I'm simply trying to upload excel.xlsx file with Python panda package so i can tokenize the text. I tried for hours but nothing works. Any help will be great:
import pandas as pd
excel_file = open(r'''C:\Users\farid-PC\Desktop\Tester.xlsx''', errors
='ignore')
movies = pd.read_excel(excel_file)
movies.head()
Errors:
Traceback (most recent call last):
File "C:/Users/farid-PC/PycharmProjects/fake_news/fault.py", line 4, in <module>
movies = pd.read_excel(excel_file)
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\pandas\util\_decorators.py", line 178, in wrapper
return func(*args, **kwargs)
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\pandas\util\_decorators.py", line 178, in wrapper
return func(*args, **kwargs)
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\pandas\io\excel.py", line 307, in read_excel
io = ExcelFile(io, engine=engine)
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\pandas\io\excel.py", line 392, in __init__
self.book = xlrd.open_workbook(file_contents=data)
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\xlrd\__init__.py", line 162, in open_workbook
ragged_rows=ragged_rows,
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\xlrd\book.py", line 91, in open_workbook_xls
biff_version = bk.getbof(XL_WORKBOOK_GLOBALS)
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\xlrd\book.py", line 1267, in getbof
opcode = self.get2bytes()
File "C:\Users\farid-PC\PycharmProjects\fake_news\venv\lib\site-packages\xlrd\book.py", line 672, in get2bytes
return (BYTES_ORD(hi) << 8) | BYTES_ORD(lo)
TypeError: unsupported operand type(s) for <<: 'str' and 'int'
Related
when i use (self.links is an array of strings)
Parallel(n_jobs=2)(delayed(self.buybysize)(link) for link in self.links)
with this function
def buybysize(self, link):
browser = self.browser()
//other commented stuff
def browser(self):
options = uc.ChromeOptions()
options.user_data_dir = self.user_data_dir
options.add_argument(self.add_argument)
driver = uc.Chrome(options=options)
return driver
i get the error
oblib.externals.loky.process_executor._RemoteTraceback:
Traceback (most recent call last):
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/externals/loky/process_executor.py", line 436, in _process_worker
r = call_item()
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/externals/loky/process_executor.py", line 288, in __call__
return self.fn(*self.args, **self.kwargs)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/_parallel_backends.py", line 595, in __call__
return self.func(*args, **kwargs)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/parallel.py", line 262, in __call__
return [func(*args, **kwargs)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/parallel.py", line 262, in <listcomp>
return [func(*args, **kwargs)
File "/home/Me/PycharmProjects/zalando_buy/Zalando.py", line 91, in buybysize
browser = self.browser()
File "/home/Me/PycharmProjects/zalando_buy/Zalando.py", line 38, in browser
driver = uc.Chrome(options=options)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/undetected_chromedriver/__init__.py", line 388, in __init__
self.browser_pid = start_detached(
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/undetected_chromedriver/dprocess.py", line 30, in start_detached
multiprocessing.Process(
File "/usr/lib/python3.8/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/usr/lib/python3.8/multiprocessing/context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/externals/loky/backend/process.py", line 39, in _Popen
return Popen(process_obj)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/externals/loky/backend/popen_loky_posix.py", line 52, in __init__
self._launch(process_obj)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/externals/loky/backend/popen_loky_posix.py", line 157, in _launch
pid = fork_exec(cmd_python, self._fds, env=process_obj.env)
AttributeError: 'Process' object has no attribute 'env'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/Me/PycharmProjects/zalando_buy/Start.py", line 4, in <module>
class Start:
File "/home/Me/PycharmProjects/zalando_buy/Start.py", line 7, in Start
zalando.startshopping()
File "/home/Me/PycharmProjects/zalando_buy/Zalando.py", line 42, in startshopping
self.openlinks()
File "/home/Me/PycharmProjects/zalando_buy/Zalando.py", line 50, in openlinks
Parallel(n_jobs=2)(delayed(self.buybysize)(link) for link in self.links)
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/parallel.py", line 1056, in __call__
self.retrieve()
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/parallel.py", line 935, in retrieve
self._output.extend(job.get(timeout=self.timeout))
File "/home/Me/PycharmProjects/zalando_buy/venv/lib/python3.8/site-packages/joblib/_parallel_backends.py", line 542, in wrap_future_result
return future.result(timeout=timeout)
File "/usr/lib/python3.8/concurrent/futures/_base.py", line 444, in result
return self.__get_result()
File "/usr/lib/python3.8/concurrent/futures/_base.py", line 389, in __get_result
raise self._exception
AttributeError: 'Process' object has no attribute 'env'
Process finished with exit code 1
For me it looks like there are instabilities because undetected chromedriver maybe uses multiprocessing already, but isnt there any way where i can open multiple Browsers with UC and process each iteration parallel?
Edit: i debugged and the error appears after trying to execute this line:
driver = uc.Chrome(options=options)
I have a model defined in Django 3.1 like
class MyModel(models.Model):
def get_path(path):
def wrapper(instance, filename):
# code to make the path
return 'path/created/for/filename.jpg'
return wrapper
image = models.ImageField(upload_to=get_path('files/'))
but when I do
python3 manage.py makemigrations
I am getting a ValueError:
Migrations for 'myproject':
myproject/migrations/0023_auto_20210128_1148.py
- Create model MyModel
Traceback (most recent call last):
File "manage.py", line 22, in <module>
main()
File "manage.py", line 18, in main
execute_from_command_line(sys.argv)
File "/Library/Python/3.7/site-packages/django/core/management/__init__.py", line 401, in execute_from_command_line
utility.execute()
File "/Library/Python/3.7/site-packages/django/core/management/__init__.py", line 395, in execute
self.fetch_command(subcommand).run_from_argv(self.argv)
File "/Library/Python/3.7/site-packages/django/core/management/base.py", line 330, in run_from_argv
self.execute(*args, **cmd_options)
File "/Library/Python/3.7/site-packages/django/core/management/base.py", line 371, in execute
output = self.handle(*args, **options)
File "/Library/Python/3.7/site-packages/django/core/management/base.py", line 85, in wrapped
res = handle_func(*args, **kwargs)
File "/Library/Python/3.7/site-packages/django/core/management/commands/makemigrations.py", line 182, in handle
self.write_migration_files(changes)
File "/Library/Python/3.7/site-packages/django/core/management/commands/makemigrations.py", line 219, in write_migration_files
migration_string = writer.as_string()
File "/Library/Python/3.7/site-packages/django/db/migrations/writer.py", line 141, in as_string
operation_string, operation_imports = OperationWriter(operation).serialize()
File "/Library/Python/3.7/site-packages/django/db/migrations/writer.py", line 99, in serialize
_write(arg_name, arg_value)
File "/Library/Python/3.7/site-packages/django/db/migrations/writer.py", line 51, in _write
arg_string, arg_imports = MigrationWriter.serialize(item)
File "/Library/Python/3.7/site-packages/django/db/migrations/writer.py", line 271, in serialize
return serializer_factory(value).serialize()
File "/Library/Python/3.7/site-packages/django/db/migrations/serializer.py", line 37, in serialize
item_string, item_imports = serializer_factory(item).serialize()
File "/Library/Python/3.7/site-packages/django/db/migrations/serializer.py", line 199, in serialize
return self.serialize_deconstructed(path, args, kwargs)
File "/Library/Python/3.7/site-packages/django/db/migrations/serializer.py", line 86, in serialize_deconstructed
arg_string, arg_imports = serializer_factory(arg).serialize()
File "/Library/Python/3.7/site-packages/django/db/migrations/serializer.py", line 159, in serialize
'Could not find function %s in %s.\n' % (self.value.__name__, module_name)
ValueError: Could not find function wrapper in myproject.models.
Normally python can have a function return a function, so what is the error here? If I create the model with a dummy path, do makemigrations, and then add the function it works fine in my code. It just seems to be erroring in makemigrations.
I have a file global_vars.py that contains file paths saved as variables:
from pandas import Timestamp
final_vol_path = 'datasets/final_vols.csv'
final_price_path = 'datasets/final_prices.csv'
final_start_date = Timestamp('2017-01-01')
with other variables written in a similar fashion. However, the functions that I'm using to read in the data throw a FileNotFoundError when attempting to do the following in file1.py:
import scripts.global_vars as gv
read_data(gv.final_vol_path, gv.final_price_path) # throws FileNotFoundError
read_data('datasets/final_vols.csv', 'datasets/final_prices.csv') # this passes
Additionally, I've checked the file paths, and have gotten the following:
gv.final_vol_path == 'datasets/final_vols.csv' # returns True
gv.final_price_path == 'datasets/final_prices.csv' # returns True
Moreover, the pandas Timestamp object is processed without any problems.
Is there any explanation for why the FileNotFoundError is being thrown when attempting to access the file path as a variable from global_vars.py, but is not thrown when the actual string is passed in?
EDIT: The overall directory structure is as follows:
working_dir
L file1.py
L scripts
L global_vars.py
L datasets
L final_vols.csv
L final_prices.csv
EDIT 2: I added in a try-catch block to ensure the rest of the function doesn't break, not sure if that has affected the traceback, but here's what I get:
Traceback (most recent call last):
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\runpy.py", line
184, in _run_module_as_main
"__main__", mod_spec)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\Ananth\Anaconda3\envs\analytics-cpu\Scripts\nose2.exe\__main__.py", line 9, in <module>
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\main.py", line 306, in discover
return main(*args, **kwargs)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\main.py", line 100, in __init__
super(PluggableTestProgram, self).__init__(**kw)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\unittest\main.py", line 93, in __init__
self.parseArgs(argv)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\main.py", line 133, in parseArgs
self.createTests()
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\main.py", line 258, in createTests
self.testNames, self.module)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\loader.py", line 69, in loadTestsFromNames
for name in event.names]
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\loader.py", line 69, in <listcomp>
for name in event.names]
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\loader.py", line 84, in loadTestsFromName
result = self.session.hooks.loadTestsFromName(event)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\events.py", line 224, in __call__
result = getattr(plugin, self.method)(event)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\plugins\loader\testcases.py", line 56, in loadTestsFromName
result = util.test_from_name(name, module)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\util.py", line 106, in test_from_name
parent, obj = object_from_name(name, module)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\nose2\util.py", line 117, in object_from_name
module = __import__('.'.join(parts_copy))
File "C:\Users\Ananth\Desktop\Modules\PortfolioVARModule\tests\test_simulation.py", line 24, in <module>
gv.test_start_date)
File "C:\Users\Ananth\Desktop\Modules\PortfolioVARModule\scripts\prep_data.py", line 119, in read_data
priceDF = pd.read_csv(pricepath).dropna()
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\pandas\io\parsers.py", line 646, in parser_f
return _read(filepath_or_buffer, kwds)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\pandas\io\parsers.py", line 389, in _read
parser = TextFileReader(filepath_or_buffer, **kwds)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\pandas\io\parsers.py", line 730, in __init__
self._make_engine(self.engine)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\pandas\io\parsers.py", line 923, in _make_engine
self._engine = CParserWrapper(self.f, **self.options)
File "c:\users\ananth\anaconda3\envs\analytics-cpu\lib\site-packages\pandas\io\parsers.py", line 1390, in __init__
self._reader = _parser.TextReader(src, **kwds)
File "pandas\parser.pyx", line 373, in pandas.parser.TextReader.__cinit__ (pandas\parser.c:4184)
File "pandas\parser.pyx", line 667, in pandas.parser.TextReader._setup_parser_source (pandas\parser.c:8449)
FileNotFoundError: File b'datasets/corn_price.csv' does not exist
Problem is the addition of the letter b in front of your file's path.
You get the b because you encoded to utf-8.
Try:
read_data(str(gv.final_vol_path,'utf-8'), str(gv.final_price_path, 'utf-8'))
I am trying to parallelize the tasks of correcting texts on many documents with Python, so I naturally found "joblib". I want each task to be to correct a given document. Here is the structure of the code:
if __name__ == '__main__':
lexicon = build_compact_lexicon()
from joblib import Parallel, delayed
import multiprocessing
num_cores = multiprocessing.cpu_count()
results = Parallel(n_jobs=num_cores)(delayed(find_errors)('GDL', i, 1, lexicon) for i in range(1798, 1820))
I am using the function find_errors summed up here :
def find_errors(newspaper, year, month, lexicon):
# parse the input newspaper text data using etree parser from LXML
# detect errors in the text
return found_errors_type1, found_errors_type2, found_errors_type3
This does raise me a few errors
multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/parallel.py", line 130, in __call__
return self.func(*args, **kwargs)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/parallel.py", line 72, in __call__
return [func(*args, **kwargs) for func, args, kwargs in self.items]
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/parallel.py", line 72, in <listcomp>
return [func(*args, **kwargs) for func, args, kwargs in self.items]
File "hellowordParallel.py", line 85, in find_errors
tree = etree.parse(xml_file_path)
File "src/lxml/lxml.etree.pyx", line 3427, in lxml.etree.parse (src/lxml/lxml.etree.c:79801)
File "src/lxml/parser.pxi", line 1805, in lxml.etree._parseDocument (src/lxml/lxml.etree.c:116293)
TypeError: cannot parse from 'NoneType'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/tokenize.py", line 392, in find_cookie
line_string = line.decode('utf-8')
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xb0 in position 24: invalid start byte
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/multiprocessing/pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/parallel.py", line 139, in __call__
tb_offset=1)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/format_stack.py", line 373, in format_exc
frames = format_records(records)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/format_stack.py", line 274, in format_records
for token in generate_tokens(linereader):
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/tokenize.py", line 514, in _tokenize
line = readline()
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/format_stack.py", line 265, in linereader
line = getline(file, lnum[0])
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/linecache.py", line 16, in getline
lines = getlines(filename, module_globals)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/linecache.py", line 47, in getlines
return updatecache(filename, module_globals)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/linecache.py", line 136, in updatecache
with tokenize.open(fullname) as fp:
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/tokenize.py", line 456, in open
encoding, lines = detect_encoding(buffer.readline)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/tokenize.py", line 433, in detect_encoding
encoding = find_cookie(first)
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/tokenize.py", line 397, in find_cookie
raise SyntaxError(msg)
File "<string>", line None
SyntaxError: invalid or missing encoding declaration for '/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/lxml/etree.so'
"""
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "hellowordParallel.py", line 160, in <module>
results = Parallel(n_jobs=num_cores)(delayed(find_errors)('GDL', i, 1, lexicon) for i in range(1798, 1820))
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/parallel.py", line 810, in __call__
self.retrieve()
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/joblib/parallel.py", line 727, in retrieve
self._output.extend(job.get())
File "/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/multiprocessing/pool.py", line 608, in get
raise self._value
SyntaxError: invalid or missing encoding declaration for '/home/mbl/anaconda3/envs/OCR_Correction/lib/python3.5/site-packages/lxml/etree.so'
I don't understand if this is due do something related with configs or if my function doesn't fit in a parallel implementation... (I guess it should...)
Did it happen to some of you before?
Hope my question is clear and there is enough information for someone to give me some help!
from jira.client import JIRA
jira_options={'server': 'https://abcjira.atlassian.net/login?dest- url=%2Fsecure%2FMyJiraHome.jspa'}
jira=JIRA(options=jira_options,basic_auth=('user','password'))
I want to do basic authentication in jira with python. Wrote above code but it gives me traceback. Could anyone please tell me what is the problem here.
Traceback (most recent call last):
File "lab.py", line 5, in <module>
jira=JIRA(options=jira_options,basic_auth=('user','password'))
File "C:\Python34\lib\site-packages\jira\client.py", line 261, in __init__
si = self.server_info()
File "C:\Python34\lib\site-packages\jira\client.py", line 1619, in server_info
return self._get_json('serverInfo')
File "C:\Python34\lib\site-packages\jira\client.py", line 2040, in _get_json
raise e
File "C:\Python34\lib\site-packages\jira\client.py", line 2037, in _get_json
r_json = json_loads(r)
File "C:\Python34\lib\site-packages\jira\utils.py", line 81, in json_loads
return json.loads(r.text)
File "C:\Python34\lib\json\__init__.py", line 318, in loads
return _default_decoder.decode(s)
File "C:\Python34\lib\json\decoder.py", line 343, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Python34\lib\json\decoder.py", line 361, in raw_decode
raise ValueError(errmsg("Expecting value", s, err.value)) from None
ValueError: Expecting value: line 4 column 1 (char 3)