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

update accuracy fns for adding invoice_no

Browse Source
This commit is contained in:
PhanThanhTrung 2024-03-13 13:18:57 +07:00
parent a8999bb9c8
commit d35a5955af
1 changed files with 61 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

218
cope2n-api/fwd_api/utils/accuracy.py
View File

@ -17,7 +17,7 @@ from fwd import settings
from ..models import SubscriptionRequest, Report, ReportFile
import json
valid_keys = ["retailername", "sold_to_party", "purchase_date", "imei_number"]
valid_keys = ["retailername", "sold_to_party", "invoice_no", "purchase_date", "imei_number"]
class ReportAccumulateByRequest:
def __init__(self, sub):
@ -41,7 +41,8 @@ class ReportAccumulateByRequest:
'imei': IterAvg(),
'purchase_date': IterAvg(),
'retailer_name': IterAvg(),
'sold_to_party': IterAvg()
'sold_to_party': IterAvg(),
'invoice_no': IterAvg()
},
'average_processing_time': {
'imei': IterAvg(),
@ -57,13 +58,15 @@ class ReportAccumulateByRequest:
'imei_number': IterAvg(),
'purchase_date': IterAvg(),
'retailername': IterAvg(),
'sold_to_party': IterAvg()
'sold_to_party': IterAvg(),
'invoice_no': IterAvg()
},
'reviewed_accuracy': {
'imei_number': IterAvg(),
'purchase_date': IterAvg(),
'retailername': IterAvg(),
'sold_to_party': IterAvg()
'sold_to_party': IterAvg(),
'invoice_no': IterAvg()
},
'num_request': 0,
"review_progress": []
@ -84,7 +87,8 @@ class ReportAccumulateByRequest:
'imei': IterAvg(),
'purchase_date': IterAvg(),
'retailer_name': IterAvg(),
'sold_to_party': IterAvg()
'sold_to_party': IterAvg(),
'invoice_no': IterAvg()
},
'average_processing_time': {
'imei': IterAvg(),
@ -100,13 +104,15 @@ class ReportAccumulateByRequest:
'imei_number': IterAvg(),
'purchase_date': IterAvg(),
'retailername': IterAvg(),
'sold_to_party': IterAvg()
'sold_to_party': IterAvg(),
'invoice_no': IterAvg()
},
'reviewed_accuracy': {
'imei_number': IterAvg(),
'purchase_date': IterAvg(),
'retailername': IterAvg(),
'sold_to_party': IterAvg()
'sold_to_party': IterAvg(),
'invoice_no': IterAvg()
},
"report_files": [],
"num_request": 0,
@ -132,15 +138,17 @@ class ReportAccumulateByRequest:
total["average_accuracy_rate"]["purchase_date"].add(report_file.reviewed_accuracy.get("purchase_date", []))
total["average_accuracy_rate"]["retailer_name"].add(report_file.reviewed_accuracy.get("retailername", []))
total["average_accuracy_rate"]["sold_to_party"].add(report_file.reviewed_accuracy.get("sold_to_party", []))
total["average_accuracy_rate"]["invoice_no"].add(report_file.reviewed_accuracy.get("invoice_no", []))
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"]["imei"].add(report_file.feedback_accuracy.get("imei_number", []))
total["average_accuracy_rate"]["purchase_date"].add(report_file.feedback_accuracy.get("purchase_date", []))
total["average_accuracy_rate"]["retailer_name"].add(report_file.feedback_accuracy.get("retailername", []))
total["average_accuracy_rate"]["sold_to_party"].add(report_file.feedback_accuracy.get("sold_to_party", []))
total["average_accuracy_rate"]["invoice_no"].add(report_file.feedback_accuracy.get("invoice_no", []))
for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
for key in ["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"]:
total["feedback_accuracy"][key].add(report_file.feedback_accuracy.get(key, []))
for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
for key in ["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"]:
total["reviewed_accuracy"][key].add(report_file.reviewed_accuracy.get(key, []))
if not total["average_processing_time"].get(report_file.doc_type, None):
@ -179,15 +187,17 @@ class ReportAccumulateByRequest:
day_data["average_accuracy_rate"]["purchase_date"].add(report_file.reviewed_accuracy.get("purchase_date", []))
day_data["average_accuracy_rate"]["retailer_name"].add(report_file.reviewed_accuracy.get("retailername", []))
day_data["average_accuracy_rate"]["sold_to_party"].add(report_file.reviewed_accuracy.get("sold_to_party", []))
day_data["average_accuracy_rate"]["invoice_no"].add(report_file.reviewed_accuracy.get("invoice_no", []))
elif sum([len(report_file.feedback_accuracy[x]) for x in report_file.feedback_accuracy.keys() if "_count" not in x]) > 0:
day_data["average_accuracy_rate"]["imei"].add(report_file.feedback_accuracy.get("imei_number", []))
day_data["average_accuracy_rate"]["purchase_date"].add(report_file.feedback_accuracy.get("purchase_date", []))
day_data["average_accuracy_rate"]["retailer_name"].add(report_file.feedback_accuracy.get("retailername", []))
day_data["average_accuracy_rate"]["sold_to_party"].add(report_file.feedback_accuracy.get("sold_to_party", []))
day_data["average_accuracy_rate"]["invoice_no"].add(report_file.feedback_accuracy.get("invoice_no", []))
for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
for key in ["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"]:
day_data["feedback_accuracy"][key].add(report_file.feedback_accuracy.get(key, []))
for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
for key in ["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"]:
day_data["reviewed_accuracy"][key].add(report_file.reviewed_accuracy.get(key, []))
if not day_data["average_processing_time"].get(report_file.doc_type, None):
@ -264,7 +274,7 @@ class ReportAccumulateByRequest:
"reviewed_accuracy": {}}
for acc_type in ["feedback_accuracy", "reviewed_accuracy"]:
avg_acc = IterAvg()
for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
for key in ["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"]:
acumulated_acc[acc_type][key] = self.data[month][1][day][acc_type][key]()
acumulated_acc[acc_type][key+"_count"] = self.data[month][1][day][acc_type][key].count
avg_acc.add_avg(acumulated_acc[acc_type][key], acumulated_acc[acc_type][key+"_count"])
@ -312,6 +322,7 @@ class ReportAccumulateByRequest:
_data[month][1][day]["average_accuracy_rate"]["purchase_date"] = _data[month][1][day]["average_accuracy_rate"]["purchase_date"]()
_data[month][1][day]["average_accuracy_rate"]["retailer_name"] = _data[month][1][day]["average_accuracy_rate"]["retailer_name"]()
_data[month][1][day]["average_accuracy_rate"]["sold_to_party"] = _data[month][1][day]["average_accuracy_rate"]["sold_to_party"]()
_data[month][1][day]["average_accuracy_rate"]["invoice_no"] = _data[month][1][day]["average_accuracy_rate"]["invoice_no"]()
for key in _data[month][1][day]["average_processing_time"].keys():
_data[month][1][day]["average_processing_time"][key] = _data[month][1][day]["average_processing_time"][key]()
@ -319,10 +330,14 @@ class ReportAccumulateByRequest:
_data[month][1][day]["feedback_accuracy"]["purchase_date"] = _data[month][1][day]["feedback_accuracy"]["purchase_date"]()
_data[month][1][day]["feedback_accuracy"]["retailername"] = _data[month][1][day]["feedback_accuracy"]["retailername"]()
_data[month][1][day]["feedback_accuracy"]["sold_to_party"] = _data[month][1][day]["feedback_accuracy"]["sold_to_party"]()
_data[month][1][day]["feedback_accuracy"]["invoice_no"] = _data[month][1][day]["feedback_accuracy"]["invoice_no"]()
_data[month][1][day]["reviewed_accuracy"]["imei_number"] = _data[month][1][day]["reviewed_accuracy"]["imei_number"]()
_data[month][1][day]["reviewed_accuracy"]["purchase_date"] = _data[month][1][day]["reviewed_accuracy"]["purchase_date"]()
_data[month][1][day]["reviewed_accuracy"]["retailername"] = _data[month][1][day]["reviewed_accuracy"]["retailername"]()
_data[month][1][day]["reviewed_accuracy"]["sold_to_party"] = _data[month][1][day]["reviewed_accuracy"]["sold_to_party"]()
_data[month][1][day]["reviewed_accuracy"]["invoice_no"] = _data[month][1][day]["reviewed_accuracy"]["invoice_no"]()
_data[month][1][day]["review_progress"] = _data[month][1][day]["review_progress"].count(1)/(_data[month][1][day]["review_progress"].count(0)+ _data[month][1][day]["review_progress"].count(1)) if (_data[month][1][day]["review_progress"].count(0)+ _data[month][1][day]["review_progress"].count(1)) >0 else 0
_data[month][1][day].pop("report_files")
@ -336,6 +351,7 @@ class ReportAccumulateByRequest:
_data[month][0]["average_accuracy_rate"]["purchase_date"] = _data[month][0]["average_accuracy_rate"]["purchase_date"]()
_data[month][0]["average_accuracy_rate"]["retailer_name"] = _data[month][0]["average_accuracy_rate"]["retailer_name"]()
_data[month][0]["average_accuracy_rate"]["sold_to_party"] = _data[month][0]["average_accuracy_rate"]["sold_to_party"]()
_data[month][0]["average_accuracy_rate"]["invoice_no"] = _data[month][0]["average_accuracy_rate"]["invoice_no"]()
for key in _data[month][0]["average_processing_time"].keys():
_data[month][0]["average_processing_time"][key] = _data[month][0]["average_processing_time"][key]()
@ -343,10 +359,14 @@ class ReportAccumulateByRequest:
_data[month][0]["feedback_accuracy"]["purchase_date"] = _data[month][0]["feedback_accuracy"]["purchase_date"]()
_data[month][0]["feedback_accuracy"]["retailername"] = _data[month][0]["feedback_accuracy"]["retailername"]()
_data[month][0]["feedback_accuracy"]["sold_to_party"] = _data[month][0]["feedback_accuracy"]["sold_to_party"]()
_data[month][0]["feedback_accuracy"]["invoice_no"] = _data[month][0]["feedback_accuracy"]["invoice_no"]()
_data[month][0]["reviewed_accuracy"]["imei_number"] = _data[month][0]["reviewed_accuracy"]["imei_number"]()
_data[month][0]["reviewed_accuracy"]["purchase_date"] = _data[month][0]["reviewed_accuracy"]["purchase_date"]()
_data[month][0]["reviewed_accuracy"]["retailername"] = _data[month][0]["reviewed_accuracy"]["retailername"]()
_data[month][0]["reviewed_accuracy"]["sold_to_party"] = _data[month][0]["reviewed_accuracy"]["sold_to_party"]()
_data[month][0]["reviewed_accuracy"]["invoice_no"] = _data[month][0]["reviewed_accuracy"]["invoice_no"]()
_data[month][0]["review_progress"] = _data[month][0]["review_progress"].count(1)/(_data[month][0]["review_progress"].count(0)+ _data[month][0]["review_progress"].count(1)) if (_data[month][0]["review_progress"].count(0)+ _data[month][0]["review_progress"].count(1)) >0 else 0
return _data
@ -367,7 +387,8 @@ class MonthReportAccumulate:
'average_accuracy_rate': {
'imei': IterAvg(),
'purchase_date': IterAvg(),
'retailer_name': IterAvg()
'retailer_name': IterAvg(),
'invoice_no': IterAvg()
},
'average_processing_time': {
'imei': IterAvg(),
@ -394,7 +415,8 @@ class MonthReportAccumulate:
'average_accuracy_rate': {
'imei': 0,
'purchase_date': 0,
'retailer_name': 0
'retailer_name': 0,
'invoice_no': 0
},
'average_processing_time': {
'imei': 0,
@ -416,10 +438,12 @@ class MonthReportAccumulate:
self.total["average_accuracy_rate"]["imei"].add_avg(report.reviewed_accuracy.get("imei_number", 0), report.reviewed_accuracy.get("imei_number_count", 0))
self.total["average_accuracy_rate"]["purchase_date"].add_avg(report.reviewed_accuracy.get("purchase_date", 0), report.reviewed_accuracy.get("purchase_date_count", 0))
self.total["average_accuracy_rate"]["retailer_name"].add_avg(report.reviewed_accuracy.get("retailername", 0), report.reviewed_accuracy.get("retailername_count", 0))
self.total["average_accuracy_rate"]["invoice_no"].add_avg(report.reviewed_accuracy.get("invoice_no", 0), report.reviewed_accuracy.get("invoice_no_count", 0))
elif sum([ report.feedback_accuracy[x] for x in report.feedback_accuracy.keys() if "_count" not in x]) > 0:
self.total["average_accuracy_rate"]["imei"].add_avg(report.feedback_accuracy.get("imei_number", 0), report.feedback_accuracy.get("imei_number_count", 0))
self.total["average_accuracy_rate"]["purchase_date"].add_avg(report.feedback_accuracy.get("purchase_date", 0), report.feedback_accuracy.get("purchase_date_count", 0))
self.total["average_accuracy_rate"]["retailer_name"].add_avg(report.feedback_accuracy.get("retailername", 0), report.feedback_accuracy.get("retailername_count", 0))
self.total["average_accuracy_rate"]["invoice_no"].add_avg(report.feedback_accuracy.get("invoice_no", 0), report.feedback_accuracy.get("invoice_no_count", 0))
self.total["average_processing_time"]["imei"].add_avg(report.average_OCR_time.get("imei", 0), report.average_OCR_time.get("imei_count", 0)) if report.average_OCR_time else 0
self.total["average_processing_time"]["invoice"].add_avg(report.average_OCR_time.get("invoice", 0), report.average_OCR_time.get("invoice_count", 0)) if report.average_OCR_time else 0
@ -453,10 +477,13 @@ class MonthReportAccumulate:
new_data["average_accuracy_rate"]["imei"] = report.reviewed_accuracy.get("imei_number", None)
new_data["average_accuracy_rate"]["purchase_date"] = report.reviewed_accuracy.get("purchase_date", None)
new_data["average_accuracy_rate"]["retailer_name"] = report.reviewed_accuracy.get("retailername", None)
new_data["average_accuracy_rate"]["invoice_no"] = report.reviewed_accuracy.get("invoice_no", None)
elif sum([ report.feedback_accuracy[x] for x in report.feedback_accuracy.keys() if "_count" not in x]):
new_data["average_accuracy_rate"]["imei"] = report.feedback_accuracy.get("imei_number", None)
new_data["average_accuracy_rate"]["purchase_date"] = report.feedback_accuracy.get("purchase_date", None)
new_data["average_accuracy_rate"]["retailer_name"] = report.feedback_accuracy.get("retailername", None)
new_data["average_accuracy_rate"]["invoice_no"] = report.feedback_accuracy.get("invoice_no", None)
new_data["average_processing_time"]["imei"] = report.average_OCR_time.get("imei", 0) if report.average_OCR_time else 0
new_data["average_processing_time"]["invoice"] = report.average_OCR_time.get("invoice", 0) if report.average_OCR_time else 0
new_data["usage"]["imei"] = report.number_imei_transaction
@ -567,6 +594,9 @@ def extract_report_detail_list(report_detail_list, lower=False, in_percent=True)
"Invoice_Retailer_Consumer": report_file.feedback_result.get("retailername", None),
"Invoice_Retailer_OCR": report_file.predict_result.get("retailername", None),
"Invoice_Retailer Accuracy": first_of_list(report_file.feedback_accuracy.get("retailername", [None])),
"Invoice_No_Consumer": report_file.feedback_result.get("invoice_no", None),
"Invoice_No_OCR": report_file.predict_result.get("invoice_no", None),
"Invoice_No Accuracy": first_of_list(report_file.feedback_accuracy.get("invoice_no", [None])),
"OCR Image Accuracy": report_file.acc,
"OCR Image Speed (seconds)": report_file.time_cost,
"Is Reviewed": report_file.is_reviewed,
@ -575,6 +605,7 @@ def extract_report_detail_list(report_detail_list, lower=False, in_percent=True)
"IMEI_Revised Accuracy": first_of_list(report_file.reviewed_accuracy.get("imei_number", [None])),
"Purchase Date_Revised Accuracy": first_of_list(report_file.reviewed_accuracy.get("purchase_date", [None])),
"Retailer_Revised Accuracy": first_of_list(report_file.reviewed_accuracy.get("retailername", [None])),
"Invoice_No_Revised Accuracy": first_of_list(report_file.reviewed_accuracy.get("invoice_no", [None]))
})
if lower:
for i, dat in enumerate(data):
@ -630,14 +661,16 @@ def convert_datetime_format(date_string: str, is_gt=False) -> str:
def predict_result_to_ready(result):
dict_result = {"retailername": "",
"sold_to_party": "",
"invoice_no": "",
"purchase_date": [],
"imei_number": [],}
if not result:
return dict_result
dict_result["retailername"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}])[0].get("value", None)
dict_result["sold_to_party"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}])[1].get("value", None)
dict_result["purchase_date"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}, {}])[2].get("value", [])
dict_result["imei_number"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}, {}, {}])[3].get("value", [])
dict_result["invoice_no"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}])[2].get("value", None)
dict_result["purchase_date"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}, {}])[3].get("value", [])
dict_result["imei_number"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}, {}, {}])[4].get("value", [])
return dict_result
def align_fine_result(ready_predict, fine_result):
@ -648,8 +681,8 @@ def align_fine_result(ready_predict, fine_result):
ready_predict["purchase_date"] = [None]
if fine_result["retailername"] and not ready_predict["retailername"]:
ready_predict["retailername"] = [None]
# if ready_predict["retailername"] and not fine_result["retailername"]:
# fine_result["retailername"] = [None]
if ready_predict["invoice_no"] and not fine_result["invoice_no"]:
fine_result["invoice_no"] = [None]
fine_result["purchase_date"] = [fine_result["purchase_date"] for _ in range(len(ready_predict["purchase_date"]))]
# fine_result["retailername"] = None if len(ready_predict["purchase_date"]))]
# else:
@ -724,76 +757,6 @@ def calculate_avg_accuracy(acc, type, keys=[]):
return sum(acc_list)/len(acc_list) if len(acc_list) > 0 else None
# Deprecated
def calculate_and_save_subcription_file(report, request):
request_att = {"acc": {"feedback": {"imei_number": [],
"purchase_date": [],
"retailername": [],
"sold_to_party": [],
},
"reviewed": {"imei_number": [],
"purchase_date": [],
"retailername": [],
"sold_to_party": [],
}},
"err": [],
"time_cost": {},
"total_images": 0,
"bad_images": 0}
images = SubscriptionRequestFile.objects.filter(request=request)
for image in images:
status, att = calculate_subcription_file(image)
if status != 200:
continue
image.feedback_accuracy = att["acc"]["feedback"]
image.reviewed_accuracy = att["acc"]["reviewed"]
image.is_bad_image_quality = att["is_bad_image"]
image.save()
new_report_file = ReportFile(report=report,
correspond_request_id=request.request_id,
correspond_redemption_id=request.redemption_id,
doc_type=image.doc_type,
predict_result=image.predict_result,
feedback_result=image.feedback_result,
reviewed_result=image.reviewed_result,
feedback_accuracy=att["acc"]["feedback"],
reviewed_accuracy=att["acc"]["reviewed"],
acc=att["avg_acc"],
time_cost=image.processing_time,
is_bad_image=att["is_bad_image"],
bad_image_reason=image.reason,
counter_measures=image.counter_measures,
error="|".join(att["err"])
)
new_report_file.save()
if request_att["time_cost"].get(image.doc_type, None):
request_att["time_cost"][image.doc_type].append(image.processing_time)
else:
request_att["time_cost"][image.doc_type] = [image.processing_time]
try:
request_att["acc"]["feedback"]["imei_number"] += att["acc"]["feedback"]["imei_number"]
request_att["acc"]["feedback"]["purchase_date"] += att["acc"]["feedback"]["purchase_date"]
request_att["acc"]["feedback"]["retailername"] += att["acc"]["feedback"]["retailername"]
request_att["acc"]["feedback"]["sold_to_party"] += att["acc"]["feedback"]["sold_to_party"]
request_att["acc"]["reviewed"]["imei_number"] += att["acc"]["reviewed"]["imei_number"]
request_att["acc"]["reviewed"]["purchase_date"] += att["acc"]["reviewed"]["purchase_date"]
request_att["acc"]["reviewed"]["retailername"] += att["acc"]["reviewed"]["retailername"]
request_att["acc"]["reviewed"]["sold_to_party"] += att["acc"]["reviewed"]["sold_to_party"]
request_att["bad_images"] += int(att["is_bad_image"])
request_att["total_images"] += 1
request_att["err"] += att["err"]
except Exception as e:
print(e)
continue
return request_att
# def result_maximize_list_values(result, acc):
# for k in acc.keys():
# if isinstance(acc[k], list) and len(acc[k]) > 0:
def acc_maximize_list_values(acc):
pos = {}
for k in acc.keys():
@ -852,16 +815,19 @@ def calculate_a_request(report, request):
"purchase_date": [],
"retailername": [],
"sold_to_party": [],
"invoice_no": [],
},
"reviewed": {"imei_number": [],
"purchase_date": [],
"retailername": [],
"sold_to_party": [],
"invoice_no": [],
},
"acumulated":{"imei_number": [],
"purchase_date": [],
"retailername": [],
"sold_to_party": [],
"invoice_no": [],
}},
"err": [],
"time_cost": {"imei": [],
@ -950,16 +916,19 @@ def calculate_a_request(report, request):
request_att["acc"]["feedback"]["purchase_date"] += _att["acc"]["feedback"]["purchase_date"]
request_att["acc"]["feedback"]["retailername"] += _att["acc"]["feedback"]["retailername"]
request_att["acc"]["feedback"]["sold_to_party"] += _att["acc"]["feedback"]["sold_to_party"]
request_att["acc"]["feedback"]["invoice_no"] += _att["acc"]["feedback"]["invoice_no"]
request_att["acc"]["reviewed"]["imei_number"] += _att["acc"]["reviewed"]["imei_number"]
request_att["acc"]["reviewed"]["purchase_date"] += _att["acc"]["reviewed"]["purchase_date"]
request_att["acc"]["reviewed"]["retailername"] += _att["acc"]["reviewed"]["retailername"]
request_att["acc"]["reviewed"]["sold_to_party"] += _att["acc"]["reviewed"]["sold_to_party"]
request_att["acc"]["reviewed"]["invoice_no"] += _att["acc"]["reviewed"]["invoice_no"]
request_att["acc"]["acumulated"]["imei_number"] += _att["acc"]["reviewed"]["imei_number"] if _att["acc"]["reviewed"]["imei_number"] else _att["acc"]["feedback"]["imei_number"]
request_att["acc"]["acumulated"]["purchase_date"] += _att["acc"]["reviewed"]["purchase_date"] if _att["acc"]["reviewed"]["purchase_date"] else _att["acc"]["feedback"]["purchase_date"]
request_att["acc"]["acumulated"]["retailername"] += _att["acc"]["reviewed"]["retailername"] if _att["acc"]["reviewed"]["retailername"] else _att["acc"]["feedback"]["retailername"]
request_att["acc"]["acumulated"]["sold_to_party"] += _att["acc"]["reviewed"]["sold_to_party"] if _att["acc"]["reviewed"]["sold_to_party"] else _att["acc"]["feedback"]["sold_to_party"]
request_att["acc"]["acumulated"]["invoice_no"] += _att["acc"]["reviewed"]["invoice_no"] if _att["acc"]["reviewed"]["invoice_no"] else _att["acc"]["feedback"]["invoice_no"]
if image.reason not in settings.ACC_EXCLUDE_RESEASONS:
request_att["bad_images"] += int(_att["is_bad_image"])
@ -987,10 +956,6 @@ def calculate_subcription_file(subcription_request_file):
inference_result = copy.deepcopy(subcription_request_file.predict_result)
inference_result, feedback_result = align_fine_result(inference_result, copy.deepcopy(subcription_request_file.feedback_result))
inference_result, reviewed_result = align_fine_result(inference_result, copy.deepcopy(subcription_request_file.reviewed_result))
# print(f"[DEBUG]: predict_result: {subcription_request_file.predict_result}")
# print(f"[DEBUG]: inference_result: {inference_result}")
# print(f"[DEBUG]: feedback_result: {feedback_result}")
# print(f"[DEBUG]: reviewed_result: {reviewed_result}")
for key_name in valid_keys:
try:
@ -1002,8 +967,8 @@ def calculate_subcription_file(subcription_request_file):
# print(f"[DEBUG]: e: {e} -key_name: {key_name}")
subcription_request_file.feedback_accuracy = att["acc"]["feedback"]
subcription_request_file.reviewed_accuracy = att["acc"]["reviewed"]
avg_reviewed = calculate_avg_accuracy(att["acc"], "reviewed", ["retailername", "sold_to_party", "purchase_date", "imei_number"])
avg_feedback = calculate_avg_accuracy(att["acc"], "feedback", ["retailername", "sold_to_party", "purchase_date", "imei_number"])
avg_reviewed = calculate_avg_accuracy(att["acc"], "reviewed", ["retailername", "sold_to_party", "invoice_no", "purchase_date", "imei_number"])
avg_feedback = calculate_avg_accuracy(att["acc"], "feedback", ["retailername", "sold_to_party", "invoice_no", "purchase_date", "imei_number"])
if avg_feedback is not None or avg_reviewed is not None:
avg_acc = 0
if avg_feedback is not None:
@ -1019,68 +984,6 @@ def calculate_subcription_file(subcription_request_file):
att["is_bad_image"] = True
return 200, att
def calculate_attributions(request): # for one request, return in order
# Deprecated
acc = {"feedback": {},
"reviewed": {}} # {"feedback": {"retailername": [0.1], "sold_to_party":[0.9], "purchase_date":[0.6], "imei_number":[0.8]},
# "reviewed": {"retailername": [0.1], "sold_to_party":[0.9], "purchase_date":[0.6], "imei_number":[0.8]}}
data = {"feedback": {},
"reviewed": {}} # {"feedback": {"retailername": [[ocr, feedback], ...], "sold_to_party":[[ocr, feedback], ...], "purchase_date":[[ocr, feedback], ...], "imei_number":[[ocr, feedback], ...]}}
# {"reviewed": {"retailername": [[ocr, reviewed], ...], "sold_to_party":[[ocr, reviewed], ...], "purchase_date":[[ocr, reviewed], ...], "imei_number":[[ocr, reviewed], ...]}}
time_cost = {} # {"imei": [0.1], "invoice": [0.1]}
image_quality_num = [0, 0] # [good, bad]
image_quality_num[0] = len(request.doc_type.split(","))
error = ""
inference_result = predict_result_to_ready(request.predict_result)
reviewed_result = align_fine_result(inference_result, request.reviewed_result)
feedback_result = align_fine_result(inference_result, request.feedback_result)
# accuracy calculation
for key_name in valid_keys:
if isinstance(inference_result[key_name], list):
if len(inference_result[key_name]) != len(reviewed_result.get(key_name, [])):
error = f"Request {request.request_id} failed with different {key_name} in predict and reviewed_result"
break
if len(inference_result[key_name]) != len(feedback_result.get(key_name, [])):
error = f"Request {request.request_id} failed with different {key_name} in predict and feedback_result"
break
# calculate accuracy for feedback result
acc["feedback"][key_name], data["feedback"][key_name] = calculate_accuracy(key_name, inference_result, feedback_result)
acc["reviewed"][key_name], data["reviewed"][key_name] = calculate_accuracy(key_name, inference_result, reviewed_result)
else:
inference_result[key_name] = [inference_result[key_name]]
feedback_result[key_name] = [feedback_result[key_name]]
reviewed_result[key_name] = [reviewed_result[key_name]]
acc["feedback"][key_name], data["feedback"][key_name] = calculate_accuracy(key_name, inference_result, feedback_result)
acc["reviewed"][key_name], data["reviewed"][key_name] = calculate_accuracy(key_name, inference_result, reviewed_result)
acc["feedback"]["purchase_date"] = [max(acc["feedback"]["purchase_date"])] if len(acc["feedback"]["purchase_date"]) > 0 else []
acc["reviewed"]["purchase_date"] = [max(acc["reviewed"]["purchase_date"])] if len(acc["reviewed"]["purchase_date"]) > 0 else []
# Count for bad and total images
avg_invoice_feedback = calculate_avg_accuracy(acc, "feedback", ["retailername", "sold_to_party", "purchase_date"])
avg_invoice_reviewed = calculate_avg_accuracy(acc, "reviewed", ["retailername", "sold_to_party", "purchase_date"])
if avg_invoice_feedback is not None or avg_invoice_reviewed is not None:
if max([x for x in [avg_invoice_feedback, avg_invoice_reviewed] if x is not None]) < settings.BAD_THRESHOLD:
image_quality_num[1] += 1
for i, _ in enumerate(acc["feedback"]["imei_number"]):
if acc["feedback"]["imei_number"][i] is not None and acc["reviewed"]["imei_number"][i] is not None:
if max([x for x in [acc["feedback"]["imei_number"][i], acc["reviewed"]["imei_number"][i]] if x is not None]) < settings.BAD_THRESHOLD:
image_quality_num[1] += 1
# time cost and quality calculation
# TODO: to be deprecated, doc_type would be in file level in the future
try:
for doc_type, doc_profile in request.ai_inference_profile.items():
doc_type = doc_type.split("_")[0]
inference_time = doc_profile["inference"][1][0] - doc_profile["inference"][0]
postprocess_time = doc_profile["postprocess"][1] - doc_profile["postprocess"][0]
time_cost[doc_type].append(inference_time + postprocess_time)
except Exception as e:
error = f"Request id {request.request_id} failed with error: {e}"
return acc, data, time_cost, image_quality_num, error
def mean_list(l):
l = [x for x in l if x is not None]
if len(l) == 0:
@ -1088,5 +991,4 @@ def mean_list(l):
return sum(l)/len(l)
def shadow_report(report_id, query):
c_connector.make_a_report_2(
(report_id, query))
c_connector.make_a_report_2((report_id, query))