EDT Processing block

README.md

@@ -1 +1,9 @@
-**Hello world!!!**
+## Overview
+This block (`block.py`) is responsible for loading and scoring the model.
+
+## Key Inputs & Outputs
+- **Request**: Refer to `request_schema.json` for detailed input fields and validation rules.  
+- **Response**: Refer to `response_schema.json` for the returned structure and data types.
+
+## Implementation Details
+- All core logic resides in `block.py` within the `__main__` function.

block.py

@@ -1,21 +1,86 @@
-@flowx_block
-def example_function(request: dict) -> dict:
+import logging
+import joblib
+import xgboost as xgb
+import pandas as pd
+import json
+import math
 
-  # Processing logic here...
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
+)
+logger = logging.getLogger(__name__)
 
-  return {
-    "meta_info": [
-      {
-        "name": "created_date",
-        "type": "string",
-        "value": "2024-11-05"
-      }
-    ],
-    "fields": [
-      {
-        "name": "",
-        "type": "",
-        "value": ""
-      }
-    ]
-  }
+# with open('C:/Users/abinisha/flowx/kiwi-blocks/sequence-2/fraud_v1_pre_processing/category_orders_train.json', 'r') as f:
+with open('./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:
+    
+    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
+    }
+
+    # Load the model
+    model = joblib.load("./xgboost_model.joblib") 
+    # model = joblib.load("C:/Users/abinisha/flowx/kiwi-blocks/sequence-2/fraud_v1_processing/xgboost_model.joblib")
+
+    df = pd.DataFrame(input_data, index=[False])
+
+    # Ensure categorical columns are treated as categories
+    categorical_columns = ['browser_os', 'ip_address_risk_level']
+    for col in categorical_columns:
+        if col in df.columns:
+            df[col] = df[col].str.lower().replace([None, "", "null", math.nan], "none")
+            df[col] = pd.Categorical(df[col], categories=category_orders.get(col, []))
+
+    # Ensure all columns are numeric where possible
+    for col in df.columns:
+        if col not in categorical_columns:
+            df[col] = pd.to_numeric(df[col], errors='ignore')
+
+    model_feature_names = model.feature_names
+
+    dmatrix = xgb.DMatrix(df[model_feature_names], enable_categorical=True)
+
+    prediction = model.predict(dmatrix)[0]
+
+    logger.info(f"Fraud V1 Predicted Score: {prediction}")
+
+    return {'probability': float(prediction)}

category_orders_train.json

@@ -0,0 +1 @@
+{"browser_os": ["android", "chrome os", "ios", "linux", "mac os x", "none", "windows"], "ip_address_risk_level": ["high-risk", "low-risk", "none"]}

request_schema.json

@@ -1 +1,119 @@
-{}
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "type": "object",
+  "properties": {
+    "user_age": {
+      "type": ["integer", "null"],
+      "description": "Age of the user at the contract date, based on birthdate and contract date"
+    },
+    "persona_entity_confidence_score": {
+      "type": ["number", "null"],
+      "description": "Based on confidence reasons assign a score between 0 and 100"
+    },
+    "persona_selfie_similarity_score_right": {
+      "type": ["number", "null"],
+      "description": "Similarity score from the right side selfie"
+    },
+    "persona_selfie_similarity_score_left": {
+      "type": ["number", "null"],
+      "description": "Similarity score from the left side selfie"
+    },
+    "persona_hesitation_percentage": {
+      "type": ["number", "null"],
+      "description": "Percentage of time in the flow where the customer did not enter inputs"
+    },
+    "persona_hesitation_count": {
+      "type": ["number", "null"],
+      "description": "Persona hesitation count"
+    },
+    "device_id_age_max": {
+      "type": ["integer", "null"],
+      "description": "This calculates the maximum device age for a user and loan, similar to min and avg logic but for the max value."
+    },
+    "selfie_consistency_score_avg": {
+      "type": ["number", "null"],
+      "description": "Average selfie consistency score for the user's persona activity"
+    },
+    "device_consistency": {
+      "type": ["integer", "null"],
+      "description": "Number of distinct devices associated with a user and loan"
+    },
+    "selfie_consistency_score": {
+      "type": ["number", "null"],
+      "description": "Average similarity score between left and right selfie"
+    },
+    "global_fs_ls": {
+      "type": ["integer", "null"],
+      "description": "Days between the first and last global appearance of the device"
+    },
+    "inquiry_frequency": {
+      "type": ["integer", "null"],
+      "description": "Number of inquiries made by the user regarding the loan"
+    },
+    "confidence_score_min": {
+      "type": ["number", "null"],
+      "description": "The minimum recorded confidence score for the user and loan during the timeframe."
+    },
+    "contract_date_fs_sub": {
+      "type": ["integer", "null"],
+      "description": "Days between the first subscription appearance and contract date"
+    },
+    "browser_os": {
+      "type": ["string", "null"],
+      "description": "Browser OS"
+    },
+    "user_city_ip_match": {
+      "type": ["integer", "null"],
+      "description": "Checks if the user's city matches the IP city"
+    },
+    "device_id_age_avg": {
+      "type": ["number", "null"],
+      "description": "This calculates the rolling average of device_id_age for a user and loan. If no previous rows, the current value is returned."
+    },
+    "persona_distraction_events": {
+      "type": ["number", "null"],
+      "description": "Persona distraction events"
+    },
+    "sub_fs_ls": {
+      "type": ["integer", "null"],
+      "description": "Days between the first and last subscription activity"
+    },
+    "device_id_age_min": {
+      "type": ["integer", "null"],
+      "description": "This calculates the minimum device age for a user and loan, falling back to the current device age if no prior values exist."
+    },
+    "confidence_score_max": {
+      "type": ["number", "null"],
+      "description": "The maximum confidence score recorded for the user and loan combination."
+    },
+    "persona_phone_risk_score": {
+      "type": ["number", "null"],
+      "description": "Risk associated with the phone number. The risk score ranges from 0 to 100. The higher the risk score, the higher the risk level."
+    },
+    "ip_address_risk_level": {
+      "type": ["string", "null"],
+      "description": "Checks if the IP country code matches the persona country code"
+    },
+    "login_frequency": {
+      "type": ["number", "null"],
+      "description": "This counts the number of times the user logs in based on the inquiry_updated_at timestamp, providing insights into the user's login behavior throughout the loan process."
+    },
+    "suspect_score": {
+      "type": ["integer", "null"],
+      "description": "Suspect score"
+    },
+    "confidence_score": {
+      "type": ["number", "null"],
+      "description": "Confidence score"
+    },
+    "name_consistency": {
+      "type": ["integer", "null"],
+      "description": "Checks if the first name in the persona matches the user-provided first name"
+    },
+    "ip_location_consistency": {
+      "type": ["integer", "null"],
+      "description": "Number of distinct IP locations for a user and loan"
+    }
+  },
+  "required": []
+}

requirements.txt

@@ -1 +1,5 @@
-{}
+jsonschema==4.23.0
+xgboost==1.7.5
+joblib==1.3.2
+pandas==2.2.2
+numpy==1.23.5

response_schema.json

@@ -1 +1,10 @@
-{}
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "type": "object",
+  "properties": {
+    "probability": {
+      "type": "number",
+      "description": "Fraud Model predicted score."
+    }
+  }
+}