encoding=utf-8 import nltk import json from nltk.corpus import stopwords import re eg_stop_words = set(stopwords.words('english')) sp_stop_words = set(stopwords.words('spanish')) all_stop_words = eg_stop_words.union(sp_stop_words) input_file_name = r'建模.txt' output_file_name = r'train.txt' out_file = open(output_file_name, encoding='utf-8', mode='w') 打开输出文件 with open(output_file_name, encoding='utf-8', mode='w') as output_file: # 打开输入文件,对每一行进行处理 with open(input_file_name, encoding='utf-8') as f: for idx, line in enumerate(f): print("正在处理第{}行数据".format(idx)) if idx == 0: # 第一行是列名, 不要 print(line) continue line = line.strip() sps = line.split("\t") # 将行按制表符分隔为列表 report_no = sps[0] target = sps[2] smses = sps[-1] smses = smses.strip(""") # 去掉短信两端的引号 smses = smses.replace("""", """) # 把两个双引号转换成单引号 root = json.loads(smses) # 解析 json 格式的短信 msg = "" for item in root: # 遍历短信中的每一条信息 body = item["body"] # 获取信息的正文 msg += body + "\n" # 把正文追加到总的信息传递过来的msg中 text = re.sub(r'[^\w\s]', '', msg) # 使用正则表达式去掉标点符号 text = re.sub(r'http\S+', '', text) # 去掉链接 text = re.sub(r'\d+', '', text)#去除数字 text = text.lower() words = text.split() filtered_words = [word for word in words if word not in all_stop_words] text = ' '.join(filtered_words) print(report_no + '\t' + target) msg = target + '\u0001' + text + '\n' out_file.write(msg) out_file.close()帮我改成用 pandas 处理
时间: 2024-01-03 19:03:18 浏览: 87
nltk-develop.zip
当使用 pandas 进行处理时,你可以使用 `pandas.read_csv()` 函数读取文件,并使用 DataFrame 进行数据处理。以下是使用 pandas 进行处理的示例代码:
```python
import pandas as pd
import nltk
from nltk.corpus import stopwords
import re
eg_stop_words = set(stopwords.words('english'))
sp_stop_words = set(stopwords.words('spanish'))
all_stop_words = eg_stop_words.union(sp_stop_words)
input_file_name = '建模.txt'
output_file_name = 'train.txt'
df = pd.read_csv(input_file_name, encoding='utf-8', sep='\t')
# 处理每一行数据
for idx, row in df.iterrows():
print("正在处理第{}行数据".format(idx))
if idx == 0:
# 第一行是列名,不需要处理
continue
smses = row['短信']
smses = smses.strip("'")
smses = smses.replace('""', "'")
root = json.loads(smses)
msg = ""
for item in root:
body = item["body"]
msg += body + "\n"
text = re.sub(r'[^\w\s]', '', msg)
text = re.sub(r'http\S+', '', text)
text = re.sub(r'\d+', '', text)
text = text.lower()
words = text.split()
filtered_words = [word for word in words if word not in all_stop_words]
text = ' '.join(filtered_words)
df.at[idx, '目标'] = row['目标'] + '\u0001' + text
df.to_csv(output_file_name, encoding='utf-8', sep='\t', index=False)
```
这段代码将会读取名为 '建模.txt' 的文件,并根据每一行的数据进行处理,最后将处理后的结果保存到 'train.txt' 文件中。注意在使用该代码前,你需要先安装 pandas 和 nltk 库。
阅读全文