Compare commits
No commits in common. "g-1-v-1" and "main" have entirely different histories.
61
block.py
61
block.py
@ -1,44 +1,21 @@
|
||||
import logging
|
||||
from typing import List, Dict
|
||||
from graph_pre_processing import pre_processing_g1, pre_processing_g2
|
||||
from graph_processing import processing_g1, processing_g2
|
||||
from graph_post_processing import post_processing_g1, post_processing_g2
|
||||
@flowx_block
|
||||
def example_function(request: dict) -> dict:
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
# Processing logic here...
|
||||
|
||||
|
||||
def __main__(results: List[Dict]) -> Dict:
|
||||
logger.info("data receiving in g1v1 block: %s", results)
|
||||
g1_input = pre_processing_g1(results)
|
||||
g2_input = pre_processing_g2(results)
|
||||
logger.info("pre_processed_data_g1: %s", g1_input)
|
||||
logger.info("pre_processed_data_g2: %s", g2_input)
|
||||
|
||||
cluster_size = g1_input.get("cluster_size", 2)
|
||||
if cluster_size is None:
|
||||
cluster_size = 2
|
||||
|
||||
if cluster_size < 2:
|
||||
g1_processed = {**g1_input, "prediction": 0}
|
||||
g2_processed = {**g2_input, "prediction_g2": 0}
|
||||
else:
|
||||
g1_processed = processing_g1(g1_input)
|
||||
g2_processed = processing_g2(g2_input)
|
||||
|
||||
logger.info("prediction_g1: %.8f", float(g1_processed.get("prediction", 0)))
|
||||
logger.info("prediction_g2: %.8f", float(g2_processed.get("prediction_g2", 0)))
|
||||
|
||||
final_g1 = post_processing_g1(g1_processed)
|
||||
final_g2 = post_processing_g2(g2_processed)
|
||||
final = {**final_g1, **final_g2}
|
||||
logger.info(final)
|
||||
|
||||
return final
|
||||
|
||||
# testing :
|
||||
# __main__
|
||||
return {
|
||||
"meta_info": [
|
||||
{
|
||||
"name": "created_date",
|
||||
"type": "string",
|
||||
"value": "2024-11-05"
|
||||
}
|
||||
],
|
||||
"fields": [
|
||||
{
|
||||
"name": "",
|
||||
"type": "",
|
||||
"value": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@ -1,55 +0,0 @@
|
||||
import logging
|
||||
import math
|
||||
from decimal import Decimal, ROUND_HALF_UP
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def post_processing_g1(data):
|
||||
try:
|
||||
prediction = data.get("prediction", 0)
|
||||
score_g1 = round(
|
||||
min(prediction * 100 + 0.00001, 1) * 89 +
|
||||
max(math.log2(prediction * 100 + 0.000001) * 193, 0),
|
||||
0
|
||||
)
|
||||
data["hd_score_g1"] = score_g1
|
||||
logger.info("score_g1 calculated: %s", score_g1)
|
||||
except Exception as e:
|
||||
logger.error("Error processing score_g1 calculations: %s", e)
|
||||
|
||||
return {
|
||||
key: data.get(key, None)
|
||||
for key in [
|
||||
"hd_score_m1", "hd_score_g1", "cluster_size_users_v2",
|
||||
"target_connected_30_sum", "email_cnt", "rejected_app_count",
|
||||
"app_dt_day_cnt", "hd_score_iso_m2"
|
||||
]
|
||||
}
|
||||
|
||||
|
||||
def post_processing_g2(data):
|
||||
prediction = data.get("prediction_g2", data.get("prediction"))
|
||||
hd_score_g2 = None
|
||||
|
||||
try:
|
||||
if prediction is not None:
|
||||
prediction_val = float(prediction)
|
||||
raw_score = (prediction_val * 100) * 20 + math.log((prediction_val + 0.000001) * 100, 2) * 41.6
|
||||
# SQL-like rounding (half up)
|
||||
hd_score_g2 = int(Decimal(str(raw_score)).quantize(Decimal("1"), rounding=ROUND_HALF_UP))
|
||||
hd_score_g2 = max(hd_score_g2, 0.0)
|
||||
logger.info("score_g2 calculated: %s", hd_score_g2)
|
||||
except Exception as e:
|
||||
logger.error("Error processing score_g2 calculations: %s", e)
|
||||
|
||||
return {"hd_score_g2": hd_score_g2}
|
||||
|
||||
|
||||
# Backward compatibility alias
|
||||
post_processing = post_processing_g1
|
||||
@ -1,91 +0,0 @@
|
||||
import logging
|
||||
import numpy as np
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
G2_PREDICTORS = [
|
||||
"hd_score_m2",
|
||||
"rejected_app_count",
|
||||
"hd_score_m2_connected_max",
|
||||
"hd_score_m2_connected_avg",
|
||||
"applicant_age_connected_max",
|
||||
"applicant_age_connected_avg",
|
||||
"account_tel_first_seen_min_conn",
|
||||
"account_tel_first_seen_max_conn",
|
||||
"account_tel_first_seen_avg_conn",
|
||||
"ssn_hash_first_seen_min_conn",
|
||||
"ssn_hash_first_seen_avg_conn",
|
||||
"account_login_first_seen_min_conn",
|
||||
"digital_id_first_seen_max_conn",
|
||||
"true_ip_first_seen_min_conn",
|
||||
"true_ip_first_seen_max_conn",
|
||||
"dist_em_ip_ref_km_min_conn",
|
||||
"pct_acc_email_attr_challenged_1_conn",
|
||||
"account_login_first_seen_range_conn",
|
||||
"account_login_first_seen_stddev_conn",
|
||||
"cpu_clock_range_conn",
|
||||
"summary_risk_score_max_conn",
|
||||
]
|
||||
|
||||
|
||||
def _coerce_float(value):
|
||||
if value is None:
|
||||
return np.nan
|
||||
try:
|
||||
return float(value)
|
||||
except (TypeError, ValueError):
|
||||
return np.nan
|
||||
|
||||
|
||||
def pre_processing_g1(results):
|
||||
result = results[0]
|
||||
dtypes = {
|
||||
"hd_score_m1": float,
|
||||
"cluster_size_users_v2": float,
|
||||
"target_connected_30_sum": float,
|
||||
"email_cnt": float,
|
||||
"rejected_app_count": float,
|
||||
"app_dt_day_cnt": float,
|
||||
"hd_score_iso_m2": float
|
||||
}
|
||||
data = {
|
||||
"hd_score_m1": result["hd_score_m1"],
|
||||
"cluster_size_users_v2": result["cluster_size_users_v2"],
|
||||
"target_connected_30_sum": result["target_connected_30_sum"],
|
||||
"email_cnt": result["email_cnt"],
|
||||
"rejected_app_count": result["rejected_app_count"],
|
||||
"app_dt_day_cnt": result["app_dt_day_cnt"],
|
||||
"cluster_size": result["cluster_size"],
|
||||
"hd_score_iso_m2": result["hd_score_iso_m2"],
|
||||
}
|
||||
|
||||
for col, dtype in dtypes.items():
|
||||
if col in data:
|
||||
value = str(data[col]).strip()
|
||||
data[col] = dtype(value) if value.replace(".", "", 1).isdigit() else None
|
||||
|
||||
return data
|
||||
|
||||
|
||||
def pre_processing_g2(results):
|
||||
result = results[0]
|
||||
working = dict(result)
|
||||
if "rejected_app_count_g2" in working:
|
||||
# Always prefer the G2-specific count for G2 preprocessing
|
||||
working["rejected_app_count"] = working.get("rejected_app_count_g2")
|
||||
|
||||
data = {}
|
||||
for feature in G2_PREDICTORS:
|
||||
data[feature] = _coerce_float(working.get(feature))
|
||||
|
||||
data["cluster_size"] = working.get("cluster_size")
|
||||
return data
|
||||
|
||||
|
||||
# Backward compatibility alias
|
||||
pre_processing = pre_processing_g1
|
||||
@ -1,61 +0,0 @@
|
||||
import xgboost as xgb
|
||||
import pandas as pd
|
||||
import joblib
|
||||
import logging
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
|
||||
)
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def processing_g1(data):
|
||||
df = pd.DataFrame([data])
|
||||
if df.empty:
|
||||
logger.error("Input DataFrame is empty.")
|
||||
|
||||
# Load Model
|
||||
# model_path = "C:/Users/abinisha/habemco_flowx/g1_v1/xgboost_model_G1.joblib"
|
||||
model_path = "./xgboost_model_G1.joblib"
|
||||
model = joblib.load(model_path)
|
||||
|
||||
expected_features = model.feature_names
|
||||
|
||||
df = df.applymap(lambda x: float("nan") if x is None else x)
|
||||
|
||||
dmatrix = xgb.DMatrix(df[expected_features], enable_categorical=True, missing=float("nan"))
|
||||
|
||||
prediction = model.predict(dmatrix)
|
||||
|
||||
df["prediction"] = prediction
|
||||
|
||||
return df.iloc[0].to_dict()
|
||||
|
||||
|
||||
def processing_g2(data):
|
||||
df = pd.DataFrame([data])
|
||||
if df.empty:
|
||||
logger.error("Input DataFrame is empty.")
|
||||
|
||||
# model_path = "C:/Users/abinisha/habemco_flowx/g1_v1/xgboost_model_G2.joblib"
|
||||
model_path = "./xgboost_model_G2.joblib"
|
||||
model = joblib.load(model_path)
|
||||
|
||||
expected_features = model.feature_names
|
||||
|
||||
df = df.reindex(columns=expected_features)
|
||||
df = df.applymap(lambda x: float("nan") if x is None else x)
|
||||
|
||||
dmatrix = xgb.DMatrix(df[expected_features], enable_categorical=True, missing=float("nan"))
|
||||
|
||||
prediction = model.predict(dmatrix)
|
||||
|
||||
df["prediction_g2"] = prediction
|
||||
|
||||
return df.iloc[0].to_dict()
|
||||
|
||||
|
||||
# Backward compatibility alias
|
||||
processing = processing_g1
|
||||
@ -1,11 +1 @@
|
||||
{
|
||||
"$schema": "http://json-schema.org/draft-07/schema",
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"results": {
|
||||
"type": ["array", "null"],
|
||||
"items": {"type": "object"}
|
||||
}
|
||||
},
|
||||
"required": []
|
||||
}
|
||||
{}
|
||||
|
||||
@ -1,5 +1 @@
|
||||
joblib==1.4.2
|
||||
pandas==2.2.3
|
||||
xgboost==2.1.3
|
||||
typing==3.6.1
|
||||
|
||||
{}
|
||||
|
||||
@ -1,42 +1 @@
|
||||
{
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"hd_score_m1": {
|
||||
"type": ["number", "null"],
|
||||
"description": "HD fraud Score M1"
|
||||
},
|
||||
"hd_score_g1": {
|
||||
"type": ["number", "null"],
|
||||
"description": "HD fraud Score G1"
|
||||
},
|
||||
"hd_score_g2": {
|
||||
"type": ["number", "null"],
|
||||
"description": "HD fraud Score G2"
|
||||
},
|
||||
"cluster_size_users_v2": {
|
||||
"type": ["number", "null"],
|
||||
"description": "Size of the user cluster in version 2."
|
||||
},
|
||||
"target_connected_30_sum": {
|
||||
"type": ["number", "null"],
|
||||
"description": "Sum of target connections within 30 days."
|
||||
},
|
||||
"email_cnt": {
|
||||
"type": ["number", "null"],
|
||||
"description": "Count of emails associated with the application."
|
||||
},
|
||||
"rejected_app_count": {
|
||||
"type": ["number", "null"],
|
||||
"description": "Count of rejected applications for the applicant."
|
||||
},
|
||||
"app_dt_day_cnt": {
|
||||
"type": ["number", "null"],
|
||||
"description": "Number of application days counted."
|
||||
},
|
||||
"hd_score_iso_m2": {
|
||||
"type": ["number", "null"],
|
||||
"description": "HD fraud Score M2"
|
||||
}
|
||||
}
|
||||
}
|
||||
{}
|
||||
|
||||
@ -1,47 +0,0 @@
|
||||
import unittest
|
||||
from block import __main__
|
||||
|
||||
|
||||
data = [{
|
||||
"application_key": "A3CDD39F-10F8-40B0-A4C9-0E1558B75131",
|
||||
"hd_score_m1": 1101.0,
|
||||
"hd_score_iso_m2": 1113,
|
||||
"cluster_size": 10,
|
||||
"cluster_size_users_v2": 3,
|
||||
"target_connected_30_sum": 0.0,
|
||||
"email_cnt": 3,
|
||||
"rejected_app_count": 6.0,
|
||||
"app_dt_day_cnt": 7,
|
||||
"hd_score_m2": 1188,
|
||||
"hd_score_m2_connected_max": 1197.0,
|
||||
"hd_score_m2_connected_avg": 1184.888889,
|
||||
"applicant_age_connected_max": 60.0,
|
||||
"applicant_age_connected_avg": 52.44444444,
|
||||
"account_tel_first_seen_min_conn": 879.0,
|
||||
"account_tel_first_seen_max_conn": 989.0,
|
||||
"account_tel_first_seen_avg_conn": 949.6666667,
|
||||
"ssn_hash_first_seen_min_conn": 5.0,
|
||||
"ssn_hash_first_seen_avg_conn": 58.0,
|
||||
"account_login_first_seen_min_conn": 0.0,
|
||||
"digital_id_first_seen_max_conn": 2652.0,
|
||||
"true_ip_first_seen_min_conn": 1857.0,
|
||||
"true_ip_first_seen_max_conn": 1967.0,
|
||||
"dist_em_ip_ref_km_min_conn": 17.43689023,
|
||||
"pct_acc_email_attr_challenged_1_conn": 0.0,
|
||||
"account_login_first_seen_range_conn": 2313.0,
|
||||
"account_login_first_seen_stddev_conn": 1042.4994,
|
||||
"cpu_clock_range_conn": 9054.0,
|
||||
"summary_risk_score_max_conn": 14.0
|
||||
}]
|
||||
|
||||
|
||||
class TestBlock(unittest.TestCase):
|
||||
def test_main_returns_scores(self):
|
||||
block_result = __main__(data)
|
||||
self.assertIsInstance(block_result, dict)
|
||||
self.assertIn("hd_score_g1", block_result)
|
||||
self.assertIn("hd_score_g2", block_result)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Loading…
x
Reference in New Issue
Block a user