def __init__(self):
AggregationAPI.__init__(self,"tate")
self.marking_params_per_shape = dict()
self.marking_params_per_shape["text"] = text_mapping2
self.workflows[683] = {},{"init":["text"]}
def __init__(self,project_id,environment):
AggregationAPI.__init__(self,project_id,environment)#"tate")#"tate",environment="staging")
# the code to extract the relevant params froma text json file
self.marking_params_per_shape["text"] = relevant_text_params
# the code to cluster lines together
self.default_clustering_algs["text"] = TextCluster
self.default_clustering_algs["image"] = BlobClustering
# the code for reducing a line segment (4d) into a 2d object
# todo - can probably replace this with the standard for line segments
# self.reduction_algs["text"] = text_line_reduction
# load in the tag file
api_details = yaml.load(open("/app/config/aggregation.yml","rb"))
try:
tag_file = api_details[self.project_id]["tags"]
self.additional_clustering_args = {"text": {"reduction":text_line_reduction,"tag_file":tag_file}}
except:
self.additional_clustering_args = {"text": {"reduction":text_line_reduction}}
self.ignore_versions = True
# self.instructions[683] = {}
self.instructions[121] = {}
self.only_retired_subjects = False
self.only_recent_subjects = True
self.rollbar_token = None
def __init__(self, project_id, environment, end_date=None):
AggregationAPI.__init__(self,
project_id,
environment,
end_date=end_date)
# just to stop me from using transcription on other projects
if not int(project_id) in [245, 376]:
raise ValueError('project_id must be either 245 or 376')
def __init__(self,project_id,csv_classification_file):
AggregationAPI.__init__(self,project_id,"development")
# read in the csv file as a dataframe (pandas)
self.classifications_dataframe = pandas.read_csv(csv_classification_file)
# extract the subject id for each subject - based on the subject data field
self.classifications_dataframe["subject_id"] = self.classifications_dataframe["subject_data"].map(lambda x: extract_subject_id(x))
self.aggregation_results = {}
def __init__(self, project_id, csv_classification_file):
AggregationAPI.__init__(self, project_id, "development")
# read in the csv file as a dataframe (pandas)
self.classifications_dataframe = pandas.read_csv(
csv_classification_file)
# extract the subject id for each subject - based on the subject data field
self.classifications_dataframe[
"subject_id"] = self.classifications_dataframe["subject_data"].map(
lambda x: extract_subject_id(x))
self.aggregation_results = {}
def __init__(self):
AggregationAPI.__init__(self,245)#"tate",environment="staging")
self.marking_params_per_shape = dict()
self.marking_params_per_shape["text"] = text_mapping2
# self.workflows[683] = {},{"init":["text"]}
# self.versions[683] = 1
self.marking_params_per_shape["text"] = relevant_text_params
reduction_algs = {"text":text_line_reduction}
self.__set_clustering_algs__({"text":TextCluster},reduction_algs)
self.ignore_versions = True
self.instructions[683] = {}
def __init__(self):
AggregationAPI.__init__(self, 245) #"tate",environment="staging")
self.marking_params_per_shape = dict()
self.marking_params_per_shape["text"] = text_mapping2
# self.workflows[683] = {},{"init":["text"]}
# self.versions[683] = 1
self.marking_params_per_shape["text"] = relevant_text_params
reduction_algs = {"text": text_line_reduction}
self.__set_clustering_algs__({"text": TextCluster}, reduction_algs)
self.ignore_versions = True
self.instructions[683] = {}
def __init__(self):
AggregationAPI.__init__(self,245)#"tate",environment="staging")
self.marking_params_per_shape = dict()
self.marking_params_per_shape["text"] = text_mapping2
# self.workflows[683] = {},{"init":["text"]}
# self.versions[683] = 1
self.marking_params_per_shape["text"] = relevant_text_params
reduction_algs = {"text":text_line_reduction}
self.__set_clustering_algs__({"text":TextCluster},reduction_algs)
self.__set_classification_alg__(SubjectRetirement,{"host":self.host_api,"project_id":self.project_id,"token":self.token,"workflow_id":121})
self.ignore_versions = True
self.instructions[683] = {}
def __init__(self):
AggregationAPI.__init__(self, 245) #"tate",environment="staging")
self.marking_params_per_shape = dict()
self.marking_params_per_shape["text"] = text_mapping2
# self.workflows[683] = {},{"init":["text"]}
# self.versions[683] = 1
self.marking_params_per_shape["text"] = relevant_text_params
reduction_algs = {"text": text_line_reduction}
self.__set_clustering_algs__({"text": TextCluster}, reduction_algs)
self.__set_classification_alg__(
SubjectRetirement, {
"host": self.host_api,
"project_id": self.project_id,
"token": self.token,
"workflow_id": 121
})
self.ignore_versions = True
self.instructions[683] = {}
def __init__(self,project_id,environment,end_date=None):
AggregationAPI.__init__(self,project_id,environment,end_date=end_date)
# just to stop me from using transcription on other projects
if not int(project_id) in [245, 376]:
raise ValueError('project_id must be either 245 or 376')
def __init__(self,project_id,environment,end_date=None):
AggregationAPI.__init__(self,project_id,environment,end_date=end_date)
# just to stop me from using transcription on other projects
assert int(project_id) in [245,376]
