The file transactions.xlsx is not updated and this is precisely due to add_chart(). If I comment out add_chart all these errors does not arise but I want to draw chart and this is the only method I know. transanctions2.xlsx file is created but it is corrupted whereas bunch of errors do come up.
from openpyxl.chart import BarChart, Reference
wb1 = xl.load_workbook('transactions.xlsx')
sheet = wb1['Sheet1']
cell = sheet.cell(1, 1)
for row in range(2, sheet.max_row + 1):
cell = sheet.cell(row, 3)
corrected_price = cell.value * 0.9
corrected_price_cell = sheet.cell(row, 4)
corrected_price_cell.value = corrected_price
values = Reference(sheet,
min_row=2,
max_row=sheet.max_row,
min_col=4,
max_col=4)
chart = BarChart()
chart.add_data(values)
sheet.add_chart(chart, 'f2')
wb1.save('transactions2.xlsx')
Traceback (most recent call last):
File "C:/Users/Saman/PycharmProjects/Excel/excel_edit.py", line 23, in <module>
wb1.save('transactions2.xlsx')
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\workbook\workbook.py", line 397, in save
save_workbook(self, filename)
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\writer\excel.py", line 294, in save_workbook
writer.save()
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\writer\excel.py", line 276, in save
self.write_data()
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\writer\excel.py", line 76, in write_data
self._write_worksheets()
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\writer\excel.py", line 219, in _write_worksheets
self._write_drawing(ws._drawing)
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\writer\excel.py", line 142, in _write_drawing
self._archive.writestr(drawing.path[1:], tostring(drawing._write()))
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\drawing\spreadsheet_drawing.py", line 283, in _write
anchor = _check_anchor(obj)
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\drawing\spreadsheet_drawing.py", line 224, in _check_anchor
row, col = coordinate_to_tuple(anchor)
File "C:\Users\Saman\PycharmProjects\Excel\venv\lib\site-packages\openpyxl\utils\cell.py", line 201, in coordinate_to_tuple
return int(row), _COL_STRING_CACHE[col]
KeyError: 'f'
The case matters when naming columns - specifically, they are uppercase:
sheet.add_chart(chart, 'F2')
I changed f to F.
Just to add up
Check out their docs
You should use uppercase
sheet.add_chart(chart, 'F2')
Related
I have a .xlsx sheet with a huge filename like this: child_id_survey_918_choose_touching_results_1541687696.xlsx when I try to use the load_workbook() to load this file it gives me a weird error.
My python file and the excel sheet both lie in the same folder.
CODE:
from openpyxl import load_workbook
workbook = load_workbook('child_id_survey_918_choose_touching_results_1541687696.xlsx')
Error:
Traceback (most recent call last):
File "test.py", line 2, in <module>
workbook = load_workbook('child_id_survey_918_choose_touching_results_1541687696.xlsx')
File "C:\Python38\lib\site-packages\openpyxl\reader\excel.py", line 315, in load_workbook
reader.read()
File "C:\Python38\lib\site-packages\openpyxl\reader\excel.py", line 280, in read
self.read_worksheets()
File "C:\Python38\lib\site-packages\openpyxl\reader\excel.py", line 228, in read_worksheets
ws_parser.bind_all()
File "C:\Python38\lib\site-packages\openpyxl\worksheet\_reader.py", line 434, in bind_all
self.bind_cells()
File "C:\Python38\lib\site-packages\openpyxl\worksheet\_reader.py", line 337, in bind_cells
for idx, row in self.parser.parse():
File "C:\Python38\lib\site-packages\openpyxl\worksheet\_reader.py", line 153, in parse
row = self.parse_row(element)
File "C:\Python38\lib\site-packages\openpyxl\worksheet\_reader.py", line 274, in parse_row
cells = [self.parse_cell(el) for el in row]
File "C:\Python38\lib\site-packages\openpyxl\worksheet\_reader.py", line 274, in <listcomp>
cells = [self.parse_cell(el) for el in row]
File "C:\Python38\lib\site-packages\openpyxl\worksheet\_reader.py", line 181, in parse_cell
style_id = int(style_id)
ValueError: invalid literal for int() with base 10: 'string'
I have also tried using this: workbook = load_workbook(filename = 'child_id_survey_918_choose_touching_results_1541687696.xlsx')
Why am I getting this error and how can I solve it?
The code gives an error saying KeyError in the end. But I believe the code is correct as written by the tutor.
import openpyxl as xl
from openpyxl.chart import BarChart, Reference
def process_workbook(filename):
wb = xl.load_workbook(filename)
sheet = wb['Sheet1']
for row in range(2,sheet.max_row + 1):
cell = sheet.cell(row, 3)
corrected_price = cell.value * 0.9
corrected_price_cell = sheet.cell(row,4)
corrected_price_cell.value = corrected_price
values = Reference(sheet,
min_row = 2 ,
max_row = sheet.max_row,
min_col = 4,
max_col = 4)
chart = BarChart() #instance of BarChart class
chart.add_data(values)
sheet.add_chart(chart, 'e2')
wb.save(filename)
filename = 'transactions.xlsx'
work = process_workbook(filename)
C:\Users\bhargav\PycharmProjects\SelfLearning\venv\Scripts\python.exe
C:/Users/bhargav/PycharmProjects/SelfLearning/app.py
Traceback (most recent call last): File
"C:/Users/bhargav/PycharmProjects/SelfLearning/app.py", line 26, in
work = process_workbook(filename)
File "C:/Users/bhargav/PycharmProjects/SelfLearning/app.py", line 5,
in process_workbook
wb = xl.load_workbook(filename)
File
"C:\Users\bhargav\PycharmProjects\SelfLearning\venv\lib\site-packages\openpyxl\reader\excel.py",
line 312, in load_workbook
reader.read()
File
"C:\Users\bhargav\PycharmProjects\SelfLearning\venv\lib\site-packages\openpyxl\reader\excel.py",
line 268, in read
self.read_manifest()
File
"C:\Users\bhargav\PycharmProjects\SelfLearning\venv\lib\site-packages\openpyxl\reader\excel.py",
line 136, in read_manifest
src = self.archive.read(ARC_CONTENT_TYPES)
File
"C:\Users\bhargav\AppData\Local\Programs\Python\Python37-32\lib\zipfile.py",
line 1428, in read
with self.open(name, "r", pwd) as fp:
File
"C:\Users\bhargav\AppData\Local\Programs\Python\Python37-32\lib\zipfile.py",
line 1467, in open
zinfo = self.getinfo(name)
File
"C:\Users\bhargav\AppData\Local\Programs\Python\Python37-32\lib\zipfile.py",
line 1395, in getinfo
'There is no item named %r in the archive' % name) KeyError: "There is no item named '[Content_Types].xml' in the archive"
Process finished with exit code 1
Check if the file 'transactions.xlsx' is in the same folder.
I am trying to open an xlsx file that is created by another system (and this is the format in which the data always comes, and is not in my control). I tried both openpyxl (v2.3.2) and xlrd (v1.0.0) (as well as pandas (v0.20.1) read_excel and pd.ExcelFile(), both of which are using xlrd, and so may be moot), and I am running into errors; plus not finding answers from my searches. Any help is appreciated.
xlrd code:
import xlrd
workbook = xlrd.open_workbook(r'C:/Temp/Data.xlsx')
Error:
Traceback (most recent call last):
File "<ipython-input-3-9e5d87f720d0>", line 2, in <module>
workbook = xlrd.open_workbook(r'C:/Temp/Data.xlsx')
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\__init__.py", line 422, in open_workbook
ragged_rows=ragged_rows,
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\xlsx.py", line 833, in open_workbook_2007_xml
x12sheet.process_stream(zflo, heading)
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\xlsx.py", line 548, in own_process_stream
self_do_row(elem)
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\xlsx.py", line 685, in do_row
self.sheet.put_cell(rowx, colx, None, float(tvalue), xf_index)
ValueError: could not convert string to float:
openpyxl code:
import openpyxl
wb = openpyxl.load_workbook(r'C:/Temp/Data.xlsx')
Error:
Traceback (most recent call last):
File "<ipython-input-2-6083ad2bc875>", line 1, in <module>
wb = openpyxl.load_workbook(r'C:/Temp/Data.xlsx')
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\reader\excel.py", line 234, in load_workbook
parser.parse()
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\reader\worksheet.py", line 106, in parse
dispatcher[tag_name](element)
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\reader\worksheet.py", line 243, in parse_row_dimensions
self.parse_cell(cell)
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\reader\worksheet.py", line 188, in parse_cell
value = _cast_number(value)
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\cell\read_only.py", line 23, in _cast_number
return long(value)
ValueError: invalid literal for int() with base 10: ' '
pandas code:
import pandas as pd
df = pd.read_excel(r'C:/Temp/Data.xlsx', sheetname='Sheet1')
Error:
Traceback (most recent call last):
File "<ipython-input-5-b86ec98a4e9e>", line 2, in <module>
df = pd.read_excel(r'C:/Temp/Data.xlsx', sheetname='Sheet1')
File "C:\Program Files\Anaconda3\lib\site-packages\pandas\io\excel.py", line 200, in read_excel
io = ExcelFile(io, engine=engine)
File "C:\Program Files\Anaconda3\lib\site-packages\pandas\io\excel.py", line 257, in __init__
self.book = xlrd.open_workbook(io)
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\__init__.py", line 422, in open_workbook
ragged_rows=ragged_rows,
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\xlsx.py", line 833, in open_workbook_2007_xml
x12sheet.process_stream(zflo, heading)
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\xlsx.py", line 548, in own_process_stream
self_do_row(elem)
File "C:\Program Files\Anaconda3\lib\site-packages\xlrd\xlsx.py", line 685, in do_row
self.sheet.put_cell(rowx, colx, None, float(tvalue), xf_index)
ValueError: could not convert string to float:
For what its worth, here is an example snippet of the input file:
I am guessing that the errors are coming from the first row having blanks beyond the first column - because the errors vanish when I delete the first two rows and . I cannot skip the first two rows, because I want to extract the value in cell A1. I would also like to force the values read to be string type, and will later convert to float with error checking. thanks!
===========
Update(Aug 9 10AM EDT): Using Charlie's suggestion, was able to open excel file in read only mode; and was able to read most of the contents - but still running into an error somewhere.
new code (sorry it is not very pythonic - still a newbie):
wb = openpyxl.load_workbook(r'C:/Temp/Data.xlsx', read_only=True)
ws = wb['Sheet1']
ws.max_row = ws.max_column = None
i=1
for row in ws.rows:
for cell in row:
if i<2000:
i += 1
try:
print(i, cell.value)
except:
print("error")
Error:
Traceback (most recent call last):
File "<ipython-input-65-2e8f3cf2294a>", line 2, in <module>
for row in ws.rows:
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\worksheet\read_only.py", line 125, in get_squared_range
yield tuple(self._get_row(element, min_col, max_col))
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\worksheet\read_only.py", line 165, in _get_row
value, data_type, style_id)
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\cell\read_only.py", line 36, in __init__
self.value = value
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\cell\read_only.py", line 132, in value
value = _cast_number(value)
File "C:\Program Files\Anaconda3\lib\site-packages\openpyxl\cell\read_only.py", line 23, in _cast_number
return long(value)
ValueError: invalid literal for int() with base 10: ' '
=========
Update2 (10:35AM): when i read the file without ws.max_row and ws.max_column set as None, the code was reading just one column, without errors. The value in cell A66 is "Generated from:". But when i read the file with ws.max_row and ws.max_column set as None, this particular cell is causing trouble. But I can read all other cells before that, and that will work fine for me, right now. thanks, #Charlie.
Sounds like the source file is probably corrupt and contains cells that with empty strings that are typed as numbers. You might be able to use openpyxl's read-only mode to skip the first tow rows.
If your program works after you delete the first two rows then lets skip them. try use skiprows to ignore the first 2 rows that are blanks or are headers. you can use the parse method from panda.
xls = pd.read_excel('C:/Temp/Data.xlsx')
df = xls.parse('Sheet1', skiprows=2) #assuming your data is on sheet1.
I am trying to append the values from one sheet row by row to a new workbook. My code works when I run it on a small test file, but when I run it on my target file it returns an error when saving.
Here is my code:
from openpyxl import load_workbook
from openpyxl import Workbook
wb = load_workbook(filename='RM Activity-Pricing Report - 2014-05-31.xlsm',keep_vba=False, data_only=True)
ws_Ottawa = wb.get_sheet_by_name('Ottawa')
wb2 = Workbook()
ws2 = wb2.create_sheet()
for row in ws_Ottawa.iter_rows():
ws2.append(row)
wb2.save('new_big_file.xlsx')
The output error I get in Spyder (python 3.5) is:
Traceback (most recent call last):
File "<ipython-input-22-171ffbcd4891>", line 1, in <module>
runfile('Z:/Revenue Management Report/ExtractPromoData.py', wdir='Z:/Revenue Management Report')
File "C:\Anaconda3-64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 699, in runfile
execfile(filename, namespace)
File "C:\Anaconda3-64\lib\site-packages\spyderlib\widgets\externalshell\sitecustomize.py", line 88, in execfile
exec(compile(open(filename, 'rb').read(), filename, 'exec'), namespace)
File "Z:/Revenue Management Report/ExtractPromoData.py", line 35, in <module>
wb2.save('new_big_file4.xlsx')
File "C:\Anaconda3-64\lib\site-packages\openpyxl\workbook\workbook.py", line 298, in save
save_workbook(self, filename)
File "C:\Anaconda3-64\lib\site-packages\openpyxl\writer\excel.py", line 198, in save_workbook
writer.save(filename, as_template=as_template)
File "C:\Anaconda3-64\lib\site-packages\openpyxl\writer\excel.py", line 181, in save
self.write_data(archive, as_template=as_template)
File "C:\Anaconda3-64\lib\site-packages\openpyxl\writer\excel.py", line 87, in write_data
self._write_worksheets(archive)
File "C:\Anaconda3-64\lib\site-packages\openpyxl\writer\excel.py", line 114, in _write_worksheets
write_worksheet(sheet, self.workbook.shared_strings,
File "C:\Anaconda3-64\lib\site-packages\openpyxl\writer\worksheet.py", line 233, in write_worksheet
write_rows(xf, worksheet)
File "C:\Anaconda3-64\lib\site-packages\openpyxl\writer\lxml_worksheet.py", line 59, in write_rows
if cell.value is None and not cell.has_style:
File "C:\Anaconda3-64\lib\site-packages\openpyxl\cell\cell.py", line 306, in value
if value is not None and self.is_date:
File "C:\Anaconda3-64\lib\site-packages\openpyxl\cell\cell.py", line 351, in is_date
if self.data_type == "n" and self.number_format != "General":
File "C:\Anaconda3-64\lib\site-packages\openpyxl\styles\styleable.py", line 49, in __get__
return coll[idx - 164]
IndexError: list index out of range
I do not get an error when I use my code on a smaller test .xlsx file.
Possible reasons for the problem that I suspect are:
1)input file is .xlsm
2)input file is has columns from A to CI
3)input file is password protected (but since the error is in saving this does not seem like it should be an issue)
Taking into account what Charlie said, this is my work-around
from openpyxl import load_workbook
from openpyxl import Workbook
wb = load_workbook(filename='RM Activity-Pricing Report - 2014-5-31.xlsm',keep_vba=False, data_only=True)#,guess_types=True)
ws_Ottawa = wb.get_sheet_by_name('Ottawa')
wb2 = Workbook()
ws2 = wb2.create_sheet()
counter = 0
new_rows = []
for rrow in ws_Ottawa.iter_rows():
new_rows.append([])
for cell in rrow:
new_rows[counter].append(cell.value)
counter +=1
for wrow in new_rows:
ws2.append(wrow)
wb2.save('new_big_file4.xlsx')
print("ALL DONE")
You quite simply cannot do what you are trying to do. Unfortunately, the way data is stored within the file formats means that much relevant information is not stored with the cell but using reference to the workbook object. These obviously differ from workbook to workbook which is why you see errors when saving: the number format you want to use doesn't exist in the new file.
I am trying to automate a report using openpyxl and am in the early stages. I have just set up the first part whereby i copy and paste a range of cells from one workbook to another. However when i go to save the workbook i am pasting into it returns a key error. It also corrupts my template file and renders it un-openable.
I have found a chap who has had the same problem however his was not resolved. Someone has instructed him to use version 1.8.5 however i could only find upto 1.8.2.
ERROR: Failure: KeyError (-8937945243006069197)
----------------------------------------------------------------------
Traceback (most recent call last):
File "//anaconda/lib/python2.7/site-packages/nose/loader.py", line 413, in loadTestsFromName
addr.filename, addr.module)
File "//anaconda/lib/python2.7/site-packages/nose/importer.py", line 47, in importFromPath
return self.importFromDir(dir_path, fqname)
File "//anaconda/lib/python2.7/site-packages/nose/importer.py", line 94, in importFromDir
mod = load_module(part_fqname, fh, filename, desc)
File "/Users/joegavin/Dropbox/Python/projects/project pymur/tests/sandbox_tests.py", line 53, in <module>
wb0.save('template.xlsx')
File "//anaconda/lib/python2.7/site-packages/openpyxl/workbook.py", line 265, in save
save_workbook(self, filename)
File "//anaconda/lib/python2.7/site-packages/openpyxl/writer/excel.py", line 187, in save_workbook
writer.save(filename)
File "//anaconda/lib/python2.7/site-packages/openpyxl/writer/excel.py", line 170, in save
self.write_data(archive)
File "//anaconda/lib/python2.7/site-packages/openpyxl/writer/excel.py", line 98, in write_data
self._write_worksheets(archive, shared_string_table, self.style_writer)
File "//anaconda/lib/python2.7/site-packages/openpyxl/writer/excel.py", line 128, in _write_worksheets
style_writer.get_style_by_hash()))
File "//anaconda/lib/python2.7/site-packages/openpyxl/writer/worksheet.py", line 98, in write_worksheet
write_worksheet_cols(doc, worksheet, style_table)
File "//anaconda/lib/python2.7/site-packages/openpyxl/writer/worksheet.py", line 209, in write_worksheet_cols
col_def['style'] = str(style_table[hash(columndimension.style_index)])
KeyError: -8937945243006069197
Here is all my code so far.
from openpyxl import load_workbook
from openpyxl import workbook
########################### CLASSES ####################################
class Institution(object):
def __init__(self, name, usage_hours,percentage_share,
target_percentage, number_of_projects):
self.name = name
self.usage_hours = usage_hours
self.percentage_share = percentage_share
self.target_percentage = target_percentage
self.number_of_projects = number_of_projects
class Project(object):
def __init__(self, project_name, project_code, percentage_share,
percentage_share_machine):
self.project_name = project_name
self.percentage_share = percentage_share
self.percentage_share_machine = percentage_share_machine
############################ Setup ########################################
# Loading the workbook to read the figures off
wb0 = load_workbook('figures.xlsx')
wb1 = load_workbook('template.xlsx')
# Navigating to the worksheet where we harvest the data
ws0 = wb0.worksheets[0]
# Navigating to the worksheet we will copy data to
ws1 = wb1.worksheets[0]
project_codes0 = ws0["B1":"B100"]
project_codes1 = ws1['B1':'B100']
#cells1 = cells0
#for i in range(0, len(cells0[0])):
#for cell in cells0:
#print cell[i].value
wb0.save('template.xlsx')
As per OP's comment
The problem was resolved by updating to the newest version 2.02