[Python] TypeError: Could not convert OscarOscarMichaelJimDwightCreed to numeric [duplicate]

I am following the code (chapter_08_reshaping_and_pivoting) from following website.

https://github.com/paskhaver/pandas-in-action

import pandas as pd
pd.read_csv('sales_by_employee.csv').head()




sales = pd.read_csv('sales_by_employee.csv', parse_dates=['Date'])
sales.tail()




sales.pivot_table(index='Date')


Above code makes error as below.

---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
File ~\anaconda3\Lib\site-packages\pandas\core\groupby\groupby.py:1942, in GroupBy._agg_py_fallback(self, how, values, ndim, alt)
1941 try:
-> 1942 res_values = self._grouper.agg_series(ser, alt, preserve_dtype=True)
1943 except Exception as err:

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\ops.py:864, in BaseGrouper.agg_series(self, obj, func, preserve_dtype)
862 preserve_dtype = True
--> 864 result = self._aggregate_series_pure_python(obj, func)
866 npvalues = lib.maybe_convert_objects(result, try_float=False)

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\ops.py:885, in BaseGrouper._aggregate_series_pure_python(self, obj, func)
884 for i, group in enumerate(splitter):
--> 885 res = func(group)
886 res = extract_result(res)

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\groupby.py:2454, in GroupBy.mean.<locals>.<lambda>(x)
2451 else:
2452 result = self._cython_agg_general(
2453 "mean",
-> 2454 alt=lambda x: Series(x, copy=False).mean(numeric_only=numeric_only),
2455 numeric_only=numeric_only,
2456 )
2457 return result.__finalize__(self.obj, method="groupby")

File ~\anaconda3\Lib\site-packages\pandas\core\series.py:6549, in Series.mean(self, axis, skipna, numeric_only, **kwargs)
6541 @doc(make_doc("mean", ndim=1))
6542 def mean(
6543 self,
(...)
6547 **kwargs,
6548 ):
-> 6549 return NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)

File ~\anaconda3\Lib\site-packages\pandas\core\generic.py:12420, in NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)
12413 def mean(
12414 self,
12415 axis: Axis | None = 0,
(...)
12418 **kwargs,
12419 ) -> Series | float:
> 12420 return self._stat_function(
12421 "mean", nanops.nanmean, axis, skipna, numeric_only, **kwargs
12422 )

File ~\anaconda3\Lib\site-packages\pandas\core\generic.py:12377, in NDFrame._stat_function(self, name, func, axis, skipna, numeric_only, **kwargs)
12375 validate_bool_kwarg(skipna, "skipna", none_allowed=False)
> 12377 return self._reduce(
12378 func, name=name, axis=axis, skipna=skipna, numeric_only=numeric_only
12379 )

File ~\anaconda3\Lib\site-packages\pandas\core\series.py:6457, in Series._reduce(self, op, name, axis, skipna, numeric_only, filter_type, **kwds)
6453 raise TypeError(
6454 f"Series.{name} does not allow {kwd_name}={numeric_only} "
6455 "with non-numeric dtypes."
6456 )
-> 6457 return op(delegate, skipna=skipna, **kwds)

File ~\anaconda3\Lib\site-packages\pandas\core\nanops.py:147, in bottleneck_switch.__call__.<locals>.f(values, axis, skipna, **kwds)
146 else:
--> 147 result = alt(values, axis=axis, skipna=skipna, **kwds)
149 return result

File ~\anaconda3\Lib\site-packages\pandas\core\nanops.py:404, in _datetimelike_compat.<locals>.new_func(values, axis, skipna, mask, **kwargs)
402 mask = isna(values)
--> 404 result = func(values, axis=axis, skipna=skipna, mask=mask, **kwargs)
406 if datetimelike:

File ~\anaconda3\Lib\site-packages\pandas\core\nanops.py:720, in nanmean(values, axis, skipna, mask)
719 the_sum = values.sum(axis, dtype=dtype_sum)
--> 720 the_sum = _ensure_numeric(the_sum)
722 if axis is not None and getattr(the_sum, "ndim", False):

File ~\anaconda3\Lib\site-packages\pandas\core\nanops.py:1701, in _ensure_numeric(x)
1699 if isinstance(x, str):
1700 # GH#44008, GH#36703 avoid casting e.g. strings to numeric
-> 1701 raise TypeError(f"Could not convert string '{x}' to numeric")
1702 try:

TypeError: Could not convert string 'OscarOscarMichaelJimDwightCreed' to numeric

The above exception was the direct cause of the following exception:

TypeError Traceback (most recent call last)
Cell In[7], line 1
----> 1 sales.pivot_table(index='Date')

File ~\anaconda3\Lib\site-packages\pandas\core\frame.py:9509, in DataFrame.pivot_table(self, values, index, columns, aggfunc, fill_value, margins, dropna, margins_name, observed, sort)
9492 @Substitution("")
9493 @Appender(_shared_docs["pivot_table"])
9494 def pivot_table(
(...)
9505 sort: bool = True,
9506 ) -> DataFrame:
9507 from pandas.core.reshape.pivot import pivot_table
-> 9509 return pivot_table(
9510 self,
9511 values=values,
9512 index=index,
9513 columns=columns,
9514 aggfunc=aggfunc,
9515 fill_value=fill_value,
9516 margins=margins,
9517 dropna=dropna,
9518 margins_name=margins_name,
9519 observed=observed,
9520 sort=sort,
9521 )

File ~\anaconda3\Lib\site-packages\pandas\core\reshape\pivot.py:102, in pivot_table(data, values, index, columns, aggfunc, fill_value, margins, dropna, margins_name, observed, sort)
99 table = concat(pieces, keys=keys, axis=1)
100 return table.__finalize__(data, method="pivot_table")
--> 102 table = __internal_pivot_table(
103 data,
104 values,
105 index,
106 columns,
107 aggfunc,
108 fill_value,
109 margins,
110 dropna,
111 margins_name,
112 observed,
113 sort,
114 )
115 return table.__finalize__(data, method="pivot_table")

File ~\anaconda3\Lib\site-packages\pandas\core\reshape\pivot.py:183, in __internal_pivot_table(data, values, index, columns, aggfunc, fill_value, margins, dropna, margins_name, observed, sort)
173 if observed is lib.no_default and any(
174 ping._passed_categorical for ping in grouped._grouper.groupings
175 ):
176 warnings.warn(
177 "The default value of observed=False is deprecated and will change "
178 "to observed=True in a future version of pandas. Specify "
(...)
181 stacklevel=find_stack_level(),
182 )
--> 183 agged = grouped.agg(aggfunc)
185 if dropna and isinstance(agged, ABCDataFrame) and len(agged.columns):
186 agged = agged.dropna(how="all")

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\generic.py:1432, in DataFrameGroupBy.aggregate(self, func, engine, engine_kwargs, *args, **kwargs)
1429 kwargs["engine_kwargs"] = engine_kwargs
1431 op = GroupByApply(self, func, args=args, kwargs=kwargs)
-> 1432 result = op.agg()
1433 if not is_dict_like(func) and result is not None:
1434 # GH #52849
1435 if not self.as_index and is_list_like(func):

File ~\anaconda3\Lib\site-packages\pandas\core\apply.py:187, in Apply.agg(self)
184 kwargs = self.kwargs
186 if isinstance(func, str):
--> 187 return self.apply_str()
189 if is_dict_like(func):
190 return self.agg_dict_like()

File ~\anaconda3\Lib\site-packages\pandas\core\apply.py:603, in Apply.apply_str(self)
601 else:
602 self.kwargs["axis"] = self.axis
--> 603 return self._apply_str(obj, func, *self.args, **self.kwargs)

File ~\anaconda3\Lib\site-packages\pandas\core\apply.py:693, in Apply._apply_str(self, obj, func, *args, **kwargs)
691 f = getattr(obj, func)
692 if callable(f):
--> 693 return f(*args, **kwargs)
695 # people may aggregate on a non-callable attribute
696 # but don't let them think they can pass args to it
697 assert len(args) == 0

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\groupby.py:2452, in GroupBy.mean(self, numeric_only, engine, engine_kwargs)
2445 return self._numba_agg_general(
2446 grouped_mean,
2447 executor.float_dtype_mapping,
2448 engine_kwargs,
2449 min_periods=0,
2450 )
2451 else:
-> 2452 result = self._cython_agg_general(
2453 "mean",
2454 alt=lambda x: Series(x, copy=False).mean(numeric_only=numeric_only),
2455 numeric_only=numeric_only,
2456 )
2457 return result.__finalize__(self.obj, method="groupby")

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\groupby.py:1998, in GroupBy._cython_agg_general(self, how, alt, numeric_only, min_count, **kwargs)
1995 result = self._agg_py_fallback(how, values, ndim=data.ndim, alt=alt)
1996 return result
-> 1998 new_mgr = data.grouped_reduce(array_func)
1999 res = self._wrap_agged_manager(new_mgr)
2000 if how in ["idxmin", "idxmax"]:

File ~\anaconda3\Lib\site-packages\pandas\core\internals\managers.py:1469, in BlockManager.grouped_reduce(self, func)
1465 if blk.is_object:
1466 # split on object-dtype blocks bc some columns may raise
1467 # while others do not.
1468 for sb in blk._split():
-> 1469 applied = sb.apply(func)
1470 result_blocks = extend_blocks(applied, result_blocks)
1471 else:

File ~\anaconda3\Lib\site-packages\pandas\core\internals\blocks.py:393, in Block.apply(self, func, **kwargs)
387 @final
388 def apply(self, func, **kwargs) -> list[Block]:
389 """
390 apply the function to my values; return a block if we are not
391 one
392 """
--> 393 result = func(self.values, **kwargs)
395 result = maybe_coerce_values(result)
396 return self._split_op_result(result)

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\groupby.py:1995, in GroupBy._cython_agg_general.<locals>.array_func(values)
1992 return result
1994 assert alt is not None
-> 1995 result = self._agg_py_fallback(how, values, ndim=data.ndim, alt=alt)
1996 return result

File ~\anaconda3\Lib\site-packages\pandas\core\groupby\groupby.py:1946, in GroupBy._agg_py_fallback(self, how, values, ndim, alt)
1944 msg = f"agg function failed [how->{how},dtype->{ser.dtype}]"
1945 # preserve the kind of exception that raised
-> 1946 raise type(err)(msg) from err
1948 if ser.dtype == object:
1949 res_values = res_values.astype(object, copy=False)

TypeError: agg function failed [how->mean,dtype->object]


My pandas version is 2.2.3.

However, when I make code as below. Then, it works fine.

sales[['Date','Revenue','Expenses']].pivot_table(index='Date')




I don't know how github code directlly filtering object and only calculate int64 columns ('Revenue','Expenses').

Continue reading...