我知道那里有帖子提到我面临的相同问题,但是这里的情况有所不同。
有时,当我尝试读取CSV时,它会被顺利读取,但是有时候,当我尝试使用pandas中的read_csv()函数读取相同的文件时,它向我显示了以下错误提示:
现在以下屏幕截图显示了已成功读取同一文件:
我无法找出错误的解决方案。
读取数据框后,在CSV文件上执行“ 打印(df.dtypes)”后的Python代码: Append_function.py
import pandas as pd
import openpyxl as ox
def append_df_to_excel(filename, df, sheet_name='Sheet1', start_row=None,
truncate_sheet=False,
**to_excel_kwargs):
# ignore [engine] parameter if it was passed
if 'engine' in to_excel_kwargs:
to_excel_kwargs.pop('engine')
writer = pd.ExcelWriter(filename, engine='openpyxl')
# Python 2.x: define [FileNotFoundError] exception if it doesn't exist
# try:
# FileNotFoundError
# except NameError:
# FileNotFoundError = IOError
try:
# try to open an existing workbook
writer.book = ox.load_workbook(filename)
# get the last row in the existing Excel sheet
# if it was not specified explicitly
if start_row is None and sheet_name in writer.book.sheetnames:
start_row = writer.book[sheet_name].max_row
# truncate sheet
if truncate_sheet and sheet_name in writer.book.sheetnames:
# index of [sheet_name] sheet
idx = writer.book.sheetnames.index(sheet_name)
# remove [sheet_name]
writer.book.remove(writer.book.worksheets[idx])
# create an empty sheet [sheet_name] using old index
writer.book.create_sheet(sheet_name, idx)
# copy existing sheets
writer.sheets = {ws.title: ws for ws in writer.book.worksheets}
except FileNotFoundError:
# file does not exist yet, we will create it
print("File does not exist")
pass
if start_row is None:
start_row = 0
# write out the new sheet
df.to_excel(writer, sheet_name, startrow=start_row, **to_excel_kwargs, header=True, float_format="%.2f")
print(df.dtypes)
# save the workbook
writer.save()
Main_file.py
import os
import pandas as pd
from PyQt5 import QtCore, QtWidgets
from watchdog.events import PatternMatchingEventHandler
from watchdog.observers import Observer
import time
from Append_Function import append_df_to_excel
class Emitter(QtCore.QObject):
newDataFrameSignal = QtCore.pyqtSignal(pd.DataFrame)
class Watcher:
def __init__(self):
self.watch_dir = os.getcwd()
self.directory_to_watch = None
self.emitter = Emitter()
self.observer = Observer()
self.event_handler = Handler(
emitter=self.emitter,
patterns=["*.CSV"],
ignore_patterns=["*.tmp"],
ignore_directories=True
)
def set_filename(self, filename):
self.directory_to_watch = os.path.join(self.watch_dir, filename)
def run(self):
self.observer.schedule(self.event_handler, self.directory_to_watch, recursive=False)
self.observer.start()
def stop_watcher(self):
self.observer.stop()
class Handler(PatternMatchingEventHandler):
def __init__(self, *args, emitter=None, **kwargs):
super(Handler, self).__init__(*args, **kwargs)
self._emitter = emitter
self.file_name = time.strftime("%Y%m%d-%H%M%S")+".xlsx"
def on_any_event(self, event):
if event.is_directory:
return None
elif event.event_type == 'created':
# Take any action here when a file is first created.
print("Received created event - %s." % event.src_path)
if os.path.isfile(os.path.join(os.getcwd(), self.file_name)):
append_df_to_excel(os.path.join(os.getcwd(), self.file_name),
pd.read_csv(event.src_path, header=1, index_col=0))
df = pd.read_csv(event.src_path, header=1, engine='python',encoding="utf-8")
else:
append_df_to_excel(os.path.join(os.getcwd(), self.file_name),
pd.read_csv(event.src_path, header=0, index_col=0))
df = pd.read_csv(event.src_path, header=0, engine='python',encoding="utf-8")
self._emitter.newDataFrameSignal.emit(df.copy())
df.set_index(df.columns.values.tolist()[0], inplace=True)
elif event.event_type == 'modified':
print("Modified created event - %s." % event.src_path)
if os.path.isfile(os.path.join(os.getcwd(), self.file_name)):
append_df_to_excel(os.path.join(os.getcwd(), self.file_name),
pd.read_csv(event.src_path, header=1, index_col=0))
df = pd.read_csv(event.src_path, header=1, engine='python',encoding="utf-8")
else:
append_df_to_excel(os.path.join(os.getcwd(), self.file_name),
pd.read_csv(event.src_path, header=0, index_col=0),)
df = pd.read_csv(event.src_path, header=0, engine='python',encoding="utf-8")
self._emitter.newDataFrameSignal.emit(df.copy())
df.set_index(df.columns.values.tolist()[0], inplace=True)
class DataFrameTableWidget(QtWidgets.QTableWidget):
@QtCore.pyqtSlot(pd.DataFrame)
def append_dataframe(self, df):
df = df.copy()
if df.columns.size > self.columnCount():
self.setColumnCount(df.columns.size)
r = self.rowCount()
self.insertRow(r)
for c, column in enumerate(df):
it = QtWidgets.QTableWidgetItem(column)
self.setItem(r, c, it)
i = self.rowCount()
for r, row in df.iterrows():
self.insertRow(self.rowCount())
for c, (column, value) in enumerate(row.iteritems()):
it = QtWidgets.QTableWidgetItem(str(value))
self.setItem(i+r, c, it)
任何建议将不胜感激。预先感谢!
答案 0 :(得分:1)
尝试在循环时读取文件:
def on_created(event):
...
# WAITING FILE TRANSFERING
file = None
while file is None:
try:
file = open(event.src_path)
except OSError:
file = None
print("WAINTING FILE TRANSFERING....")
time.sleep(3)