tannedcung/sbt-idp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix: misleading avg, update accuracy formula

Browse Source
This commit is contained in:
TannedCung 2024-06-17 19:05:20 +07:00
parent 74ff2a6794
commit c3114534fc
1 changed files with 29 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
cope2n-api/fwd_api/utils/accuracy.py
View File

@ -18,8 +18,10 @@ from ..models import SubscriptionRequest, Report, ReportFile
import json import json
from typing import Union, List, Dict from typing import Union, List, Dict
valid_keys = ["retailername", "sold_to_party", "invoice_no", "purchase_date", "imei_number"] VALID_KEYS = ["retailername", "sold_to_party", "invoice_no", "purchase_date", "imei_number"]
optional_keys = ['invoice_no'] KEYS_BY_FILE_TYPE = {"imei": ["imei_number"],
"invoice": ["retailername", "invoice_no", "purchase_date"]}
OPTIONAL_KEYS = ['invoice_no']
class ReportAccumulateByRequest: class ReportAccumulateByRequest:
def __init__(self, sub): def __init__(self, sub):
@ -123,6 +125,7 @@ class ReportAccumulateByRequest:
"review_progress": [] "review_progress": []
}, },
self.report = copy.deepcopy(self.month_format) self.report = copy.deepcopy(self.month_format)
self.report["average_accuracy_rate"]["avg"] = IterAvg()
@staticmethod @staticmethod
def update_total(total, report_file): def update_total(total, report_file):
@ -142,8 +145,10 @@ class ReportAccumulateByRequest:
for key in settings.FIELD: for key in settings.FIELD:
if sum([len(report_file.reviewed_accuracy[x]) for x in report_file.reviewed_accuracy.keys() if "_count" not in x]) > 0 : if sum([len(report_file.reviewed_accuracy[x]) for x in report_file.reviewed_accuracy.keys() if "_count" not in x]) > 0 :
total["average_accuracy_rate"][key].add(report_file.reviewed_accuracy.get(key, [])) total["average_accuracy_rate"][key].add(report_file.reviewed_accuracy.get(key, []))
total["average_accuracy_rate"]['avg'].add(report_file.reviewed_accuracy.get(key, []))
elif sum([len(report_file.feedback_accuracy[x]) for x in report_file.feedback_accuracy.keys() if "_count" not in x]) > 0: elif sum([len(report_file.feedback_accuracy[x]) for x in report_file.feedback_accuracy.keys() if "_count" not in x]) > 0:
total["average_accuracy_rate"][key].add(report_file.feedback_accuracy.get(key, [])) total["average_accuracy_rate"][key].add(report_file.feedback_accuracy.get(key, []))
total["average_accuracy_rate"]['avg'].add(report_file.feedback_accuracy.get(key, []))
total["feedback_accuracy"][key].add(report_file.feedback_accuracy.get(key, [])) total["feedback_accuracy"][key].add(report_file.feedback_accuracy.get(key, []))
total["reviewed_accuracy"][key].add(report_file.reviewed_accuracy.get(key, [])) total["reviewed_accuracy"][key].add(report_file.reviewed_accuracy.get(key, []))
@ -346,17 +351,17 @@ class ReportAccumulateByRequest:
for key in _report["average_processing_time"].keys(): for key in _report["average_processing_time"].keys():
_report["average_processing_time"][key] = _report["average_processing_time"][key]() _report["average_processing_time"][key] = _report["average_processing_time"][key]()
avg_acc = 0 # avg_acc = 0
count_acc = 0 # count_acc = 0
for key in settings.FIELD: for key in settings.FIELD:
_report["average_accuracy_rate"][key] = _report["average_accuracy_rate"][key]() _report["average_accuracy_rate"][key] = _report["average_accuracy_rate"][key]()
for accuracy_type in ["feedback_accuracy", "reviewed_accuracy"]: for accuracy_type in ["feedback_accuracy", "reviewed_accuracy"]:
if (_report[accuracy_type][key].count + count_acc) > 0: # if (_report[accuracy_type][key].count + count_acc) > 0:
avg_acc = (avg_acc*count_acc + _report[accuracy_type][key].avg*_report[accuracy_type][key].count) / (_report[accuracy_type][key].count + count_acc) # avg_acc = (avg_acc*count_acc + _report[accuracy_type][key].avg*_report[accuracy_type][key].count) / (_report[accuracy_type][key].count + count_acc)
count_acc += _report[accuracy_type][key].count # count_acc += _report[accuracy_type][key].count
_report[accuracy_type][key] = _report[accuracy_type][key]() _report[accuracy_type][key] = _report[accuracy_type][key]()
_report["average_accuracy_rate"]["avg"] = avg_acc _report["average_accuracy_rate"]["avg"] = _report["average_accuracy_rate"]["avg"]()
_report["review_progress"] = _report["review_progress"].count(1)/(_report["review_progress"].count(0)+ _report["review_progress"].count(1)) if (_report["review_progress"].count(0)+ _report["review_progress"].count(1)) >0 else 0 _report["review_progress"] = _report["review_progress"].count(1)/(_report["review_progress"].count(0)+ _report["review_progress"].count(1)) if (_report["review_progress"].count(0)+ _report["review_progress"].count(1)) >0 else 0
_report["images_quality"]["successful_percent"] = _report["images_quality"]["successful"]/_report["total_images"] if _report["total_images"] > 0 else 0 _report["images_quality"]["successful_percent"] = _report["images_quality"]["successful"]/_report["total_images"] if _report["total_images"] > 0 else 0
@ -734,9 +739,11 @@ def _accuracy_calculate_formatter(inference, target):
Make both list inference and target to be the same length. Make both list inference and target to be the same length.
""" """
if not isinstance(inference, list): if not isinstance(inference, list):
inference = [] if inference is None else [inference] # inference = [] if inference is None else [inference]
inference = [inference]
if not isinstance(target, list): if not isinstance(target, list):
target = [] if target is None else [target] # target = [] if target is None else [target]
target = [target]
length = max(len(target), len(inference)) length = max(len(target), len(inference))
target = target + (length - len(target))*[target[0]] if len(target) > 0 else target + (length - len(target))*[None] target = target + (length - len(target))*[target[0]] if len(target) > 0 else target + (length - len(target))*[None]
@ -745,7 +752,7 @@ def _accuracy_calculate_formatter(inference, target):
return inference, target return inference, target
def _acc_will_be_ignored(key_name, _target): def _acc_will_be_ignored(key_name, _target):
is_optional_key = key_name in optional_keys is_optional_key = key_name in OPTIONAL_KEYS
is_empty_target = _target in [[], None, ''] is_empty_target = _target in [[], None, '']
if is_optional_key and is_empty_target: if is_optional_key and is_empty_target:
return True return True
@ -1043,7 +1050,15 @@ def calculate_subcription_file(subcription_request_file):
feedback_result = copy.deepcopy(subcription_request_file.feedback_result) feedback_result = copy.deepcopy(subcription_request_file.feedback_result)
reviewed_result = copy.deepcopy(subcription_request_file.reviewed_result) reviewed_result = copy.deepcopy(subcription_request_file.reviewed_result)
for key_name in valid_keys: accuracy_keys_for_this_image = KEYS_BY_FILE_TYPE.get(subcription_request_file.doc_type, [])
for key_name in VALID_KEYS:
att["acc"]["feedback"][key_name] = []
att["normalized_data"]["feedback"][key_name] = []
att["acc"]["reviewed"][key_name] = []
att["normalized_data"]["reviewed"][key_name] = []
for key_name in accuracy_keys_for_this_image:
try: try:
att["acc"]["feedback"][key_name], att["normalized_data"]["feedback"][key_name] = calculate_accuracy(key_name, inference_result, feedback_result, "feedback", sub=subcription_request_file.request.subsidiary) att["acc"]["feedback"][key_name], att["normalized_data"]["feedback"][key_name] = calculate_accuracy(key_name, inference_result, feedback_result, "feedback", sub=subcription_request_file.request.subsidiary)
att["acc"]["reviewed"][key_name], att["normalized_data"]["reviewed"][key_name] = calculate_accuracy(key_name, inference_result, reviewed_result, "reviewed", sub=subcription_request_file.request.subsidiary) att["acc"]["reviewed"][key_name], att["normalized_data"]["reviewed"][key_name] = calculate_accuracy(key_name, inference_result, reviewed_result, "reviewed", sub=subcription_request_file.request.subsidiary)
@ -1052,8 +1067,8 @@ def calculate_subcription_file(subcription_request_file):
subcription_request_file.feedback_accuracy = att["acc"]["feedback"] subcription_request_file.feedback_accuracy = att["acc"]["feedback"]
subcription_request_file.reviewed_accuracy = att["acc"]["reviewed"] subcription_request_file.reviewed_accuracy = att["acc"]["reviewed"]
avg_reviewed = calculate_avg_accuracy(att["acc"], "reviewed", valid_keys) avg_reviewed = calculate_avg_accuracy(att["acc"], "reviewed", VALID_KEYS)
avg_feedback = calculate_avg_accuracy(att["acc"], "feedback", valid_keys) avg_feedback = calculate_avg_accuracy(att["acc"], "feedback", VALID_KEYS)
if avg_feedback is not None or avg_reviewed is not None: if avg_feedback is not None or avg_reviewed is not None:
avg_acc = 0 avg_acc = 0