我正在运行this article中的代码,并进行了一些更改以监视仅在指定目录中为.csv
的一种格式的文件创建/添加。
现在的问题是:
只要添加的新文件不是.csv格式,我的程序就会中断(停止监视,但继续运行);为了弥补这一点,这是我对ignore_patterns
参数所做的操作(但是在添加其他格式的新文件后,程序仍然停止监视):PatternmatchingEventHandler(patterns="*.csv",ignore_patterns=["*~"],ignore_directories=True,case_sensitive=True)
完整的代码是:
import time
import csv
from datetime import datetime
from watchdog.observers import Observer
from watchdog.events import PatternmatchingEventHandler
from os import path
from pandas import read_csv
# class that takes care of everything
class file_validator(PatternmatchingEventHandler):
def __init__(self,source_path):
# setting parameters for 'PatternmatchingEventHandler'
super(file_validator,self).__init__(patterns="*.csv",case_sensitive=True)
self.source_path = source_path
self.print_info = None
def on_created(self,event):
# this is the new file that was created
new_file = event.src_path
# details of each new .csv file
# demographic details
file_name = path.basename(new_file)
file_size = f"{path.getsize(new_file) / 1000} KiB"
file_creation = f"{datetime.fromtimestamp(path.getmtime(new_file)).strftime('%Y-%m-%d %H:%M:%S')}"
new_data = read_csv(new_file)
# more details
number_columns = new_data.shape[1]
data_types_data = [
('float' if i == 'float64' else ('int' if i == 'int64' else ('character' if i == 'object' else i))) for i in
[x.name for x in list(new_data.dtypes)]]
null_count_data = list(dict(new_data.isna().sum()).values())
print(f"{file_name},{file_size},{file_creation},{number_columns}")
# trying to access this info,but of no help
self.print_info = f"{file_name},{number_columns}"
def return_logs(self):
return self.print_info
# main function
if __name__ == "__main__":
some_path = "C:\\Users\\neevaN_Reddy\\Documents\\learning dash\\"
my_validator = file_validator(source_path=some_path)
my_observer = Observer()
my_observer.schedule(my_validator,some_path,recursive=True)
my_observer.start()
try:
while True:
time.sleep(1)
except KeyboardInterrupt:
my_observer.stop()
my_observer.join()
# # this doesn't print anything
print(my_validator.return_logs)
编辑1(在Quentin Pradet发表评论后): 在评论中提出您的建议后,我的论点已更改为:
super(file_validator,# ignore_patterns=["*~"],case_sensitive=True)
并且当我复制其他格式的文件(我尝试使用.ipynb
文件)时,我看到了此错误(此后程序也停止监视.csv
文件):
Exception in thread Thread-1:
Traceback (most recent call last):
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\threading.py",line 926,in _bootstrap_inner
self.run()
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\watchdog\observers\api.py",line 199,in run
self.dispatch_events(self.event_queue,self.timeout)
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\watchdog\observers\api.py",line 368,in dispatch_events
handler.dispatch(event)
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\watchdog\events.py",line 454,in dispatch
_method_map[event_type](event)
File "C:/Users/neevaN_Reddy/Documents/Work/Project-Aretaeus/diabetes_risk project/file validation using a class.py",line 26,in on_created
new_data = read_csv(new_file)
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\pandas\io\parsers.py",line 685,in parser_f
return _read(filepath_or_buffer,kwds)
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\pandas\io\parsers.py",line 463,in _read
data = parser.read(nrows)
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\pandas\io\parsers.py",line 1154,in read
ret = self._engine.read(nrows)
File "C:\Users\neevaN_Reddy\AppData\Local\Programs\Python\Python37\lib\site-packages\pandas\io\parsers.py",line 2059,in read
data = self._reader.read(nrows)
File "pandas/_libs/parsers.pyx",line 881,in pandas._libs.parsers.textreader.read
File "pandas/_libs/parsers.pyx",line 896,in pandas._libs.parsers.textreader._read_low_memory
File "pandas/_libs/parsers.pyx",line 950,in pandas._libs.parsers.textreader._read_rows
File "pandas/_libs/parsers.pyx",line 937,in pandas._libs.parsers.textreader._tokenize_rows
File "pandas/_libs/parsers.pyx",line 2132,in pandas._libs.parsers.raise_parser_error
pandas.errors.ParserError: Error tokenizing data. C error: Expected 1 fields in line 4,saw 2
显然,pandas
出现了一些错误,这意味着我的on_created
函数也针对非.csv
的文件格式被触发,我认为这意味着必须执行一些操作ignore_patterns
中的参数中没有添加其他格式的文件时触发on_created
函数。