Related
I currently have this code. It works perfectly.
It loops through excel files in a folder,
removes the first 2 rows, then saves them as individual excel files,
and it also saves the files in the loop as an appended file.
Currently the appended file overwrites the existing file each time I run the code.
I need to append the new data to the bottom of the already existing excel sheet ('master_data.xlsx)
dfList = []
path = 'C:\\Test\\TestRawFile'
newpath = 'C:\\Path\\To\\New\\Folder'
for fn in os.listdir(path):
# Absolute file path
file = os.path.join(path, fn)
if os.path.isfile(file):
# Import the excel file and call it xlsx_file
xlsx_file = pd.ExcelFile(file)
# View the excel files sheet names
xlsx_file.sheet_names
# Load the xlsx files Data sheet as a dataframe
df = xlsx_file.parse('Sheet1',header= None)
df_NoHeader = df[2:]
data = df_NoHeader
# Save individual dataframe
data.to_excel(os.path.join(newpath, fn))
dfList.append(data)
appended_data = pd.concat(dfList)
appended_data.to_excel(os.path.join(newpath, 'master_data.xlsx'))
I thought this would be a simple task, but I guess not.
I think I need to bring in the master_data.xlsx file as a dataframe, then match the index up with the new appended data, and save it back out. Or maybe there is an easier way. Any Help is appreciated.
UPDATE [2022-01-08]: starting from version 1.4.0 Pandas supports appending to existing Excel sheet, preserving the old contents, "out of the box"!
Good job Pandas Team!
Excerpt from the ExcelWriter documentation:
if_sheet_exists : {'error', 'new', 'replace', 'overlay'}, default 'error'
How to behave when trying to write to a sheet that already
exists (append mode only).
...
* overlay: Write contents to the existing sheet without removing the old contents.
.. versionadded:: 1.3.0
.. versionchanged:: 1.4.0
Added ``overlay`` option
For Pandas versions < 1.4.0 please find below a helper function for appending a Pandas DataFrame to an existing Excel file.
If an Excel file doesn't exist then it will be created.
UPDATE [2021-09-12]: fixed for Pandas 1.3.0+
The following functions have been tested with:
Pandas 1.3.2
OpenPyxl 3.0.7
from pathlib import Path
from copy import copy
from typing import Union, Optional
import numpy as np
import pandas as pd
import openpyxl
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter
def copy_excel_cell_range(
src_ws: openpyxl.worksheet.worksheet.Worksheet,
min_row: int = None,
max_row: int = None,
min_col: int = None,
max_col: int = None,
tgt_ws: openpyxl.worksheet.worksheet.Worksheet = None,
tgt_min_row: int = 1,
tgt_min_col: int = 1,
with_style: bool = True
) -> openpyxl.worksheet.worksheet.Worksheet:
"""
copies all cells from the source worksheet [src_ws] starting from [min_row] row
and [min_col] column up to [max_row] row and [max_col] column
to target worksheet [tgt_ws] starting from [tgt_min_row] row
and [tgt_min_col] column.
#param src_ws: source worksheet
#param min_row: smallest row index in the source worksheet (1-based index)
#param max_row: largest row index in the source worksheet (1-based index)
#param min_col: smallest column index in the source worksheet (1-based index)
#param max_col: largest column index in the source worksheet (1-based index)
#param tgt_ws: target worksheet.
If None, then the copy will be done to the same (source) worksheet.
#param tgt_min_row: target row index (1-based index)
#param tgt_min_col: target column index (1-based index)
#param with_style: whether to copy cell style. Default: True
#return: target worksheet object
"""
if tgt_ws is None:
tgt_ws = src_ws
# https://stackoverflow.com/a/34838233/5741205
for row in src_ws.iter_rows(min_row=min_row, max_row=max_row,
min_col=min_col, max_col=max_col):
for cell in row:
tgt_cell = tgt_ws.cell(
row=cell.row + tgt_min_row - 1,
column=cell.col_idx + tgt_min_col - 1,
value=cell.value
)
if with_style and cell.has_style:
# tgt_cell._style = copy(cell._style)
tgt_cell.font = copy(cell.font)
tgt_cell.border = copy(cell.border)
tgt_cell.fill = copy(cell.fill)
tgt_cell.number_format = copy(cell.number_format)
tgt_cell.protection = copy(cell.protection)
tgt_cell.alignment = copy(cell.alignment)
return tgt_ws
def append_df_to_excel(
filename: Union[str, Path],
df: pd.DataFrame,
sheet_name: str = 'Sheet1',
startrow: Optional[int] = None,
max_col_width: int = 30,
autofilter: bool = False,
fmt_int: str = "#,##0",
fmt_float: str = "#,##0.00",
fmt_date: str = "yyyy-mm-dd",
fmt_datetime: str = "yyyy-mm-dd hh:mm",
truncate_sheet: bool = False,
storage_options: Optional[dict] = None,
**to_excel_kwargs
) -> None:
"""
Append a DataFrame [df] to existing Excel file [filename]
into [sheet_name] Sheet.
If [filename] doesn't exist, then this function will create it.
#param filename: File path or existing ExcelWriter
(Example: '/path/to/file.xlsx')
#param df: DataFrame to save to workbook
#param sheet_name: Name of sheet which will contain DataFrame.
(default: 'Sheet1')
#param startrow: upper left cell row to dump data frame.
Per default (startrow=None) calculate the last row
in the existing DF and write to the next row...
#param max_col_width: maximum column width in Excel. Default: 40
#param autofilter: boolean - whether add Excel autofilter or not. Default: False
#param fmt_int: Excel format for integer numbers
#param fmt_float: Excel format for float numbers
#param fmt_date: Excel format for dates
#param fmt_datetime: Excel format for datetime's
#param truncate_sheet: truncate (remove and recreate) [sheet_name]
before writing DataFrame to Excel file
#param storage_options: dict, optional
Extra options that make sense for a particular storage connection, e.g. host, port,
username, password, etc., if using a URL that will be parsed by fsspec, e.g.,
starting “s3://”, “gcs://”.
#param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
[can be a dictionary]
#return: None
Usage examples:
>>> append_df_to_excel('/tmp/test.xlsx', df, autofilter=True,
freeze_panes=(1,0))
>>> append_df_to_excel('/tmp/test.xlsx', df, header=None, index=False)
>>> append_df_to_excel('/tmp/test.xlsx', df, sheet_name='Sheet2',
index=False)
>>> append_df_to_excel('/tmp/test.xlsx', df, sheet_name='Sheet2',
index=False, startrow=25)
>>> append_df_to_excel('/tmp/test.xlsx', df, index=False,
fmt_datetime="dd.mm.yyyy hh:mm")
(c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
"""
def set_column_format(ws, column_letter, fmt):
for cell in ws[column_letter]:
cell.number_format = fmt
filename = Path(filename)
file_exists = filename.is_file()
# process parameters
# calculate first column number
# if the DF will be written using `index=True`, then `first_col = 2`, else `first_col = 1`
first_col = int(to_excel_kwargs.get("index", True)) + 1
# ignore [engine] parameter if it was passed
if 'engine' in to_excel_kwargs:
to_excel_kwargs.pop('engine')
# save content of existing sheets
if file_exists:
wb = load_workbook(filename)
sheet_names = wb.sheetnames
sheet_exists = sheet_name in sheet_names
sheets = {ws.title: ws for ws in wb.worksheets}
with pd.ExcelWriter(
filename.with_suffix(".xlsx"),
engine="openpyxl",
mode="a" if file_exists else "w",
if_sheet_exists="new" if file_exists else None,
date_format=fmt_date,
datetime_format=fmt_datetime,
storage_options=storage_options
) as writer:
if file_exists:
# try to open an existing workbook
writer.book = wb
# get the last row in the existing Excel sheet
# if it was not specified explicitly
if startrow is None and sheet_name in writer.book.sheetnames:
startrow = 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 = sheets
else:
# file doesn't exist, we are creating a new one
startrow = 0
# write out the DataFrame to an ExcelWriter
df.to_excel(writer, sheet_name=sheet_name, **to_excel_kwargs)
worksheet = writer.sheets[sheet_name]
if autofilter:
worksheet.auto_filter.ref = worksheet.dimensions
for xl_col_no, dtyp in enumerate(df.dtypes, first_col):
col_no = xl_col_no - first_col
width = max(df.iloc[:, col_no].astype(str).str.len().max(),
len(df.columns[col_no]) + 6)
width = min(max_col_width, width)
column_letter = get_column_letter(xl_col_no)
worksheet.column_dimensions[column_letter].width = width
if np.issubdtype(dtyp, np.integer):
set_column_format(worksheet, column_letter, fmt_int)
if np.issubdtype(dtyp, np.floating):
set_column_format(worksheet, column_letter, fmt_float)
if file_exists and sheet_exists:
# move (append) rows from new worksheet to the `sheet_name` worksheet
wb = load_workbook(filename)
# retrieve generated worksheet name
new_sheet_name = set(wb.sheetnames) - set(sheet_names)
if new_sheet_name:
new_sheet_name = list(new_sheet_name)[0]
# copy rows written by `df.to_excel(...)` to
copy_excel_cell_range(
src_ws=wb[new_sheet_name],
tgt_ws=wb[sheet_name],
tgt_min_row=startrow + 1,
with_style=True
)
# remove new (generated by Pandas) worksheet
del wb[new_sheet_name]
wb.save(filename)
wb.close()
Old version (tested with Pandas 1.2.3 and Openpyxl 3.0.5):
import os
from openpyxl import load_workbook
def append_df_to_excel(filename, df, sheet_name='Sheet1', startrow=None,
truncate_sheet=False,
**to_excel_kwargs):
"""
Append a DataFrame [df] to existing Excel file [filename]
into [sheet_name] Sheet.
If [filename] doesn't exist, then this function will create it.
#param filename: File path or existing ExcelWriter
(Example: '/path/to/file.xlsx')
#param df: DataFrame to save to workbook
#param sheet_name: Name of sheet which will contain DataFrame.
(default: 'Sheet1')
#param startrow: upper left cell row to dump data frame.
Per default (startrow=None) calculate the last row
in the existing DF and write to the next row...
#param truncate_sheet: truncate (remove and recreate) [sheet_name]
before writing DataFrame to Excel file
#param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
[can be a dictionary]
#return: None
Usage examples:
>>> append_df_to_excel('d:/temp/test.xlsx', df)
>>> append_df_to_excel('d:/temp/test.xlsx', df, header=None, index=False)
>>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
index=False)
>>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
index=False, startrow=25)
(c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
"""
# Excel file doesn't exist - saving and exiting
if not os.path.isfile(filename):
df.to_excel(
filename,
sheet_name=sheet_name,
startrow=startrow if startrow is not None else 0,
**to_excel_kwargs)
return
# ignore [engine] parameter if it was passed
if 'engine' in to_excel_kwargs:
to_excel_kwargs.pop('engine')
writer = pd.ExcelWriter(filename, engine='openpyxl', mode='a')
# try to open an existing workbook
writer.book = load_workbook(filename)
# get the last row in the existing Excel sheet
# if it was not specified explicitly
if startrow is None and sheet_name in writer.book.sheetnames:
startrow = 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}
if startrow is None:
startrow = 0
# write out the new sheet
df.to_excel(writer, sheet_name, startrow=startrow, **to_excel_kwargs)
# save the workbook
writer.save()
Usage examples:
filename = r'C:\OCC.xlsx'
append_df_to_excel(filename, df)
append_df_to_excel(filename, df, header=None, index=False)
append_df_to_excel(filename, df, sheet_name='Sheet2', index=False)
append_df_to_excel(filename, df, sheet_name='Sheet2', index=False, startrow=25)
c:/temp/test.xlsx:
PS you may also want to specify header=None if you don't want to duplicate column names...
UPDATE: you may also want to check this old solution
If you aren't strictly looking for an excel file, then get the output as csv file and just copy the csv to a new excel file.
Note: this only works when you have less than 1000 columns since csv has a limit on the number of columns you can write.
df.to_csv('filepath', mode='a', index = False, header=None)
mode='a' means append.
This is a roundabout way it but works neat!
Building on MaxU and others' code and comments but simplifying to only fix the bug with pandas ExcelWriter that causes to_excel to create a new sheet rather than append to an existing sheet in append mode.
As others have noted, to_excel uses the ExcelWriter.sheets property and this is not populated when by ExcelWriter.
Fix is a one liner, otherwise code is standard pandas approach as documented in to_excel.
# xl_path is destination xlsx spreadsheet
with pd.ExcelWriter(xl_path, 'openpyxl', mode='a') as writer:
# fix line
writer.sheets = dict((ws.title, ws) for ws in writer.book.worksheets)
df.to_excel(writer, sheet_name)
import pandas as pd
import openpyxl
workbook = openpyxl.load_workbook("test.xlsx")
writer = pd.ExcelWriter('test.xlsx', engine='openpyxl')
writer.book = workbook
writer.sheets = dict((ws.title, ws) for ws in workbook.worksheets)
data_df.to_excel(writer, 'Existing_sheetname')
writer.save()
writer.close()
If you use ExcelWriter on the sheet every time it is going to override the previous sheet and all that will be visible is the last data sheet you appended to the workbook.
Instead you can maintain a counter that is 1 initially for which you need to initialize the excel sheet and add initial data using the existing approach of
writer = pd.ExcelWriter(output_file, engine='openpyxl')
df = pd.read_excel(output_file, sheet_name='TestSheet1')
or you can use the following approach i used. to load the workbook next time you want to use it or else file not find exception if you try to load it in the first case.
USage:
from bs4 import BeautifulSoup
import requests
import pandas as pd
from openpyxl import load_workbook
urls = ["http://millenniumcricketleague.com/Home/ShowTeam.aspx?tid=22",
"http://millenniumcricketleague.com/Home/ShowTeam.aspx?tid=40"]
path = "F:\meta_1.xlsx"
writer = pd.ExcelWriter(path,engine='openpyxl')
counter = 1
for url in urls:
table_data = []
final = []
html_content = requests.get(url).text
soup = BeautifulSoup(html_content, "lxml")
x = soup.find_all('table')
for table in x[1:]:
for tr in table.find_all("tr"):
newrow = []
for td in tr.find_all("td"):
newrow.append(td.text.replace('\n', ' ').strip())
table_data.append(newrow)
df = pd.DataFrame(table_data)
sheetname = 'Sheet%s' % counter
if(counter!=1):
writer.book = load_workbook(path)
df.to_excel(writer, sheet_name=sheetname)
counter = counter + 1
writer.save()
NO need to close the excelwriter. its an automatic function. Will show you a warning if you define it explicitly
This worked for me
import os
import openpyxl
import pandas as pd
from openpyxl.utils.dataframe import dataframe_to_rows
file = r"myfile.xlsx"
df = pd.DataFrame({'A': 1, 'B': 2})
# create excel file
if os.path.isfile(file): # if file already exists append to existing file
workbook = openpyxl.load_workbook(file) # load workbook if already exists
sheet = workbook['my_sheet_name'] # declare the active sheet
# append the dataframe results to the current excel file
for row in dataframe_to_rows(df, header = False, index = False):
sheet.append(row)
workbook.save(file) # save workbook
workbook.close() # close workbook
else: # create the excel file if doesn't already exist
with pd.ExcelWriter(path = file, engine = 'openpyxl') as writer:
df.to_excel(writer, index = False, sheet_name = 'my_sheet_name')
This question has been out here a while. The answer is ok, but I believe this will solve most peoples question.
simply use glob to access the files in a specific directory, loop through them, create a dataframe of each file, append it to the last one, then export to a folder. I also included commented out code to run through this with csvs.
import os
import pandas as pd
import glob
# put in path to folder with files you want to append
# *.xlsx or *.csv will get all files of that type
path = "C:/Users/Name/Folder/*.xlsx"
#path = "C:/Users/Name/Folder/*.csv"
# initialize a empty df
appended_data = pd.DataFrame()
#loop through each file in the path
for file in glob.glob(path):
print(file)
# create a df of that file path
df = pd.read_excel(file, sheet_name = 0)
#df = pd.read_csv(file, sep=',')
# appened it
appended_data = appended_data.append(df)
appended_data
# export the appeneded data to a folder of your choice
exportPath = 'C:/My/EXPORT/PATH/appended_dataExport.csv'
appended_data.to_csv(os.path.join(exportPath),index=False)
Complementing to #david, if you dont care the index and you can use .csv, this function helps to append any df to an existing csv
def append_df(self, path_file, df):
with open(path_file, 'a+') as f:
df.to_csv(f, header=f.tell() == 0, encoding='utf-8', index=False)
Notes:
a+ create the file if it doesnot exist
f.tell() == 0 add header if the first row
from openpyxl import load_workbook
wb = load_workbook(filepath)
ws = wb["Sheet1"]
df = dataframe.values.tolist()
for i in range(len(df)):
ws.append(df[i])
wb.save(filepath)
Append DataFrame to existing excel file
Use ExcelWriter to append DataFrame to an existing excel file. This is a simple approach and uses the existing library features.
with pd.ExcelWriter('existing_excel_file.xlsx',mode='a') as writer:
df.to_excel(writer, sheet_name='existing_sheet_name')
For detailed examples refer to pandas read Excel File with Examples
I am trying to convert the DataFrame to excel without overwriting the existing sheet.
The solution is using pd.ExcelWriter with openpyxl engine which supports append mode.
Now, I have to increase the column size of the excel, I use pd.ExcelWriter with XlsxWriter engine but it overwrites the remaining sheets.
Openpyxl as an engine:
with pd.ExcelWriter("test.xlsx", engine="openpyxl", mode="a") as writer:
df.to_excel(writer, sheet_name="name", startrow=num, startcol=num)
XlsxWriter as an engine:
workbook = xlsxwriter.Workbook('test.xlsx')
worksheet = workbook.add_worksheet()
worksheet.set_column(0, 0, 20)
Can someone please suggest to me a solution where I can do both things:
Keep the existing sheets
Increase the column width
you can use your ExcelWriter to adjust the column width. Example below. Note that you can only add a new tab and the data with this, not update text within an existing tab. But, it will NOT delete any contents, like in case of xlsxwriter.
from openpyxl.utils.cell import get_column_letter
startRow = 12 #Change as per your req
startCol = 3 #Change as per your req
with pd.ExcelWriter("test.xlsx", engine="openpyxl", mode="a") as writer: #Your code
df.to_excel(writer, sheet_name="name", startrow=startRow, startcol=startCol) #Your code... mostly
worksheet = writer.sheets['name'] #Get worksheet name
for i, col in enumerate(df.columns): #For each column in df, set width to 60
worksheet.column_dimensions[get_column_letter(startCol+i+1)].width = 60
I am being asked to generate some Excel reports. I am currently using pandas quite heavily for my data, so naturally I would like to use the pandas.ExcelWriter method to generate these reports. However the fixed column widths are a problem.
The code I have so far is simple enough. Say I have a dataframe called df:
writer = pd.ExcelWriter(excel_file_path, engine='openpyxl')
df.to_excel(writer, sheet_name="Summary")
I was looking over the pandas docs, and I don't really see any options to set column widths. Is there a trick to make it such that the columns auto-adjust to the data? Or is there something I can do after the fact to the xlsx file to adjust the column widths?
(I am using the OpenPyXL library, and generating .xlsx files - if that makes any difference.)
Inspired by user6178746's answer, I have the following:
# Given a dict of dataframes, for example:
# dfs = {'gadgets': df_gadgets, 'widgets': df_widgets}
writer = pd.ExcelWriter(filename, engine='xlsxwriter')
for sheetname, df in dfs.items(): # loop through `dict` of dataframes
df.to_excel(writer, sheet_name=sheetname) # send df to writer
worksheet = writer.sheets[sheetname] # pull worksheet object
for idx, col in enumerate(df): # loop through all columns
series = df[col]
max_len = max((
series.astype(str).map(len).max(), # len of largest item
len(str(series.name)) # len of column name/header
)) + 1 # adding a little extra space
worksheet.set_column(idx, idx, max_len) # set column width
writer.save()
Dynamically adjust all the column lengths
writer = pd.ExcelWriter('/path/to/output/file.xlsx')
df.to_excel(writer, sheet_name='sheetName', index=False, na_rep='NaN')
for column in df:
column_length = max(df[column].astype(str).map(len).max(), len(column))
col_idx = df.columns.get_loc(column)
writer.sheets['sheetName'].set_column(col_idx, col_idx, column_length)
writer.save()
Manually adjust a column using Column Name
col_idx = df.columns.get_loc('columnName')
writer.sheets['sheetName'].set_column(col_idx, col_idx, 15)
Manually adjust a column using Column Index
writer.sheets['sheetName'].set_column(col_idx, col_idx, 15)
In case any of the above is failing with
AttributeError: 'Worksheet' object has no attribute 'set_column'
make sure to install xlsxwriter:
pip install xlsxwriter
For a more comprehensive explanation you can read the article How to Auto-Adjust the Width of Excel Columns with Pandas ExcelWriter on TDS.
I'm posting this because I just ran into the same issue and found that the official documentation for Xlsxwriter and pandas still have this functionality listed as unsupported. I hacked together a solution that solved the issue i was having. I basically just iterate through each column and use worksheet.set_column to set the column width == the max length of the contents of that column.
One important note, however. This solution does not fit the column headers, simply the column values. That should be an easy change though if you need to fit the headers instead. Hope this helps someone :)
import pandas as pd
import sqlalchemy as sa
import urllib
read_server = 'serverName'
read_database = 'databaseName'
read_params = urllib.quote_plus("DRIVER={SQL Server};SERVER="+read_server+";DATABASE="+read_database+";TRUSTED_CONNECTION=Yes")
read_engine = sa.create_engine("mssql+pyodbc:///?odbc_connect=%s" % read_params)
#Output some SQL Server data into a dataframe
my_sql_query = """ SELECT * FROM dbo.my_table """
my_dataframe = pd.read_sql_query(my_sql_query,con=read_engine)
#Set destination directory to save excel.
xlsFilepath = r'H:\my_project' + "\\" + 'my_file_name.xlsx'
writer = pd.ExcelWriter(xlsFilepath, engine='xlsxwriter')
#Write excel to file using pandas to_excel
my_dataframe.to_excel(writer, startrow = 1, sheet_name='Sheet1', index=False)
#Indicate workbook and worksheet for formatting
workbook = writer.book
worksheet = writer.sheets['Sheet1']
#Iterate through each column and set the width == the max length in that column. A padding length of 2 is also added.
for i, col in enumerate(my_dataframe.columns):
# find length of column i
column_len = my_dataframe[col].astype(str).str.len().max()
# Setting the length if the column header is larger
# than the max column value length
column_len = max(column_len, len(col)) + 2
# set the column length
worksheet.set_column(i, i, column_len)
writer.save()
There is a nice package that I started to use recently called StyleFrame.
it gets DataFrame and lets you to style it very easily...
by default the columns width is auto-adjusting.
for example:
from StyleFrame import StyleFrame
import pandas as pd
df = pd.DataFrame({'aaaaaaaaaaa': [1, 2, 3],
'bbbbbbbbb': [1, 1, 1],
'ccccccccccc': [2, 3, 4]})
excel_writer = StyleFrame.ExcelWriter('example.xlsx')
sf = StyleFrame(df)
sf.to_excel(excel_writer=excel_writer, row_to_add_filters=0,
columns_and_rows_to_freeze='B2')
excel_writer.save()
you can also change the columns width:
sf.set_column_width(columns=['aaaaaaaaaaa', 'bbbbbbbbb'],
width=35.3)
UPDATE 1
In version 1.4 best_fit argument was added to StyleFrame.to_excel.
See the documentation.
UPDATE 2
Here's a sample of code that works for StyleFrame 3.x.x
from styleframe import StyleFrame
import pandas as pd
columns = ['aaaaaaaaaaa', 'bbbbbbbbb', 'ccccccccccc', ]
df = pd.DataFrame(data={
'aaaaaaaaaaa': [1, 2, 3, ],
'bbbbbbbbb': [1, 1, 1, ],
'ccccccccccc': [2, 3, 4, ],
}, columns=columns,
)
excel_writer = StyleFrame.ExcelWriter('example.xlsx')
sf = StyleFrame(df)
sf.to_excel(
excel_writer=excel_writer,
best_fit=columns,
columns_and_rows_to_freeze='B2',
row_to_add_filters=0,
)
excel_writer.save()
There is probably no automatic way to do it right now, but as you use openpyxl, the following line (adapted from another answer by user Bufke on how to do in manually) allows you to specify a sane value (in character widths):
writer.sheets['Summary'].column_dimensions['A'].width = 15
By using pandas and xlsxwriter you can do your task, below code will perfectly work in Python 3.x. For more details on working with XlsxWriter with pandas this link might be useful https://xlsxwriter.readthedocs.io/working_with_pandas.html
import pandas as pd
writer = pd.ExcelWriter(excel_file_path, engine='xlsxwriter')
df.to_excel(writer, sheet_name="Summary")
workbook = writer.book
worksheet = writer.sheets["Summary"]
#set the column width as per your requirement
worksheet.set_column('A:A', 25)
writer.save()
I found that it was more useful to adjust the column with based on the column header rather than column content.
Using df.columns.values.tolist() I generate a list of the column headers and use the lengths of these headers to determine the width of the columns.
See full code below:
import pandas as pd
import xlsxwriter
writer = pd.ExcelWriter(filename, engine='xlsxwriter')
df.to_excel(writer, index=False, sheet_name=sheetname)
workbook = writer.book # Access the workbook
worksheet= writer.sheets[sheetname] # Access the Worksheet
header_list = df.columns.values.tolist() # Generate list of headers
for i in range(0, len(header_list)):
worksheet.set_column(i, i, len(header_list[i])) # Set column widths based on len(header)
writer.save() # Save the excel file
At work, I am always writing the dataframes to excel files. So instead of writing the same code over and over, I have created a modulus. Now I just import it and use it to write and formate the excel files. There is one downside though, it takes a long time if the dataframe is extra large.
So here is the code:
def result_to_excel(output_name, dataframes_list, sheet_names_list, output_dir):
out_path = os.path.join(output_dir, output_name)
writerReport = pd.ExcelWriter(out_path, engine='xlsxwriter',
datetime_format='yyyymmdd', date_format='yyyymmdd')
workbook = writerReport.book
# loop through the list of dataframes to save every dataframe into a new sheet in the excel file
for i, dataframe in enumerate(dataframes_list):
sheet_name = sheet_names_list[i] # choose the sheet name from sheet_names_list
dataframe.to_excel(writerReport, sheet_name=sheet_name, index=False, startrow=0)
# Add a header format.
format = workbook.add_format({
'bold': True,
'border': 1,
'fg_color': '#0000FF',
'font_color': 'white'})
# Write the column headers with the defined format.
worksheet = writerReport.sheets[sheet_name]
for col_num, col_name in enumerate(dataframe.columns.values):
worksheet.write(0, col_num, col_name, format)
worksheet.autofilter(0, 0, 0, len(dataframe.columns) - 1)
worksheet.freeze_panes(1, 0)
# loop through the columns in the dataframe to get the width of the column
for j, col in enumerate(dataframe.columns):
max_width = max([len(str(s)) for s in dataframe[col].values] + [len(col) + 2])
# define a max width to not get to wide column
if max_width > 50:
max_width = 50
worksheet.set_column(j, j, max_width)
writerReport.save()
return output_dir + output_name
Combining the other answers and comments and also supporting multi-indices:
def autosize_excel_columns(worksheet, df):
autosize_excel_columns_df(worksheet, df.index.to_frame())
autosize_excel_columns_df(worksheet, df, offset=df.index.nlevels)
def autosize_excel_columns_df(worksheet, df, offset=0):
for idx, col in enumerate(df):
series = df[col]
max_len = max((
series.astype(str).map(len).max(),
len(str(series.name))
)) + 1
worksheet.set_column(idx+offset, idx+offset, max_len)
sheetname=...
df.to_excel(writer, sheet_name=sheetname, freeze_panes=(df.columns.nlevels, df.index.nlevels))
worksheet = writer.sheets[sheetname]
autosize_excel_columns(worksheet, df)
writer.save()
you can solve the problem by calling the following function, where df is the dataframe you want to get the sizes and the sheetname is the sheet in excel where you want the modifications to take place
def auto_width_columns(df, sheetname):
workbook = writer.book
worksheet= writer.sheets[sheetname]
for i, col in enumerate(df.columns):
column_len = max(df[col].astype(str).str.len().max(), len(col) + 2)
worksheet.set_column(i, i, column_len)
import re
import openpyxl
..
for col in _ws.columns:
max_lenght = 0
print(col[0])
col_name = re.findall('\w\d', str(col[0]))
col_name = col_name[0]
col_name = re.findall('\w', str(col_name))[0]
print(col_name)
for cell in col:
try:
if len(str(cell.value)) > max_lenght:
max_lenght = len(cell.value)
except:
pass
adjusted_width = (max_lenght+2)
_ws.column_dimensions[col_name].width = adjusted_width
Yes, there is there is something you can do subsequently to the xlsx file to adjust the column widths.
Use xlwings to autofit columns. It's a pretty simple solution, see the 6 last lines of the example code. The advantage of this procedure is that you don't have to worry about font size, font type or anything else.
Requirement: Excel installation.
import pandas as pd
import xlwings as xw
path = r"test.xlsx"
# Export your dataframe in question.
df = pd._testing.makeDataFrame()
df.to_excel(path)
# Autofit all columns with xlwings.
with xw.App(visible=False) as app:
wb = xw.Book(path)
for ws in wb.sheets:
ws.autofit(axis="columns")
wb.save(path)
wb.close()
Easiest solution is to specify width of column in set_column method.
for worksheet in writer.sheets.values():
worksheet.set_column(0,last_column_value, required_width_constant)
This function works for me, also fixes the index width
def write_to_excel(writer, X, sheet_name, sep_only=False):
#writer=writer object
#X=dataframe
#sheet_name=name of sheet
#sep_only=True:write only as separate excel file, False: write as sheet to the writer object
if sheet_name=="":
print("specify sheet_name!")
else:
X.to_excel(f"{output_folder}{prefix_excel_save}_{sheet_name}.xlsx")
if not sep_only:
X.to_excel(writer, sheet_name=sheet_name)
#fix column widths
worksheet = writer.sheets[sheet_name] # pull worksheet object
for idx, col in enumerate(X.columns): # loop through all columns
series = X[col]
max_len = max((
series.astype(str).map(len).max(), # len of largest item
len(str(series.name)) # len of column name/header
)) + 1 # adding a little extra space
worksheet.set_column(idx+1, idx+1, max_len) # set column width (=1 because index = 1)
#fix index width
max_len=pd.Series(X.index.values).astype(str).map(len).max()+1
worksheet.set_column(0, 0, max_len)
if sep_only:
print(f'{sheet_name} is written as seperate file')
else:
print(f'{sheet_name} is written as seperate file')
print(f'{sheet_name} is written as sheet')
return writer
call example:
writer = write_to_excel(writer, dataframe, "Statistical_Analysis")
I may be a bit late to the party but this code works when using 'openpyxl' as your engine, sometimes pip install xlsxwriter wont solve the issue. This code below works like a charm. Edit any part as you wish.
def text_length(text):
"""
Get the effective text length in characters, taking into account newlines
"""
if not text:
return 0
lines = text.split("\n")
return max(len(line) for line in lines)
def _to_str_for_length(v, decimals=3):
"""
Like str() but rounds decimals to predefined length
"""
if isinstance(v, float):
# Round to [decimal] places
return str(Decimal(v).quantize(Decimal('1.' + '0' * decimals)).normalize())
else:
return str(v)
def auto_adjust_xlsx_column_width(df, writer, sheet_name, margin=3, length_factor=1.0, decimals=3, index=False):
sheet = writer.sheets[sheet_name]
_to_str = functools.partial(_to_str_for_length, decimals=decimals)
# Compute & set column width for each column
for column_name in df.columns:
# Convert the value of the columns to string and select the
column_length = max(df[column_name].apply(_to_str).map(text_length).max(), text_length(column_name)) + 5
# Get index of column in XLSX
# Column index is +1 if we also export the index column
col_idx = df.columns.get_loc(column_name)
if index:
col_idx += 1
# Set width of column to (column_length + margin)
sheet.column_dimensions[openpyxl.utils.cell.get_column_letter(col_idx + 1)].width = column_length * length_factor + margin
# Compute column width of index column (if enabled)
if index: # If the index column is being exported
index_length = max(df.index.map(_to_str).map(text_length).max(), text_length(df.index.name))
sheet.column_dimensions["A"].width = index_length * length_factor + margin
An openpyxl version based on #alichaudry's code.
The code 1) loads an excel file, 2) adjusts column widths and 3) saves it.
def auto_adjust_column_widths(excel_file : "Excel File Path", extra_space = 1) -> None:
"""
Adjusts column widths of the excel file and replaces it with the adjusted one.
Adjusting columns is based on the lengths of columns values (including column names).
Parameters
----------
excel_file :
excel_file to adjust column widths.
extra_space :
extra column width in addition to the value-based-widths
"""
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter
wb = load_workbook(excel_file)
for ws in wb:
df = pd.DataFrame(ws.values,)
for i,r in (df.astype(str).applymap(len).max(axis=0) + extra_space).iteritems():
ws.column_dimensions[get_column_letter(i+1)].width = r
wb.save(excel_file)
I'm using Python to generate an excel document from a Pandas DataFrame.
I can set column width and text wrap with workbook.add_format({"text_wrap": True}) and worksheet.set_column(f"{cols[idx]}:{cols[idx]}", 30, format), but I don't know how to activate "Hyphenation active". I fail to find it in the doc : https://xlsxwriter.readthedocs.io/format.html
Here is a sample of my code :
df = get_pandas_dataframe()
writer = pd.ExcelWriter(path, engine="xlsxwriter")
sheet_name = "abc"
df.to_excel(writer, index=False, sheet_name=sheet_name)
workbook = writer.book
worksheet = writer.sheets[sheet_name]
max_row, max_col = pdf.shape
format = workbook.add_format({"text_wrap": True})
cols = dict(zip(range(26), list(string.ascii_uppercase)))
for idx, col in enumerate(df):
worksheet.set_column(f"{cols[idx]}:{cols[idx]}", 30, format)
writer.save()
Any idea?
"Hyphenation Active" isn't an Excel option and hence it isn't supported by XlsxWriter.
You can verify that yourself in Libreoffice by saving an xlsx file with that option in a cell, closing the file, and then re-opening it. The option will no longer be there.
I currently have this code. It works perfectly.
It loops through excel files in a folder,
removes the first 2 rows, then saves them as individual excel files,
and it also saves the files in the loop as an appended file.
Currently the appended file overwrites the existing file each time I run the code.
I need to append the new data to the bottom of the already existing excel sheet ('master_data.xlsx)
dfList = []
path = 'C:\\Test\\TestRawFile'
newpath = 'C:\\Path\\To\\New\\Folder'
for fn in os.listdir(path):
# Absolute file path
file = os.path.join(path, fn)
if os.path.isfile(file):
# Import the excel file and call it xlsx_file
xlsx_file = pd.ExcelFile(file)
# View the excel files sheet names
xlsx_file.sheet_names
# Load the xlsx files Data sheet as a dataframe
df = xlsx_file.parse('Sheet1',header= None)
df_NoHeader = df[2:]
data = df_NoHeader
# Save individual dataframe
data.to_excel(os.path.join(newpath, fn))
dfList.append(data)
appended_data = pd.concat(dfList)
appended_data.to_excel(os.path.join(newpath, 'master_data.xlsx'))
I thought this would be a simple task, but I guess not.
I think I need to bring in the master_data.xlsx file as a dataframe, then match the index up with the new appended data, and save it back out. Or maybe there is an easier way. Any Help is appreciated.
UPDATE [2022-01-08]: starting from version 1.4.0 Pandas supports appending to existing Excel sheet, preserving the old contents, "out of the box"!
Good job Pandas Team!
Excerpt from the ExcelWriter documentation:
if_sheet_exists : {'error', 'new', 'replace', 'overlay'}, default 'error'
How to behave when trying to write to a sheet that already
exists (append mode only).
...
* overlay: Write contents to the existing sheet without removing the old contents.
.. versionadded:: 1.3.0
.. versionchanged:: 1.4.0
Added ``overlay`` option
For Pandas versions < 1.4.0 please find below a helper function for appending a Pandas DataFrame to an existing Excel file.
If an Excel file doesn't exist then it will be created.
UPDATE [2021-09-12]: fixed for Pandas 1.3.0+
The following functions have been tested with:
Pandas 1.3.2
OpenPyxl 3.0.7
from pathlib import Path
from copy import copy
from typing import Union, Optional
import numpy as np
import pandas as pd
import openpyxl
from openpyxl import load_workbook
from openpyxl.utils import get_column_letter
def copy_excel_cell_range(
src_ws: openpyxl.worksheet.worksheet.Worksheet,
min_row: int = None,
max_row: int = None,
min_col: int = None,
max_col: int = None,
tgt_ws: openpyxl.worksheet.worksheet.Worksheet = None,
tgt_min_row: int = 1,
tgt_min_col: int = 1,
with_style: bool = True
) -> openpyxl.worksheet.worksheet.Worksheet:
"""
copies all cells from the source worksheet [src_ws] starting from [min_row] row
and [min_col] column up to [max_row] row and [max_col] column
to target worksheet [tgt_ws] starting from [tgt_min_row] row
and [tgt_min_col] column.
#param src_ws: source worksheet
#param min_row: smallest row index in the source worksheet (1-based index)
#param max_row: largest row index in the source worksheet (1-based index)
#param min_col: smallest column index in the source worksheet (1-based index)
#param max_col: largest column index in the source worksheet (1-based index)
#param tgt_ws: target worksheet.
If None, then the copy will be done to the same (source) worksheet.
#param tgt_min_row: target row index (1-based index)
#param tgt_min_col: target column index (1-based index)
#param with_style: whether to copy cell style. Default: True
#return: target worksheet object
"""
if tgt_ws is None:
tgt_ws = src_ws
# https://stackoverflow.com/a/34838233/5741205
for row in src_ws.iter_rows(min_row=min_row, max_row=max_row,
min_col=min_col, max_col=max_col):
for cell in row:
tgt_cell = tgt_ws.cell(
row=cell.row + tgt_min_row - 1,
column=cell.col_idx + tgt_min_col - 1,
value=cell.value
)
if with_style and cell.has_style:
# tgt_cell._style = copy(cell._style)
tgt_cell.font = copy(cell.font)
tgt_cell.border = copy(cell.border)
tgt_cell.fill = copy(cell.fill)
tgt_cell.number_format = copy(cell.number_format)
tgt_cell.protection = copy(cell.protection)
tgt_cell.alignment = copy(cell.alignment)
return tgt_ws
def append_df_to_excel(
filename: Union[str, Path],
df: pd.DataFrame,
sheet_name: str = 'Sheet1',
startrow: Optional[int] = None,
max_col_width: int = 30,
autofilter: bool = False,
fmt_int: str = "#,##0",
fmt_float: str = "#,##0.00",
fmt_date: str = "yyyy-mm-dd",
fmt_datetime: str = "yyyy-mm-dd hh:mm",
truncate_sheet: bool = False,
storage_options: Optional[dict] = None,
**to_excel_kwargs
) -> None:
"""
Append a DataFrame [df] to existing Excel file [filename]
into [sheet_name] Sheet.
If [filename] doesn't exist, then this function will create it.
#param filename: File path or existing ExcelWriter
(Example: '/path/to/file.xlsx')
#param df: DataFrame to save to workbook
#param sheet_name: Name of sheet which will contain DataFrame.
(default: 'Sheet1')
#param startrow: upper left cell row to dump data frame.
Per default (startrow=None) calculate the last row
in the existing DF and write to the next row...
#param max_col_width: maximum column width in Excel. Default: 40
#param autofilter: boolean - whether add Excel autofilter or not. Default: False
#param fmt_int: Excel format for integer numbers
#param fmt_float: Excel format for float numbers
#param fmt_date: Excel format for dates
#param fmt_datetime: Excel format for datetime's
#param truncate_sheet: truncate (remove and recreate) [sheet_name]
before writing DataFrame to Excel file
#param storage_options: dict, optional
Extra options that make sense for a particular storage connection, e.g. host, port,
username, password, etc., if using a URL that will be parsed by fsspec, e.g.,
starting “s3://”, “gcs://”.
#param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
[can be a dictionary]
#return: None
Usage examples:
>>> append_df_to_excel('/tmp/test.xlsx', df, autofilter=True,
freeze_panes=(1,0))
>>> append_df_to_excel('/tmp/test.xlsx', df, header=None, index=False)
>>> append_df_to_excel('/tmp/test.xlsx', df, sheet_name='Sheet2',
index=False)
>>> append_df_to_excel('/tmp/test.xlsx', df, sheet_name='Sheet2',
index=False, startrow=25)
>>> append_df_to_excel('/tmp/test.xlsx', df, index=False,
fmt_datetime="dd.mm.yyyy hh:mm")
(c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
"""
def set_column_format(ws, column_letter, fmt):
for cell in ws[column_letter]:
cell.number_format = fmt
filename = Path(filename)
file_exists = filename.is_file()
# process parameters
# calculate first column number
# if the DF will be written using `index=True`, then `first_col = 2`, else `first_col = 1`
first_col = int(to_excel_kwargs.get("index", True)) + 1
# ignore [engine] parameter if it was passed
if 'engine' in to_excel_kwargs:
to_excel_kwargs.pop('engine')
# save content of existing sheets
if file_exists:
wb = load_workbook(filename)
sheet_names = wb.sheetnames
sheet_exists = sheet_name in sheet_names
sheets = {ws.title: ws for ws in wb.worksheets}
with pd.ExcelWriter(
filename.with_suffix(".xlsx"),
engine="openpyxl",
mode="a" if file_exists else "w",
if_sheet_exists="new" if file_exists else None,
date_format=fmt_date,
datetime_format=fmt_datetime,
storage_options=storage_options
) as writer:
if file_exists:
# try to open an existing workbook
writer.book = wb
# get the last row in the existing Excel sheet
# if it was not specified explicitly
if startrow is None and sheet_name in writer.book.sheetnames:
startrow = 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 = sheets
else:
# file doesn't exist, we are creating a new one
startrow = 0
# write out the DataFrame to an ExcelWriter
df.to_excel(writer, sheet_name=sheet_name, **to_excel_kwargs)
worksheet = writer.sheets[sheet_name]
if autofilter:
worksheet.auto_filter.ref = worksheet.dimensions
for xl_col_no, dtyp in enumerate(df.dtypes, first_col):
col_no = xl_col_no - first_col
width = max(df.iloc[:, col_no].astype(str).str.len().max(),
len(df.columns[col_no]) + 6)
width = min(max_col_width, width)
column_letter = get_column_letter(xl_col_no)
worksheet.column_dimensions[column_letter].width = width
if np.issubdtype(dtyp, np.integer):
set_column_format(worksheet, column_letter, fmt_int)
if np.issubdtype(dtyp, np.floating):
set_column_format(worksheet, column_letter, fmt_float)
if file_exists and sheet_exists:
# move (append) rows from new worksheet to the `sheet_name` worksheet
wb = load_workbook(filename)
# retrieve generated worksheet name
new_sheet_name = set(wb.sheetnames) - set(sheet_names)
if new_sheet_name:
new_sheet_name = list(new_sheet_name)[0]
# copy rows written by `df.to_excel(...)` to
copy_excel_cell_range(
src_ws=wb[new_sheet_name],
tgt_ws=wb[sheet_name],
tgt_min_row=startrow + 1,
with_style=True
)
# remove new (generated by Pandas) worksheet
del wb[new_sheet_name]
wb.save(filename)
wb.close()
Old version (tested with Pandas 1.2.3 and Openpyxl 3.0.5):
import os
from openpyxl import load_workbook
def append_df_to_excel(filename, df, sheet_name='Sheet1', startrow=None,
truncate_sheet=False,
**to_excel_kwargs):
"""
Append a DataFrame [df] to existing Excel file [filename]
into [sheet_name] Sheet.
If [filename] doesn't exist, then this function will create it.
#param filename: File path or existing ExcelWriter
(Example: '/path/to/file.xlsx')
#param df: DataFrame to save to workbook
#param sheet_name: Name of sheet which will contain DataFrame.
(default: 'Sheet1')
#param startrow: upper left cell row to dump data frame.
Per default (startrow=None) calculate the last row
in the existing DF and write to the next row...
#param truncate_sheet: truncate (remove and recreate) [sheet_name]
before writing DataFrame to Excel file
#param to_excel_kwargs: arguments which will be passed to `DataFrame.to_excel()`
[can be a dictionary]
#return: None
Usage examples:
>>> append_df_to_excel('d:/temp/test.xlsx', df)
>>> append_df_to_excel('d:/temp/test.xlsx', df, header=None, index=False)
>>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
index=False)
>>> append_df_to_excel('d:/temp/test.xlsx', df, sheet_name='Sheet2',
index=False, startrow=25)
(c) [MaxU](https://stackoverflow.com/users/5741205/maxu?tab=profile)
"""
# Excel file doesn't exist - saving and exiting
if not os.path.isfile(filename):
df.to_excel(
filename,
sheet_name=sheet_name,
startrow=startrow if startrow is not None else 0,
**to_excel_kwargs)
return
# ignore [engine] parameter if it was passed
if 'engine' in to_excel_kwargs:
to_excel_kwargs.pop('engine')
writer = pd.ExcelWriter(filename, engine='openpyxl', mode='a')
# try to open an existing workbook
writer.book = load_workbook(filename)
# get the last row in the existing Excel sheet
# if it was not specified explicitly
if startrow is None and sheet_name in writer.book.sheetnames:
startrow = 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}
if startrow is None:
startrow = 0
# write out the new sheet
df.to_excel(writer, sheet_name, startrow=startrow, **to_excel_kwargs)
# save the workbook
writer.save()
Usage examples:
filename = r'C:\OCC.xlsx'
append_df_to_excel(filename, df)
append_df_to_excel(filename, df, header=None, index=False)
append_df_to_excel(filename, df, sheet_name='Sheet2', index=False)
append_df_to_excel(filename, df, sheet_name='Sheet2', index=False, startrow=25)
c:/temp/test.xlsx:
PS you may also want to specify header=None if you don't want to duplicate column names...
UPDATE: you may also want to check this old solution
If you aren't strictly looking for an excel file, then get the output as csv file and just copy the csv to a new excel file.
Note: this only works when you have less than 1000 columns since csv has a limit on the number of columns you can write.
df.to_csv('filepath', mode='a', index = False, header=None)
mode='a' means append.
This is a roundabout way it but works neat!
Building on MaxU and others' code and comments but simplifying to only fix the bug with pandas ExcelWriter that causes to_excel to create a new sheet rather than append to an existing sheet in append mode.
As others have noted, to_excel uses the ExcelWriter.sheets property and this is not populated when by ExcelWriter.
Fix is a one liner, otherwise code is standard pandas approach as documented in to_excel.
# xl_path is destination xlsx spreadsheet
with pd.ExcelWriter(xl_path, 'openpyxl', mode='a') as writer:
# fix line
writer.sheets = dict((ws.title, ws) for ws in writer.book.worksheets)
df.to_excel(writer, sheet_name)
This worked for me
import os
import openpyxl
import pandas as pd
from openpyxl.utils.dataframe import dataframe_to_rows
file = r"myfile.xlsx"
df = pd.DataFrame({'A': 1, 'B': 2})
# create excel file
if os.path.isfile(file): # if file already exists append to existing file
workbook = openpyxl.load_workbook(file) # load workbook if already exists
sheet = workbook['my_sheet_name'] # declare the active sheet
# append the dataframe results to the current excel file
for row in dataframe_to_rows(df, header = False, index = False):
sheet.append(row)
workbook.save(file) # save workbook
workbook.close() # close workbook
else: # create the excel file if doesn't already exist
with pd.ExcelWriter(path = file, engine = 'openpyxl') as writer:
df.to_excel(writer, index = False, sheet_name = 'my_sheet_name')
import pandas as pd
import openpyxl
workbook = openpyxl.load_workbook("test.xlsx")
writer = pd.ExcelWriter('test.xlsx', engine='openpyxl')
writer.book = workbook
writer.sheets = dict((ws.title, ws) for ws in workbook.worksheets)
data_df.to_excel(writer, 'Existing_sheetname')
writer.save()
writer.close()
If you use ExcelWriter on the sheet every time it is going to override the previous sheet and all that will be visible is the last data sheet you appended to the workbook.
Instead you can maintain a counter that is 1 initially for which you need to initialize the excel sheet and add initial data using the existing approach of
writer = pd.ExcelWriter(output_file, engine='openpyxl')
df = pd.read_excel(output_file, sheet_name='TestSheet1')
or you can use the following approach i used. to load the workbook next time you want to use it or else file not find exception if you try to load it in the first case.
USage:
from bs4 import BeautifulSoup
import requests
import pandas as pd
from openpyxl import load_workbook
urls = ["http://millenniumcricketleague.com/Home/ShowTeam.aspx?tid=22",
"http://millenniumcricketleague.com/Home/ShowTeam.aspx?tid=40"]
path = "F:\meta_1.xlsx"
writer = pd.ExcelWriter(path,engine='openpyxl')
counter = 1
for url in urls:
table_data = []
final = []
html_content = requests.get(url).text
soup = BeautifulSoup(html_content, "lxml")
x = soup.find_all('table')
for table in x[1:]:
for tr in table.find_all("tr"):
newrow = []
for td in tr.find_all("td"):
newrow.append(td.text.replace('\n', ' ').strip())
table_data.append(newrow)
df = pd.DataFrame(table_data)
sheetname = 'Sheet%s' % counter
if(counter!=1):
writer.book = load_workbook(path)
df.to_excel(writer, sheet_name=sheetname)
counter = counter + 1
writer.save()
NO need to close the excelwriter. its an automatic function. Will show you a warning if you define it explicitly
This question has been out here a while. The answer is ok, but I believe this will solve most peoples question.
simply use glob to access the files in a specific directory, loop through them, create a dataframe of each file, append it to the last one, then export to a folder. I also included commented out code to run through this with csvs.
import os
import pandas as pd
import glob
# put in path to folder with files you want to append
# *.xlsx or *.csv will get all files of that type
path = "C:/Users/Name/Folder/*.xlsx"
#path = "C:/Users/Name/Folder/*.csv"
# initialize a empty df
appended_data = pd.DataFrame()
#loop through each file in the path
for file in glob.glob(path):
print(file)
# create a df of that file path
df = pd.read_excel(file, sheet_name = 0)
#df = pd.read_csv(file, sep=',')
# appened it
appended_data = appended_data.append(df)
appended_data
# export the appeneded data to a folder of your choice
exportPath = 'C:/My/EXPORT/PATH/appended_dataExport.csv'
appended_data.to_csv(os.path.join(exportPath),index=False)
Complementing to #david, if you dont care the index and you can use .csv, this function helps to append any df to an existing csv
def append_df(self, path_file, df):
with open(path_file, 'a+') as f:
df.to_csv(f, header=f.tell() == 0, encoding='utf-8', index=False)
Notes:
a+ create the file if it doesnot exist
f.tell() == 0 add header if the first row
from openpyxl import load_workbook
wb = load_workbook(filepath)
ws = wb["Sheet1"]
df = dataframe.values.tolist()
for i in range(len(df)):
ws.append(df[i])
wb.save(filepath)
Append DataFrame to existing excel file
Use ExcelWriter to append DataFrame to an existing excel file. This is a simple approach and uses the existing library features.
with pd.ExcelWriter('existing_excel_file.xlsx',mode='a') as writer:
df.to_excel(writer, sheet_name='existing_sheet_name')
For detailed examples refer to pandas read Excel File with Examples