def __repr__(self):
"""
Return a string description of the model, including a description of
the training data, training statistics, and model hyper-parameters.
Returns
-------
out : string
A description of the model.
"""
model_fields = [
('Number of coefficients', 'num_coefficients'),
('Number of examples', 'num_examples'),
('Number of feature columns', 'num_features'),
('Number of unpacked features', 'num_unpacked_features')]
hyperparam_fields = [
("L1 penalty", 'l1_penalty'),
("L2 penalty", 'l2_penalty')
]
solver_fields = [
("Solver", 'solver'),
("Solver iterations", 'training_iterations'),
("Solver status", 'training_solver_status'),
("Training time (sec)", 'training_time')]
training_fields = [
("Residual sum of squares", 'training_loss'),
("Training RMSE", 'training_rmse')]
return _toolkit_repr_print(self, [model_fields, hyperparam_fields,
solver_fields, training_fields], width=30)
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, section_titles, width=30)
def __repr__(self):
"""
Print a string description of the model, when the model name is entered
in the terminal.
"""
model_fields = [
('Number of coefficients', 'num_coefficients'),
('Number of examples', 'num_examples'),
('Number of classes', 'num_classes'),
('Number of feature columns', 'num_features'),
('Number of unpacked features', 'num_unpacked_features')]
hyperparam_fields = [
("Mis-classification penalty", 'penalty'),
]
solver_fields = [
("Solver", 'solver'),
("Solver iterations", 'training_iterations'),
("Solver status", 'training_solver_status'),
("Training time (sec)", 'training_time')]
training_fields = [
("Train Loss", 'training_loss')]
return _toolkit_repr_print(self, [model_fields, hyperparam_fields,
solver_fields, training_fields], width=30)
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 __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, section_titles, width=30)
def __repr__(self):
"""
Print a string description of the model, when the model name is entered
in the terminal.
"""
model_fields = [
("Number of coefficients", "num_coefficients"),
("Number of examples", "num_examples"),
("Number of feature columns", "num_features"),
("Number of unpacked features", "num_unpacked_features"),
]
hyperparam_fields = [("L1 penalty", "l1_penalty"), ("L2 penalty", "l2_penalty")]
solver_fields = [
("Solver", "solver"),
("Solver iterations", "training_iterations"),
("Solver status", "training_solver_status"),
("Training time (sec)", "training_time"),
]
training_fields = [("Log-likelihood", "training_loss")]
return _toolkit_repr_print(self, [model_fields, hyperparam_fields, solver_fields, training_fields], width=30)
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 __repr__(self):
"""
Return a string description of the model, including a description of
the training data, training statistics, and model hyper-parameters.
Returns
-------
out : string
A description of the model.
"""
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, section_titles, width=30)
def __repr__(self):
"""
Return a string description of the model, including a description of
the training data, training statistics, and model hyper-parameters.
Returns
-------
out : string
A description of the model.
"""
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, section_titles, width=30)
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 40
sections, section_titles = self._get_summary_struct()
accessible_fields = {
"cluster_id": "Cluster label for each row in the input dataset."
}
out = _toolkit_repr_print(self, sections, section_titles, width=width)
out2 = _summarize_accessible_fields(accessible_fields, width=width)
return out + "\n" + out2
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 36
key_str = "{:<{}}: {}"
(sections, section_titles) = self._get_summary_struct()
accessible_fields = {
"entities": "Consolidated input records plus entity labels."}
out = _toolkit_repr_print(self, sections, section_titles, \
width=width)
out2 = _summarize_accessible_fields(accessible_fields, width=width)
return out + "\n" + out2
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 40
key_str = "{:<{}}: {}"
sections, section_titles = self._get_summary_struct()
accessible_fields = {
"scores": "Anomaly score for each instance in the current dataset."}
out = _tkutl._toolkit_repr_print(self, sections, section_titles,
width=width)
out2 = _summarize_accessible_fields(accessible_fields, width=width)
return out + "\n" + out2
def __repr__(self):
"""
Return a string description of the model, including a description of
the training data, training statistics, and model hyper-parameters.
Returns
-------
out : string
A description of the model.
"""
accessible_fields = {
"vocabulary": "The vocabulary of the trimmed input."
}
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=30)
out2 = _summarize_accessible_fields(accessible_fields, width=30)
return out + "\n" + out2
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 40
key_str = "{:<{}}: {}"
sections, section_titles = self._get_summary_struct()
accessible_fields = {
"scores": "Local outlier factor for each row in the input dataset.",
"nearest_neighbors_model": "Model used internally to compute nearest neighbors."}
out = _tkutl._toolkit_repr_print(self, sections, section_titles,
width=width)
out2 = _summarize_accessible_fields(accessible_fields, width=width)
return out + "\n" + out2
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 36
sections, section_titles = self._get_summary_struct()
accessible_fields = {
"nearest_neighbors_model":
"Model used internally to compute nearest neighbors."
}
out = _tkutl._toolkit_repr_print(self,
sections,
section_titles,
width=width)
out2 = _summarize_accessible_fields(accessible_fields, width=width)
return out + "\n" + out2
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 36
key_str = "{:<{}}: {}"
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, \
width=width)
extra = []
extra.append(key_str.format("Accessible fields", width, ""))
extra.append(key_str.format(" entities", width,
"Consolidated input records plus entity labels."))
return out + '\n' + '\n'.join(extra)
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__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 32
key_str = "{:<{}}: {}"
(sections, section_titles) = self._get_summary_struct()
accessible_fields = {
"cluster_id": "An SFrame containing the cluster assignments.",
"cluster_info": "An SFrame containing the cluster centers."}
out = _tkutl._toolkit_repr_print(self, sections, section_titles,
width=width)
out2 = _summarize_accessible_fields(accessible_fields, width=width)
return out + "\n" + out2
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 32
key_str = "{:<{}}: {}"
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=width)
extra = []
extra.append(key_str.format("Accessible fields", width, ""))
extra.append(key_str.format(" cluster_id", width, "An SFrame containing the cluster assignments."))
extra.append(key_str.format(" cluster_info", width, "An SFrame containing the cluster centers."))
return out + '\n' + '\n'.join(extra)
def __repr__(self):
"""
Print a string description of the model, when the model name is entered
in the terminal.
"""
data_fields = [
('Number of examples', 'num_examples'),
('Number of feature columns', 'num_features'),
('Number of unpacked features', 'num_unpacked_features')]
training_fields = [
("Number of trees", 'num_trees'),
("Max tree depth", 'max_depth'),
("Train RMSE", 'training_rmse'),
("Validation RMSE", 'validation_rmse'),
("Training time (sec)", 'training_time')]
return _toolkit_repr_print(self, [data_fields, training_fields], width=30)
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
key_str = "{:<{}}: {}"
width = 30
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=width)
extra = []
extra.append(key_str.format("Accessible fields", width, ""))
extra.append(key_str.format("m['topics']",width,"An SFrame containing the topics."))
extra.append(key_str.format("m['vocabulary']",width,"An SArray containing the words in the vocabulary."))
extra.append(key_str.format("Useful methods", width, ""))
extra.append(key_str.format("m.get_topics()",width,"Get the most probable words per topic."))
extra.append(key_str.format("m.predict(new_docs)",width,"Make predictions for new documents."))
return out + '\n' + '\n'.join(extra)
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 40
key_str = "{:<{}}: {}"
sections, section_titles = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=width)
extra = []
extra.append("Accessible fields")
extra.append("-" * len("Accessible fields"))
extra.append(key_str.format(" cluster_id", width,
"Cluster label for each row in the input dataset."))
return out + "\n" + "\n".join(extra)
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
key_str = "{:<{}}: {}"
width = 30
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=width)
extra = []
extra.append(key_str.format("Accessible fields", width, ""))
extra.append(key_str.format("m['topics']",width,"An SFrame containing the topics."))
extra.append(key_str.format("m['vocabulary']",width,"An SArray containing the words in the vocabulary."))
extra.append(key_str.format("Useful methods", width, ""))
extra.append(key_str.format("m.get_topics()",width,"Get the most probable words per topic."))
extra.append(key_str.format("m.predict(new_docs)",width,"Make predictions for new documents."))
return out + '\n' + '\n'.join(extra)
def __repr__(self):
"""
Print a string description of the model, when the model name is entered
in the terminal.
"""
data_fields = [
("Examples", 'num_examples'),
("Features", 'num_features'),
("Target column", 'target')]
metric_key = 'metric'
if not metric_key in self.list_fields():
metric_key = 'metrics'
metrics = self.get(metric_key).split(',')
training_fields = []
for m in metrics:
training_fields.append(('Training %s' % m, 'training_%s' % m))
training_fields.append(('Validation %s' % m, 'validation_%s' % m))
training_fields.append(("Training time (sec)", 'training_time'))
return _toolkit_repr_print(self, [data_fields, training_fields])
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
model_fields = [
("Distance", 'distance'),
("Method", 'method'),
("Number of examples", 'num_examples'),
("Number of feature columns", 'num_features'),
("Number of unpacked features", 'num_unpacked_features'),
("Total training time (seconds)", 'training_time')]
ball_tree_fields = [
("Tree depth", 'tree_depth'),
("Leaf size", 'leaf_size')]
out = [model_fields]
if self.get('method') == 'ball tree':
out += [ball_tree_fields]
return _tkutl._toolkit_repr_print(self, out, width=30)
def __repr__(self):
"""
Print a string description of the model when the model name is entered
in the terminal.
"""
width = 30
key_str = "{:<{}}: {}"
model_fields = [
('Total training time (seconds)', 'training_time'),
('Number of clusters', 'num_clusters'),
('Number of training iterations', 'training_iterations'),
('Number of examples', 'num_examples'),
('Number of feature columns', 'num_features'),
('Number of unpacked features', 'num_unpacked_features')]
out = [_toolkit_repr_print(self, [model_fields], width=width)]
out.append(key_str.format("Accessible fields", width, ""))
out.append(key_str.format(" cluster_id", width, "An SFrame containing the cluster assignments."))
out.append(key_str.format(" cluster_info", width, "An SFrame containing the cluster centers."))
return '\n'.join(out)
def __repr__(self):
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, section_titles, width=30)
def __repr__(self):
width = 32
key_str = "{:<{}}: {}"
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=width)
return out
def __repr__(self):
width = 32
key_str = "{:<{}}: {}"
(sections, section_titles) = self._get_summary_struct()
out = _toolkit_repr_print(self, sections, section_titles, width=width)
return out
def __repr__(self):
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, section_titles, width= 30)
def __repr__(self):
"""
Return a string description of the transform.
"""
(sections, section_titles) = self._get_summary_struct()
return _toolkit_repr_print(self, sections, 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'])