Can't perform calculations on DataFrame values - pandas

Question

I am trying to apply a formula to each value in a Pandas DataFrame, however, I am getting an error.
def transform_x(x):
return x/0.65
transformed = input_df.applymap(transform_x)
This returns the following error:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-72-66afcc1d1b80> in <module>
3
4
----> 5 transformed = input_df.applymap(transform_x)
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in applymap(self, func)
6551 return lib.map_infer(x.astype(object).values, func)
6552
-> 6553 return self.apply(infer)
6554
6555 # ----------------------------------------------------------------------
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
6485 args=args,
6486 kwds=kwds)
-> 6487 return op.get_result()
6488
6489 def applymap(self, func):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\apply.py in get_result(self)
149 return self.apply_raw()
150
--> 151 return self.apply_standard()
152
153 def apply_empty_result(self):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\apply.py in apply_standard(self)
255
256 # compute the result using the series generator
--> 257 self.apply_series_generator()
258
259 # wrap results
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\apply.py in apply_series_generator(self)
284 try:
285 for i, v in enumerate(series_gen):
--> 286 results[i] = self.f(v)
287 keys.append(v.name)
288 except Exception as e:
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in infer(x)
6549 if x.empty:
6550 return lib.map_infer(x, func)
-> 6551 return lib.map_infer(x.astype(object).values, func)
6552
6553 return self.apply(infer)
pandas\_libs\lib.pyx in pandas._libs.lib.map_infer()
<ipython-input-72-66afcc1d1b80> in transform_x(x)
1 def transform_x(x):
----> 2 return x/0.65
3
4
5 transformed = input_df.applymap(transform_x)
TypeError: ("unsupported operand type(s) for /: 'str' and 'float'", 'occurred at index (column_a)')
I have tried converting the type of the DataFrame to float, as I thought that this might be the issue, however, I am encountering a different problem.
input_df = input_df.astype(float)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-71-2102a8e5c505> in <module>
----> 1 input_df= input_df.astype(float)
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\generic.py in astype(self, dtype, copy, errors, **kwargs)
5689 # else, only a single dtype is given
5690 new_data = self._data.astype(dtype=dtype, copy=copy, errors=errors,
-> 5691 **kwargs)
5692 return self._constructor(new_data).__finalize__(self)
5693
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in astype(self, dtype, **kwargs)
529
530 def astype(self, dtype, **kwargs):
--> 531 return self.apply('astype', dtype=dtype, **kwargs)
532
533 def convert(self, **kwargs):
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\managers.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
393 copy=align_copy)
394
--> 395 applied = getattr(b, f)(**kwargs)
396 result_blocks = _extend_blocks(applied, result_blocks)
397
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\blocks.py in astype(self, dtype, copy, errors, values, **kwargs)
532 def astype(self, dtype, copy=False, errors='raise', values=None, **kwargs):
533 return self._astype(dtype, copy=copy, errors=errors, values=values,
--> 534 **kwargs)
535
536 def _astype(self, dtype, copy=False, errors='raise', values=None,
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\internals\blocks.py in _astype(self, dtype, copy, errors, values, **kwargs)
631
632 # _astype_nansafe works fine with 1-d only
--> 633 values = astype_nansafe(values.ravel(), dtype, copy=True)
634
635 # TODO(extension)
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\dtypes\cast.py in astype_nansafe(arr, dtype, copy, skipna)
700 if copy or is_object_dtype(arr) or is_object_dtype(dtype):
701 # Explicit copy, or required since NumPy can't view from / to object.
--> 702 return arr.astype(dtype, copy=True)
703
704 return arr.view(dtype)
ValueError: could not convert string to float:
I am really not sure what is going wrong. I have tried exporting the DataFrames as a csv and, aside from the indexes which do contain text, the values are all floats. Is this something to do with the indexes perhaps?
As an addendum, I tried using pd.to_numeric outside of a lambda function but it also returned an error:
input_df = pd.to_numeric(input_df, errors='coerce')
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-93-7178dce9054b> in <module>
----> 1 input_df = pd.to_numeric(input_df, errors='coerce')
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\tools\numeric.py in to_numeric(arg, errors, downcast)
120 values = np.array([arg], dtype='O')
121 elif getattr(arg, 'ndim', 1) > 1:
--> 122 raise TypeError('arg must be a list, tuple, 1-d array, or Series')
123 else:
124 values = arg
TypeError: arg must be a list, tuple, 1-d array, or Series

Answer 1

You may try something like:
input_df = input_df.apply(lambda x: pd.to_neumeric(x,errors='coerce')).applymap(transform_x)
the input_df is a 2D array but pd.to_neumeric() takes only list, tuple, 1-d array, or Series so you cannot call a dataframe under it.Hence we take the help of lambda x to pass each series individually .
Once all the df has neumeric data, apply your function.