ZaneYork
/
chinese-wordle-tool
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

添加词频调序输出

This commit is contained in:
zhiyang7 2022-02-08 17:55:30 +08:00
parent 5d7318e5f8
commit e818c25acf
3 changed files with 8549 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md Normal file
View File

@ -0,0 +1,7 @@
# 拼音猜成语工具
## 说明
模式0：输入拼音字数，提供候选
模式1：输入猜测历史，提供筛选结果
## 引用
[成语数据库来源](https://github.com/crazywhalecc/idiom-database)

8520
idiom_frequency.csv Normal file
View File

File diff suppressed because it is too large Load Diff

33
stat.py
View File

@ -2,6 +2,7 @@ import sys
import getopt import getopt
import pandas as pd import pandas as pd
import re import re
import math
def trim_space(s): def trim_space(s):
@ -15,10 +16,11 @@ def main(argv):
parameter = '3323' parameter = '3323'
mode = '1' mode = '1'
parameter = 'bai vvv vv vvv,012 000 00 000;bai tou er xin,012 010 10 001' parameter = 'bai vvv vv vvv,012 000 00 000;bai tou er xin,012 010 10 001'
num = 3
try: try:
opts, args = getopt.getopt(argv, "hm:p:", ["mode=", "parameter="]) opts, args = getopt.getopt(argv, "hm:p:n:", ["mode=", "parameter=", "num="])
except getopt.GetoptError: except getopt.GetoptError:
print('test.py -m <mode> -p <parameter>') print('test.py -m <mode> -p <parameter> -n <num>')
sys.exit(2) sys.exit(2)
for opt, arg in opts: for opt, arg in opts:
if opt == '-h': if opt == '-h':
@ -28,13 +30,17 @@ def main(argv):
mode = arg mode = arg
elif opt in ("-p", "--parameter"): elif opt in ("-p", "--parameter"):
parameter = arg parameter = arg
df = pd.read_json('idiom.json') elif opt in ("-n", "--num"):
num = int(arg)
all_idiom = pd.read_json('idiom.json')
idiom_frequency = pd.read_csv('idiom_frequency.csv')
all_idiom = all_idiom.merge(idiom_frequency, how='left', on='word')
all_idiom['frequency'] = all_idiom['frequency'].fillna(1).astype(int)
if mode == '0': if mode == '0':
df['pinyin_rt'] = df.apply(lambda x: ''.join(map(lambda y: str(len(y)), re.split('[ ,，]',x['pinyin_r']))), axis=1) all_idiom['pinyin_rt'] = all_idiom.apply(lambda x: ''.join(map(lambda y: str(len(y)), re.split('[ ,，]',x['pinyin_r']))), axis=1)
groups = df.groupby(by='pinyin_rt') groups = all_idiom.groupby(by='pinyin_rt')
group = groups.get_group(parameter).copy() group = groups.get_group(parameter).copy()
group['pinyin_c'] = group.apply(lambda x: len(set(trim_space(x['pinyin_r']))), axis=1) print_max_group(all_idiom, group, num)
print(df.loc[group['pinyin_c'].idxmax()])
elif mode == '1': elif mode == '1':
parameter_rst = parameter.split(';', 1) parameter_rst = parameter.split(';', 1)
if len(parameter_rst) > 1: if len(parameter_rst) > 1:
@ -47,8 +53,8 @@ def main(argv):
parameter = trim_space(parameter.split(',')[0]) parameter = trim_space(parameter.split(',')[0])
count = ''.join([str(len(x)) for x in hits.split()]) count = ''.join([str(len(x)) for x in hits.split()])
df['pinyin_rt'] = df.apply(lambda x: ''.join(map(lambda y: str(len(y)), re.split('[ ,，]',x['pinyin_r']))), axis=1) all_idiom['pinyin_rt'] = all_idiom.apply(lambda x: ''.join(map(lambda y: str(len(y)), re.split('[ ,，]',x['pinyin_r']))), axis=1)
groups = df.groupby(by='pinyin_rt') groups = all_idiom.groupby(by='pinyin_rt')
group = groups.get_group(count).copy() group = groups.get_group(count).copy()
while(True): while(True):
@ -67,8 +73,13 @@ def main(argv):
return return
else: else:
break break
group['pinyin_c'] = group.apply(lambda x: len(set(trim_space(x['pinyin_r']))), axis=1) print_max_group(all_idiom, group, num)
print(df.loc[group['pinyin_c'].idxmax()])
def print_max_group(all_idiom, group, num):
group['pinyin_c'] = group.apply(lambda x: (math.log(x['frequency'], 2)/16 + 1) * len(set(trim_space(x['pinyin_r']))), axis=1)
list = group.nlargest(num, ['pinyin_c', 'frequency']).index.tolist()
for i in list:
print(all_idiom.loc[i])
def filter_group_mode1(parameter, group, hits): def filter_group_mode1(parameter, group, hits):
for i in range(len(parameter)): for i in range(len(parameter)):