sbt-idp/cope2n-api/fwd_api/utils/accuracy.py

import re
from datetime import datetime

import copy
from typing import Any
from .ocr_utils.ocr_metrics import eval_ocr_metric
from .ocr_utils.sbt_report import post_processing_str
import uuid
from fwd_api.models import SubscriptionRequest, SubscriptionRequestFile, ReportFile
from ..celery_worker.client_connector import c_connector
from ..utils.file import dict2xlsx, save_workbook_file, save_report_to_S3
from django.db.models import Q
from django.utils import timezone
import redis
from fwd import settings
from ..models import SubscriptionRequest, Report, ReportFile
import json

BAD_THRESHOLD = 0.75

valid_keys = ["retailername", "sold_to_party", "purchase_date", "imei_number"]

class ReportAccumulateByRequest:
    def __init__(self, sub):
        # self.redis_client = redis.Redis(host=settings.REDIS_HOST, port=settings.REDIS_PORT, decode_responses=True)
        self.sub = sub
        self.current_time = None
        self.data = {} # {"month": [total, {"day": day_data}]}
        self.total_format = {
                    'subs': "+",
                    'extraction_date': "Subtotal ()",
                    'total_images': 0,
                    'images_quality': {
                        'successful': 0,
                        'successful_percent': 0,
                        'bad': 0,
                        'bad_percent': 0
                    },
                    'average_accuracy_rate': {
                        'imei': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailer_name': IterAvg(),
                        'sold_to_party': IterAvg()
                    },
                    'average_processing_time': {
                        'imei': IterAvg(),
                        'invoice': IterAvg()
                    },
                    'usage': {
                        'imei':0,
                        'invoice': 0,
                        'request': 0
                        },
                    'feedback_accuracy': {
                        'imei_number': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailername': IterAvg(),
                        'sold_to_party': IterAvg()
                    },
                    'reviewed_accuracy': {
                        'imei_number': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailername': IterAvg(),
                        'sold_to_party': IterAvg()
                    },
                    'num_request': 0
                }
        self.day_format =  {
                    'subs': sub,
                    'extraction_date': "",
                    'num_imei': 0,
                    'num_invoice': 0,
                    'total_images': 0,
                    'images_quality': {
                        'successful': 0,
                        'successful_percent': 0,
                        'bad': 0,
                        'bad_percent': 0
                    },
                    'average_accuracy_rate': {
                        'imei': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailer_name': IterAvg(),
                        'sold_to_party': IterAvg()
                    },
                    'average_processing_time': {
                        'imei': IterAvg(),
                        'invoice': IterAvg()
                    },
                    'usage': {
                        'imei': 0,
                        'invoice': 0,
                        'request': 0
                    },
                    'feedback_accuracy': {
                        'imei_number': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailername': IterAvg(),
                        'sold_to_party': IterAvg()
                    },
                    'reviewed_accuracy': {
                        'imei_number': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailername': IterAvg(),
                        'sold_to_party': IterAvg()
                    },
                    "report_files": [],
                    'num_request': 0
                },
    
    @staticmethod
    def update_total(total, report_file):
        total["total_images"] += 1
        total["images_quality"]["successful"] += 1 if not report_file.is_bad_image else 0
        total["images_quality"]["bad"] += 1 if report_file.is_bad_image else 0
        # total["report_files"].append(report_file)

        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"]["imei"].add(report_file.reviewed_accuracy.get("imei_number", []))
            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", []))
        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", []))

        for key in ["imei_number", "purchase_date", "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"]:
            total["reviewed_accuracy"][key].add(report_file.reviewed_accuracy.get(key, []))

        if not total["average_processing_time"].get(report_file.doc_type, None):
            print(f"[WARM]: Weird doctype: {report_file.doc_type}")
            total["average_processing_time"] = IterAvg()
        total["average_processing_time"][report_file.doc_type].add_avg(report_file.time_cost, 1) if report_file.time_cost else 0 

        total["usage"]["imei"] += 1 if report_file.doc_type == "imei" else 0
        total["usage"]["invoice"] += 1 if report_file.doc_type == "invoice" else 0
        
        return total

    @staticmethod
    def update_day(day_data, report_file):
        day_data["total_images"] += 1
        day_data["images_quality"]["successful"] += 1 if not report_file.is_bad_image else 0
        day_data["images_quality"]["bad"] += 1 if report_file.is_bad_image else 0
        day_data["num_imei"] += 1 if report_file.doc_type == "imei" else 0
        day_data["num_invoice"] += 1 if report_file.doc_type == "invoice" else 0
        day_data["report_files"].append(report_file)
        
        if sum([len(report_file.reviewed_accuracy[x]) for x in report_file.reviewed_accuracy.keys() if "_count" not in x]) > 0 :
            day_data["average_accuracy_rate"]["imei"].add(report_file.reviewed_accuracy.get("imei_number", 0))
            day_data["average_accuracy_rate"]["purchase_date"].add(report_file.reviewed_accuracy.get("purchase_date", 0))
            day_data["average_accuracy_rate"]["retailer_name"].add(report_file.reviewed_accuracy.get("retailername", 0))
            day_data["average_accuracy_rate"]["sold_to_party"].add(report_file.reviewed_accuracy.get("sold_to_party", 0))
        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", 0))
            day_data["average_accuracy_rate"]["purchase_date"].add(report_file.feedback_accuracy.get("purchase_date", 0))
            day_data["average_accuracy_rate"]["retailer_name"].add(report_file.feedback_accuracy.get("retailername", 0))
            day_data["average_accuracy_rate"]["sold_to_party"].add(report_file.feedback_accuracy.get("sold_to_party", 0))

        for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
            day_data["feedback_accuracy"][key].add(report_file.feedback_accuracy.get(key, 0))
        for key in ["imei_number", "purchase_date", "retailername", "sold_to_party"]:
            day_data["reviewed_accuracy"][key].add(report_file.reviewed_accuracy.get(key, 0))

        if not day_data["average_processing_time"].get(report_file.doc_type, None):
            print(f"[WARM]: Weird doctype: {report_file.doc_type}")
            day_data["average_processing_time"] = IterAvg()
        day_data["average_processing_time"][report_file.doc_type].add_avg(report_file.time_cost, 1) if report_file.time_cost else 0 

        return day_data
    
    def add(self, request, report_files):
        this_month = request.created_at.strftime("%Y%m")
        this_day = request.created_at.strftime("%Y%m%d")
        if not self.data.get(this_month, None):
            self.data[this_month] = [copy.deepcopy(self.total_format), {}]
            self.data[this_month][0]["extraction_date"] = "Subtotal (" + request.created_at.strftime("%Y-%m") + ")"
        if not self.data[this_month][1].get(this_day, None):
            self.data[this_month][1][this_day] = copy.deepcopy(self.day_format)[0]
            self.data[this_month][1][this_day]['extraction_date'] = request.created_at.strftime("%Y-%m-%d")
            usage = self.count_transactions_within_day(this_day)
            self.data[this_month][1][this_day]["usage"]["imei"] = usage.get("imei", 0)
            self.data[this_month][1][this_day]["usage"]["invoice"] = usage.get("invoice", 0)
            self.data[this_month][1][this_day]["usage"]["request"] = usage.get("request", 0)

        self.data[this_month][1][this_day]['num_request'] += 1
        self.data[this_month][0]['num_request'] += 1
        for report_file in report_files:
            self.data[this_month][0] = self.update_total(self.data[this_month][0], report_file) # Update the subtotal within the month
            self.data[this_month][1][this_day] = self.update_day(self.data[this_month][1][this_day], report_file) # Update the subtotal of the day

    def count_transactions_within_day(self, date_string):
        # convert this day into timezone.datetime at UTC
        start_date = datetime.strptime(date_string, "%Y%m%d")
        start_date_with_timezone = timezone.make_aware(start_date)
        end_date_with_timezone = start_date_with_timezone + timezone.timedelta(days=1)
        return count_transactions(start_date_with_timezone, end_date_with_timezone, self.sub)

    def save(self, root_report_id, is_daily_report=False, include_test=False):
        report_data = self.get()
        fine_data = []
        save_data = {"file": {"overview": f"{root_report_id}/{root_report_id}.xlsx"},
                    "data": fine_data} # {"sub_report_id": "S3 location", "data": fine_data}
        # extract data
        month_keys = list(report_data.keys())
        month_keys.sort(reverse=True)
        for month in month_keys:
            fine_data.append(report_data[month][0])
            day_keys = list(report_data[month][1].keys())
            day_keys.sort(reverse = True)
            for day in day_keys:
                fine_data.append(report_data[month][1][day])
                # save daily reports
                report_id = root_report_id + "_" + day
                start_date = datetime.strptime(day, "%Y%m%d")
                start_date_with_timezone = timezone.make_aware(start_date)
                end_date_with_timezone = start_date_with_timezone + timezone.timedelta(days=1)
                _average_OCR_time = {"invoice": self.data[month][1][day]["average_processing_time"]["invoice"](), "imei": self.data[month][1][day]["average_processing_time"]["imei"](),
                                   "invoice_count": self.data[month][1][day]["average_processing_time"]["invoice"].count, "imei_count": self.data[month][1][day]["average_processing_time"]["imei"].count}
        
                _average_OCR_time["avg"] = (_average_OCR_time["invoice"]*_average_OCR_time["invoice_count"] + _average_OCR_time["imei"]*_average_OCR_time["imei_count"])/(_average_OCR_time["imei_count"] + _average_OCR_time["invoice_count"]) if (_average_OCR_time["imei_count"] + _average_OCR_time["invoice_count"]) > 0 else None
                acumulated_acc = {"feedback_accuracy": {},
                    "reviewed_accuracy": {}}
                for acc_type in ["feedback_accuracy", "reviewed_accuracy"]:
                    avg_acc = IterAvg()
                    for key in ["imei_number", "purchase_date", "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"])
                    acumulated_acc[acc_type]["avg"] = avg_acc()
                    acumulated_acc[acc_type]["avg_count"] = avg_acc.count
                new_report: Report = Report(
                        report_id=report_id,
                        is_daily_report=is_daily_report,
                        subsidiary=self.sub.lower().replace(" ", ""),
                        include_test=include_test,
                        start_at=start_date_with_timezone,
                        end_at=end_date_with_timezone,
                        status="Ready",
                        number_request=report_data[month][1][day]["num_request"],
                        number_images=report_data[month][1][day]["total_images"],
                        number_imei=report_data[month][1][day]["num_imei"],
                        number_invoice=report_data[month][1][day]["num_invoice"],
                        number_bad_images=report_data[month][1][day]["images_quality"]["bad"],
                        average_OCR_time=_average_OCR_time,
                        number_imei_transaction=report_data[month][1][day]["usage"]["imei"],
                        number_invoice_transaction=report_data[month][1][day]["usage"]["invoice"],
                        feedback_accuracy=acumulated_acc["feedback_accuracy"],
                        reviewed_accuracy=acumulated_acc["reviewed_accuracy"],
                    )
                new_report.save()
                data = extract_report_detail_list(self.data[month][1][day]["report_files"], lower=True)
                data_workbook = dict2xlsx(data, _type='report_detail')
                local_workbook = save_workbook_file(report_id + ".xlsx", new_report, data_workbook)
                s3_key=save_report_to_S3(report_id, local_workbook)
        return fine_data, save_data
    
    def get(self) -> Any:
        # FIXME: This looks like a junk
        _data = copy.deepcopy(self.data)
        for month in _data.keys():
            _data[month][0]["images_quality"]["successful_percent"] = _data[month][0]["images_quality"]["successful"]/_data[month][0]["total_images"] if _data[month][0]["total_images"] > 0 else 0
            _data[month][0]["images_quality"]["bad_percent"] = _data[month][0]["images_quality"]["bad"]/_data[month][0]["total_images"] if _data[month][0]["total_images"] > 0 else 0
            num_transaction_imei = 0
            num_transaction_invoice = 0
            for day in _data[month][1].keys():
                num_transaction_imei += _data[month][1][day]["usage"].get("imei", 0)
                num_transaction_invoice += _data[month][1][day]["usage"].get("invoice", 0)
                _data[month][1][day]["average_accuracy_rate"]["imei"] = _data[month][1][day]["average_accuracy_rate"]["imei"]()
                _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_processing_time"]["imei"] = _data[month][1][day]["average_processing_time"]["imei"]()
                _data[month][1][day]["average_processing_time"]["invoice"] = _data[month][1][day]["average_processing_time"]["invoice"]()
            
                _data[month][1][day]["feedback_accuracy"]["imei_number"] = _data[month][1][day]["feedback_accuracy"]["imei_number"]()
                _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]["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].pop("report_files")

                _data[month][1][day]["images_quality"]["successful_percent"] = _data[month][1][day]["images_quality"]["successful"]/_data[month][1][day]["total_images"]  if _data[month][1][day]["total_images"] > 0 else 0
                _data[month][1][day]["images_quality"]["bad_percent"] = _data[month][1][day]["images_quality"]["bad"]/_data[month][1][day]["total_images"] if _data[month][1][day]["total_images"] > 0 else 0

            _data[month][0]["usage"]["imei"] = num_transaction_imei
            _data[month][0]["usage"]["invoice"] = num_transaction_invoice
            _data[month][0]["average_accuracy_rate"]["imei"] = _data[month][0]["average_accuracy_rate"]["imei"]()
            _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_processing_time"]["imei"] = _data[month][0]["average_processing_time"]["imei"]()
            _data[month][0]["average_processing_time"]["invoice"] = _data[month][0]["average_processing_time"]["invoice"]()

            _data[month][0]["feedback_accuracy"]["imei_number"] = _data[month][0]["feedback_accuracy"]["imei_number"]()
            _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]["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"]()

        return _data
    

class MonthReportAccumulate:
    def __init__(self):
        self.month = None
        self.total = {
                    'subs': "+",
                    'extraction_date': "Subtotal ()",
                    'total_images': 0,
                    'images_quality': {
                        'successful': 0,
                        'successful_percent': 0,
                        'bad': 0,
                        'bad_percent': 0
                    },
                    'average_accuracy_rate': {
                        'imei': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailer_name': IterAvg()
                    },
                    'average_processing_time': {
                        'imei': IterAvg(),
                        'invoice': IterAvg()
                    },
                    'usage': {
                        'imei':0,
                        'invoice': 0
                        }
                    }
        self.data = []
        self.data_format =  {
                    'subs': "",
                    'extraction_date': "",
                    'num_imei': 0,
                    'num_invoice': 0,
                    'total_images': 0,
                    'images_quality': {
                        'successful': 0,
                        'successful_percent': 0,
                        'bad': 0,
                        'bad_percent': 0
                    },
                    'average_accuracy_rate': {
                        'imei': 0,
                        'purchase_date': 0,
                        'retailer_name': 0
                    },
                    'average_processing_time': {
                        'imei': 0,
                        'invoice': 0
                    },
                    'usage': {
                        'imei':0,
                        'invoice': 0
                        }
                },

    def accumulate(self, report):
        self.total["total_images"] += report.number_images
        self.total["images_quality"]["successful"] += report.number_images - report.number_bad_images
        self.total["images_quality"]["bad"] += report.number_bad_images
        

        if sum([report.reviewed_accuracy[x] for x in report.reviewed_accuracy.keys() if "_count" not in x]) > 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"]["retailer_name"].add_avg(report.reviewed_accuracy.get("retailername", 0), report.reviewed_accuracy.get("retailername_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_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["usage"]["imei"] += report.number_imei_transaction
        self.total["usage"]["invoice"] += report.number_invoice_transaction

    def add(self, report):
        report_month = report.start_at.month

        if self.month is None:
            self.month = report_month
            self.total["extraction_date"] = f"Subtotal ({self.month})"

        elif self.month != report_month:
            self.total["images_quality"]["successful_percent"] += self.total["images_quality"]["successful"]/self.total["total_images"]
            self.total["images_quality"]["bad_percent"] += self.total["images_quality"]["bad"]/self.total["total_images"]
            return False  # Reports from a different month, stop accumulating
        # accumulate fields
        new_data = copy.deepcopy(self.data_format)[0]
        new_data["num_imei"] = report.number_imei
        new_data["subs"] = report.subsidiary
        new_data["extraction_date"] = report.start_at
        new_data["num_invoice"] = report.number_invoice
        new_data["total_images"] = report.number_images
        new_data["images_quality"]["successful"] = report.number_images - report.number_bad_images
        new_data["images_quality"]["bad"] = report.number_bad_images

        report.reviewed_accuracy = {} if report.reviewed_accuracy is None else report.reviewed_accuracy
        report.feedback_accuracy = {} if report.feedback_accuracy is None else report.feedback_accuracy
        if sum([ report.reviewed_accuracy[x] for x in report.reviewed_accuracy.keys() if "_count" not in x]):
            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)
        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_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
        new_data["usage"]["invoice"] = report.number_invoice_transaction

        new_data["images_quality"]["successful_percent"] += new_data["images_quality"]["successful"]/new_data["total_images"] if new_data["total_images"] else 0
        new_data["images_quality"]["bad_percent"] += new_data["images_quality"]["bad"]/new_data["total_images"] if new_data["total_images"] else 0
        self.data.append(new_data)
        self.accumulate(report)
        return True

    def clear(self):
        self.month = None
        self.total = {
                    'subs': "+",
                    'extraction_date': "Subtotal ()",
                    'total_images': 0,
                    'images_quality': {
                        'successful': 0,
                        'successful_percent': 0,
                        'bad': 0,
                        'bad_percent': 0
                    },
                    'average_accuracy_rate': {
                        'imei': IterAvg(),
                        'purchase_date': IterAvg(),
                        'retailer_name': IterAvg()
                    },
                    'average_processing_time': {
                        'imei': IterAvg(),
                        'invoice': IterAvg()
                    },
                    'usage': {
                        'imei':0,
                        'invoice': 0
                        }
                    }
        self.data = []

    def __call__(self):
        total = copy.deepcopy(self.total)
        total["images_quality"]["successful_percent"] = total["images_quality"]["successful"]/total["total_images"] if total["total_images"] else 0
        total["images_quality"]["bad_percent"] = total["images_quality"]["bad"]/total["total_images"] if total["total_images"] else 0
        total["average_accuracy_rate"]["imei"] = total["average_accuracy_rate"]["imei"]()
        total["average_accuracy_rate"]["purchase_date"] = total["average_accuracy_rate"]["purchase_date"]()
        total["average_accuracy_rate"]["retailer_name"] = total["average_accuracy_rate"]["retailer_name"]()
        total["average_processing_time"]["imei"] = total["average_processing_time"]["imei"]()
        total["average_processing_time"]["invoice"] = total["average_processing_time"]["invoice"]()
        return self.month, self.data, total

class IterAvg:
    def __init__(self, name="default"):
        self.name = name
        self.avg = 0
        self.count = 0
    
    def add(self, values):
        """
        Args: 
            values (list[float]):
        """
        values = [x for x in values if x is not None]
        if len(values) == 0:
            return 
        self.avg = (self.avg*self.count + sum(values))/(self.count+len(values))
        self.count += len(values)
    
    def add_avg(self, avg, count):
        if avg is None or count is None or count == 0:
            return
        self.count += count
        self.avg = (self.avg*(self.count-count) + avg*count)/(self.count)
    
    def __call__(self):
        return self.avg

def validate_feedback_file(feedback, predict):
    if feedback:
        imei_feedback = feedback.get("imei_number", [])
        imei_feedback = [x for x in imei_feedback if x != ""]
        num_imei_feedback = len(imei_feedback)
        num_imei_predict = len(predict.get("imei_number", []))
        if num_imei_feedback != num_imei_predict:
            return False
    return True
        
def first_of_list(the_list):
    if not the_list:
        return None
    return the_list[0]

def extract_report_detail_list(report_detail_list, lower=False, in_percent=True):
    data = []
    for report_file in report_detail_list:
        data.append({
            "Request ID": report_file.correspond_request_id,
            "Redemption Number": report_file.correspond_redemption_id,
            "Image type": report_file.doc_type,
            "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])),
            "IMEI1 Accuracy": first_of_list(report_file.feedback_accuracy.get("imei_number", [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 Accuracy": first_of_list(report_file.feedback_accuracy.get("purchase_date", [None])),
            "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])),
            "OCR Image Accuracy": report_file.acc,
            "OCR Image Speed (seconds)": report_file.time_cost,
            "Reviewed?": "No",
            "Bad Image Reasons": report_file.bad_image_reason,
            "Countermeasures": report_file.counter_measures,
            "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])),
        })
    if lower:
        for i, dat in enumerate(data):
            keys = list(dat.keys())
            for old_key in keys:
                data[i][old_key.lower().replace(" ", "_")] = data[i].pop(old_key)
    if in_percent:
        for i, dat in enumerate(data):
            keys = [x for x in list(dat.keys()) if "accuracy" in x.lower()]
            for key in keys:
                if data[i][key]:
                    data[i][key] = data[i][key]*100
    return data

def count_transactions(start_date, end_date, subsidiary="all"):
    base_query = Q(created_at__range=(start_date, end_date))
    base_query &= Q(is_test_request=False)
    if subsidiary and subsidiary.lower().replace(" ", "")!="all":
        base_query &= Q(redemption_id__startswith=subsidiary)
    transaction_att = {}

    print(f"[DEBUG]: atracting transactions attribute...")
    total_transaction_requests = SubscriptionRequest.objects.filter(base_query).order_by('created_at')
    for request in total_transaction_requests:
        if not request.doc_type:
            continue
        doc_types = request.doc_type.split(",")
        for doc_type in doc_types:
            if transaction_att.get(doc_type, None) == None:
                transaction_att[doc_type] = 1
            else:
                transaction_att[doc_type] += 1
        if not transaction_att.get("request", None):
            transaction_att["request"] = 1
        else:
            transaction_att["request"] += 1
    return transaction_att

def convert_datetime_format(date_string: str, is_gt=False) -> str:
    # pattern_date_string = "2023-02-28"
    input_format = "%Y-%m-%d"
    output_format = "%d/%m/%Y"
    # Validate the input date string format
    pattern = r"\d{4}-\d{2}-\d{2}"
    if re.match(pattern, date_string):
        # Convert the date string to a datetime object
        date_object = datetime.strptime(date_string, input_format)
        # Convert the datetime object to the desired output format
        formatted_date = date_object.strftime(output_format)
        return formatted_date
    return date_string

def predict_result_to_ready(result):
    dict_result = {"retailername": "",
                   "sold_to_party": "",
                   "purchase_date": [],
                   "imei_number": [],}
    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", [])
    return dict_result

def align_fine_result(ready_predict, fine_result):
    # print(f"[DEBUG]: fine_result: {fine_result}")
    # print(f"[DEBUG]: ready_predict: {ready_predict}")
    if fine_result:
        if fine_result["purchase_date"] and len(ready_predict["purchase_date"]) == 0:
            ready_predict["purchase_date"] = [None]
        if fine_result["retailername"] and not ready_predict["retailername"]:
            ready_predict["retailername"] = [None]
        fine_result["purchase_date"] = [fine_result["purchase_date"] for _ in range(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

def update_temp_accuracy(accuracy, acc, keys):
    for key in keys:
        accuracy[key].add(acc[key])
    return accuracy
def calculate_accuracy(key_name, inference, target):
    """_summary_

    Args:
        key_name (string): key to calculate accuracy on, ex: retailername
        inference (dict): result from ocr, refined to align with the target down below
        target (dict): result of type
    """
    acc = []
    data = []

    if not target or not inference:
        return acc, data
    if not isinstance(inference[key_name], list):
        if inference[key_name] is None:
            inference[key_name] = []
        else:
            inference[key_name] = [inference[key_name]]
    if not isinstance(target[key_name], list):
        if target[key_name] is None:
            target[key_name] = []
        else:
            target[key_name] = [target[key_name]]
    for i, v in enumerate(inference[key_name]):
        # TODO: target[key_name][i] is None, ""
        x = post_processing_str(key_name, inference[key_name][i], is_gt=False)
        y = post_processing_str(key_name, target[key_name][i], is_gt=True)

        score = eval_ocr_metric(
            [x], 
            [y], 
            metric=[
                "one_minus_ned",
                # "line_acc_ignore_case_symbol",
                # "line_acc",
                # "one_minus_ned_word",
            ])
        acc.append(list(score.values())[0])
        data.append([x, y])
    return acc, data

def calculate_avg_accuracy(acc, type, keys=[]):
    acc_list = []
    # print(f"[DEBUG]: type: {type} - acc: {acc}")
    for key in keys:
        acc_list += acc.get(type, {}).get(key, [])
    
    acc_list = [x for x in acc_list if x is not None]
    return sum(acc_list)/len(acc_list) if len(acc_list) > 0 else None


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 calculate_a_request(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)
    report_files = []
    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"],
                                    is_bad_image=att["is_bad_image"],
                                    time_cost=image.processing_time,
                                    bad_image_reason=image.reason,
                                    counter_measures=image.counter_measures,
                                    error="|".join(att["err"])
                                    )
        report_files.append(new_report_file)
        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, report_files
    

def calculate_subcription_file(subcription_request_file):
    att = {"acc": {"feedback": {},
                    "reviewed": {}},
             "err": [],
             "is_bad_image": False,
             "avg_acc": None}
    if not subcription_request_file.predict_result:
        return 400, att

    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:
            att["acc"]["feedback"][key_name], _ = calculate_accuracy(key_name, inference_result, feedback_result)
            att["acc"]["reviewed"][key_name], _ = calculate_accuracy(key_name, inference_result, reviewed_result)
        except Exception as e:
            att["err"].append(str(e))
            # print(f"[DEBUG]: e: {e} -key_name: {key_name}")
    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"])
    if avg_feedback is not None or avg_reviewed is not None:
        avg_acc = max([x for x in [avg_feedback, avg_reviewed] if x is not None])
        if avg_acc < BAD_THRESHOLD:
            att["is_bad_image"] = True
            # exclude bad images
            for key_name in valid_keys:
                att["acc"]["feedback"][key_name] = []
                att["acc"]["reviewed"][key_name] = []
                att["avg_acc"] = None
        else:
            att["avg_acc"] = avg_acc
    return 200, att

def calculate_attributions(request): # for one request, return in order
    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]) < 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]) < 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 shadow_report(report_id, query):
    c_connector.make_a_report_2(
                (report_id, query))