Spaces:
Sleeping
Sleeping
| import pandas as pd | |
| KIFU_TO_SQUARE_NAMES = [ | |
| '１一', '１二', '１三', '１四', '１五', '１六', '１七', '１八', '１九', | |
| '２一', '２二', '２三', '２四', '２五', '２六', '２七', '２八', '２九', | |
| '３一', '３二', '３三', '３四', '３五', '３六', '３七', '３八', '３九', | |
| '４一', '４二', '４三', '４四', '４五', '４六', '４七', '４八', '４九', | |
| '５一', '５二', '５三', '５四', '５五', '５六', '５七', '５八', '５九', | |
| '６一', '６二', '６三', '６四', '６五', '６六', '６七', '６八', '６九', | |
| '７一', '７二', '７三', '７四', '７五', '７六', '７七', '７八', '７九', | |
| '８一', '８二', '８三', '８四', '８五', '８六', '８七', '８八', '８九', | |
| '９一', '９二', '９三', '９四', '９五', '９六', '９七', '９八', '９九', | |
| ] | |
| KIFU_FROM_SQUARE_NAMES = [ | |
| '11', '12', '13', '14', '15', '16', '17', '18', '19', | |
| '21', '22', '23', '24', '25', '26', '27', '28', '29', | |
| '31', '32', '33', '34', '35', '36', '37', '38', '39', | |
| '41', '42', '43', '44', '45', '46', '47', '48', '49', | |
| '51', '52', '53', '54', '55', '56', '57', '58', '59', | |
| '61', '62', '63', '64', '65', '66', '67', '68', '69', | |
| '71', '72', '73', '74', '75', '76', '77', '78', '79', | |
| '81', '82', '83', '84', '85', '86', '87', '88', '89', | |
| '91', '92', '93', '94', '95', '96', '97', '98', '99', | |
| ] | |
| def nomalize_precedence_name(df): | |
| #先手の対局者の名前から段位、タイトル名を削除する | |
| for x in range(len(df)): | |
| df["precedence_name"].iloc[x] = df["precedence_name"].iloc[x].replace(" ","").replace(" ","").replace("\u3000","") | |
| if df["precedence_name"].iloc[x].endswith("段"): | |
| df["precedence_name"].iloc[x] = df["precedence_name"].iloc[x][:-2] | |
| df["precedence_name"].iloc[x] = df["precedence_name"].iloc[x].replace("十七世名人","").replace("十八世名人","").replace("十九世名人","") | |
| df["precedence_name"].iloc[x] = df["precedence_name"].iloc[x].replace("王将","").replace("王座","").replace("名人","").replace("竜王","").replace("棋聖","").replace("叡王","").replace("王位","").replace("棋王","") | |
| df["precedence_name"].iloc[x] = df["precedence_name"].iloc[x].replace("・","").replace("二冠","").replace("三冠","") | |
| return df | |
| def nomalize_kif(df): | |
| for x in range(len(df)): | |
| kif = eval(df.iloc[x]["kif"]) | |
| #kifの正規化処理 手数、消費時間を削除する | |
| cnt = -1 | |
| for y in kif: | |
| cnt += 1 | |
| while(1): | |
| if "0" <= y[0] <= "9": | |
| y = y[1:] | |
| kif[cnt] = y | |
| else: | |
| break | |
| kif[cnt] = kif[cnt].replace("\u3000","") | |
| for z in range(len(y)): | |
| if y[z] == "(": | |
| kif[cnt] = y[:z] | |
| break | |
| kifs = "" | |
| for i in kif: | |
| kifs += i.replace("\u3000","") | |
| df["kif"].iloc[x] = kifs | |
| return df | |
| def nomalize_comment(df): | |
| #文章中のword省略処理 | |
| for cnt in range(len(df["output"])): | |
| x = df["output"].iloc[cnt] | |
| read = x.split("。") | |
| #print(read) | |
| line = "" | |
| for z in read: | |
| if "期" in z or "出身" in z or "優勝" in z or "受賞" in z or "回" in z or "記録" in z or "棋士番号" in z or "勝" in z or "敗" in z or "名人" in z: | |
| pass | |
| elif "時" in z or "分" in z or "成績" in z or "棋戦" in z or "段" in z or "本日" in z or "立会" in z or "ABEMA" in z or "第" in z or "本局" in z: | |
| pass | |
| elif "対局" in z or "永世" in z: | |
| pass | |
| elif z == "": | |
| pass | |
| else: | |
| #print(z) | |
| line += z+"。" | |
| df["output"].iloc[cnt] = line | |
| return df | |
| def accuracy_bestlist(df): | |
| cnt2 = 0 | |
| num = 0 | |
| for z in range(len(df)): | |
| blist = eval(df["bestlist"].iloc[z]) | |
| b2list = eval(df["best2list"].iloc[z]) | |
| te = eval(df["kif"].iloc[z]) | |
| #print(blist[0][0]) | |
| #print(b2list[0][0]) | |
| cnt = 0 | |
| for x in range(1,len(te)): | |
| try: | |
| if blist[x-1][0] in te[x] or b2list[x-1][0] in te[x]: | |
| cnt += 1 | |
| #print(te[x],blist[x][0],b2list[x][0]) | |
| except Exception as e: | |
| pass | |
| if cnt == 0: | |
| print("accuracy = 0",z) | |
| print("z = ",z," accuracy = ",cnt/len(te)) | |
| cnt2 += cnt/len(te) | |
| num += 1 | |
| print("mean_acuuracy",cnt2/num) | |
| def nomalize_sfen(s): | |
| flag = 0 | |
| movelist = [] | |
| for x in range(len(s)): | |
| if x < 2: | |
| continue | |
| if len(s[x]) < 30 and flag == 0: | |
| #半角の指し手を全角に変換する | |
| temp = s[x].split() | |
| num = temp[1][0] + temp[1][1] | |
| for y in range(len(KIFU_FROM_SQUARE_NAMES)): | |
| if num == KIFU_FROM_SQUARE_NAMES[y]: | |
| sq = KIFU_TO_SQUARE_NAMES[y] | |
| word = sq+temp[1][2:] | |
| word = word.replace("竜","龍").replace("成銀","全").replace("成桂","圭").replace("成香","杏") | |
| if s[x].split()[1] not in ["投了" , "千日手" , "持将棋" , "反則勝ち"]: | |
| movelist.append(word) | |
| else: | |
| movelist.append(s[x].split()[1]) | |
| flag = 1 | |
| return movelist | |
| def make_triplets(df, column): | |
| # 重複を除いたユニークな文章リストを作成 | |
| triplets = [] | |
| for x in range(len(df)): | |
| anchor = df.iloc[x] | |
| # Anchorと同じではない文章をPositiveとして選択 | |
| num = df.loc[(df[column] == anchor[column]) & (df["kif"] != anchor["kif"])].sample(n=1).index | |
| # print(df.loc[num]) | |
| positive = df.loc[num]["kif"].values[0] | |
| # Anchorと異なる文章をNegativeとして選択 | |
| num2 = df.loc[(df[column] != anchor[column]) & (df["kif"] != anchor["kif"])].sample(n=1).index | |
| # print(df.loc[num2]) | |
| negative = df.loc[num2]["kif"].values[0] | |
| triplets.append((anchor["kif"], positive, negative,df.loc[num][column].values[0],df.loc[num2][column].values[0])) | |
| def add_symbol(df,column): | |
| teban ="▲" | |
| kif = "" | |
| for x in range(len(df)): | |
| for y in df[column].iloc[x]: | |
| if y in ["０","１","２","３","４","５","６","７","８","９","同",0,1,2,3,4,5,6,7,8,9]: | |
| kif += teban + y | |
| if teban =="▲": | |
| teban = "△" | |
| else: | |
| teban = "▲" | |
| else: | |
| kif += y | |
| df[column].iloc[x] = kif | |
| kif = "" | |
| return df | |