I am trying to view the dataframe generated from a .xlsx file. When I view it with just print, it generates just fine in a Jupyter Notebook.

import seaborn as sns
import scienceplots
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import openpyxl

df = pd.read_excel('2022-Nov-14_Neut.xlsx', engine='openpyxl')
print(df)

When I try to print it with

pd.set_option('display.max_rows', True)

I get:

TypeError                                 Traceback (most recent call last)
Cell In[14], line 9
      6 import openpyxl
      8 df = pd.read_excel('2022-Nov-14_Neut.xlsx', engine='openpyxl')
----> 9 print(df)

File ~/.local/lib/python3.10/site-packages/pandas/core/frame.py:1063, in DataFrame.__repr__(self)
   1060     return buf.getvalue()
   1062 repr_params = fmt.get_dataframe_repr_params()
-> 1063 return self.to_string(**repr_params)

File ~/.local/lib/python3.10/site-packages/pandas/core/frame.py:1226, in DataFrame.to_string(self, buf, columns, col_space, header, index, na_rep, formatters, float_format, sparsify, index_names, justify, max_rows, max_cols, show_dimensions, decimal, line_width, min_rows, max_colwidth, encoding)
   1223 from pandas import option_context
   1225 with option_context("display.max_colwidth", max_colwidth):
-> 1226     formatter = fmt.DataFrameFormatter(
   1227         self,
   1228         columns=columns,
   1229         col_space=col_space,
   1230         na_rep=na_rep,
   1231         formatters=formatters,
   1232         float_format=float_format,
   1233         sparsify=sparsify,
   1234         justify=justify,
   1235         index_names=index_names,
   1236         header=header,
   1237         index=index,
   1238         min_rows=min_rows,
   1239         max_rows=max_rows,
   1240         max_cols=max_cols,
   1241         show_dimensions=show_dimensions,
   1242         decimal=decimal,
   1243     )
   1244     return fmt.DataFrameRenderer(formatter).to_string(
   1245         buf=buf,
   1246         encoding=encoding,
   1247         line_width=line_width,
   1248     )

File ~/.local/lib/python3.10/site-packages/pandas/io/formats/format.py:610, in DataFrameFormatter.__init__(self, frame, columns, col_space, header, index, na_rep, formatters, justify, float_format, sparsify, index_names, max_rows, min_rows, max_cols, show_dimensions, decimal, bold_rows, escape)
    607 self.max_rows_fitted = self._calc_max_rows_fitted()
    609 self.tr_frame = self.frame
--> 610 self.truncate()
    611 self.adj = get_adjustment()

File ~/.local/lib/python3.10/site-packages/pandas/io/formats/format.py:801, in DataFrameFormatter.truncate(self)
    798     self._truncate_horizontally()
    800 if self.is_truncated_vertically:
--> 801     self._truncate_vertically()

File ~/.local/lib/python3.10/site-packages/pandas/io/formats/format.py:844, in DataFrameFormatter._truncate_vertically(self)
    842 else:
    843     row_num = cast(int, self.max_rows)
--> 844     self.tr_frame = self.tr_frame.iloc[:row_num, :]
    845 self.tr_row_num = row_num

File ~/.local/lib/python3.10/site-packages/pandas/core/indexing.py:1067, in _LocationIndexer.__getitem__(self, key)
   1065     if self._is_scalar_access(key):
   1066         return self.obj._get_value(*key, takeable=self._takeable)
-> 1067     return self._getitem_tuple(key)
   1068 else:
   1069     # we by definition only have the 0th axis
   1070     axis = self.axis or 0

File ~/.local/lib/python3.10/site-packages/pandas/core/indexing.py:1567, in _iLocIndexer._getitem_tuple(self, tup)
   1564 with suppress(IndexingError):
   1565     return self._getitem_lowerdim(tup)
-> 1567 return self._getitem_tuple_same_dim(tup)

File ~/.local/lib/python3.10/site-packages/pandas/core/indexing.py:924, in _LocationIndexer._getitem_tuple_same_dim(self, tup)
    921 if com.is_null_slice(key):
    922     continue
--> 924 retval = getattr(retval, self.name)._getitem_axis(key, axis=i)
    925 # We should never have retval.ndim < self.ndim, as that should
    926 #  be handled by the _getitem_lowerdim call above.
    927 assert retval.ndim == self.ndim

File ~/.local/lib/python3.10/site-packages/pandas/core/indexing.py:1602, in _iLocIndexer._getitem_axis(self, key, axis)
   1596     raise IndexError(
   1597         "DataFrame indexer is not allowed for .iloc\n"
   1598         "Consider using .loc for automatic alignment."
   1599     )
   1601 if isinstance(key, slice):
-> 1602     return self._get_slice_axis(key, axis=axis)
   1604 if is_iterator(key):
   1605     key = list(key)

File ~/.local/lib/python3.10/site-packages/pandas/core/indexing.py:1637, in _iLocIndexer._get_slice_axis(self, slice_obj, axis)
   1634     return obj.copy(deep=False)
   1636 labels = obj._get_axis(axis)
-> 1637 labels._validate_positional_slice(slice_obj)
   1638 return self.obj._slice(slice_obj, axis=axis)

File ~/.local/lib/python3.10/site-packages/pandas/core/indexes/base.py:4213, in Index._validate_positional_slice(self, key)
   4208 """
   4209 For positional indexing, a slice must have either int or None
   4210 for each of start, stop, and step.
   4211 """
   4212 self._validate_indexer("positional", key.start, "iloc")
-> 4213 self._validate_indexer("positional", key.stop, "iloc")
   4214 self._validate_indexer("positional", key.step, "iloc")

File ~/.local/lib/python3.10/site-packages/pandas/core/indexes/base.py:6634, in Index._validate_indexer(self, form, key, kind)
   6631 assert kind in ["getitem", "iloc"]
   6633 if key is not None and not is_integer(key):
-> 6634     raise self._invalid_indexer(form, key)

TypeError: cannot do positional indexing on RangeIndex with these indexers [True] of type bool

I tried to first convert the .xlsx to .csv, but I got the same error upon trying to print the dataframe with all rows showing.

I expected to see a full view of the .xlsx.

I'm a newbie, so any help would be thoroughly appreciated.

Here are a few rows of the xlsx, if it helps:

CodePudding user response：

The pandas library uses integer indices to select rows from a DataFrame.

It's not possible use only boolean values.

To select rows from a DataFrame based on a boolean condition, you can use the DataFrame.loc indexer and pass it a boolean array that has the same length as the DataFrame.

Exemple:

df = pd.read_excel('2022-Nov-14_Neut.xlsx', engine='openpyxl')
df_selected = df.loc[df['column_name'] > 5]

CodePudding user response：

The default value of max_rows is 10. If set to None then it means all rows of the data frame. So instead of True, put None.