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')))
_stopwords = _precomputed_field(
_internal_utils.pretty_print_list(self.get('stopwords')))
fields = [("Features", _features), ("Excluded features", _exclude),
("Output column name", 'output_column_prefix'),
("Word count threshold", 'threshold'),
("Manually specified stopwords", _stopwords),
("Whether to convert to lowercase", "to_lower"),
("Delimiters", "delimiters")]
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')))
_exclude = _precomputed_field(
_internal_utils.pretty_print_list(self.get('excluded_features')))
fields = [("Features", _features), ("Excluded features", _exclude),
("Output column name", 'output_column_name'),
("Number of bits", 'num_bits')]
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')))
_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):
"""
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.
"""
section_titles = ["Schema", "Settings"]
vocab_length = len(self.get("vocabulary"))
num_topics = len(self.get("topics"))
verbose = self.get("verbose") == 1
sections = [
[("Vocabulary Size", _precomputed_field(vocab_length)), ("Topic Size", _precomputed_field(num_topics))],
[
("Number of Topics", "num_topics"),
("alpha", "alpha"),
("beta", "beta"),
("Iterations", "num_iterations"),
("Training time", "training_time"),
("Verbose", _precomputed_field(verbose)),
],
]
return (sections, 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')))
_exclude = _precomputed_field(
_internal_utils.pretty_print_list(self.get('excluded_features')))
fields = [
("Target", "target"),
("Features", _features),
("Excluded features", _exclude),
("Number of bits", 'num_bits'),
("Random seed", 'random_seed'),
("Laplace Smearing", 'laplace_smearing'),
("Count Column Prefix", 'count_column_prefix'),
("Probability Column Prefix", 'prob_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')))
_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):
_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):
_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),
("Separator", "separator"),
("None Tag", "none_tag"),
("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')))
_exclude = _precomputed_field(
_internal_utils.pretty_print_list(self.get('excluded_features')))
fields = [
("Features", _features),
("Excluded_features", _exclude),
("Chosen parts of speech", 'chosen_pos'),
("Output column prefix", 'output_column_prefix'),
]
section_titles = ['Model fields']
return ([fields], section_titles)
def __repr__(steps):
for name, tr in self._transformers:
model_fields.append(
(name, _precomputed_field(self._compact_class_repr(tr))))
return _toolkit_repr_print(steps, [model_fields],
width=8,
section_titles=['Steps'])
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.
"""
fields = [
("Min support", 'min_support'),
("Max patterns", 'max_patterns'),
("Min pattern length", 'min_length'),
]
patterns_sf = self.get('frequent_patterns').topk('support')
patterns = [(p['pattern'], _precomputed_field(p['support']))
for p in patterns_sf]
section_titles = ['Model fields', 'Most frequent patterns']
return ([fields, patterns], section_titles)
def _get_summary_struct(self):
model_fields = []
for attr in self.__dict__:
if not attr.startswith('_'):
model_fields.append((attr, _precomputed_field(getattr(self, attr))))
return ([model_fields], ['Attributes'] )
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.
"""
fields = [
("Min support", 'min_support'),
("Max patterns", 'max_patterns'),
("Min pattern length", 'min_length'),
]
patterns_sf = self.get('frequent_patterns').topk('support')
patterns = [(p['pattern'], _precomputed_field(p['support']))
for p in patterns_sf]
section_titles = ['Model fields', 'Most frequent patterns']
return ([fields, patterns], 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):
model_fields = []
for attr in self.__dict__:
if not attr.startswith('_'):
model_fields.append(
(attr, _precomputed_field(getattr(self, attr))))
return ([model_fields], ['Attributes'])
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):
"""
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.
"""
g = self['graph']
section_titles = ['Graph']
graph_summary = [(k, _precomputed_field(v))
for k, v in six.iteritems(g.summary())]
sections = [graph_summary]
# collect other sections
results = [(k, _precomputed_field(v))
for k, v in six.iteritems(self._result_fields())]
methods = [(k, _precomputed_field(v))
for k, v in six.iteritems(self._method_fields())]
settings = [(k, v) for k, v in six.iteritems(self._setting_fields())]
metrics = [(k, v) for k, v in six.iteritems(self._metric_fields())]
optional_sections = [('Results', results), ('Settings', settings), \
('Metrics', metrics), ('Methods', methods)]
# if section is not empty, append to summary structure
for (title, section) in optional_sections:
if len(section) > 0:
section_titles.append(title)
sections.append(section)
return (sections, section_titles)
def _get_struct_summary(self):
model_fields = []
for name, tr in self._transformers:
model_fields.append((name,
_precomputed_field(self._compact_class_repr(tr))))
sections = [model_fields]
section_titles = ['Steps']
return (sections, 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_struct_summary(self):
model_fields = []
for name, tr in self._transformers:
model_fields.append(
(name, _precomputed_field(self._compact_class_repr(tr))))
sections = [model_fields]
section_titles = ['Steps']
return (sections, 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),
("Minimimum Document Frequency", 'min_document_frequency'),
("Maximimum Document Frequency", 'max_document_frequency'),
("Output Column Prefix", 'output_column_prefix')
]
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.
"""
g = self['graph']
section_titles = ['Graph']
graph_summary = [(k, _precomputed_field(v)) for k, v in g.summary().iteritems()]
sections = [graph_summary]
# collect other sections
results = [(k, _precomputed_field(v)) for k, v in self._result_fields().iteritems()]
methods = [(k, _precomputed_field(v)) for k, v in self._method_fields().iteritems()]
settings = [(k, v) for k, v in self._setting_fields().iteritems()]
metrics = [(k, v) for k, v in self._metric_fields().iteritems()]
optional_sections = [('Results', results), ('Settings', settings), \
('Metrics', metrics), ('Methods', methods)]
# if section is not empty, append to summary structure
for (title, section) in optional_sections:
if len(section) > 0:
section_titles.append(title)
sections.append(section)
return (sections, section_titles)
def __repr__(self):
descriptions = [(k, _precomputed_field(v)) for k, v in self._describe_fields().iteritems()]
(sections, section_titles) = self._get_summary_struct()
non_empty_sections = [s for s in sections if len(s) > 0]
non_empty_section_titles = [section_titles[i] for i in range(len(sections)) if len(sections[i]) > 0]
non_empty_section_titles.append('Queryable Fields')
non_empty_sections.append(descriptions)
return _toolkit_repr_print(self, non_empty_sections, non_empty_section_titles, width=40)
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.
"""
section_titles=['Schema','Settings']
vocab_length = len(self.get('vocabulary'))
num_topics = len(self.get('topics'))
verbose = self.get('verbose') == 1
sections=[
[
('Vocabulary Size',_precomputed_field(vocab_length)),
('Topic Size', _precomputed_field(num_topics))
],
[
('Number of Topics', 'num_topics'),
('alpha','alpha'),
('beta','beta'),
('Iterations', 'num_iterations'),
('Training time', 'training_time'),
('Verbose', _precomputed_field(verbose))
]
]
return (sections, 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 _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.
"""
section_titles=['Schema','Settings']
vocab_length = len(self.get('vocabulary'))
verbose = self.get('verbose') == 1
sections=[
[
('Vocabulary Size',_precomputed_field(vocab_length))
],
[
('Number of Topics', 'num_topics'),
('alpha','alpha'),
('beta','beta'),
('Iterations', 'num_iterations'),
('Training time', 'training_time'),
('Verbose', _precomputed_field(verbose))
]
]
return (sections, 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 __repr__(self):
descriptions = [(k, _precomputed_field(v))
for k, v in six.iteritems(self._describe_fields())]
(sections, section_titles) = self._get_summary_struct()
non_empty_sections = [s for s in sections if len(s) > 0]
non_empty_section_titles = [
section_titles[i] for i in range(len(sections))
if len(sections[i]) > 0
]
non_empty_section_titles.append('Queryable Fields')
non_empty_sections.append(descriptions)
return _toolkit_repr_print(self,
non_empty_sections,
non_empty_section_titles,
width=40)
def __repr__(steps):
for name, tr in self._transformers:
model_fields.append((name,
_precomputed_field(self._compact_class_repr(tr))))
return _toolkit_repr_print(steps, [model_fields], width=8,
section_titles = ['Steps'])
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.
"""
sections = []
fields = []
_features = _precomputed_field(
_internal_utils.pretty_print_list(self.features))
_exclude = _precomputed_field(
_internal_utils.pretty_print_list(self.excluded_features))
header_fields = [("Features", "features"),
("Excluded Features", "excluded_features")]
sections.append("Model Fields")
fields.append(header_fields)
if self.user_column_interpretations:
sections.append("User Specified Interpretations")
fields.append(
list(sorted(self.get("user_column_interpretations").items())))
column_interpretations = self.get("column_interpretations")
features = self.get("features")
if self.get("fitted") and features is not None:
n_rows = len(features)
transform_info = [None] * n_rows
for i, f in enumerate(features):
interpretation = column_interpretations[f]
input_type = self.input_types[f]
description, output_type = _get_interpretation_description_and_output_type(
interpretation, input_type)
transform_info[i] = (f, input_type.__name__, interpretation,
description, output_type.__name__)
transform_table = _SFrame()
transform_table["Column"] = [t[0] for t in transform_info]
transform_table["Type"] = [t[1] for t in transform_info]
transform_table["Interpretation"] = [t[2] for t in transform_info]
transform_table["Transforms"] = [t[3] for t in transform_info]
transform_table["Output Type"] = [t[4] for t in transform_info]
fields[-1].append(transform_table)
return fields, sections
