[BUG] Can't print TokenCooccurrenceVectorizer object
cakiki opened this issue · comments
Hello!
Not sure this is actually a bug, but it seemed a bit odd so I figured I'd report it. I just trained a vectorizer using the following:
%%time
word_vectorizer = vectorizers.TokenCooccurrenceVectorizer(
min_document_occurrences=2,
window_radii=20,
window_functions='variable',
kernel_functions='geometric',
n_iter = 3,
normalize_windows=True,
).fit(subset['tokenized'])When I try to display or print it in a Jupyter Notebook cell I get the following error (actually repeated a few times):
AttributeError: 'TokenCooccurrenceVectorizer' object has no attribute 'coo_initial_memory'Full trace in case it's useful:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
File /opt/conda/lib/python3.9/site-packages/IPython/core/formatters.py:973, in MimeBundleFormatter.__call__(self, obj, include, exclude)
970 method = get_real_method(obj, self.print_method)
972 if method is not None:
--> 973 return method(include=include, exclude=exclude)
974 return None
975 else:
File /opt/conda/lib/python3.9/site-packages/sklearn/base.py:614, in BaseEstimator._repr_mimebundle_(self, **kwargs)
612 def _repr_mimebundle_(self, **kwargs):
613 """Mime bundle used by jupyter kernels to display estimator"""
--> 614 output = {"text/plain": repr(self)}
615 if get_config()["display"] == "diagram":
616 output["text/html"] = estimator_html_repr(self)
File /opt/conda/lib/python3.9/site-packages/sklearn/base.py:279, in BaseEstimator.__repr__(self, N_CHAR_MAX)
271 # use ellipsis for sequences with a lot of elements
272 pp = _EstimatorPrettyPrinter(
273 compact=True,
274 indent=1,
275 indent_at_name=True,
276 n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW,
277 )
--> 279 repr_ = pp.pformat(self)
281 # Use bruteforce ellipsis when there are a lot of non-blank characters
282 n_nonblank = len("".join(repr_.split()))
File /opt/conda/lib/python3.9/pprint.py:153, in PrettyPrinter.pformat(self, object)
151 def pformat(self, object):
152 sio = _StringIO()
--> 153 self._format(object, sio, 0, 0, {}, 0)
154 return sio.getvalue()
File /opt/conda/lib/python3.9/pprint.py:170, in PrettyPrinter._format(self, object, stream, indent, allowance, context, level)
168 self._readable = False
169 return
--> 170 rep = self._repr(object, context, level)
171 max_width = self._width - indent - allowance
172 if len(rep) > max_width:
File /opt/conda/lib/python3.9/pprint.py:431, in PrettyPrinter._repr(self, object, context, level)
430 def _repr(self, object, context, level):
--> 431 repr, readable, recursive = self.format(object, context.copy(),
432 self._depth, level)
433 if not readable:
434 self._readable = False
File /opt/conda/lib/python3.9/site-packages/sklearn/utils/_pprint.py:189, in _EstimatorPrettyPrinter.format(self, object, context, maxlevels, level)
188 def format(self, object, context, maxlevels, level):
--> 189 return _safe_repr(
190 object, context, maxlevels, level, changed_only=self._changed_only
191 )
File /opt/conda/lib/python3.9/site-packages/sklearn/utils/_pprint.py:440, in _safe_repr(object, context, maxlevels, level, changed_only)
438 recursive = False
439 if changed_only:
--> 440 params = _changed_params(object)
441 else:
442 params = object.get_params(deep=False)
File /opt/conda/lib/python3.9/site-packages/sklearn/utils/_pprint.py:93, in _changed_params(estimator)
89 def _changed_params(estimator):
90 """Return dict (param_name: value) of parameters that were given to
91 estimator with non-default values."""
---> 93 params = estimator.get_params(deep=False)
94 init_func = getattr(estimator.__init__, "deprecated_original", estimator.__init__)
95 init_params = inspect.signature(init_func).parameters
File /opt/conda/lib/python3.9/site-packages/sklearn/base.py:210, in BaseEstimator.get_params(self, deep)
208 out = dict()
209 for key in self._get_param_names():
--> 210 value = getattr(self, key)
211 if deep and hasattr(value, "get_params"):
212 deep_items = value.get_params().items()
AttributeError: 'TokenCooccurrenceVectorizer' object has no attribute 'coo_initial_memory'
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
File /opt/conda/lib/python3.9/site-packages/IPython/core/formatters.py:707, in PlainTextFormatter.__call__(self, obj)
700 stream = StringIO()
701 printer = pretty.RepresentationPrinter(stream, self.verbose,
702 self.max_width, self.newline,
703 max_seq_length=self.max_seq_length,
704 singleton_pprinters=self.singleton_printers,
705 type_pprinters=self.type_printers,
706 deferred_pprinters=self.deferred_printers)
--> 707 printer.pretty(obj)
708 printer.flush()
709 return stream.getvalue()
File /opt/conda/lib/python3.9/site-packages/IPython/lib/pretty.py:410, in RepresentationPrinter.pretty(self, obj)
407 return meth(obj, self, cycle)
408 if cls is not object \
409 and callable(cls.__dict__.get('__repr__')):
--> 410 return _repr_pprint(obj, self, cycle)
412 return _default_pprint(obj, self, cycle)
413 finally:
File /opt/conda/lib/python3.9/site-packages/IPython/lib/pretty.py:778, in _repr_pprint(obj, p, cycle)
776 """A pprint that just redirects to the normal repr function."""
777 # Find newlines and replace them with p.break_()
--> 778 output = repr(obj)
779 lines = output.splitlines()
780 with p.group():
File /opt/conda/lib/python3.9/site-packages/sklearn/base.py:279, in BaseEstimator.__repr__(self, N_CHAR_MAX)
271 # use ellipsis for sequences with a lot of elements
272 pp = _EstimatorPrettyPrinter(
273 compact=True,
274 indent=1,
275 indent_at_name=True,
276 n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW,
277 )
--> 279 repr_ = pp.pformat(self)
281 # Use bruteforce ellipsis when there are a lot of non-blank characters
282 n_nonblank = len("".join(repr_.split()))
File /opt/conda/lib/python3.9/pprint.py:153, in PrettyPrinter.pformat(self, object)
151 def pformat(self, object):
152 sio = _StringIO()
--> 153 self._format(object, sio, 0, 0, {}, 0)
154 return sio.getvalue()
File /opt/conda/lib/python3.9/pprint.py:170, in PrettyPrinter._format(self, object, stream, indent, allowance, context, level)
168 self._readable = False
169 return
--> 170 rep = self._repr(object, context, level)
171 max_width = self._width - indent - allowance
172 if len(rep) > max_width:
File /opt/conda/lib/python3.9/pprint.py:431, in PrettyPrinter._repr(self, object, context, level)
430 def _repr(self, object, context, level):
--> 431 repr, readable, recursive = self.format(object, context.copy(),
432 self._depth, level)
433 if not readable:
434 self._readable = False
File /opt/conda/lib/python3.9/site-packages/sklearn/utils/_pprint.py:189, in _EstimatorPrettyPrinter.format(self, object, context, maxlevels, level)
188 def format(self, object, context, maxlevels, level):
--> 189 return _safe_repr(
190 object, context, maxlevels, level, changed_only=self._changed_only
191 )
File /opt/conda/lib/python3.9/site-packages/sklearn/utils/_pprint.py:440, in _safe_repr(object, context, maxlevels, level, changed_only)
438 recursive = False
439 if changed_only:
--> 440 params = _changed_params(object)
441 else:
442 params = object.get_params(deep=False)
File /opt/conda/lib/python3.9/site-packages/sklearn/utils/_pprint.py:93, in _changed_params(estimator)
89 def _changed_params(estimator):
90 """Return dict (param_name: value) of parameters that were given to
91 estimator with non-default values."""
---> 93 params = estimator.get_params(deep=False)
94 init_func = getattr(estimator.__init__, "deprecated_original", estimator.__init__)
95 init_params = inspect.signature(init_func).parameters
File /opt/conda/lib/python3.9/site-packages/sklearn/base.py:210, in BaseEstimator.get_params(self, deep)
208 out = dict()
209 for key in self._get_param_names():
--> 210 value = getattr(self, key)
211 if deep and hasattr(value, "get_params"):
212 deep_items = value.get_params().items()
AttributeError: 'TokenCooccurrenceVectorizer' object has no attribute 'coo_initial_memory'
That's definitely a bug. I don't think we've ever explored the sklearn pretty printing of models, so this certainly never came up for us, but I think it should be relatively easy to fix.
I'm going to look into this. I'll submit a PR if I'm able to figure out how to fix it.