def _get_summary_struct(self):
"""
Returns a structured description of the model, including (where relevant)
the schema of the training data, description of the training data,
training statistics, and model hyperparameters.
Returns
-------
sections : list (of list of tuples)
A list of summary sections.
Each section is a list.
Each item in a section list is a tuple of the form:
('<label>','<field>')
section_titles: list
A list of section titles.
The order matches that of the 'sections' object.
"""
_features = _precomputed_field(
_internal_utils.pretty_print_list(self.get('features')))
_exclude = _precomputed_field(
_internal_utils.pretty_print_list(self.get('excluded_features')))
fields = [
("Features", _features),
("Excluded features", _exclude),
("Output column name", 'output_column_name'),
("Max categories per column", 'max_categories'),
]
section_titles = ['Model fields']
return ([fields], section_titles)
def _get_summary_struct(self):
_features = _precomputed_field(
_internal_utils.pretty_print_list(self.get('features')))
_exclude = _precomputed_field(
_internal_utils.pretty_print_list(self.get('excluded_features')))
fields = [
("Features", _features),
("Excluded features", _exclude),
]
section_titles = ['Model fields']
return ([fields], section_titles)
def _get_summary_struct(self):
"""
Returns a structured description of the model, including (where relevant)
the schema of the training data, description of the training data,
training statistics, and model hyperparameters.
Returns
-------
sections : list (of list of tuples)
A list of summary sections.
Each section is a list.
Each item in a section list is a tuple of the form:
('<feature>','<field>')
section_titles: list
A list of section titles.
The order matches that of the 'sections' object.
"""
_reference_features = _precomputed_field(
_internal_utils.pretty_print_list(self.get('reference_features')))
fields = [
("reference_features", _reference_features),
("Column to impute", 'feature')
]
section_titles = ['Model fields']
return ([fields], section_titles)
def _get_summary_struct(self):
"""
Returns a structured description of the model, including (where relevant)
the schema of the training data, description of the training data,
training statistics, and model hyperparameters.
Returns
-------
sections : list (of list of tuples)
A list of summary sections.
Each section is a list.
Each item in a section list is a tuple of the form:
('<label>','<field>')
section_titles: list
A list of section titles.
The order matches that of the 'sections' object.
"""
_features = _precomputed_field(_internal_utils.pretty_print_list(self.get("features")))
fields = [
("Features", _features),
("Convert strings to lower case", "to_lower"),
("Delimiters", "delimiters"),
("Output column prefix", "output_column_prefix"),
]
section_titles = ["Model fields"]
return ([fields], section_titles)
def _get_summary_struct(self):
_features = _precomputed_field(_internal_utils.pretty_print_list(self.get("features")))
fields = [
("Features", _features),
("Minimimum Document Frequency", "min_document_frequency"),
("Maximimum Document Frequency", "max_document_frequency"),
("Output Column Name", "output_column_name"),
]
section_titles = ["Model fields"]
return ([fields], section_titles)
def _get_summary_struct(self):
_features = _precomputed_field(
_internal_utils.pretty_print_list(self.get('features')))
fields = [
("Features", _features),
("Convert strings to lower case", 'to_lower'),
("Delimiters", "delimiters"),
("Output column prefix", 'output_column_prefix')
]
section_titles = ['Model fields']
return ([fields], section_titles)
def _get_summary_struct(self):
_features = _precomputed_field(
_internal_utils.pretty_print_list(self.get('features')))
fields = [
("Features", _features),
("query", 'query'),
("k1", 'k1'),
("b", 'b'),
("Minimimum Document Frequency", 'min_document_frequency'),
("Maximimum Document Frequency", 'max_document_frequency'),
("Output Column Name", 'output_column_name')
]
section_titles = ['Model fields']
return ([fields], section_titles)
def _get_summary_struct(self):
_features = _precomputed_field(
_internal_utils.pretty_print_list(self.get('features')))
fields = [
("NGram length", 'n'),
("NGram type (word or character)", 'ngram_type'),
("Convert strings to lower case", 'to_lower'),
("Ignore punctuation in character ngram", 'ignore_punct'),
("Ignore space in character ngram", 'ignore_space'),
("Delimiters", "delimiters"),
("Features", _features),
("Output column prefix", 'output_column_prefix')
]
section_titles = ['Model fields']
return ([fields], section_titles)
def _compact_class_repr(obj):
""" A compact version of __repr__ for each of the steps.
"""
dict_str_list = []
post_repr_string = ""
# If features are present, then shorten it.
fields = _inspect.getargspec(obj.__init__.im_func).args
fields = fields[1:] # remove self
if 'features' in fields:
fields.remove('features')
features = obj.get("features")
if features != None:
post_repr_string = ' on %s feature(s)' % len(features)
if 'excluded_features' in fields:
fields.remove('excluded_features')
# GLC transformers.
if issubclass(obj.__class__, _Transformer):
for attr in fields:
dict_str_list.append("%s=%s" % (attr, obj.get(attr).__repr__()))
# Chains
elif obj.__class__ == TransformerChain:
_step_classes = map(lambda x: x.__class__.__name__, obj.get('steps'))
_steps = _internal_utils.pretty_print_list(
_step_classes, 'steps', False)
dict_str_list.append(_steps)
# For user defined transformers.
else:
for attr in fields:
dict_str_list.append("%s=%s" % (attr, obj.__dict__[attr]))
return "%s(%s)%s" % (obj.__class__.__name__, ", ".join(dict_str_list),
post_repr_string)
