How to read EXCEL file in Python Jupyter Notebook | Pandas

How to read EXCEL file in Python Jupyter Notebook | Pandas

About this video: In this video, you will learn How to read EXCEL file in Python Jupyter Notebook

Large Language Model (LLM) - LangChain

Large Language Model (LLM) - LlamaIndex

Machine Learning Model Deployment

Spark with Python (PySpark)

Data Preprocessing (scikit-learn)

Social Media Links

#datascience #machinelearning #python #ai #ml #deeplearning #opencv #imageprocessing #ai #tensorflow #neuralnetworks #deeplearning #pandas

[nicholasrice]

Thanks a lot man, I am new to pandas/jupyter notebooks and was having trouble opening an excel file for quite some time. This video was very useful!

[kavanakundapur]

Helpful video, thank you. Can we not store the excel in the folder of our Jupyter and access it from there in the notebook using pandas?

[sundram]

Thank you so much sir it's beneficial

[jermaineoh]

Thank you for helping! The video was easy to understand :-)

[mariashoukat]

thanks alot..found this video after wasting 3 hours

[shreyasonkar]

Hey, can you help?. I'm trying to copy the path and doing it exactly like you're but it is giving an error that "file is not found".

[venkatexplorermetturdam]

my error is
ileNotFoundError Traceback (most recent call last)
in <module>
----> 1

in wrapper(*args, **kwargs)
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)
312
313 return wrapper

in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, error_bad_lines, warn_bad_lines, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options)
584 kwds.update(kwds_defaults)
585
--> 586 return _read(filepath_or_buffer, kwds)
587
588

in _read(filepath_or_buffer, kwds)
480
481 # Create the parser.
--> 482 parser = TextFileReader(filepath_or_buffer, **kwds)
483
484 if chunksize or iterator:

in __init__(self, f, engine, **kwds)
809 = kwds["has_index_names"]
810
--> 811 self._engine =
812
813 def close(self):

in _make_engine(self, engine)
1038 )
1039 # error: Too many arguments for "ParserBase"
-> 1040 return mapping[engine](self.f, **self.options) # type: ignore[call-arg]
1041
1042 def _failover_to_python(self):

in __init__(self, src, **kwds)
49
50 # open handles
---> 51 self._open_handles(src, kwds)
52 assert self.handles is not None
53

in _open_handles(self, src, kwds)
220 Let the readers open IOHandles after they are done with their potential raises.
221 """
--> 222 self.handles = get_handle(
223 src,
224 "r",

in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
700 if ioargs.encoding and "b" not in ioargs.mode:
701 # Encoding
--> 702 handle = open(
703 handle,
704 ioargs.mode,

FileNotFoundError: [Errno 2] No such file or directory:
bro please help me bro

[ASHISHSHARMA-mtnj]

import pandas as pd

df.head()



Getting below error


AttributeError Traceback (most recent call last)
Input In [9], in <cell line: 2>()
1 import pandas as pd
----> 2
3 df.head()

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\util\_decorators.py:311, in deprecate_nonkeyword_arguments.<locals>.decorate.<locals>.wrapper(*args, **kwargs)
305 if len(args) > num_allow_args:
306 warnings.warn(
307 msg.format(arguments=arguments),
308 FutureWarning,
309 stacklevel=stacklevel,
310 )
--> 311 return func(*args, **kwargs)

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\excel\_base.py:457, in read_excel(io, sheet_name, header, names, index_col, usecols, squeeze, dtype, engine, converters, true_values, false_values, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, parse_dates, date_parser, thousands, decimal, comment, skipfooter, convert_float, mangle_dupe_cols, storage_options)
455 if not isinstance(io, ExcelFile):
456 should_close = True
--> 457 io = ExcelFile(io, storage_options=storage_options, engine=engine)
458 elif engine and engine != io.engine:
459 raise ValueError(
460 "Engine should not be specified when passing "
461 "an ExcelFile - ExcelFile already has the engine set"
462 )

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\excel\_base.py:1419, in ExcelFile.__init__(self, path_or_buffer, engine, storage_options)
1416 self.engine = engine
1417 self.storage_options = storage_options
-> 1419 self._reader = self._engines[engine](self._io,

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\excel\_openpyxl.py:525, in OpenpyxlReader.__init__(self, filepath_or_buffer, storage_options)
514 """
515 Reader using openpyxl engine.
516
(...)
522 passed to fsspec for appropriate URLs (see ``_get_filepath_or_buffer``)
523 """
524
--> 525 super().__init__(filepath_or_buffer,

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\excel\_base.py:518, in BaseExcelReader.__init__(self, filepath_or_buffer, storage_options)
516 self.handles.handle.seek(0)
517 try:
--> 518 self.book =
519 except Exception:
520 self.close()

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\excel\_openpyxl.py:536, in OpenpyxlReader.load_workbook(self, filepath_or_buffer)
533 def load_workbook(self, filepath_or_buffer: FilePath | ReadBuffer[bytes]):
534 from openpyxl import load_workbook
--> 536 return load_workbook(
537 filepath_or_buffer, read_only=True, data_only=True, keep_links=False
538 )

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\openpyxl\reader\excel.py:346, in load_workbook(filename, read_only, keep_vba, data_only, keep_links, rich_text)
316 """Open the given filename and return the workbook
317
318 :param filename: the path to open or a file-like object
(...)
342
343 """
344 reader = ExcelReader(filename, read_only, keep_vba,
345 data_only, keep_links, rich_text)
--> 346 reader.read()
347 return reader.wb

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\openpyxl\reader\excel.py:303, in ExcelReader.read(self)
301 self.read_worksheets()
302 action = "assign names"
--> 303 self.parser.assign_names()
304 if not self.read_only:
305 self.archive.close()

File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\openpyxl\reader\workbook.py:109, in
107 reserved = defn.is_reserved
108 if reserved is None:
--> 109 sheet.defined_names[name] = defn
111 elif reserved == "Print_Titles":
112 titles =

AttributeError: 'ReadOnlyWorksheet' object has no attribute 'defined_names'