def python(self, out, docstring, input_map=False):
"""Writes a python function that implements the model.
"""
args = []
parameters = sort_fields(self.fields)
if not input_map:
input_map = len(parameters) > MAX_ARGS_LENGTH
reserved_keywords = keyword.kwlist if not input_map else None
prefix = "_" if not input_map else ""
for field in [(key, val) for key, val in parameters]:
slug = slugify(self.fields[field[0]]['name'],
reserved_keywords=reserved_keywords, prefix=prefix)
self.fields[field[0]].update(slug=slug)
if not input_map:
if field[0] != self.objective_field:
args.append("%s=None" % (slug))
if input_map:
args.append("data={}")
predictor_definition = (u"def predict_%s" %
self.fields[self.objective_field]['slug'])
depth = len(predictor_definition) + 1
predictor = u"%s(%s):\n" % (predictor_definition,
(",\n" + " " * depth).join(args))
predictor_doc = (INDENT + u"\"\"\" " + docstring +
u"\n" + INDENT + u"\"\"\"\n")
body, term_analysis_predicates = self.python_body(input_map=input_map)
terms_body = ""
if term_analysis_predicates:
terms_body = self.term_analysis_body(term_analysis_predicates)
predictor += predictor_doc + terms_body + body
out.write(utf8(predictor))
out.flush()
def python(self, out, docstring, input_map=False):
"""Writes a python function that implements the model.
"""
args = []
parameters = sort_fields(self.fields)
if not input_map:
input_map = len(parameters) > MAX_ARGS_LENGTH
for field in [(key, val) for key, val in parameters]:
slug = slugify(self.fields[field[0]]['name'])
self.fields[field[0]].update(slug=slug)
if not input_map:
if field[0] != self.objective_field:
args.append("%s=None" % (slug))
if input_map:
args.append("data={}")
predictor_definition = (u"def predict_%s" %
self.fields[self.objective_field]['slug'])
depth = len(predictor_definition) + 1
predictor = u"%s(%s):\n" % (predictor_definition,
(",\n" + " " * depth).join(args))
predictor_doc = (INDENT + u"\"\"\" " + docstring +
u"\n" + INDENT + u"\"\"\"\n")
predictor += predictor_doc + self.python_body(input_map=input_map)
out.write(utf8(predictor))
out.flush()
def python(self, out, docstring, input_map=False):
"""Writes a python function that implements the model.
"""
args = []
parameters = sort_fields(self.fields)
if not input_map:
input_map = len(parameters) > MAX_ARGS_LENGTH
for field in [(key, val) for key, val in parameters]:
slug = slugify(self.fields[field[0]]['name'])
self.fields[field[0]].update(slug=slug)
if not input_map:
if field[0] != self.objective_field:
args.append("%s=None" % (slug))
if input_map:
args.append("data={}")
predictor_definition = (u"def predict_%s" %
self.fields[self.objective_field]['slug'])
depth = len(predictor_definition) + 1
predictor = u"%s(%s):\n" % (predictor_definition,
(",\n" + " " * depth).join(args))
predictor_doc = (INDENT + u"\"\"\" " + docstring +
u"\n" + INDENT + u"\"\"\"\n")
predictor += predictor_doc + self.python_body(input_map=input_map)
out.write(utf8(predictor))
out.flush()
def python(self, out, docstring, input_map=False):
"""Writes a python function that implements the model.
"""
args = []
parameters = sort_fields(self.fields)
if not input_map:
input_map = len(parameters) > MAX_ARGS_LENGTH
reserved_keywords = keyword.kwlist if not input_map else None
prefix = "_" if not input_map else ""
for field in [(key, val) for key, val in parameters]:
slug = slugify(self.fields[field[0]]['name'],
reserved_keywords=reserved_keywords,
prefix=prefix)
self.fields[field[0]].update(slug=slug)
if not input_map:
if field[0] != self.objective_field:
args.append("%s=None" % (slug))
if input_map:
args.append("data={}")
predictor_definition = (u"def predict_%s" %
self.fields[self.objective_field]['slug'])
depth = len(predictor_definition) + 1
predictor = u"%s(%s):\n" % (predictor_definition,
(",\n" + " " * depth).join(args))
predictor_doc = (INDENT + u"\"\"\" " + docstring + u"\n" + INDENT +
u"\"\"\"\n")
body, term_analysis_predicates = self.python_body(input_map=input_map)
terms_body = ""
if term_analysis_predicates:
terms_body = self.term_analysis_body(term_analysis_predicates)
predictor += predictor_doc + terms_body + body
out.write(utf8(predictor))
out.flush()
def list_fields(self, out):
"""Lists a description of the model's fields.
"""
for field in [(val['name'], val['optype']) for _, val in
sort_fields(self.fields)]:
out.write(utf8(u'[%-32s : %s]\n' % (field[0], field[1])))
out.flush()
return self.fields
def rules(self, out):
"""Prints out an IF-THEN rule version of the tree.
"""
for field in [(key, val) for key, val in sort_fields(self.fields)]:
slug = slugify(self.fields[field[0]]['name'])
self.fields[field[0]].update(slug=slug)
out.write(utf8(self.generate_rules()))
out.flush()
def rules(self, out):
"""Prints out an IF-THEN rule version of the tree.
"""
for field in [(key, val) for key, val in sort_fields(self.fields)]:
slug = slugify(self.fields[field[0]]['name'])
self.fields[field[0]].update(slug=slug)
out.write(utf8(self.generate_rules()))
out.flush()
def list_fields(self, out):
"""Lists a description of the model's fields.
"""
out.write(utf8(u'<%-32s : %s>\n' % (
self.fields[self.objective_id]['name'],
self.fields[self.objective_id]['optype'])))
out.flush()
for field in [(val['name'], val['optype']) for key, val in
sort_fields(self.fields)
if key != self.objective_id]:
out.write(utf8(u'[%-32s : %s]\n' % (field[0], field[1])))
out.flush()
return self.fields
def list_fields(self, out):
"""Lists a description of the model's fields.
"""
out.write(utf8(u'<%-32s : %s>\n' % (
self.fields[self.objective_field]['name'],
self.fields[self.objective_field]['optype'])))
out.flush()
for field in [(val['name'], val['optype']) for key, val in
sort_fields(self.fields)
if key != self.objective_field]:
out.write(utf8(u'[%-32s : %s]\n' % (field[0], field[1])))
out.flush()
return self.fields
def get_features(self):
"""
Parse the BigML tree model to get all the features
"""
features = []
tree = self.model.tree
for key, val in util.sort_fields(tree.fields):
if key and key != tree.objective_id:
ftype = str(val['optype'])
if ftype == "numeric":
features.append(ContFeature(str(val['name']), key,
val['summary']['minimum'],
val['summary']['maximum']))
elif ftype == "categorical":
categories = sorted([str(name) for (name, _)
in val['summary']['categories']])
features.append(CatFeature(str(val['name']), key,
list(categories)))
else:
raise ValueError("Unknown feature type {}".format(ftype))
return features
def get_features(self):
"""
Parse the BigML tree model to get all the features
"""
features = []
tree = self.model.tree
for key, val in util.sort_fields(tree.fields):
if key and key != tree.objective_id:
ftype = str(val['optype'])
if ftype == "numeric":
features.append(
ContFeature(str(val['name']), key,
val['summary']['minimum'],
val['summary']['maximum']))
elif ftype == "categorical":
categories = sorted([
str(name) for (name, _) in val['summary']['categories']
])
features.append(
CatFeature(str(val['name']), key, list(categories)))
else:
raise ValueError("Unknown feature type {}".format(ftype))
return features
def get_classes(self):
tree = self.model.tree
for key, val in util.sort_fields(tree.fields):
if key == tree.objective_id:
return [str(x[0]) for x in val['summary']['categories']]
def get_classes(self):
tree = self.model.tree
for key, val in util.sort_fields(tree.fields):
if key == tree.objective_id:
return [str(x[0]) for x in val['summary']['categories']]
