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

Merge pull request #87 from SDSRV-IDP/trungpt/invoice_no

Browse Source 
Add Invoice_no
This commit is contained in:
Đỗ Xuân Tân 2024-03-13 15:39:25 +07:00 committed by GitHub Enterprise
commit 44900ac555
10 changed files with 80 additions and 326 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
cope2n-ai-fi/Dockerfile
View File

@ -24,10 +24,10 @@ RUN python -m pip install 'git+https://github.com/facebookresearch/detectron2.gi
# Install SDSV packages # Install SDSV packages
COPY . /workspace/cope2n-ai-fi COPY . /workspace/cope2n-ai-fi
RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr/externals/sdsv_dewarp && pip3 install -v -e . --no-cache-dir RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr/sdsvocr/externals/sdsv_dewarp && pip3 install -v -e . --no-cache-dir
RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr/externals/sdsvtd && pip3 install -v -e . --no-cache-dir RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr/sdsvocr/externals/sdsvtd && pip3 install -v -e . --no-cache-dir
RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr/externals/sdsvtr && pip3 install -v -e . --no-cache-dir RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr/sdsvocr/externals/sdsvtr && pip3 install -v -e . --no-cache-dir
RUN cd /workspace/cope2n-ai-fi/modules/sdsvkvu/sdsvkvu/externals/sdsvocr && pip3 install -v -e . --no-cache-dir
# COPY ./modules/sdsvkvu/sdsvkvu/externals/sdsvocr/externals/sdsv_dewarp /tmp/sdsv_dewarp # COPY ./modules/sdsvkvu/sdsvkvu/externals/sdsvocr/externals/sdsv_dewarp /tmp/sdsv_dewarp
# RUN cd /tmp/sdsv_dewarp && pip install -v -e . --no-cache-dir # RUN cd /tmp/sdsv_dewarp && pip install -v -e . --no-cache-dir
@ -65,3 +65,4 @@ ENV PYTHONPATH="."
ENV TZ="Asia/Ho_Chi_Minh" ENV TZ="Asia/Ho_Chi_Minh"
CMD [ "sh", "run.sh"] CMD [ "sh", "run.sh"]
# ENTRYPOINT [ "sleep", "infinity" ]

3
cope2n-ai-fi/api/sdsap_sbt/prediction_sbt.py
View File

@ -38,7 +38,7 @@ def sbt_predict(image_url, engine) -> None:
os.makedirs(save_dir, exist_ok = True) os.makedirs(save_dir, exist_ok = True)
tmp_image_path = os.path.join(save_dir, f"{uuid.uuid4()}.jpg") tmp_image_path = os.path.join(save_dir, f"{uuid.uuid4()}.jpg")
cv2.imwrite(tmp_image_path, img) cv2.imwrite(tmp_image_path, img)
outputs = process_img(img_path=tmp_image_path, outputs = process_img(img=tmp_image_path,
save_dir=save_dir, save_dir=save_dir,
engine=engine, engine=engine,
export_all=False, # False export_all=False, # False
@ -71,7 +71,6 @@ def predict(page_numb, image_url):
""" """
sbt_result = sbt_predict(image_url, engine=sbt_engine) sbt_result = sbt_predict(image_url, engine=sbt_engine)
print(sbt_result)
output_dict = { output_dict = {
"document_type": "invoice", "document_type": "invoice",
"document_class": " ", "document_class": " ",

3
cope2n-ai-fi/common/utils_kvu/split_docs.py
View File

@ -107,6 +107,7 @@ def merge_sbt_output(loutputs):
merged_output = [] merged_output = []
combined_output = {"retailername": None, combined_output = {"retailername": None,
"sold_to_party": None, "sold_to_party": None,
"invoice_no": None,
"purchase_date": [], "purchase_date": [],
"imei_number": []} # place holder for the output "imei_number": []} # place holder for the output
for output in loutputs: for output in loutputs:
@ -123,7 +124,7 @@ def merge_sbt_output(loutputs):
combined_output[field["label"]].append(field["value"]) combined_output[field["label"]].append(field["value"])
if output['doc_type'] == "invoice": if output['doc_type'] == "invoice":
for field in fields: for field in fields:
if field["label"] in ["retailername", "sold_to_party", "purchase_date"] : if field["label"] in ["retailername", "sold_to_party", "purchase_date", "invoice_no"] :
if isinstance(combined_output[field["label"]], list): if isinstance(combined_output[field["label"]], list):
if field["value"] is not None: if field["value"] is not None:
if isinstance(field["value"], list): if isinstance(field["value"], list):

2
cope2n-ai-fi/requirements.txt
View File

@ -9,6 +9,6 @@ pymupdf
easydict easydict
imagesize==1.4.1 imagesize==1.4.1
pdf2image==1.16.3 pdf2image==1.17.0
redis==5.0.1 redis==5.0.1
celery==5.3.6 celery==5.3.6

8
cope2n-api/fwd_api/api/accuracy_view.py
View File

@ -409,7 +409,7 @@ class AccuracyViewSet(viewsets.ViewSet):
data = [] data = []
for report in page: for report in page:
acc_keys = ["purchase_date", "retailername", "imei_number", "avg"] acc_keys = ["purchase_date", "retailername", "invoice_no", "imei_number", "avg"]
acc = {} acc = {}
for key in acc_keys: for key in acc_keys:
fb = report.feedback_accuracy.get(key, 0) if report.feedback_accuracy else 0 fb = report.feedback_accuracy.get(key, 0) if report.feedback_accuracy else 0
@ -649,7 +649,7 @@ class AccuracyViewSet(viewsets.ViewSet):
'properties': { 'properties': {
'reviewed_result': { 'reviewed_result': {
'type': 'string', 'type': 'string',
'default': '''{"request_id": "Sample request_id", "imei_number": ["sample_imei1", "sample_imei2"], "retailername": "Sample Retailer", "purchase_date": "01/01/1970", "sold_to_party": "Sample party"}''', 'default': '''{"request_id": "Sample request_id", "imei_number": ["sample_imei1", "sample_imei2"], "retailername": "Sample Retailer", "purchase_date": "01/01/1970", "sold_to_party": "Sample party", "invoice_no": "Sample Invoice no"}''',
}, },
}, },
}, },
@ -673,6 +673,7 @@ class AccuracyViewSet(viewsets.ViewSet):
"request_id": subscription_request.request_id, "request_id": subscription_request.request_id,
"retailername": None, "retailername": None,
"sold_to_party": None, "sold_to_party": None,
"invoice_no": None,
"purchase_date": None, "purchase_date": None,
"imei_number": [] "imei_number": []
} }
@ -774,7 +775,7 @@ class AccuracyViewSet(viewsets.ViewSet):
raise InvalidException(excArgs=f'reviewed_result') raise InvalidException(excArgs=f'reviewed_result')
reviewed_result = data["reviewed_result"] reviewed_result = data["reviewed_result"]
for field in ['retailername', 'sold_to_party', 'purchase_date', 'imei_number']: for field in ['retailername', 'sold_to_party', 'invoice_no', 'purchase_date', 'imei_number']:
if not field in reviewed_result.keys(): if not field in reviewed_result.keys():
raise RequiredFieldException(excArgs=f'reviewed_result.{field}') raise RequiredFieldException(excArgs=f'reviewed_result.{field}')
reviewed_result['request_id'] = request_id reviewed_result['request_id'] = request_id
@ -787,6 +788,7 @@ class AccuracyViewSet(viewsets.ViewSet):
subscription_request_file.reviewed_result = { subscription_request_file.reviewed_result = {
"retailername": None, "retailername": None,
"sold_to_party": None, "sold_to_party": None,
"invoice_no": None,
"purchase_date": [], "purchase_date": [],
"imei_number": []} "imei_number": []}
if len(reviewed_result["imei_number"]) - 1 >= subscription_request_file.index_in_request: if len(reviewed_result["imei_number"]) - 1 >= subscription_request_file.index_in_request:

5
cope2n-api/fwd_api/api/ctel_view.py
View File

@ -320,6 +320,9 @@ class CtelViewSet(viewsets.ViewSet):
'retailername': { 'retailername': {
'type': 'string', 'type': 'string',
}, },
'invoice_no': {
'type': 'string',
},
'sold_to_party': { 'sold_to_party': {
'type': 'string', 'type': 'string',
}, },
@ -336,7 +339,7 @@ class CtelViewSet(viewsets.ViewSet):
} }
}, },
}, },
'required': ['request_id', 'retailername', 'sold_to_party', 'purchase_date', 'imei_number'] 'required': ['request_id', 'retailername', 'invoice_no', 'sold_to_party', 'purchase_date', 'imei_number']
} }
}, responses=None, tags=['OCR']) }, responses=None, tags=['OCR'])
@action(detail=False, url_path="images/feedback", methods=["POST"]) @action(detail=False, url_path="images/feedback", methods=["POST"])

11
cope2n-api/fwd_api/celery_worker/internal_task.py
View File

@ -90,11 +90,13 @@ def process_csv_feedback(csv_file_path, feedback_id):
imei2 = row.get('imeiNumber2') imei2 = row.get('imeiNumber2')
purchase_date = row.get('Purchase Date') purchase_date = row.get('Purchase Date')
retailer = row.get('retailer') retailer = row.get('retailer')
invoice_no = row.get('invoice_no')
sold_to_party = row.get('Sold to party') sold_to_party = row.get('Sold to party')
server_time = float(row.get('timetakenmilli')) server_time = float(row.get('timetakenmilli'))
fb['request_id'] = request_id fb['request_id'] = request_id
fb['retailername'] = retailer fb['retailername'] = retailer
fb['sold_to_party'] = sold_to_party fb['sold_to_party'] = sold_to_party
fb["invoice_no"] = invoice_no
fb['purchase_date'] = purchase_date fb['purchase_date'] = purchase_date
fb['imei_number'] = [imei1, imei2] fb['imei_number'] = [imei1, imei2]
sub_rq.feedback_result = fb sub_rq.feedback_result = fb
@ -119,7 +121,6 @@ def process_csv_feedback(csv_file_path, feedback_id):
continue continue
_predict_result = copy.deepcopy(predict_result_to_ready(sub_rq.predict_result)) _predict_result = copy.deepcopy(predict_result_to_ready(sub_rq.predict_result))
_feedback_result = copy.deepcopy(sub_rq.feedback_result) _feedback_result = copy.deepcopy(sub_rq.feedback_result)
# _reviewed_result = copy.deepcopy(sub_rq.reviewed_result)
try: try:
image.processing_time = time_cost.get(image.doc_type, [0 for _ in range(image.index_in_request)])[image.index_in_request] image.processing_time = time_cost.get(image.doc_type, [0 for _ in range(image.index_in_request)])[image.index_in_request]
except Exception as e: except Exception as e:
@ -132,14 +133,10 @@ def process_csv_feedback(csv_file_path, feedback_id):
if _feedback_result: if _feedback_result:
_feedback_result["imei_number"] = [] _feedback_result["imei_number"] = []
# if _reviewed_result:
# _reviewed_result["imei_number"] = []
else: else:
try: try:
_predict_result = {"retailername": None, "sold_to_party": None, "purchase_date": [], "imei_number": [_predict_result["imei_number"][image.index_in_request]]} _predict_result = {"retailername": None, "sold_to_party": None, "invoice_no": None, "purchase_date": [], "imei_number": [_predict_result["imei_number"][image.index_in_request]]}
_feedback_result = {"retailername": None, "sold_to_party": None, "purchase_date": None, "imei_number": [_feedback_result["imei_number"][image.index_in_request]]} if _feedback_result else None _feedback_result = {"retailername": None, "sold_to_party": None, "invoice_no": None, "purchase_date": None, "imei_number": [_feedback_result["imei_number"][image.index_in_request]]} if _feedback_result else None
# _reviewed_result = {"retailername": None, "sold_to_party": None, "purchase_date": None, "imei_number": [_reviewed_result["imei_number"][image.index_in_request]]} if _reviewed_result else None
except Exception as e: except Exception as e:
print (f"[ERROR]: {request_id} - {e}") print (f"[ERROR]: {request_id} - {e}")
image.predict_result = _predict_result image.predict_result = _predict_result

145
cope2n-api/fwd_api/celery_worker/process_report_tasks.py
View File

@ -35,135 +35,6 @@ def mean_list(l):
return 0 return 0
return sum(l)/len(l) return sum(l)/len(l)
@app.task(name='make_a_report')
def make_a_report(report_id, query_set):
# TODO: to be deprecated
try:
start_date = timezone.datetime.strptime(query_set["start_date_str"], '%Y-%m-%dT%H:%M:%S%z')
end_date = timezone.datetime.strptime(query_set["end_date_str"], '%Y-%m-%dT%H:%M:%S%z')
base_query = Q(created_at__range=(start_date, end_date))
if query_set["request_id"]:
base_query &= Q(request_id=query_set["request_id"])
if query_set["redemption_id"]:
base_query &= Q(redemption_id=query_set["redemption_id"])
base_query &= Q(is_test_request=False)
if isinstance(query_set["include_test"], str):
query_set["include_test"] = True if query_set["include_test"].lower() in ["true", "yes", "1"] else False
if query_set["include_test"]:
# base_query = ~base_query
base_query.children = base_query.children[:-1]
elif isinstance(query_set["include_test"], bool):
if query_set["include_test"]:
base_query = ~base_query
if isinstance(query_set["subsidiary"], str):
if query_set["subsidiary"] and query_set["subsidiary"].lower().replace(" ", "")!="all":
base_query &= Q(redemption_id__startswith=query_set["subsidiary"])
if isinstance(query_set["is_reviewed"], str):
if query_set["is_reviewed"] == "reviewed":
base_query &= Q(is_reviewed=True)
elif query_set["is_reviewed"] == "not reviewed":
base_query &= Q(is_reviewed=False)
# elif query_set["is_reviewed"] == "all":
# pass
errors = []
# Create a placeholder to fill
accuracy = {"feedback" :{"imei_number": IterAvg(),
"purchase_date": IterAvg(),
"retailername": IterAvg(),
"sold_to_party": IterAvg(),},
"reviewed" :{"imei_number": IterAvg(),
"purchase_date": IterAvg(),
"retailername": IterAvg(),
"sold_to_party": IterAvg(),}
} # {"imei": {"acc": 0.1, count: 1}, ...}
time_cost = {"invoice": IterAvg(),
"imei": IterAvg()}
number_images = 0
number_bad_images = 0
# TODO: Multithreading
# Calculate accuracy, processing time, ....Then save.
subscription_requests = SubscriptionRequest.objects.filter(base_query).order_by('created_at')
report: Report = \
Report.objects.filter(report_id=report_id).first()
# TODO: number of transaction by doc type
num_request = 0
for request in subscription_requests:
if request.status != 200 or not (request.reviewed_result or request.feedback_result):
# Failed requests or lack of reviewed_result/feedback_result
continue
request_att = calculate_and_save_subcription_file(report, request)
request.feedback_accuracy = {"imei_number" : mean_list(request_att["acc"]["feedback"].get("imei_number", [None])),
"purchase_date" : mean_list(request_att["acc"]["feedback"].get("purchase_date", [None])),
"retailername" : mean_list(request_att["acc"]["feedback"].get("retailername", [None])),
"sold_to_party" : mean_list(request_att["acc"]["feedback"].get("sold_to_party", [None]))}
request.reviewed_accuracy = {"imei_number" : mean_list(request_att["acc"]["reviewed"].get("imei_number", [None])),
"purchase_date" : mean_list(request_att["acc"]["reviewed"].get("purchase_date", [None])),
"retailername" : mean_list(request_att["acc"]["reviewed"].get("retailername", [None])),
"sold_to_party" : mean_list(request_att["acc"]["reviewed"].get("sold_to_party", [None]))}
request.save()
number_images += request_att["total_images"]
number_bad_images += request_att["bad_images"]
update_temp_accuracy(accuracy["feedback"], request_att["acc"]["feedback"], keys=["imei_number", "purchase_date", "retailername", "sold_to_party"])
update_temp_accuracy(accuracy["reviewed"], request_att["acc"]["reviewed"], keys=["imei_number", "purchase_date", "retailername", "sold_to_party"])
time_cost["imei"].add(request_att["time_cost"].get("imei", []))
time_cost["invoice"].add(request_att["time_cost"].get("invoice", []))
errors += request_att["err"]
num_request += 1
transaction_att = count_transactions(start_date, end_date, report.subsidiary)
# Do saving process
report.number_request = num_request
report.number_images = number_images
report.number_imei = time_cost["imei"].count
report.number_invoice = time_cost["invoice"].count
report.number_bad_images = number_bad_images
# FIXME: refactor this data stream for endurability
report.average_OCR_time = {"invoice": time_cost["invoice"](), "imei": time_cost["imei"](),
"invoice_count": time_cost["invoice"].count, "imei_count": time_cost["imei"].count}
report.average_OCR_time["invoice"] = 0 if report.average_OCR_time["invoice"] is None else report.average_OCR_time["invoice"]
report.average_OCR_time["imei"] = 0 if report.average_OCR_time["imei"] is None else report.average_OCR_time["imei"]
report.average_OCR_time["avg"] = (report.average_OCR_time["invoice"]*report.average_OCR_time["invoice_count"] + report.average_OCR_time["imei"]*report.average_OCR_time["imei_count"])/(report.average_OCR_time["imei_count"] + report.average_OCR_time["invoice_count"]) if (report.average_OCR_time["imei_count"] + report.average_OCR_time["invoice_count"]) > 0 else None
report.number_imei_transaction = transaction_att.get("imei", 0)
report.number_invoice_transaction = transaction_att.get("invoice", 0)
acumulated_acc = {"feedback": {},
"reviewed": {}}
for acc_type in ["feedback", "reviewed"]:
avg_acc = IterAvg()
for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
acumulated_acc[acc_type][key] = accuracy[acc_type][key]()
acumulated_acc[acc_type][key+"_count"] = accuracy[acc_type][key].count
avg_acc.add_avg(acumulated_acc[acc_type][key], acumulated_acc[acc_type][key+"_count"])
acumulated_acc[acc_type]["avg"] = avg_acc()
report.feedback_accuracy = acumulated_acc["feedback"]
report.reviewed_accuracy = acumulated_acc["reviewed"]
report.errors = "|".join(errors)
report.status = "Ready"
report.save()
# Saving a xlsx file
report_files = ReportFile.objects.filter(report=report)
data = extract_report_detail_list(report_files, lower=True)
data_workbook = dict2xlsx(data, _type='report_detail')
local_workbook = save_workbook_file(report.report_id + ".xlsx", report, data_workbook)
s3_key=save_report_to_S3(report.report_id, local_workbook)
except IndexError as e:
print(e)
traceback.print_exc()
print("NotFound request by report id, %d", report_id)
except Exception as e:
print("[ERROR]: an error occured while processing report: ", report_id)
traceback.print_exc()
return 400
@app.task(name='make_a_report_2') @app.task(name='make_a_report_2')
def make_a_report_2(report_id, query_set): def make_a_report_2(report_id, query_set):
report_type = query_set.pop("report_type", "accuracy") report_type = query_set.pop("report_type", "accuracy")
@ -241,18 +112,20 @@ def create_accuracy_report(report_id, **kwargs):
request.feedback_accuracy = {"imei_number": mean_list(request_att["acc"]["feedback"].get("imei_number", [None])), request.feedback_accuracy = {"imei_number": mean_list(request_att["acc"]["feedback"].get("imei_number", [None])),
"purchase_date": mean_list(request_att["acc"]["feedback"].get("purchase_date", [None])), "purchase_date": mean_list(request_att["acc"]["feedback"].get("purchase_date", [None])),
"retailername": mean_list(request_att["acc"]["feedback"].get("retailername", [None])), "retailername": mean_list(request_att["acc"]["feedback"].get("retailername", [None])),
"sold_to_party": mean_list(request_att["acc"]["feedback"].get("sold_to_party", [None]))} "sold_to_party": mean_list(request_att["acc"]["feedback"].get("sold_to_party", [None])),
"invoice_no": mean_list(request_att["acc"]["feedback"].get("invoice_no", [None]))}
request.reviewed_accuracy = {"imei_number": mean_list(request_att["acc"]["reviewed"].get("imei_number", [None])), request.reviewed_accuracy = {"imei_number": mean_list(request_att["acc"]["reviewed"].get("imei_number", [None])),
"purchase_date": mean_list(request_att["acc"]["reviewed"].get("purchase_date", [None])), "purchase_date": mean_list(request_att["acc"]["reviewed"].get("purchase_date", [None])),
"retailername": mean_list(request_att["acc"]["reviewed"].get("retailername", [None])), "retailername": mean_list(request_att["acc"]["reviewed"].get("retailername", [None])),
"sold_to_party": mean_list(request_att["acc"]["reviewed"].get("sold_to_party", [None]))} "sold_to_party": mean_list(request_att["acc"]["reviewed"].get("sold_to_party", [None])),
"invoice_no": mean_list(request_att["acc"]["reviewed"].get("invoice_no", [None]))}
request.save() request.save()
number_images += request_att["total_images"] number_images += request_att["total_images"]
number_bad_images += request_att["bad_images"] number_bad_images += request_att["bad_images"]
bad_image_list += request_att["bad_image_list"] bad_image_list += request_att["bad_image_list"]
update_temp_accuracy(accuracy["feedback"], request_att["acc"]["feedback"], keys=["imei_number", "purchase_date", "retailername", "sold_to_party"]) update_temp_accuracy(accuracy["feedback"], request_att["acc"]["feedback"], keys=["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"])
update_temp_accuracy(accuracy["reviewed"], request_att["acc"]["reviewed"], keys=["imei_number", "purchase_date", "retailername", "sold_to_party"]) update_temp_accuracy(accuracy["reviewed"], request_att["acc"]["reviewed"], keys=["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"])
update_temp_accuracy(accuracy["acumulated"], request_att["acc"]["acumulated"], keys=["imei_number", "purchase_date", "retailername", "sold_to_party"]) update_temp_accuracy(accuracy["acumulated"], request_att["acc"]["acumulated"], keys=["imei_number", "purchase_date", "invoice_no", "retailername", "sold_to_party"])
time_cost["imei"].add(request_att["time_cost"].get("imei", [])) time_cost["imei"].add(request_att["time_cost"].get("imei", []))
time_cost["invoice"].add(request_att["time_cost"].get("invoice", [])) time_cost["invoice"].add(request_att["time_cost"].get("invoice", []))
@ -285,7 +158,7 @@ def create_accuracy_report(report_id, **kwargs):
"acumulated": {}} "acumulated": {}}
for acc_type in ["feedback", "reviewed", "acumulated"]: for acc_type in ["feedback", "reviewed", "acumulated"]:
avg_acc = IterAvg() 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] = accuracy[acc_type][key]() acumulated_acc[acc_type][key] = accuracy[acc_type][key]()
acumulated_acc[acc_type][key + "_count"] = accuracy[acc_type][key].count acumulated_acc[acc_type][key + "_count"] = accuracy[acc_type][key].count
avg_acc.add_avg(acumulated_acc[acc_type][key], acumulated_acc[acc_type][key+"_count"]) avg_acc.add_avg(acumulated_acc[acc_type][key], acumulated_acc[acc_type][key+"_count"])
@ -362,7 +235,7 @@ def create_billing_report(report_id, **kwargs):
"reviewed": {}, "reviewed": {},
"acumulated": {}} "acumulated": {}}
for acc_type in ["feedback", "reviewed", "acumulated"]: for acc_type in ["feedback", "reviewed", "acumulated"]:
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] = None acumulated_acc[acc_type][key] = None
acumulated_acc[acc_type][key + "_count"] = None acumulated_acc[acc_type][key + "_count"] = None
acumulated_acc[acc_type]["avg"] = None acumulated_acc[acc_type]["avg"] = None

17
cope2n-api/fwd_api/celery_worker/process_result_tasks.py
View File

@ -29,8 +29,8 @@ def aggregate_result(results):
des_result["content"]["total_pages"] = 0 des_result["content"]["total_pages"] = 0
des_result["content"]["ocr_num_pages"] = 0 des_result["content"]["ocr_num_pages"] = 0
des_result["content"]["document"][0]["end_page"] = 0 des_result["content"]["document"][0]["end_page"] = 0
des_result["content"]["document"][0]["content"][3]["value"] = [None for _ in range(doc_types.count("imei"))] des_result["content"]["document"][0]["content"][4]["value"] = [None for _ in range(doc_types.count("imei"))]
des_result["content"]["document"][0]["content"][2]["value"] = [] des_result["content"]["document"][0]["content"][3]["value"] = []
imei_count = 0 imei_count = 0
for doc_type, result in sorted_results: for doc_type, result in sorted_results:
@ -38,12 +38,14 @@ def aggregate_result(results):
des_result["content"]["ocr_num_pages"] += 1 des_result["content"]["ocr_num_pages"] += 1
des_result["content"]["document"][0]["end_page"] += 1 des_result["content"]["document"][0]["end_page"] += 1
if doc_type == "imei": if doc_type == "imei":
des_result["content"]["document"][0]["content"][3]["value"][imei_count] = result["content"]["document"][0]["content"][3]["value"][0] if len(result["content"]["document"][0]["content"][4]["value"]):
des_result["content"]["document"][0]["content"][4]["value"][imei_count] = result["content"]["document"][0]["content"][4]["value"][0]
imei_count += 1 imei_count += 1
elif doc_type == "invoice": elif doc_type == "invoice":
des_result["content"]["document"][0]["content"][0]["value"] = result["content"]["document"][0]["content"][0]["value"] des_result["content"]["document"][0]["content"][0]["value"] = result["content"]["document"][0]["content"][0]["value"]
des_result["content"]["document"][0]["content"][1]["value"] = result["content"]["document"][0]["content"][1]["value"] des_result["content"]["document"][0]["content"][1]["value"] = result["content"]["document"][0]["content"][1]["value"]
des_result["content"]["document"][0]["content"][2]["value"] += result["content"]["document"][0]["content"][2]["value"] des_result["content"]["document"][0]["content"][2]["value"] = result["content"]["document"][0]["content"][2]["value"]
des_result["content"]["document"][0]["content"][3]["value"] += result["content"]["document"][0]["content"][3]["value"]
elif doc_type == "all": elif doc_type == "all":
des_result.update(result) des_result.update(result)
else: else:
@ -151,7 +153,6 @@ def process_invoice_sbt_result(rq_id, result, metadata):
index_in_request = metadata.pop("index_to_image_type", 0) index_in_request = metadata.pop("index_to_image_type", 0)
result["metadata"] = metadata result["metadata"] = metadata
_update_subscription_rq_file(request_id=rq, index_in_request=index_in_request, doc_type=image_type, result=result) _update_subscription_rq_file(request_id=rq, index_in_request=index_in_request, doc_type=image_type, result=result)
status = result.get("status", 200) status = result.get("status", 200)
redis_client.set_cache(rq_id, page_index, result) redis_client.set_cache(rq_id, page_index, result)
done = rq.pages == redis_client.get_size(rq_id) done = rq.pages == redis_client.get_size(rq_id)
@ -194,9 +195,9 @@ def process_invoice_sbt_result(rq_id, result, metadata):
def _update_subscription_rq_file(request_id, index_in_request, doc_type, result): def _update_subscription_rq_file(request_id, index_in_request, doc_type, result):
image = SubscriptionRequestFile.objects.filter(request=request_id, index_in_request=index_in_request, doc_type=doc_type).first() image = SubscriptionRequestFile.objects.filter(request=request_id, index_in_request=index_in_request, doc_type=doc_type).first()
retailer_name = None retailer_name = None
sold_to_party = None sold_to_party = None
invoice_no = None
purchase_date = [] purchase_date = []
imei_number = [] imei_number = []
predicted_res = __get_actual_predict_result(result=result) predicted_res = __get_actual_predict_result(result=result)
@ -208,12 +209,15 @@ def _update_subscription_rq_file(request_id, index_in_request, doc_type, result)
sold_to_party = elem['value'] sold_to_party = elem['value']
elif elem["label"] == "purchase_date": elif elem["label"] == "purchase_date":
purchase_date = elem['value'] purchase_date = elem['value']
elif elem["label"] == "invoice_no":
invoice_no = elem['value']
else: else:
imei_number = elem['value'] imei_number = elem['value']
if doc_type=='invoice': if doc_type=='invoice':
_predict_result = { _predict_result = {
"retailername": retailer_name, "retailername": retailer_name,
"sold_to_party": sold_to_party, "sold_to_party": sold_to_party,
"invoice_no": invoice_no,
"purchase_date": purchase_date, "purchase_date": purchase_date,
"imei_number": [] "imei_number": []
} }
@ -221,6 +225,7 @@ def _update_subscription_rq_file(request_id, index_in_request, doc_type, result)
_predict_result = { _predict_result = {
"retailername": None, "retailername": None,
"sold_to_party": None, "sold_to_party": None,
"invoice_no": None,
"purchase_date": [], "purchase_date": [],
"imei_number": imei_number "imei_number": imei_number
} }

195
cope2n-api/fwd_api/utils/accuracy.py
View File

@ -17,7 +17,7 @@ from fwd import settings
from ..models import SubscriptionRequest, Report, ReportFile from ..models import SubscriptionRequest, Report, ReportFile
import json 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: class ReportAccumulateByRequest:
def __init__(self, sub): def __init__(self, sub):
@ -42,7 +42,7 @@ class ReportAccumulateByRequest:
'purchase_date': IterAvg(), 'purchase_date': IterAvg(),
'retailer_name': IterAvg(), 'retailer_name': IterAvg(),
'sold_to_party': IterAvg(), 'sold_to_party': IterAvg(),
'invoice_no': IterAvg(), 'invoice_no': IterAvg()
}, },
'average_processing_time': { 'average_processing_time': {
'imei': IterAvg(), 'imei': IterAvg(),
@ -339,7 +339,8 @@ class MonthReportAccumulate:
'average_accuracy_rate': { 'average_accuracy_rate': {
'imei': IterAvg(), 'imei': IterAvg(),
'purchase_date': IterAvg(), 'purchase_date': IterAvg(),
'retailer_name': IterAvg() 'retailer_name': IterAvg(),
'invoice_no': IterAvg()
}, },
'average_processing_time': { 'average_processing_time': {
'imei': IterAvg(), 'imei': IterAvg(),
@ -366,7 +367,8 @@ class MonthReportAccumulate:
'average_accuracy_rate': { 'average_accuracy_rate': {
'imei': 0, 'imei': 0,
'purchase_date': 0, 'purchase_date': 0,
'retailer_name': 0 'retailer_name': 0,
'invoice_no': 0
}, },
'average_processing_time': { 'average_processing_time': {
'imei': 0, 'imei': 0,
@ -388,10 +390,12 @@ 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"]["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"]["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"]["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: 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"]["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"]["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"]["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"]["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 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
@ -425,10 +429,13 @@ class MonthReportAccumulate:
new_data["average_accuracy_rate"]["imei"] = report.reviewed_accuracy.get("imei_number", None) 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"]["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"]["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]): 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"]["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"]["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"]["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"]["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["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 new_data["usage"]["imei"] = report.number_imei_transaction
@ -533,19 +540,19 @@ def extract_report_detail_list(report_detail_list, lower=False, in_percent=True)
"Image type": report_file.doc_type, "Image type": report_file.doc_type,
"IMEI_user submitted": first_of_list(report_file.feedback_result.get("imei_number", [None])), "IMEI_user submitted": first_of_list(report_file.feedback_result.get("imei_number", [None])),
"IMEI_OCR retrieved": first_of_list(report_file.predict_result.get("imei_number", [None])), "IMEI_OCR retrieved": first_of_list(report_file.predict_result.get("imei_number", [None])),
"IMEI Revised": None, "IMEI Revised": first_of_list(report_file.reviewed_result.get("imei_number", [None])),
"IMEI1 Accuracy": first_of_list(report_file.feedback_accuracy.get("imei_number", [None])), "IMEI1 Accuracy": first_of_list(report_file.feedback_accuracy.get("imei_number", [None])),
"Invoice_Number_User": None, "Invoice_Number_User": report_file.feedback_result.get("invoice_no", None),
"Invoice_Number_OCR": None, "Invoice_Number_OCR": report_file.predict_result.get("invoice_no", None),
"Invoice_Number Revised": None, "Invoice_Number Revised": report_file.reviewed_result.get("invoice_no", None),
"Invoice_Number_Accuracy": None, "Invoice_Number_Accuracy": first_of_list(report_file.feedback_accuracy.get("invoice_no", [None])),
"Invoice_Purchase Date_Consumer": report_file.feedback_result.get("purchase_date", None), "Invoice_Purchase Date_Consumer": report_file.feedback_result.get("purchase_date", None),
"Invoice_Purchase Date_OCR": report_file.predict_result.get("purchase_date", []), "Invoice_Purchase Date_OCR": report_file.predict_result.get("purchase_date", []),
"Invoice_Purchase Date Revised": None, "Invoice_Purchase Date Revised": report_file.reviewed_result.get("purchase_date", None),
"Invoice_Purchase Date Accuracy": first_of_list(report_file.feedback_accuracy.get("purchase_date", [None])), "Invoice_Purchase Date Accuracy": first_of_list(report_file.feedback_accuracy.get("purchase_date", [None])),
"Invoice_Retailer_Consumer": report_file.feedback_result.get("retailername", None), "Invoice_Retailer_Consumer": report_file.feedback_result.get("retailername", None),
"Invoice_Retailer_OCR": report_file.predict_result.get("retailername", None), "Invoice_Retailer_OCR": report_file.predict_result.get("retailername", None),
"Invoice_Purchase Date Revised": None, "Invoice_Retailer Revised": report_file.reviewed_result.get("retailername", None),
"Invoice_Retailer Accuracy": first_of_list(report_file.feedback_accuracy.get("retailername", [None])), "Invoice_Retailer Accuracy": first_of_list(report_file.feedback_accuracy.get("retailername", [None])),
"OCR Image Accuracy": report_file.acc, "OCR Image Accuracy": report_file.acc,
"OCR Image Speed (seconds)": report_file.time_cost, "OCR Image Speed (seconds)": report_file.time_cost,
@ -555,6 +562,7 @@ 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])), "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])), "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])), "Retailer_Revised Accuracy": first_of_list(report_file.reviewed_accuracy.get("retailername", [None])),
"Invoice_Number_Revised Accuracy": first_of_list(report_file.reviewed_accuracy.get("invoice_no", [None]))
}) })
if lower: if lower:
for i, dat in enumerate(data): for i, dat in enumerate(data):
@ -610,14 +618,16 @@ def convert_datetime_format(date_string: str, is_gt=False) -> str:
def predict_result_to_ready(result): def predict_result_to_ready(result):
dict_result = {"retailername": "", dict_result = {"retailername": "",
"sold_to_party": "", "sold_to_party": "",
"invoice_no": "",
"purchase_date": [], "purchase_date": [],
"imei_number": [],} "imei_number": [],}
if not result: if not result:
return dict_result return dict_result
dict_result["retailername"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}])[0].get("value", None) 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["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["invoice_no"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}])[2].get("value", None)
dict_result["imei_number"] = result.get("content", {}).get("document", [{}])[0].get("content", [{}, {}, {}, {}])[3].get("value", []) 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 return dict_result
def align_fine_result(ready_predict, fine_result): def align_fine_result(ready_predict, fine_result):
@ -628,15 +638,9 @@ def align_fine_result(ready_predict, fine_result):
ready_predict["purchase_date"] = [None] ready_predict["purchase_date"] = [None]
if fine_result["retailername"] and not ready_predict["retailername"]: if fine_result["retailername"] and not ready_predict["retailername"]:
ready_predict["retailername"] = [None] ready_predict["retailername"] = [None]
# if ready_predict["retailername"] and not fine_result["retailername"]: if ready_predict["invoice_no"] and not fine_result["invoice_no"]:
# fine_result["retailername"] = [None] fine_result["invoice_no"] = [None]
fine_result["purchase_date"] = [fine_result["purchase_date"] for _ in range(len(ready_predict["purchase_date"]))] 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:
# fine_result = {}
# for key in ready_predict.keys():
# fine_result[key] = []
# fine_result["purchase_date"] = [None for _ in range(len(ready_predict["purchase_date"]))]
return ready_predict, fine_result return ready_predict, fine_result
def update_temp_accuracy(accuracy, acc, keys): def update_temp_accuracy(accuracy, acc, keys):
@ -704,76 +708,6 @@ def calculate_avg_accuracy(acc, type, keys=[]):
return sum(acc_list)/len(acc_list) if len(acc_list) > 0 else None 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): def acc_maximize_list_values(acc):
pos = {} pos = {}
for k in acc.keys(): for k in acc.keys():
@ -838,16 +772,19 @@ def calculate_a_request(report, request):
"purchase_date": [], "purchase_date": [],
"retailername": [], "retailername": [],
"sold_to_party": [], "sold_to_party": [],
"invoice_no": [],
}, },
"reviewed": {"imei_number": [], "reviewed": {"imei_number": [],
"purchase_date": [], "purchase_date": [],
"retailername": [], "retailername": [],
"sold_to_party": [], "sold_to_party": [],
"invoice_no": [],
}, },
"acumulated":{"imei_number": [], "acumulated":{"imei_number": [],
"purchase_date": [], "purchase_date": [],
"retailername": [], "retailername": [],
"sold_to_party": [], "sold_to_party": [],
"invoice_no": [],
}}, }},
"err": [], "err": [],
"time_cost": {"imei": [], "time_cost": {"imei": [],
@ -936,16 +873,19 @@ def calculate_a_request(report, request):
request_att["acc"]["feedback"]["purchase_date"] += _att["acc"]["feedback"]["purchase_date"] request_att["acc"]["feedback"]["purchase_date"] += _att["acc"]["feedback"]["purchase_date"]
request_att["acc"]["feedback"]["retailername"] += _att["acc"]["feedback"]["retailername"] 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"]["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"]["imei_number"] += _att["acc"]["reviewed"]["imei_number"]
request_att["acc"]["reviewed"]["purchase_date"] += _att["acc"]["reviewed"]["purchase_date"] request_att["acc"]["reviewed"]["purchase_date"] += _att["acc"]["reviewed"]["purchase_date"]
request_att["acc"]["reviewed"]["retailername"] += _att["acc"]["reviewed"]["retailername"] 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"]["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"]["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"]["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"]["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"]["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: if image.reason not in settings.ACC_EXCLUDE_RESEASONS:
request_att["bad_images"] += int(_att["is_bad_image"]) request_att["bad_images"] += int(_att["is_bad_image"])
@ -973,10 +913,6 @@ def calculate_subcription_file(subcription_request_file):
inference_result = copy.deepcopy(subcription_request_file.predict_result) 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, 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)) 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: for key_name in valid_keys:
try: try:
@ -988,8 +924,8 @@ def calculate_subcription_file(subcription_request_file):
# print(f"[DEBUG]: e: {e} -key_name: {key_name}") # print(f"[DEBUG]: e: {e} -key_name: {key_name}")
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", ["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", "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: if avg_feedback is not None or avg_reviewed is not None:
avg_acc = 0 avg_acc = 0
if avg_feedback is not None: if avg_feedback is not None:
@ -1009,68 +945,6 @@ def calculate_subcription_file(subcription_request_file):
att["is_bad_image"] = True att["is_bad_image"] = True
return 200, att 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): def mean_list(l):
l = [x for x in l if x is not None] l = [x for x in l if x is not None]
if len(l) == 0: if len(l) == 0:
@ -1078,5 +952,4 @@ def mean_list(l):
return sum(l)/len(l) return sum(l)/len(l)
def shadow_report(report_id, query): def shadow_report(report_id, query):
c_connector.make_a_report_2( c_connector.make_a_report_2((report_id, query))
(report_id, query))