Python BigML.error_message方法代码示例

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, anomaly, api=None):

        self.resource_id = None
        self.sample_size = None
        self.input_fields = None
        self.mean_depth = None
        self.expected_mean_depth = None
        self.iforest = None
        self.top_anomalies = None
        self.id_fields = []
        if not (isinstance(anomaly, dict) and 'resource' in anomaly and
                anomaly['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_anomaly_id(anomaly)
            if self.resource_id is None:
                raise Exception(api.error_message(anomaly,
                                                  resource_type='anomaly',
                                                  method='get'))
            query_string = ONLY_MODEL
            anomaly = retrieve_resource(api, self.resource_id,
                                        query_string=query_string)
        else:
            self.resource_id = get_anomaly_id(anomaly)
        if 'object' in anomaly and isinstance(anomaly['object'], dict):
            anomaly = anomaly['object']
            self.sample_size = anomaly.get('sample_size')
            self.input_fields = anomaly.get('input_fields')
            self.id_fields = anomaly.get('id_fields', [])
        if 'model' in anomaly and isinstance(anomaly['model'], dict):
            ModelFields.__init__(self, anomaly['model'].get('fields'))
            if ('top_anomalies' in anomaly['model'] and
                    isinstance(anomaly['model']['top_anomalies'], list)):
                self.mean_depth = anomaly['model'].get('mean_depth')
                status = get_status(anomaly)
                if 'code' in status and status['code'] == FINISHED:
                    self.expected_mean_depth = None
                    if self.mean_depth is None or self.sample_size is None:
                        raise Exception("The anomaly data is not complete. "
                                        "Score will"
                                        " not be available")
                    else:
                        default_depth = (
                            2 * (DEPTH_FACTOR + \
                            math.log(self.sample_size - 1) - \
                            (float(self.sample_size - 1) / self.sample_size)))
                        self.expected_mean_depth = min(self.mean_depth,
                                                       default_depth)
                    iforest = anomaly['model'].get('trees', [])
                    if iforest:
                        self.iforest = [
                            AnomalyTree(anomaly_tree['root'], self.fields)
                            for anomaly_tree in iforest]
                    self.top_anomalies = anomaly['model']['top_anomalies']
                else:
                    raise Exception("The anomaly isn't finished yet")
            else:
                raise Exception("Cannot create the Anomaly instance. Could not"
                                " find the 'top_anomalies' key in the"
                                " resource:\n\n%s" % anomaly['model'].keys())

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
def get_resource_dict(resource, resource_type, api=None):
    """Extracting the resource JSON info as a dict from the first argument of
       the local object constructors, that can be:

        - the path to a file that contains the JSON
        - the ID of the resource
        - the resource dict itself

    """
    if api is None:
        api = BigML(storage=STORAGE)
    get_id = ID_GETTERS[resource_type]
    resource_id = None
    # the string can be a path to a JSON file
    if isinstance(resource, basestring):
        try:
            with open(resource) as resource_file:
                resource = json.load(resource_file)
                resource_id = get_id(resource)
                if resource_id is None:
                    raise ValueError("The JSON file does not seem"
                                     " to contain a valid BigML %s"
                                     " representation." % resource_type)
        except IOError:
            # if it is not a path, it can be a model id
            resource_id = get_id(resource)
            if resource_id is None:
                if resource.find("%s/" % resource_type) > -1:
                    raise Exception(
                        api.error_message(resource,
                                          resource_type=resource_type,
                                          method="get"))
                else:
                    raise IOError("Failed to open the expected JSON file"
                                  " at %s." % resource)
        except ValueError:
            raise ValueError("Failed to interpret %s."
                             " JSON file expected." % resource)

    # checks whether the information needed for local predictions is in
    # the first argument
    if isinstance(resource, dict) and \
            not check_model_fields(resource):
        # if the fields used by the model are not
        # available, use only ID to retrieve it again
        resource = get_id(resource)
        resource_id = resource

    if not (isinstance(resource, dict) and 'resource' in resource and
            resource['resource'] is not None):
        query_string = ONLY_MODEL
        resource = retrieve_resource(api, resource_id,
                                     query_string=query_string)
    else:
        resource_id = get_id(resource)

    return resource_id, resource

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, model, api=None):

        if check_model_structure(model):
            self.resource_id = model["resource"]
        else:
            # If only the model id is provided, the short version of the model
            # resource is used to build a basic summary of the model
            if api is None:
                api = BigML()
            self.resource_id = get_model_id(model)
            if self.resource_id is None:
                raise Exception(api.error_message(model, resource_type="model", method="get"))
            query_string = ONLY_MODEL
            model = retrieve_resource(api, self.resource_id, query_string=query_string)
            # Stored copies of the model structure might lack some necessary
            # keys
            if not check_model_structure(model):
                model = api.get_model(self.resource_id, query_string=query_string)

        if "object" in model and isinstance(model["object"], dict):
            model = model["object"]

        if "model" in model and isinstance(model["model"], dict):
            status = get_status(model)
            if "code" in status and status["code"] == FINISHED:
                if "model_fields" in model["model"] or "fields" in model["model"]:
                    fields = model["model"].get("model_fields", model["model"].get("fields", []))
                    # pagination or exclusion might cause a field not to
                    # be in available fields dict
                    if not all(key in model["model"]["fields"] for key in fields.keys()):
                        raise Exception(
                            "Some fields are missing"
                            " to generate a local model."
                            " Please, provide a model with"
                            " the complete list of fields."
                        )
                    for field in fields:
                        field_info = model["model"]["fields"][field]
                        if "summary" in field_info:
                            fields[field]["summary"] = field_info["summary"]
                        fields[field]["name"] = field_info["name"]
                objective_field = model["objective_fields"]
                ModelFields.__init__(self, fields, objective_id=extract_objective(objective_field))
                self.description = model["description"]
                self.field_importance = model["model"].get("importance", None)
                if self.field_importance:
                    self.field_importance = [element for element in self.field_importance if element[0] in fields]
                self.locale = model.get("locale", DEFAULT_LOCALE)

            else:
                raise Exception("The model isn't finished yet")
        else:
            raise Exception(
                "Cannot create the BaseModel instance. Could not" " find the 'model' key in the resource:\n\n%s" % model
            )

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, cluster, api=None):

        if not (isinstance(cluster, dict) and 'resource' in cluster and
                cluster['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_cluster_id(cluster)
            if self.resource_id is None:
                raise Exception(api.error_message(cluster,
                                                  resource_type='cluster',
                                                  method='get'))
            query_string = ONLY_MODEL
            cluster = retrieve_resource(api, self.resource_id,
                                        query_string=query_string)
        if 'object' in cluster and isinstance(cluster['object'], dict):
            cluster = cluster['object']

        if 'clusters' in cluster and isinstance(cluster['clusters'], dict):
            status = get_status(cluster)
            if 'code' in status and status['code'] == FINISHED:
                clusters = cluster['clusters']['clusters']
                self.centroids = [Centroid(centroid) for centroid in clusters]
                self.scales = {}
                self.scales.update(cluster['scales'])
                self.term_forms = {}
                self.tag_clouds = {}
                self.term_analysis = {}
                fields = cluster['clusters']['fields']
                for field_id, field in fields.items():
                    if field['optype'] == 'text':

                        self.term_forms[field_id] = {}
                        self.term_forms[field_id].update(field[
                            'summary']['term_forms'])
                        self.tag_clouds[field_id] = {}
                        self.tag_clouds[field_id].update(field[
                            'summary']['tag_cloud'])
                        self.term_analysis[field_id] = {}
                        self.term_analysis[field_id].update(
                            field['term_analysis'])
                ModelFields.__init__(self, fields)
                if not all([field_id in self.fields for
                            field_id in self.scales]):
                    raise Exception("Some fields are missing"
                                    " to generate a local cluster."
                                    " Please, provide a cluster with"
                                    " the complete list of fields.")
            else:
                raise Exception("The cluster isn't finished yet")
        else:
            raise Exception("Cannot create the Cluster instance. Could not"
                            " find the 'clusters' key in the resource:\n\n%s" %
                            cluster)

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, model, api=None):

        if not (isinstance(model, dict) and 'resource' in model and
                model['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_model_id(model)
            if self.resource_id is None:
                raise Exception(api.error_message(model,
                                                  resource_type='model',
                                                  method='get'))
            query_string = ONLY_MODEL
            model = retrieve_model(api, self.resource_id,
                                   query_string=query_string)
        BaseModel.__init__(self, model, api=api)
        if ('object' in model and isinstance(model['object'], dict)):
            model = model['object']

        if ('model' in model and isinstance(model['model'], dict)):
            status = get_status(model)
            if ('code' in status and status['code'] == FINISHED):
                distribution = model['model']['distribution']['training']
                self.ids_map = {}
                self.tree = Tree(
                    model['model']['root'],
                    self.fields,
                    objective_field=self.objective_field,
                    root_distribution=distribution,
                    parent_id=None,
                    ids_map=self.ids_map)
                self.terms = {}
            else:
                raise Exception("The model isn't finished yet")
        else:
            raise Exception("Cannot create the Model instance. Could not"
                            " find the 'model' key in the resource:\n\n%s" %
                            model)
        if self.tree.regression:
            try:
                import numpy
                import scipy
                self.regression_ready = True
            except ImportError:
                self.regression_ready = False

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, time_series, api=None):

        self.resource_id = None
        self.input_fields = []
        self.objective_fields = []
        self.all_numeric_objectives = False
        self.period = 1
        self.ets_models = {}
        self.error = None
        self.damped_trend = None
        self.seasonality = None
        self.trend = None
        self.time_range = {}
        self.field_parameters = {}
        self._forecast = []

        # checks whether the information needed for local predictions is in
        # the first argument
        if isinstance(time_series, dict) and \
                not check_model_fields(time_series):
            # if the fields used by the logistic regression are not
            # available, use only ID to retrieve it again
            time_series = get_time_series_id( \
                time_series)
            self.resource_id = time_series

        if not (isinstance(time_series, dict)
                and 'resource' in time_series and
                time_series['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_time_series_id(time_series)
            if self.resource_id is None:
                raise Exception(
                    api.error_message(time_series,
                                      resource_type='time_series',
                                      method='get'))
            query_string = ONLY_MODEL
            time_series = retrieve_resource(
                api, self.resource_id, query_string=query_string)
        else:
            self.resource_id = get_time_series_id(time_series)

        if 'object' in time_series and \
            isinstance(time_series['object'], dict):
            time_series = time_series['object']
        try:
            self.input_fields = time_series.get("input_fields", [])
            self._forecast = time_series.get("forecast")
            self.objective_fields = time_series.get(
                "objective_fields", [])
            objective_field = time_series['objective_field'] if \
                time_series.get('objective_field') else \
                time_series['objective_fields']
        except KeyError:
            raise ValueError("Failed to find the time series expected "
                             "JSON structure. Check your arguments.")
        if 'time_series' in time_series and \
            isinstance(time_series['time_series'], dict):
            status = get_status(time_series)
            if 'code' in status and status['code'] == FINISHED:
                time_series_info = time_series['time_series']
                fields = time_series_info.get('fields', {})
                self.fields = fields
                if not self.input_fields:
                    self.input_fields = [ \
                        field_id for field_id, _ in
                        sorted(self.fields.items(),
                               key=lambda x: x[1].get("column_number"))]
                self.all_numeric_objectives = time_series_info.get( \
                    'all_numeric_objectives')
                self.period = time_series_info.get('period', 1)
                self.ets_models = time_series_info.get('ets_models', {})
                self.error = time_series_info.get('error')
                self.damped_trend = time_series_info.get('damped_trend')
                self.seasonality = time_series_info.get('seasonality')
                self.trend = time_series_info.get('trend')
                self.time_range = time_series_info.get('time_range')
                self.field_parameters = time_series_info.get( \
                    'field_parameters', {})

                objective_id = extract_objective(objective_field)
                ModelFields.__init__(
                    self, fields,
                    objective_id=objective_id)
            else:
                raise Exception("The time series isn't finished yet")
        else:
            raise Exception("Cannot create the TimeSeries instance."
                            " Could not find the 'time_series' key"
                            " in the resource:\n\n%s" %
                            time_series)

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, logistic_regression, api=None):

        self.resource_id = None
        self.input_fields = []
        self.term_forms = {}
        self.tag_clouds = {}
        self.term_analysis = {}
        self.items = {}
        self.item_analysis = {}
        self.categories = {}
        self.coefficients = {}
        self.data_field_types = {}
        self.numeric_fields = {}
        self.bias = None
        self.missing_numerics = None
        self.c = None
        self.eps = None
        self.lr_normalize = None
        self.regularization = None
        if not (isinstance(logistic_regression, dict)
                and 'resource' in logistic_regression and
                logistic_regression['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_logistic_regression_id(logistic_regression)
            if self.resource_id is None:
                raise Exception(
                    api.error_message(logistic_regression,
                                      resource_type='logistic_regression',
                                      method='get'))
            query_string = ONLY_MODEL
            logistic_regression = retrieve_resource(
                api, self.resource_id, query_string=query_string)
        else:
            self.resource_id = get_logistic_regression_id(logistic_regression)

        if 'object' in logistic_regression and \
            isinstance(logistic_regression['object'], dict):
            logistic_regression = logistic_regression['object']
        try:
            self.input_fields = logistic_regression.get("input_fields", [])
            self.dataset_field_types = logistic_regression.get(
                "dataset_field_types", {})
            objective_field = logistic_regression['objective_fields'] if \
                logistic_regression['objective_fields'] else \
                logistic_regression['objective_field']
        except KeyError:
            raise ValueError("Failed to find the logistic regression expected "
                             "JSON structure. Check your arguments.")
        if 'logistic_regression' in logistic_regression and \
            isinstance(logistic_regression['logistic_regression'], dict):
            status = get_status(logistic_regression)
            if 'code' in status and status['code'] == FINISHED:
                logistic_regression_info = logistic_regression[ \
                    'logistic_regression']
                fields = logistic_regression_info.get('fields', {})

                if not self.input_fields:
                    self.input_fields = [ \
                        field_id for field_id, _ in
                        sorted(self.fields.items(),
                               key=lambda x: x[1].get("column_number"))]
                self.coefficients.update(logistic_regression_info.get( \
                    'coefficients', []))
                self.bias = logistic_regression_info.get('bias', 0)
                self.c = logistic_regression_info.get('c')
                self.eps = logistic_regression_info.get('eps')
                self.lr_normalize = logistic_regression_info.get('normalize')
                self.regularization = logistic_regression_info.get( \
                    'regularization')
                # old models have no such attribute, so we set it to False in
                # this case
                self.missing_numerics = logistic_regression_info.get( \
                    'missing_numerics', False)
                objective_id = extract_objective(objective_field)
                for field_id, field in fields.items():
                    if field['optype'] == 'text':
                        self.term_forms[field_id] = {}
                        self.term_forms[field_id].update(
                            field['summary']['term_forms'])
                        self.tag_clouds[field_id] = []
                        self.tag_clouds[field_id] = [tag for [tag, _] in field[
                            'summary']['tag_cloud']]
                        self.term_analysis[field_id] = {}
                        self.term_analysis[field_id].update(
                            field['term_analysis'])
                    if field['optype'] == 'items':
                        self.items[field_id] = []
                        self.items[field_id] = [item for item, _ in \
                            field['summary']['items']]
                        self.item_analysis[field_id] = {}
                        self.item_analysis[field_id].update(
                            field['item_analysis'])
                    if field['optype'] == 'categorical':
                        self.categories[field_id] = [category for \
                            [category, _] in field['summary']['categories']]
                    if self.missing_numerics and field['optype'] == 'numeric':
                        self.numeric_fields[field_id] = True
                ModelFields.__init__(
                    self, fields,
#.........这里部分代码省略.........

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, cluster, api=None):

        self.resource_id = None
        self.centroids = None
        self.cluster_global = None
        self.total_ss = None
        self.within_ss = None
        self.between_ss = None
        self.ratio_ss = None
        self.critical_value = None
        self.k = None
        self.scales = {}
        self.term_forms = {}
        self.tag_clouds = {}
        self.term_analysis = {}
        self.item_analysis = {}
        self.items = {}
        if not (isinstance(cluster, dict) and 'resource' in cluster and
                cluster['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_cluster_id(cluster)
            if self.resource_id is None:
                raise Exception(api.error_message(cluster,
                                                  resource_type='cluster',
                                                  method='get'))
            query_string = ONLY_MODEL
            cluster = retrieve_resource(api, self.resource_id,
                                        query_string=query_string)
        else:
            self.resource_id = get_cluster_id(cluster)
        if 'object' in cluster and isinstance(cluster['object'], dict):
            cluster = cluster['object']

        if 'clusters' in cluster and isinstance(cluster['clusters'], dict):
            status = get_status(cluster)
            if 'code' in status and status['code'] == FINISHED:
                the_clusters = cluster['clusters']
                cluster_global = the_clusters.get('global')
                clusters = the_clusters['clusters']
                self.centroids = [Centroid(centroid) for centroid in clusters]
                self.cluster_global = cluster_global
                if cluster_global:
                    self.cluster_global = Centroid(cluster_global)
                    # "global" has no "name" and "count" then we set them
                    self.cluster_global.name = GLOBAL_CLUSTER_LABEL
                    self.cluster_global.count = \
                        self.cluster_global.distance['population']
                self.total_ss = the_clusters.get('total_ss')
                self.within_ss = the_clusters.get('within_ss')
                if not self.within_ss:
                    self.within_ss = sum(centroid.distance['sum_squares'] for
                                         centroid in self.centroids)
                self.between_ss = the_clusters.get('between_ss')
                self.ratio_ss = the_clusters.get('ratio_ss')
                self.critical_value = cluster.get('critical_value', None)
                self.k = cluster.get('k')
                self.scales.update(cluster['scales'])
                self.term_forms = {}
                self.tag_clouds = {}
                self.term_analysis = {}
                fields = cluster['clusters']['fields']
                summary_fields = cluster['summary_fields']
                for field_id in summary_fields:
                    del fields[field_id]
                for field_id, field in fields.items():
                    if field['optype'] == 'text':
                        self.term_forms[field_id] = {}
                        self.term_forms[field_id].update(field[
                            'summary']['term_forms'])
                        self.tag_clouds[field_id] = {}
                        self.tag_clouds[field_id].update(field[
                            'summary']['tag_cloud'])
                        self.term_analysis[field_id] = {}
                        self.term_analysis[field_id].update(
                            field['term_analysis'])
                    if field['optype'] == 'items':
                        self.items[field_id] = {}
                        self.items[field_id].update(
                            dict(field['summary']['items']))
                        self.item_analysis[field_id] = {}
                        self.item_analysis[field_id].update(
                            field['item_analysis'])

                ModelFields.__init__(self, fields)
                if not all([field_id in self.fields for
                            field_id in self.scales]):
                    raise Exception("Some fields are missing"
                                    " to generate a local cluster."
                                    " Please, provide a cluster with"
                                    " the complete list of fields.")
            else:
                raise Exception("The cluster isn't finished yet")
        else:
            raise Exception("Cannot create the Cluster instance. Could not"
                            " find the 'clusters' key in the resource:\n\n%s" %
                            cluster)

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]

#.........这里部分代码省略.........
            objective_field = self.fields[self.objective_id]
            categories = objective_field['summary']['categories']
            classes = [category[0] for category in categories]
            self.class_names = sorted(classes)
            self.objective_categories = [category for \
                category, _ in self.fields[self.objective_id][ \
               "summary"]["categories"]]

        ModelFields.__init__( \
            self, self.fields,
            objective_id=self.objective_id)

    def get_fusion_resource(self, fusion):
        """Extracts the fusion resource info. The fusion argument can be
           - a path to a local file
           - an fusion id
        """
        # the string can be a path to a JSON file
        if isinstance(fusion, basestring):
            try:
                with open(fusion) as fusion_file:
                    fusion = json.load(fusion_file)
                    self.resource_id = get_fusion_id(fusion)
                    if self.resource_id is None:
                        raise ValueError("The JSON file does not seem"
                                         " to contain a valid BigML fusion"
                                         " representation.")
            except IOError:
                # if it is not a path, it can be an fusion id
                self.resource_id = get_fusion_id(fusion)
                if self.resource_id is None:
                    if fusion.find('fusion/') > -1:
                        raise Exception(
                            self.api.error_message(fusion,
                                                   resource_type='fusion',
                                                   method='get'))
                    else:
                        raise IOError("Failed to open the expected JSON file"
                                      " at %s" % fusion)
            except ValueError:
                raise ValueError("Failed to interpret %s."
                                 " JSON file expected.")
        if not isinstance(fusion, dict):
            fusion = retrieve_resource(self.api, self.resource_id,
                                       no_check_fields=False)
        return fusion

    def list_models(self):
        """Lists all the model/ids that compound the fusion.

        """
        return self.model_ids

    def predict_probability(self, input_data,
                            missing_strategy=LAST_PREDICTION,
                            compact=False):

        """For classification models, Predicts a probability for
        each possible output class, based on input values.  The input
        fields must be a dictionary keyed by field name or field ID.

        For regressions, the output is a single element list
        containing the prediction.

        :param input_data: Input data to be predicted
        :param missing_strategy: LAST_PREDICTION|PROPORTIONAL missing strategy

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, topic_model, api=None):

        self.resource_id = None
        self.stemmer = None
        self.seed = None
        self.case_sensitive = False
        self.bigrams = False
        self.ntopics = None
        self.temp = None
        self.phi = None
        self.term_to_index = None
        self.topics = []

        if not (isinstance(topic_model, dict) and 'resource' in topic_model and
                topic_model['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_topic_model_id(topic_model)
            if self.resource_id is None:
                raise Exception(api.error_message(topic_model,
                                                  resource_type='topicmodel',
                                                  method='get'))
            query_string = ONLY_MODEL
            topic_model = retrieve_resource(api, self.resource_id,
                                            query_string=query_string)
        else:
            self.resource_id = get_topic_model_id(topic_model)

        if 'object' in topic_model and isinstance(topic_model['object'], dict):
            topic_model = topic_model['object']

        if 'topic_model' in topic_model \
                and isinstance(topic_model['topic_model'], dict):
            status = get_status(topic_model)
            if 'code' in status and status['code'] == FINISHED:

                model = topic_model['topic_model']
                self.topics = model['topics']

                if 'language' in model and  model['language'] is not None:
                    lang = model['language']
                    if lang in CODE_TO_NAME:
                        self.stemmer = Stemmer.Stemmer(CODE_TO_NAME[lang])

                self.term_to_index = {self.stem(term): index for index, term
                                      in enumerate(model['termset'])}

                self.seed = abs(model['hashed_seed'])
                self.case_sensitive = model['case_sensitive']
                self.bigrams = model['bigrams']

                self.ntopics = len(model['term_topic_assignments'][0])

                self.alpha = model['alpha']
                self.ktimesalpha = self.ntopics * self.alpha

                self.temp = [0] * self.ntopics

                assignments = model['term_topic_assignments']
                beta = model['beta']
                nterms = len(self.term_to_index)

                sums = [sum(n[index] for n in assignments) for index
                        in range(self.ntopics)]

                self.phi = [[0 for _ in range(nterms)]
                            for _ in range(self.ntopics)]

                for k in range(self.ntopics):
                    norm = sums[k] + nterms * beta
                    for w in range(nterms):
                        self.phi[k][w] = (assignments[w][k] + beta) / norm

                ModelFields.__init__(self, model['fields'])
            else:
                raise Exception("The topic model isn't finished yet")
        else:
            raise Exception("Cannot create the topic model instance. Could not"
                            " find the 'topic_model' key in the"
                            " resource:\n\n%s" % topic_model)

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, model, api=None, fields=None):

        if check_model_structure(model):
            self.resource_id = model['resource']
        else:
            # If only the model id is provided, the short version of the model
            # resource is used to build a basic summary of the model
            if api is None:
                api = BigML()
            self.resource_id = get_model_id(model)
            if self.resource_id is None:
                raise Exception(api.error_message(model,
                                                  resource_type='model',
                                                  method='get'))
            if fields is not None and isinstance(fields, dict):
                query_string = EXCLUDE_FIELDS
            else:
                query_string = ONLY_MODEL
            model = retrieve_resource(api, self.resource_id,
                                      query_string=query_string)
            # Stored copies of the model structure might lack some necessary
            # keys
            if not check_model_structure(model):
                model = api.get_model(self.resource_id,
                                      query_string=query_string)

        if 'object' in model and isinstance(model['object'], dict):
            model = model['object']

        if 'model' in model and isinstance(model['model'], dict):
            status = get_status(model)
            if 'code' in status and status['code'] == FINISHED:
                if (fields is None and ('model_fields' in model['model'] or
                                        'fields' in model['model'])):
                    fields = model['model'].get('model_fields',
                                                model['model'].get('fields',
                                                                   []))
                    # pagination or exclusion might cause a field not to
                    # be in available fields dict
                    if not all(key in model['model']['fields']
                               for key in fields.keys()):
                        raise Exception("Some fields are missing"
                                        " to generate a local model."
                                        " Please, provide a model with"
                                        " the complete list of fields.")
                    for field in fields:
                        field_info = model['model']['fields'][field]
                        if 'summary' in field_info:
                            fields[field]['summary'] = field_info['summary']
                        fields[field]['name'] = field_info['name']
                objective_field = model['objective_fields']
                ModelFields.__init__(
                    self, fields,
                    objective_id=extract_objective(objective_field))
                self.description = model['description']
                self.field_importance = model['model'].get('importance',
                                                           None)
                if self.field_importance:
                    self.field_importance = [element for element
                                             in self.field_importance
                                             if element[0] in fields]
                self.locale = model.get('locale', DEFAULT_LOCALE)

            else:
                raise Exception("The model isn't finished yet")
        else:
            raise Exception("Cannot create the BaseModel instance. Could not"
                            " find the 'model' key in the resource:\n\n%s" %
                            model)

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]
    def __init__(self, association, api=None):

        self.resource_id = None
        self.complement = None
        self.discretization = {}
        self.field_discretizations = {}
        self.items = []
        self.max_k = None
        self.max_lhs = None
        self.min_confidence = None
        self.min_leverage = None
        self.min_support = None
        self.min_lift = None
        self.search_strategy = DEFAULT_SEARCH_STRATEGY
        self.rules = []
        self.significance_level = None

        if not (isinstance(association, dict) and 'resource' in association and
                association['resource'] is not None):
            if api is None:
                api = BigML(storage=STORAGE)
            self.resource_id = get_association_id(association)
            if self.resource_id is None:
                raise Exception(api.error_message(association,
                                                  resource_type='association',
                                                  method='get'))
            query_string = ONLY_MODEL
            association = retrieve_resource(api, self.resource_id,
                                            query_string=query_string)
        else:
            self.resource_id = get_association_id(association)
        if 'object' in association and isinstance(association['object'], dict):
            association = association['object']

        if 'associations' in association and \
                isinstance(association['associations'], dict):
            status = get_status(association)
            if 'code' in status and status['code'] == FINISHED:
                associations = association['associations']
                fields = associations['fields']
                ModelFields.__init__(self, fields)
                self.complement = associations.get('complement', False)
                self.discretization = associations.get('discretization', {})
                self.field_discretizations = associations.get(
                    'field_discretizations', {})
                self.items = [Item(index, item, fields) for index, item in
                              enumerate(associations.get('items', []))]
                self.max_k = associations.get('max_k', 100)
                self.max_lhs = associations.get('max_lhs', 4)
                self.min_confidence = associations.get('min_confidence', 0)
                self.min_leverage = associations.get('min_leverage', -1)
                self.min_support = associations.get('min_support', 0)
                self.min_lift = associations.get('min_lift', 0)
                self.search_strategy = associations.get('search_strategy', \
                    DEFAULT_SEARCH_STRATEGY)
                self.rules = [AssociationRule(rule) for rule in
                              associations.get('rules', [])]
                self.significance_level = associations.get(
                    'significance_level', 0.05)
            else:
                raise Exception("The association isn't finished yet")
        else:
            raise Exception("Cannot create the Association instance. Could not"
                            " find the 'associations' key in the "
                            "resource:\n\n%s" %
                            association)

# 需要导入模块: from bigml.api import BigML [as 别名]
# 或者: from bigml.api.BigML import error_message [as 别名]

#.........这里部分代码省略.........
        for model_id in self.model_ids:
            module_name = "%s.%s" % (module_path,
                                     model_id.replace("/", "_"))
            try:
                __import__(module_name)
                prediction_module = sys.modules[module_name]
                function = getattr(prediction_module, function_name)
                self.predict_functions.append(function)
            except ImportError:
                raise ImportError("Failed to import the predict function"
                                  " from %s." % module_name)

    def get_ensemble_resource(self, ensemble):
        """Extracts the ensemble resource info. The ensemble argument can be
           - a path to a local file
           - an ensemble id
        """
        # the string can be a path to a JSON file
        if isinstance(ensemble, basestring):
            try:
                with open(ensemble) as ensemble_file:
                    ensemble = json.load(ensemble_file)
                    self.resource_id = get_ensemble_id(ensemble)
                    if self.resource_id is None:
                        raise ValueError("The JSON file does not seem"
                                         " to contain a valid BigML ensemble"
                                         " representation.")
            except IOError:
                # if it is not a path, it can be an ensemble id
                self.resource_id = get_ensemble_id(ensemble)
                if self.resource_id is None:
                    if ensemble.find('ensemble/') > -1:
                        raise Exception(
                            self.api.error_message(ensemble,
                                                   resource_type='ensemble',
                                                   method='get'))
                    else:
                        raise IOError("Failed to open the expected JSON file"
                                      " at %s" % ensemble)
            except ValueError:
                raise ValueError("Failed to interpret %s."
                                 " JSON file expected.")
        return ensemble

    def list_models(self):
        """Lists all the model/ids that compound the ensemble.

        """
        return self.model_ids

    def predict(self, input_data, by_name=True, method=PLURALITY_CODE):
        """Makes a prediction based on the prediction made by every model.

        :param input_data: Test data to be used as input
        :param by_name: Boolean that is set to True if field_names (as
                        alternative to field ids) are used in the
                        input_data dict
        :param method: numeric key code for the following combination
                       methods in classifications/regressions:
              0 - majority vote (plurality)/ average: PLURALITY_CODE
              1 - confidence weighted majority vote / error weighted:
                  CONFIDENCE_CODE
              2 - probability weighted majority vote / average:
                  PROBABILITY_CODE
        """