def get_csv_table(self): resource_id = self.resource_id #first 20 lines of the csv file tf = TabularFile(resource_id) csv_obj = tf.get_csv_data() csv_obj = csv_obj.fillna(0) return self.structure_by_rows(csv_obj)
def _getResourceMetadata(self, resourceId): resource = Resource(resourceId) resource.init() mapping = Mapping(resourceId) headers = mapping.get_mapping_headers() headers = self._concatHeaders(headers) tf = TabularFile(resourceId) csvDataframe = tf.get_csv_data() refine = Refine(resourceId) table = refine.structure_by_cols(csvDataframe) table = self._concatTable(table) package = Package(resource.package_name) return (resource, package, headers, table)