DeepLottery/1_FilterTest_25.py

import os
import pandas as pd
import itertools
from BallFilter_25 import BallFilter
import time
import datetime

class FilterTest:

    ballFilter = None

    def __init__(self, resources_path):
        lottoHistoryFileName = os.path.join(resources_path, 'lotto_history.json')
        self.ballFilter = BallFilter(lottoHistoryFileName)

        return

    def find_filter_method(self, df_ball, filter_ball=None):
        win_count = 0

        no_filter_ball = {}

        printLog = True
        filter_dic = {}
        filter_dic_len = {}
        filter_dic_1 = {}
        filter_dic_2 = {}
        for i in range(len(df_ball)-1, 19, -1):

            no = df_ball['no'].iloc[i]
            answer = df_ball[df_ball['no'] == no].values.tolist()[0]
            answer = answer[1:7]

            filter_type = self.ballFilter.filter(ball=answer, no=no, until_end=True, df=df_ball)
            filter_type = list(filter_type)
            size = len(filter_type)

            if size == 0:
                win_count += 1
                no_filter_ball[no] = answer
                print("\t", no)
            elif size == 1:
                key = filter_type[0]
                if key not in filter_dic_1:
                    filter_dic_1[key] = 1
                else:
                    filter_dic_1[key] += 1

                if printLog:
                    print("\t", no, filter_type)
            elif size == 2:
                key = ','.join(filter_type)
                if key not in filter_dic_2:
                    filter_dic_2[key] = 1
                else:
                    filter_dic_2[key] += 1

                if printLog:
                    print("\t", no, filter_type)
            else:
                if printLog:
                    print("\t", no, filter_type)

                # 회차별 필터개수가 적은 것을 정렬하기 위함
                if size not in filter_dic_len:
                    filter_dic_len[size] = []
                filter_dic_len[size].append(filter_type)

            for f_t in filter_type:
                if f_t not in filter_dic:
                    filter_dic[f_t] = 1
                else:
                    filter_dic[f_t] += 1

        print("\n\t[필터 개수가 적은 것부터 최적화를 위함]")
        sorted_filter_dic_len = sorted(filter_dic_len.keys())
        for filter_count in sorted_filter_dic_len:
            for filter_type in filter_dic_len[filter_count]:
                print("\t\t>{} > {}".format(filter_count, filter_type))

        print("\n\t[걸러진 유일 필터]")
        sorted_filter_dic_1 = sorted(filter_dic_1.items(), key=lambda x: x[1], reverse=True)
        for i in range(len(sorted_filter_dic_1)):
            print("\t\t>", sorted_filter_dic_1[i][0], "->", sorted_filter_dic_1[i][1])

        print("\n\t[2개 필터에 걸린 경우]")
        sorted_filter_dic_2 = sorted(filter_dic_2.items(), key=lambda x: x[1], reverse=True)
        for i in range(len(sorted_filter_dic_2)):
            print("\t\t>", sorted_filter_dic_2[i][0], "->", sorted_filter_dic_2[i][1])

        print("\n\t[Filter 유형 별 걸린 개수]")
        sorted_filter_dic = sorted(filter_dic.items(), key=lambda x: x[1], reverse=True)
        for i in range(len(sorted_filter_dic)):
            print("\t\t>", sorted_filter_dic[i][0], "->", sorted_filter_dic[i][1])

        print("\n\t# 필터에 걸리지 않고 당첨된 회차")
        print("\tcount: {:,} / total: {:,}".format(len(no_filter_ball), len(df_ball)))
        for no in no_filter_ball:
            print("\t\t>", no, no_filter_ball[no])
        print("\tcount: {:,} / total: {:,}".format(len(no_filter_ball), len(df_ball)))

        return win_count

    def find_final_candidates(self, no, df_ball, filter_ball=None):
        final_candidates = []

        generation_balls = list(range(1, 46))

        nCr = list(itertools.combinations(generation_balls, 6))
        for idx, ball in enumerate(nCr):

            if idx % 1000000 == 0:
                print("   - {} processed...".format(idx))

            if filter_ball is not None and 0 < len(set(ball) & set(filter_ball)):
                continue

            filter_type = self.ballFilter.filter(ball=ball, no=no, until_end=False, df=df_ball)
            filter_size = len(filter_type)

            if filter_size:
                continue

            final_candidates.append(ball)

        return final_candidates

    def check_filter_method(self, df_ball, p_win_count, filter_ball=None):

        win_count = 0
        for i in range(len(df_ball)-1, 0, -1):

            no = df_ball['no'].iloc[i]
            answer = df_ball[df_ball['no'] == no].values.tolist()[0]
            answer = answer[1:7]

            if filter_ball is not None and len(set(answer) & set(filter_ball)):
                continue

            filter_type = self.ballFilter.extract_final_candidates(answer, no=no, until_end=True, df=df_ball)

            if len(filter_type) == 0:
                win_count += 1
                print("\t\t>{}. {}".format(no, answer))

        print("\n\t> {} / {} p_win_count, {} total".format( win_count, p_win_count, len(df_ball)-1) )

        return

    def validate(self, df_ball, nos=None):
        win_history = {}

        for no in nos:
            print(no, "processing...")
            answer = df_ball[df_ball['no'] == no].values.tolist()[0]
            answer = answer[1:7]

            generation_balls = list(range(1, 46))
            nCr = list(itertools.combinations(generation_balls, 6))
            for idx, ball in enumerate(nCr):
                if idx % 1000000 == 0:
                    print("   - {} processed...".format(idx))
                ball = list(ball)
                filter_type = self.ballFilter.extract_final_candidates(ball, no=no, until_end=True, df=df_ball)
                if 0 == len(filter_type) and len(set(answer)&set(ball))==6:
                    win_history[no] = answer
                    print("win.. no: {}, answer: {}".format(no, str(answer)))
                    break

        return win_history


if __name__ == '__main__':

    resources_path = 'resources'

    lottoHistoryFileName = os.path.join(resources_path, 'lotto_history.txt')
    df_ball = pd.read_csv(lottoHistoryFileName, header=None)
    df_ball.columns = ['no', 'b1', 'b2', 'b3', 'b4', 'b5', 'b6', 'bn']

    filter_ball=[]
    filterTest = FilterTest(resources_path)

    print("STEP #1. 필터 방법 추출")
    start = time.time()
    win_count = filterTest.find_filter_method(df_ball, filter_ball)
    process_time = datetime.timedelta(seconds=time.time() - start)
    print("process_time: ", process_time)

    """
    print("\n\n")
    no = df_ball['no'].values[-1]
    ball = df_ball[df_ball['no'] == no].values.tolist()[0]
    answer = ball[1:7]

    print("STEP #0. 최종 후보 선정")
    start = time.time()
    final_candidates = filterTest.find_final_candidates(no, df_ball, filter_ball=None)
    process_time = datetime.timedelta(seconds=time.time() - start)
    print("process_time: ", process_time)

    print("   > size: {}".format(len(final_candidates)))
    file_name = os.path.join(resources_path, 'final_candidates.biz_a1.txt')
    with open(file_name, 'w+') as outFp:
        for ball in final_candidates:
            ball_str = [str(b) for b in answer]
            outFp.write("{}\n".format(','.join(ball_str)))

    print('{}회, 정답: {}\n'.format(no, str(answer)))
    """

    #print("\n\n")
    #print("STEP #2. 당첨 회수 확인")
    #filterTest.check_filter_method(df_ball, win_count)

    # 오리지널 버전 (자질 파일에 고정): 당첨 22개