'can only concatenate str (not "float") to str' while all dtypes are float64, int64 #23
Description
Just runed as in example
from boostaroota import BoostARoota
br = BoostARoota(metric='logloss')
br.fit(X, y)
for classification task
getting
[06:31:00] WARNING: ../src/learner.cc:767:
Parameters: { "silent" } are not used.
Round: 1 iteration: 10
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
Cell In[22], line 4
1 br = BoostARoota(metric='logloss')
3 #Fit the model for the subset of variables
----> 4 br.fit(X, y)
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/boostaroota/boostaroota.py:46, in BoostARoota.fit(self, x, y)
45 def fit(self, x, y):
---> 46 self.keep_vars_ = _BoostARoota(x, y,
47 metric=self.metric,
48 clf = self.clf,
49 cutoff=self.cutoff,
50 iters=self.iters,
51 max_rounds=self.max_rounds,
52 delta=self.delta,
53 silent=self.silent)
54 return self
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/boostaroota/boostaroota.py:219, in _BoostARoota(x, y, metric, clf, cutoff, iters, max_rounds, delta, silent)
217 i += 1
218 if clf is None:
--> 219 crit, keep_vars = _reduce_vars_xgb(new_x,
220 y,
221 metric=metric,
222 this_round=i,
223 cutoff=cutoff,
224 n_iterations=iters,
225 delta=delta,
226 silent=silent)
227 else:
228 crit, keep_vars = _reduce_vars_sklearn(new_x,
229 y,
230 clf=clf,
(...)
234 delta=delta,
235 silent=silent)
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/boostaroota/boostaroota.py:130, in _reduce_vars_xgb(x, y, metric, this_round, cutoff, n_iterations, delta, silent)
127 if not silent:
128 print("Round: ", this_round, " iteration: ", i)
--> 130 df['Mean'] = df.mean(axis=1)
131 #Split them back out
132 real_vars = df[~df['feature'].isin(shadow_names)]
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/generic.py:11556, in NDFrame._add_numeric_operations.<locals>.mean(self, axis, skipna, numeric_only, **kwargs)
11539 @doc(
11540 _num_doc,
11541 desc="Return the mean of the values over the requested axis.",
(...)
11554 **kwargs,
11555 ):
> 11556 return NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/generic.py:11201, in NDFrame.mean(self, axis, skipna, numeric_only, **kwargs)
11194 def mean(
11195 self,
11196 axis: Axis | None = 0,
(...)
11199 **kwargs,
11200 ) -> Series | float:
> 11201 return self._stat_function(
11202 "mean", nanops.nanmean, axis, skipna, numeric_only, **kwargs
11203 )
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/generic.py:11158, in NDFrame._stat_function(self, name, func, axis, skipna, numeric_only, **kwargs)
11154 nv.validate_stat_func((), kwargs, fname=name)
11156 validate_bool_kwarg(skipna, "skipna", none_allowed=False)
> 11158 return self._reduce(
11159 func, name=name, axis=axis, skipna=skipna, numeric_only=numeric_only
11160 )
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/frame.py:10524, in DataFrame._reduce(self, op, name, axis, skipna, numeric_only, filter_type, **kwds)
10520 df = df.T
10522 # After possibly _get_data and transposing, we are now in the
10523 # simple case where we can use BlockManager.reduce
> 10524 res = df._mgr.reduce(blk_func)
10525 out = df._constructor(res).iloc[0]
10526 if out_dtype is not None:
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/internals/managers.py:1534, in BlockManager.reduce(self, func)
1532 res_blocks: list[Block] = []
1533 for blk in self.blocks:
-> 1534 nbs = blk.reduce(func)
1535 res_blocks.extend(nbs)
1537 index = Index([None]) # placeholder
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/internals/blocks.py:339, in Block.reduce(self, func)
333 @final
334 def reduce(self, func) -> list[Block]:
335 # We will apply the function and reshape the result into a single-row
336 # Block with the same mgr_locs; squeezing will be done at a higher level
337 assert self.ndim == 2
--> 339 result = func(self.values)
341 if self.values.ndim == 1:
342 # TODO(EA2D): special case not needed with 2D EAs
343 res_values = np.array([[result]])
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/frame.py:10487, in DataFrame._reduce.<locals>.blk_func(values, axis)
10485 return values._reduce(name, skipna=skipna, **kwds)
10486 else:
> 10487 return op(values, axis=axis, skipna=skipna, **kwds)
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/nanops.py:96, in disallow.__call__.<locals>._f(*args, **kwargs)
94 try:
95 with np.errstate(invalid="ignore"):
---> 96 return f(*args, **kwargs)
97 except ValueError as e:
98 # we want to transform an object array
99 # ValueError message to the more typical TypeError
100 # e.g. this is normally a disallowed function on
101 # object arrays that contain strings
102 if is_object_dtype(args[0]):
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/nanops.py:158, in bottleneck_switch.__call__.<locals>.f(values, axis, skipna, **kwds)
156 result = alt(values, axis=axis, skipna=skipna, **kwds)
157 else:
--> 158 result = alt(values, axis=axis, skipna=skipna, **kwds)
160 return result
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/nanops.py:421, in _datetimelike_compat.<locals>.new_func(values, axis, skipna, mask, **kwargs)
418 if datetimelike and mask is None:
419 mask = isna(values)
--> 421 result = func(values, axis=axis, skipna=skipna, mask=mask, **kwargs)
423 if datetimelike:
424 result = _wrap_results(result, orig_values.dtype, fill_value=iNaT)
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/pandas/core/nanops.py:727, in nanmean(values, axis, skipna, mask)
724 dtype_count = dtype
726 count = _get_counts(values.shape, mask, axis, dtype=dtype_count)
--> 727 the_sum = _ensure_numeric(values.sum(axis, dtype=dtype_sum))
729 if axis is not None and getattr(the_sum, "ndim", False):
730 count = cast(np.ndarray, count)
File ~/anaconda3/envs/filter/lib/python3.11/site-packages/numpy/core/_methods.py:48, in _sum(a, axis, dtype, out, keepdims, initial, where)
43 def _amin(a, axis=None, out=None, keepdims=False,
44 initial=_NoValue, where=True):
45 return umr_minimum(a, axis, None, out, keepdims, initial, where)
47 def _sum(a, axis=None, dtype=None, out=None, keepdims=False,
---> 48 initial=_NoValue, where=True):
49 return umr_sum(a, axis, dtype, out, keepdims, initial, where)
51 def _prod(a, axis=None, dtype=None, out=None, keepdims=False,
52 initial=_NoValue, where=True):
TypeError: can only concatenate str (not "float") to str```
When I calculate `df.mean(axis=1)` it outputs correct answer without failing.