def operator_create_network(self, method, year, discharge_type):
folder_path = self.get_operator_folder_path(
SharedCareAreaScript.TYPE_NETWORK)
filename = f'{method}_{year}_{discharge_type}'
filepath = f'{folder_path}/{filename}'
net = NetworkSharedCare.instance(method)
dict_match = {
HospitalDischargeDocument.discharge_year: year,
HospitalDischargeDocument.discharge_type: discharge_type
}
df = net.create_network(dict_match)
df.to_csv(f'{filepath}.csv', index=False)
df.to_hdf(f'{filepath}.hdf', key='df')
G = build_from_dataframe(df)
write_graph(G, folder=folder_path, filename=filename)
del G
dict_network = {
NetworkHospitalDischargeDocument.network_method.name: method,
NetworkHospitalDischargeDocument.network_year.name: year,
NetworkHospitalDischargeDocument.network_type.name: discharge_type
}
dao = BaseDAO(NetworkHospitalDischargeDocument)
dao.delete(**dict_network)
#
df = df.rename(
columns={
NetworkHospitalDischargeDocument.node_in.db_field:
NetworkHospitalDischargeDocument.node_in.name,
NetworkHospitalDischargeDocument.node_out.db_field:
NetworkHospitalDischargeDocument.node_out.name,
NetworkHospitalDischargeDocument.weight.db_field:
NetworkHospitalDischargeDocument.weight.name,
})
df[NetworkHospitalDischargeDocument.network_method.name] = method
df[NetworkHospitalDischargeDocument.network_year.name] = year
df[NetworkHospitalDischargeDocument.network_type.name] = discharge_type
# list_objects = list(
# map(self.get_object_network, [(dict_network, row) for (index, row) in df.iterrows()]))
#
# dao.insert(list_objects)
dao.init_bulk(max_bulk_insert=100000)
for (i, d) in df.iterrows():
# (i, d) = next(df.iterrows())
o = NetworkHospitalDischargeDocument(**d.to_dict())
dao.insert_bulk(o)
dao.exit_bulk()
del df
def operator_calculate_network_metrics(self, metric, method, year,
discharge_type):
dict_match = {
NetworkHospitalDischargeDocument.network_method: method,
NetworkHospitalDischargeDocument.network_type: discharge_type,
NetworkHospitalDischargeDocument.network_year: year
}
dict_project = [
# NetworkHospitalDischargeDocument.network_type,
# NetworkHospitalDischargeDocument.network_year,
NetworkHospitalDischargeDocument.node_in,
NetworkHospitalDischargeDocument.node_out,
NetworkHospitalDischargeDocument.weight,
]
dao_network = BaseDAO(NetworkHospitalDischargeDocument)
list_network = dao_network.obtain_pipeline(dict_match=dict_match,
dict_project=dict_project,
math_none=False)
G = nx.Graph()
G.add_weighted_edges_from((tuple(i.values()) for i in list_network))
# list_metrics = NetworkMetricFactory.get_types()
# for metric in list_metrics:
mod_network_metric = NetworkMetricFactory.instance(metric)
df_metric = mod_network_metric.get_metric(G)
df_metric.columns = [
MetricsNetworkSharedCareAreaDocument.metric_value.name
]
folder_path_out = self.get_operator_folder_path(
SharedCareAreaScript.TYPE_NETWORK_METRICS)
filename_out = f'{method}_{year}_{discharge_type}_{metric}'
filepath_out = f'{folder_path_out}/{filename_out}'
df_metric.to_csv(f'{filepath_out}.csv', index=False)
metrics_dict = {
MetricsNetworkSharedCareAreaDocument.method.name: method,
MetricsNetworkSharedCareAreaDocument.year.name: year,
MetricsNetworkSharedCareAreaDocument.type_discharge.name:
discharge_type,
MetricsNetworkSharedCareAreaDocument.metric.name: metric,
}
list_metrics = list(
map(self.get_metrics_network_shared_care,
[(metrics_dict, row)
for (index, row) in df_metric.iterrows()]))
dao_metrics = BaseDAO(MetricsNetworkSharedCareAreaDocument)
dao_metrics.delete(**metrics_dict)
dao_metrics.insert(list_metrics)
def operator_extract_communities(self, method, year, discharge_type,
type_community_detection):
folder_path_in = self.get_operator_folder_path(
SharedCareAreaScript.TYPE_NETWORK)
filename_in = f'{method}_{year}_{discharge_type}'
filepath_in = f'{folder_path_in}/{filename_in}'
folder_path_out = self.get_operator_folder_path(
SharedCareAreaScript.TYPE_COMMUNITIES)
filename_out = f'{method}_{year}_{discharge_type}_{type_community_detection}'
filepath_out = f'{folder_path_out}/{filename_out}'
# exists = os.path.exists(f'{filepath_out}.csv')
# if exists and not drop:
# return
G = nx.read_pajek(f'{filepath_in}.pajek')
community_detection = CommunityDetection.build_community_detection(
type_community_detection)
df_communities = community_detection.find_communities(
(G, filepath_in, filename_in))
df_communities.rename(
columns={
SharedCareArea.zcta.db_field: 'NODE_ID',
SharedCareArea.sca_id.db_field: 'COMMUNITY_ID'
})
df_communities.to_csv(f'{filepath_out}.csv', index=False)
df_communities.to_hdf(f'{filepath_out}.hdf', 'df')
sca_dict = {
SharedCareArea.method.name: method,
SharedCareArea.year.name: year,
SharedCareArea.type_discharge.name: discharge_type,
SharedCareArea.type_community_detection.name:
type_community_detection
}
dao = BaseDAO(SharedCareArea)
dao.delete(**sca_dict)
list_shared_care_areas = list(
map(self.get_shared_care,
[(sca_dict, row)
for (index, row) in df_communities.iterrows()]))
dao.insert(list_shared_care_areas)