error in 03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb

[vlsireddy]

Hi,

03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb

error in ### Step 6. Print the mean alcohol consumption per continent for every column

i thought something wrong in my own code. but then i opened and executed the Exercise_with_solutions.pynb file, the error can be replicated there as well

drinks.groupby('continent').mean()

=================================================================

TypeError Traceback (most recent call last)
File ~\OneDrive\Documents\pandas_exercises\venv\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 ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\groupby\ops.py:863, in BaseGrouper.agg_series(self, obj, func, preserve_dtype)
861 preserve_dtype = True
--> 863 result = self._aggregate_series_pure_python(obj, func)
865 npvalues = lib.maybe_convert_objects(result, try_float=False)

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

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\groupby\groupby.py:2454, in GroupBy.mean..(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 ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\series.py:6409, in Series.mean(self, axis, skipna, numeric_only, **kwargs)
6401 @doc(make_doc("mean", ndim=1))
6402 def mean(
6403 self,
(...)
6407 **kwargs,
6408 ):
-> 6409 return NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\generic.py:12407, in NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)
12400 def mean(
12401 self,
12402 axis: Axis | None = 0,
(...)
12405 **kwargs,
12406 ) -> Series | float:

12407 return self._stat_function(
12408 "mean", nanops.nanmean, axis, skipna, numeric_only, **kwargs
12409 )

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\generic.py:12364, in NDFrame._stat_function(self, name, func, axis, skipna, numeric_only, **kwargs)
12362 validate_bool_kwarg(skipna, "skipna", none_allowed=False)

12364 return self._reduce(
12365 func, name=name, axis=axis, skipna=skipna, numeric_only=numeric_only
12366 )

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\series.py:6317, in Series._reduce(self, op, name, axis, skipna, numeric_only, filter_type, **kwds)
6313 raise TypeError(
6314 f"Series.{name} does not allow {kwd_name}={numeric_only} "
6315 "with non-numeric dtypes."
6316 )
-> 6317 return op(delegate, skipna=skipna, **kwds)

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\nanops.py:147, in bottleneck_switch.call..f(values, axis, skipna, **kwds)
146 else:
--> 147 result = alt(values, axis=axis, skipna=skipna, **kwds)
149 return result

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\nanops.py:404, in _datetimelike_compat..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 ~\OneDrive\Documents\pandas_exercises\venv\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 ~\OneDrive\Documents\pandas_exercises\venv\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 'AlgeriaAngolaBeninBotswanaBurkina FasoBurundiCote d'IvoireCabo VerdeCameroonCentral African RepublicChadComorosCongoDR CongoDjiboutiEgyptEquatorial GuineaEritreaEthiopiaGabonGambiaGhanaGuineaGuinea-BissauKenyaLesothoLiberiaLibyaMadagascarMalawiMaliMauritaniaMauritiusMoroccoMozambiqueNamibiaNigerNigeriaRwandaSao Tome & PrincipeSenegalSeychellesSierra LeoneSomaliaSouth AfricaSudanSwazilandTogoTunisiaUgandaTanzaniaZambiaZimbabwe' to numeric

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

TypeError Traceback (most recent call last)
Cell In[5], line 1
----> 1 drinks.groupby('continent').mean()

File ~\OneDrive\Documents\pandas_exercises\venv\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 ~\OneDrive\Documents\pandas_exercises\venv\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 ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\internals\managers.py:1470, in BlockManager.grouped_reduce(self, func)
1466 if blk.is_object:
1467 # split on object-dtype blocks bc some columns may raise
1468 # while others do not.
1469 for sb in blk._split():
-> 1470 applied = sb.apply(func)
1471 result_blocks = extend_blocks(applied, result_blocks)
1472 else:

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

File ~\OneDrive\Documents\pandas_exercises\venv\Lib\site-packages\pandas\core\groupby\groupby.py:1995, in GroupBy._cython_agg_general..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 ~\OneDrive\Documents\pandas_exercises\venv\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]

Thanks

[ManiRazeghi]

me too

[Utkarsh-Karambhe]

Issue

In 03_Grouping/Alcohol_Consumption/Exercise_with_solutions.ipynb, Step 6 (drinks.groupby('continent').mean()) raises a TypeError in modern pandas versions (e.g., 2.x) due to attempting to compute the mean of the non-numeric country column.

Fix

Updated the code to drinks.groupby('continent').mean(numeric_only=True) to exclude non-numeric columns, ensuring compatibility with pandas 2.x.

Impact

This fixes the error and aligns the solution with current pandas behavior, improving the exercise for learners.

[Utkarsh-Karambhe]

I created a pull request please review it!