Develop Reference

TypeError: loop of ufunc does not support argument 0 of type float which has no callable exp method

Here's my dataset
Id B C
1 0.784 -1.6745
2 2.123 -2.8934
Here's what I try
import numpy as np
df.apply(lambda x: np.exp(x)/(1+np.exp(x)))
The error message
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
AttributeError: 'float' object has no attribute 'exp'
The above exception was the direct cause of the following exception:
TypeError Traceback (most recent call last)
<ipython-input-43-288751cc2e1d> in <module>
----> 1 A.apply(lambda x: np.exp(x)/(1+np.exp(x)))
~/.local/lib/python3.6/site-packages/pandas/core/frame.py in apply(self, func, axis, raw, result_type, args, **kwds)
7550 kwds=kwds,
7551 )
-> 7552 return op.get_result()
7553
7554 def applymap(self, func) -> "DataFrame":
~/.local/lib/python3.6/site-packages/pandas/core/apply.py in get_result(self)
183 return self.apply_raw()
184
--> 185 return self.apply_standard()
186
187 def apply_empty_result(self):
~/.local/lib/python3.6/site-packages/pandas/core/apply.py in apply_standard(self)
274
275 def apply_standard(self):
--> 276 results, res_index = self.apply_series_generator()
277
278 # wrap results
~/.local/lib/python3.6/site-packages/pandas/core/apply.py in apply_series_generator(self)
303 for i, v in enumerate(series_gen):
304 # ignore SettingWithCopy here in case the user mutates
--> 305 results[i] = self.f(v)
306 if isinstance(results[i], ABCSeries):
307 # If we have a view on v, we need to make a copy because
<ipython-input-43-288751cc2e1d> in <lambda>(x)
----> 1 A.apply(lambda x: np.exp(x)/(1+np.exp(x)))
~/.local/lib/python3.6/site-packages/pandas/core/series.py in __array_ufunc__(self, ufunc, method, *inputs, **kwargs)
724
725 inputs = tuple(extract_array(x, extract_numpy=True) for x in inputs)
--> 726 result = getattr(ufunc, method)(*inputs, **kwargs)
727
728 name = names[0] if len(set(names)) == 1 else None
TypeError: loop of ufunc does not support argument 0 of type float which has no callable exp method

Looks like a data type issue.
df = pd.DataFrame({'B':[0.784,2.123], 'C':[-1.6745,-2.8934]})
print(df.info())
Info:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2 entries, 0 to 1
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 B 2 non-null float64
1 C 2 non-null float64
dtypes: float64(2)
memory usage: 160.0 bytes
Apply:
df.apply(lambda x: np.exp(x)/(1+np.exp(x)))
print(df)
Result:
B C
0 0.784 -1.6745
1 2.123 -2.8934
Reproduce error:
df = pd.DataFrame({'B':[0.784,2.123], 'C':[-1.6745,-2.8934]}, dtype=object)
df.apply(lambda x: np.exp(x)/(1+np.exp(x)))

Remove % symbol from all the rows of a column of dataframe and convert the entire column values into float

A column of a dataframe named 'int.rate' has values like: 11.26%, 13.67%,..... where I need to remove the '%' symbol from all the rows of the column 'int.rate' and convert entire column values into float. I have already tried all other codes mentioned but even they threw errors so I need to know the exact code for this task. Please help! Below is the code that I tried:
x = data['int.rate'].str.split('%').astype(float)
which gives
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-1-52f9e2c36b19> in <module>()
4
5 #Code starts here
----> 6 x = data['int.rate'].str.split('%').astype(float)
7 print(x)
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs)
176 else:
177 kwargs[new_arg_name] = new_arg_value
--> 178 return func(*args, **kwargs)
179 return wrapper
180 return _deprecate_kwarg
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/core/generic.py in astype(self, dtype, copy, errors, **kwargs)
4999 # else, only a single dtype is given
5000 new_data = self._data.astype(dtype=dtype, copy=copy, errors=errors,
-> 5001 **kwargs)
5002 return self._constructor(new_data).__finalize__(self)
5003
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/core/internals.py in astype(self, dtype, **kwargs)
3712
3713 def astype(self, dtype, **kwargs):
-> 3714 return self.apply('astype', dtype=dtype, **kwargs)
3715
3716 def convert(self, **kwargs):
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/core/internals.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
3579
3580 kwargs['mgr'] = self
-> 3581 applied = getattr(b, f)(**kwargs)
3582 result_blocks = _extend_blocks(applied, result_blocks)
3583
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/core/internals.py in astype(self, dtype, copy, errors, values, **kwargs)
573 def astype(self, dtype, copy=False, errors='raise', values=None, **kwargs):
574 return self._astype(dtype, copy=copy, errors=errors, values=values,
--> 575 **kwargs)
576
577 def _astype(self, dtype, copy=False, errors='raise', values=None,
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/core/internals.py in _astype(self, dtype, copy, errors, values, klass, mgr, **kwargs)
662
663 # _astype_nansafe works fine with 1-d only
--> 664 values = astype_nansafe(values.ravel(), dtype, copy=True)
665 values = values.reshape(self.shape)
666
/opt/greyatom/kernel-gateway/runtime-environments/python/lib/python3.6/site-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy)
728
729 if copy:
--> 730 return arr.astype(dtype, copy=True)
731 return arr.view(dtype)
732
ValueError: setting an array element with a sequence.

split just split str, when you need to remove characters at ends of str you might use strip. Try doing:
x = data['int.rate'].str.strip('%').astype(float)
in place of:
x = data['int.rate'].str.split('%').astype(float)

Instead of split, use replace. See the demo code:
import pandas as pd
# initialize list of lists
data = [['tom', '10.2%'], ['nick', '15.7%'], ['juli', '14.67%']]
# Create the pandas DataFrame
df = pd.DataFrame(data, columns = ['Name', 'Interest'])
# print dataframe.
df
Name Interest
0 tom 10.2%
1 nick 15.7%
2 juli 14.67%
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Name 3 non-null object
1 Interest 3 non-null object
dtypes: object(2)
memory usage: 176.0+ bytes
df['Interest'] = df['Interest'].str.replace('%', '').astype(float)
df
Name Interest
0 tom 10.20
1 nick 15.70
2 juli 14.67
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 2 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Name 3 non-null object
1 Interest 3 non-null float64
dtypes: float64(1), object(1)
memory usage: 176.0+ bytes

Value Error: Couldn't Convert String to Float

I have two input spreadsheets.
Sheet 1 has 7 columns and 3 rows
/ FID / Total / A1 / B1 / A2 / B2
1 / 1 / 0.720168405 / 0.635589112 / XXX / 0.031112358 / YYY
1 / 2 / 0.760438562 / 0.328168557 / YYY / 0.311172576 / ZZZ
Sheet 2 has 2 columns and 4 rows
/ 0
XXX / 0.55
YYY / 0.52
ZZZ / 0.35
This is the code:
import pandas as pd
df = pd.read_excel("C:/Users/Sheet1.xls")
df2 = pd.read_excel("C:/Users/Sheet2.xlsx")
dictionary = df2.to_dict(orient='dict')
b = df.filter(like ='A').values
c = df.filter(like ='B').replace(dictionary[0]).astype(float).values
df['AA'] = ((c * b).sum(axis =1))
df['BB'] = df.AA / df.Total
def custom_round(x, base=5):
return base * round(float(x)/base)
df['C'] = df['BB'].apply(lambda x: custom_round(x, base=.05))
df['C'] = "X = " + df['C'].apply(lambda s: '{:,.2f}'.format(s))
df.to_excel("C:/Users/Results.xlsx")
print(df)
I have got error message: Value Error Couldn't Convert String to Float: XXX
ValueError Traceback (most recent call last)
<ipython-input-1-f42c7cb99da5> in <module>()
8
9 b = df.filter(like ='A').values
---> 10 c = df.filter(like ='B').replace(dictionary[0]).astype(float).values
11
12 df['AA'] = ((c * b).sum(axis =1))
C:\ProgramData\Anaconda2\lib\site-packages\pandas\core\generic.pyc 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\Anaconda2\lib\site-packages\pandas\core\internals\managers.pyc 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\Anaconda2\lib\site-packages\pandas\core\internals\managers.pyc 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\Anaconda2\lib\site-packages\pandas\core\internals\blocks.pyc 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\Anaconda2\lib\site-packages\pandas\core\internals\blocks.pyc 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\Anaconda2\lib\site-packages\pandas\core\dtypes\cast.pyc 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: XXX

I see in the 6th line of your code you are trying to replace some set in a dataframe (XXX, YYY,.. to 0.55, 0.52, ..). But you end up supplying a dictionary
{0:55, 1:52,..} where the keys are actually array indices.
I have changed your sheet 2 header for easier indexing like
0 / 1
XXX / 0.55
YYY / 0.52
ZZZ / 0.35
and set index using existing column 0 by replacing your line 4 as,
dictionary = df2.set_index(0)[1].to_dict()
and your line 6 as,
c = df.filter(like ='B').replace(dictionary).astype(float).values
This supplied proper dictionary to replace the dataframes.

Possible bug with `xarray.Dataset.groupby()`?

I'm using Xarray version 0.8.0, Python 3.5.1, on Mac OS X El Capitan 10.11.6.
The following code works as expected.
id_data_array = xarray.DataArray([280, 306, 280], coords={"index": range(3)})
random = numpy.random.rand(3)
score_data_array = xarray.DataArray(random, coords={"index": range(3)})
score_dataset = xarray.Dataset({"id": id_data_array, "score": score_data_array})
print(score_dataset)
print("======")
print(score_dataset.groupby("id").count())
Output:
<xarray.Dataset>
Dimensions: (index: 3)
Coordinates:
* index (index) int64 0 1 2
Data variables:
id (index) int64 280 306 280
score (index) float64 0.8358 0.7536 0.9495
======
<xarray.Dataset>
Dimensions: (id: 2)
Coordinates:
* id (id) int64 280 306
Data variables:
score (id) int64 2 1
In [ ]:
However, if I change just one little thing, to make the elements of id_data_array all distinct, then there is an error.
Code:
id_data_array = xarray.DataArray([280, 306, 120], coords={"index": range(3)})
random = numpy.random.rand(3)
score_data_array = xarray.DataArray(random, coords={"index": range(3)})
score_dataset = xarray.Dataset({"id": id_data_array, "score": score_data_array})
print(score_dataset)
print("======")
print(score_dataset.groupby("id").count())
Output:
<xarray.Dataset>
Dimensions: (index: 3)
Coordinates:
* index (index) int64 0 1 2
Data variables:
id (index) int64 280 306 120
score (index) float64 0.1353 0.0437 0.1687
======
---------------------------------------------------------------------------
InvalidIndexError Traceback (most recent call last)
<ipython-input-92-cc412270ba2e> in <module>()
5 print(score_dataset)
6 print("======")
----> 7 print(score_dataset.groupby("id").count())
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/common.py in wrapped_func(self, dim, keep_attrs, **kwargs)
44 return self.reduce(func, dim, keep_attrs,
45 numeric_only=numeric_only, allow_lazy=True,
---> 46 **kwargs)
47 return wrapped_func
48
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/groupby.py in reduce(self, func, dim, keep_attrs, **kwargs)
605 def reduce_dataset(ds):
606 return ds.reduce(func, dim, keep_attrs, **kwargs)
--> 607 return self.apply(reduce_dataset)
608
609 def assign(self, **kwargs):
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/groupby.py in apply(self, func, **kwargs)
562 kwargs.pop('shortcut', None) # ignore shortcut if set (for now)
563 applied = (func(ds, **kwargs) for ds in self._iter_grouped())
--> 564 combined = self._concat(applied)
565 result = self._maybe_restore_empty_groups(combined)
566 return result
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/groupby.py in _concat(self, applied)
570 concat_dim, positions = self._infer_concat_args(applied_example)
571
--> 572 combined = concat(applied, concat_dim)
573 reordered = _maybe_reorder(combined, concat_dim, positions)
574 return reordered
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/combine.py in concat(objs, dim, data_vars, coords, compat, positions, indexers, mode, concat_over)
114 raise TypeError('can only concatenate xarray Dataset and DataArray '
115 'objects, got %s' % type(first_obj))
--> 116 return f(objs, dim, data_vars, coords, compat, positions)
117
118
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/combine.py in _dataset_concat(datasets, dim, data_vars, coords, compat, positions)
276 if coord is not None:
277 # add concat dimension last to ensure that its in the final Dataset
--> 278 result[coord.name] = coord
279
280 return result
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/dataset.py in __setitem__(self, key, value)
536 raise NotImplementedError('cannot yet use a dictionary as a key '
537 'to set Dataset values')
--> 538 self.update({key: value})
539
540 def __delitem__(self, key):
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/dataset.py in update(self, other, inplace)
1434 dataset.
1435 """
-> 1436 variables, coord_names, dims = dataset_update_method(self, other)
1437
1438 return self._replace_vars_and_dims(variables, coord_names, dims,
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/merge.py in dataset_update_method(dataset, other)
490 priority_arg = 1
491 indexes = dataset.indexes
--> 492 return merge_core(objs, priority_arg=priority_arg, indexes=indexes)
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/merge.py in merge_core(objs, compat, join, priority_arg, explicit_coords, indexes)
371
372 coerced = coerce_pandas_values(objs)
--> 373 aligned = deep_align(coerced, join=join, copy=False, indexes=indexes)
374 expanded = expand_variable_dicts(aligned)
375
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/alignment.py in deep_align(list_of_variable_maps, join, copy, indexes)
146 out.append(variables)
147
--> 148 aligned = partial_align(*targets, join=join, copy=copy, indexes=indexes)
149
150 for key, aligned_obj in zip(keys, aligned):
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/alignment.py in partial_align(*objects, **kwargs)
109 valid_indexers = dict((k, v) for k, v in joined_indexes.items()
110 if k in obj.dims)
--> 111 result.append(obj.reindex(copy=copy, **valid_indexers))
112 return tuple(result)
113
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/dataset.py in reindex(self, indexers, method, tolerance, copy, **kw_indexers)
1216
1217 variables = alignment.reindex_variables(
-> 1218 self.variables, self.indexes, indexers, method, tolerance, copy=copy)
1219 return self._replace_vars_and_dims(variables)
1220
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/xarray/core/alignment.py in reindex_variables(variables, indexes, indexers, method, tolerance, copy)
218 target = utils.safe_cast_to_index(indexers[name])
219 indexer = index.get_indexer(target, method=method,
--> 220 **get_indexer_kwargs)
221
222 to_shape[name] = len(target)
/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/pandas/indexes/base.py in get_indexer(self, target, method, limit, tolerance)
2080
2081 if not self.is_unique:
-> 2082 raise InvalidIndexError('Reindexing only valid with uniquely'
2083 ' valued Index objects')
2084
InvalidIndexError: Reindexing only valid with uniquely valued Index objects
To me this seems buggy because if this is the desired behaviour then it would be very strange. Surely, we should include the case when all the elements of the DataArray we're grouping by are distinct?
Update
I've now uninstalled and reinstalled Xarray. The new Xarray is version 0.8.1, and it seems to work fine. So it may indeed be a bug in Xarray 0.8.0.

Index must be called with a collection of some kind: assign column name to dataframe

I have reweightTarget as follows and I want to convert it to a pandas Dataframe. However, I got following error:
TypeError: Index(...) must be called with a collection of some kind,
't' was passed
If I remove columns='t', it works fine. Can anyone please explain what's going on?
reweightTarget
Trading dates
2004-01-31 4.35
2004-02-29 4.46
2004-03-31 4.44
2004-04-30 4.39
2004-05-31 4.50
2004-06-30 4.53
2004-07-31 4.63
2004-08-31 4.58
dtype: float64
pd.DataFrame(reweightTarget, columns='t')
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-334-bf438351aaf2> in <module>()
----> 1 pd.DataFrame(reweightTarget, columns='t')
C:\Anaconda3\lib\site-packages\pandas\core\frame.py in __init__(self, data, index, columns, dtype, copy)
253 else:
254 mgr = self._init_ndarray(data, index, columns, dtype=dtype,
--> 255 copy=copy)
256 elif isinstance(data, (list, types.GeneratorType)):
257 if isinstance(data, types.GeneratorType):
C:\Anaconda3\lib\site-packages\pandas\core\frame.py in _init_ndarray(self, values, index, columns, dtype, copy)
421 raise_with_traceback(e)
422
--> 423 index, columns = _get_axes(*values.shape)
424 values = values.T
425
C:\Anaconda3\lib\site-packages\pandas\core\frame.py in _get_axes(N, K, index, columns)
388 columns = _default_index(K)
389 else:
--> 390 columns = _ensure_index(columns)
391 return index, columns
392
C:\Anaconda3\lib\site-packages\pandas\indexes\base.py in _ensure_index(index_like, copy)
3407 index_like = copy(index_like)
3408
-> 3409 return Index(index_like)
3410
3411
C:\Anaconda3\lib\site-packages\pandas\indexes\base.py in __new__(cls, data, dtype, copy, name, fastpath, tupleize_cols, **kwargs)
266 **kwargs)
267 elif data is None or lib.isscalar(data):
--> 268 cls._scalar_data_error(data)
269 else:
270 if (tupleize_cols and isinstance(data, list) and data and
C:\Anaconda3\lib\site-packages\pandas\indexes\base.py in _scalar_data_error(cls, data)
481 raise TypeError('{0}(...) must be called with a collection of some '
482 'kind, {1} was passed'.format(cls.__name__,
--> 483 repr(data)))
484
485 #classmethod
TypeError: Index(...) must be called with a collection of some kind, 't' was passed

Documentation: http://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.html
columns : Index or array-like
Column labels to use for resulting frame. Will default to np.arange(n) if no column labels are provided
Example:
df3 = DataFrame(np.random.randn(10, 5), columns=['a', 'b', 'c', 'd', 'e'])
Try to use:
pd.DataFrame(reweightTarget, columns=['t'])

When you want to set an index or columns in data frame you must pass it as a list, so either:
pd.DataFrame(reweightTarget, columns=['t'])
pd.DataFrame(reweightTarget, columns=list('t'))