字符计数

import os
import json
from collections import Counter# 按字符计数
label_dir="/Users/thy/Downloads/chinese20240613"
zi_ls=[]
with open(os.path.join(label_dir,"Label.txt")) as f:lines=f.readlines()for line in lines:line = line.strip("\r\n")# print("line:",line)line1=line.split("\t")# print("line1:", line1[1])json_str = json.loads(line1[1])# 提取所有转录文本transcriptions = [item["transcription"] for item in json_str]print(transcriptions)transcriptions1=[]for trans in transcriptions:if len(trans)==1:transcriptions1.append(trans)else:trans=[char for char in trans]for tran in trans:transcriptions1.append(tran)# print(transcriptions1)for zi in transcriptions1:zi_ls.append(zi)# print("出现的字符串：",set(zi_ls))
char_counts = Counter(zi_ls)# 打印结果
for char, count in char_counts.items():print(f"字符 '{char}' 出现了 {count} 次")# 如果需要将结果存储到字典，可以直接使用char_counts
# 输出字典内容
print(char_counts)

字符出现的次数

import os
import json
from collections import Counter# 按字符计数
label_dir="/Users/thy/Downloads/chinese20240613"
zi_ls=[]
with open(os.path.join(label_dir,"Label.txt")) as f:lines=f.readlines()for line in lines:line = line.strip("\r\n")# print("line:",line)line1=line.split("\t")# print("line1:", line1[1])json_str = json.loads(line1[1])# 提取所有转录文本transcriptions = [item["transcription"] for item in json_str]# print(transcriptions)transcriptions1=[]for trans in transcriptions:transcriptions1.append(trans)print(transcriptions1)for zi in transcriptions1:zi_ls.append(zi)print("出现的字符串：",set(zi_ls))
char_counts = Counter(zi_ls)# 打印结果
for char, count in char_counts.items():print(f"字符 '{char}' 出现了 {count} 次")# 如果需要将结果存储到字典，可以直接使用char_counts
# 输出字典内容
print(char_counts)