I have a dataframe similar to the following, which we'll call "df":
id value time
a 1 1
a 1.5 2
a 2 3
a 2.5 4
b 1 1
b 1.5 2
b 2 3
b 2.5 4
I am running various regressions by "id" in Python on this dataframe. Generally, this requires a grouping by "id" and then applying a function to those groupings that calculates the regression.
I am working with 2 similar regression techniques in Scipy's stats library:
Theil-Sen estimator:
(https://docs.scipy.org/doc/scipy-0.15.1/reference/generated/scipy.stats.mstats.theilslopes.html)
Siegel estimator:
(https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.siegelslopes.html).
Both of these intake the same type of data. Therefore the function to calculate them should be the same aside from the actual technique used.
For Theil-Sen, I wrote the following function and the groupby statement that would be applied to that function:
def theil_reg(df, xcol, ycol):
model = stats.theilslopes(ycol,xcol)
return pd.Series(model)
out = df.groupby('id').apply(theil_reg, xcol='time', ycol='value')
However, I get the following error, which I've been having the hardest time understanding how to address:
ValueError: could not convert string to float: 'time'
The actual variable time is a numpy float object, so it isn't a string. This makes me believe that the stats.theilslopes
function is not recognizing that time is a column in the dataframe and is instead using 'time' as a string input into the function.
However if that's the case, then this seems to be a bug in the stats.theilslopes
package, and would need to be addressed by Scipy. The reason I believe this to be the case is because the exact same function as above, but instead using the siegelslopes
package, works perfectly fine and provides the output I'm expecting, and they're essentially the same estimation with the same inputs.
Doing the following on Siegel:
def siegel_reg(df, xcol, ycol):
model = stats.siegelslopes(ycol,xcol)
return pd.Series(model)
out = df.groupby('id').apply(siegel_reg, xcol='time',ycol='value')
Does not create any errors about the time variable and conducts the regression as needed.
Does anyone have thoughts on whether I'm missing something here? If so I would appreciate any thoughts, or if not, any thoughts on how to address this with Scipy.
Edit: here is the full error message that shows up when I run this script:
ValueError Traceback (most recent call last)
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
688 try:
--> 689 result = self._python_apply_general(f)
690 except Exception:
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
706 keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 707 self.axis)
708
C:\Anaconda\lib\site-packages\pandas\core\groupby\ops.py in apply(self, f, data, axis)
189 group_axes = _get_axes(group)
--> 190 res = f(group)
191 if not _is_indexed_like(res, group_axes):
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in f(g)
678 with np.errstate(all='ignore'):
--> 679 return func(g, *args, **kwargs)
680 else:
<ipython-input-506-0a1696f0aecd> in theil_reg(df, xcol, ycol)
1 def theil_reg(df, xcol, ycol):
----> 2 model = stats.theilslopes(ycol,xcol)
3 return pd.Series(model)
C:\Anaconda\lib\site-packages\scipy\stats\_stats_mstats_common.py in
theilslopes(y, x, alpha)
221 else:
--> 222 x = np.array(x, dtype=float).flatten()
223 if len(x) != len(y):
ValueError: could not convert string to float: 'time'
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-507-9a199e0ce924> in <module>
----> 1 df_accel_correct.groupby('chart').apply(theil_reg, xcol='time',
ycol='value')
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
699
700 with _group_selection_context(self):
--> 701 return self._python_apply_general(f)
702
703 return result
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
705 def _python_apply_general(self, f):
706 keys, values, mutated = self.grouper.apply(f,
self._selected_obj,
--> 707 self.axis)
708
709 return self._wrap_applied_output(
C:\Anaconda\lib\site-packages\pandas\core\groupby\ops.py in apply(self, f, data, axis)
188 # group might be modified
189 group_axes = _get_axes(group)
--> 190 res = f(group)
191 if not _is_indexed_like(res, group_axes):
192 mutated = True
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in f(g)
677 def f(g):
678 with np.errstate(all='ignore'):
--> 679 return func(g, *args, **kwargs)
680 else:
681 raise ValueError('func must be a callable if args or '
<ipython-input-506-0a1696f0aecd> in theil_reg(df, xcol, ycol)
1 def theil_reg(df, xcol, ycol):
----> 2 model = stats.theilslopes(ycol,xcol)
3 return pd.Series(model)
C:\Anaconda\lib\site-packages\scipy\stats\_stats_mstats_common.py in theilslopes(y, x, alpha)
220 x = np.arange(len(y), dtype=float)
221 else:
--> 222 x = np.array(x, dtype=float).flatten()
223 if len(x) != len(y):
224 raise ValueError("Incompatible lengths ! (%s<>%s)" % (len(y), len(x)))
ValueError: could not convert string to float: 'time'
Update 2: after calling df in the function, I received the following error message:
ValueError Traceback (most recent call last)
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
688 try:
--> 689 result = self._python_apply_general(f)
690 except Exception:
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
706 keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 707 self.axis)
708
C:\Anaconda\lib\site-packages\pandas\core\groupby\ops.py in apply(self, f, data, axis)
189 group_axes = _get_axes(group)
--> 190 res = f(group)
191 if not _is_indexed_like(res, group_axes):
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in f(g)
678 with np.errstate(all='ignore'):
--> 679 return func(g, *args, **kwargs)
680 else:
<ipython-input-563-5db69048f347> in theil_reg(df, xcol, ycol)
1 def theil_reg(df, xcol, ycol):
----> 2 model = stats.theilslopes(df[ycol],df[xcol])
3 return pd.Series(model)
C:\Anaconda\lib\site-packages\scipy\stats\_stats_mstats_common.py in theilslopes(y, x, alpha)
248 sigma = np.sqrt(sigsq)
--> 249 Ru = min(int(np.round((nt - z*sigma)/2.)), len(slopes)-1)
250 Rl = max(int(np.round((nt + z*sigma)/2.)) - 1, 0)
ValueError: cannot convert float NaN to integer
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-564-d7794bd1d495> in <module>
----> 1 correct_theil = df_accel_correct.groupby('chart').apply(theil_reg, xcol='time', ycol='value')
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in apply(self, func, *args, **kwargs)
699
700 with _group_selection_context(self):
--> 701 return self._python_apply_general(f)
702
703 return result
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in _python_apply_general(self, f)
705 def _python_apply_general(self, f):
706 keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 707 self.axis)
708
709 return self._wrap_applied_output(
C:\Anaconda\lib\site-packages\pandas\core\groupby\ops.py in apply(self, f, data, axis)
188 # group might be modified
189 group_axes = _get_axes(group)
--> 190 res = f(group)
191 if not _is_indexed_like(res, group_axes):
192 mutated = True
C:\Anaconda\lib\site-packages\pandas\core\groupby\groupby.py in f(g)
677 def f(g):
678 with np.errstate(all='ignore'):
--> 679 return func(g, *args, **kwargs)
680 else:
681 raise ValueError('func must be a callable if args or '
<ipython-input-563-5db69048f347> in theil_reg(df, xcol, ycol)
1 def theil_reg(df, xcol, ycol):
----> 2 model = stats.theilslopes(df[ycol],df[xcol])
3 return pd.Series(model)
C:\Anaconda\lib\site-packages\scipy\stats\_stats_mstats_common.py in theilslopes(y, x, alpha)
247 # Find the confidence interval indices in `slopes`
248 sigma = np.sqrt(sigsq)
--> 249 Ru = min(int(np.round((nt - z*sigma)/2.)), len(slopes)-1)
250 Rl = max(int(np.round((nt + z*sigma)/2.)) - 1, 0)
251 delta = slopes[[Rl, Ru]]
ValueError: cannot convert float NaN to integer
However, I have no null values in either column, and both columns are floats. Any suggestions on this error?