger.info(f"Fraud V1 Pre processed data: {output_data}")

    return output_data