def ingest_habitats(self):
base_msg = "Ingesting 'habitats'..."
self.logger.info(base_msg)
habs_logger = self.get_section_logger('habs', base_msg)
self.habs = {}
self.habs_spatial_hash = SpatialHash(cell_size=self.hash_cell_size)
habs_file = os.path.join(self.data_dir, 'habitats', "habitats.shp")
habs_config = self.config.get('sections', {}).get('habitats', {})
def add_to_habs_spatial_hash(data=None, **kwargs):
self.habs_spatial_hash.add_rect(data.mbr, data)
return data
def process_neg_depth(neg_depth):
if neg_depth is not None:
depth = -1.0 * float(neg_depth)
return depth
Ingestor(
reader=ShapefileReader(
shp_file=habs_file,
reproject_to='EPSG:4326',
),
processors=[
ClassMapper(clazz=self.dao.schema['sources']['Habitat'],
mappings=[
{
'source': 'SUBSTRATE',
'target': 'substrate_id'
},
{
'source': 'ENERGY',
'target': 'energy_id'
},
{
'source': 'Z',
'target': 'depth',
'processor': process_neg_depth
},
{
'source': '__shape',
'target': 'shape'
},
]),
self.add_area_mbr,
add_to_habs_spatial_hash,
DictWriter(dict_=self.habs),
],
logger=habs_logger,
limit=habs_config.get('limit'),
).ingest()
def ingest_stat_areas(self, parent_logger=None, limit=None):
self.stat_areas = {}
self.sa_spatial_hash = SpatialHash(cell_size=.1)
self.sa_values = {}
logger = self.get_logger_logger(
name='stat_area_ingest',
base_msg='Ingesting stat_areas...',
parent_logger=parent_logger
)
Ingestor(
reader=ShapefileReader(shp_file=self.stat_areas_path,
reproject_to='EPSG:4326'),
processors=[
ClassMapper(
clazz=models.StatArea,
mappings=[{'source': 'SAREA', 'target': 'id'},
{'source': '__shape', 'target': 'shape'},],
),
DictWriter(dict_=self.stat_areas, key_func=lambda sa: sa.id),
],
logger=logger,
limit=limit
).ingest()
# Add to spatial hash.
for stat_area in self.stat_areas.values():
stat_area.mbr = gis_util.get_shape_mbr(stat_area.shape)
self.sa_spatial_hash.add_rect(stat_area.mbr, stat_area)
def ingest_cells(self, parent_logger=None, limit=None):
self.cells = {}
self.cell_spatial_hash = SpatialHash(cell_size=.1)
self.c_values = {}
logger = self.get_logger_logger(
name='cell_ingest',
base_msg='Ingesting cells...',
parent_logger=parent_logger
)
Ingestor(
reader=ShapefileReader(shp_file=self.grid_path,
reproject_to='EPSG:4326'),
processors=[
ClassMapper(
clazz=models.Cell,
mappings=[{'source': 'ID', 'target': 'id'},
{'source': '__shape', 'target': 'shape'},],
),
DictWriter(dict_=self.cells, key_func=lambda c: c.id),
],
logger=logger,
limit=limit
).ingest()
# Calculate cell areas and add cells to spatial hash,
# and initialize c_values.
for cell in self.cells.values():
cell.area = gis_util.get_shape_area(cell.shape)
cell.mbr = gis_util.get_shape_mbr(cell.shape)
self.cell_spatial_hash.add_rect(cell.mbr, cell)
self.c_values[cell.id] = {}
def ingest_habitats(self):
base_msg = "Ingesting 'habitats'..."
self.logger.info(base_msg)
habs_logger=self.get_section_logger('habs', base_msg)
self.habs = {}
self.habs_spatial_hash = SpatialHash(cell_size=self.hash_cell_size)
habs_file = os.path.join(self.data_dir, 'habitats', "habitats.shp")
habs_config = self.config.get('sections', {}).get('habitats', {})
def add_to_habs_spatial_hash(data=None, **kwargs):
self.habs_spatial_hash.add_rect(data.mbr, data)
return data
def process_neg_depth(neg_depth):
if neg_depth is not None:
depth = -1.0 * float(neg_depth)
return depth
Ingestor(
reader=ShapefileReader(
shp_file=habs_file,
reproject_to='EPSG:4326',
),
processors=[
ClassMapper(
clazz=self.dao.schema['sources']['Habitat'],
mappings=[
{'source': 'SUBSTRATE', 'target': 'substrate_id'},
{'source': 'ENERGY', 'target': 'energy_id'},
{'source': 'Z', 'target': 'depth',
'processor': process_neg_depth},
{'source': '__shape', 'target': 'shape'},
]
),
self.add_area_mbr,
add_to_habs_spatial_hash,
DictWriter(dict_=self.habs),
],
logger=habs_logger,
limit=habs_config.get('limit'),
).ingest()
class SASI_Ingestor(object):
def __init__(self, data_dir=None, dao=None, logger=logging.getLogger(),
config={}, hash_cell_size=.1, **kwargs):
self.data_dir = data_dir
self.dao = dao
self.logger = logger
self.hash_cell_size = hash_cell_size
self.config = config
self.commit_interval = config.get('commit_interval', 1e4)
def ingest(self):
# Define generic CSV ingests.
csv_sections = [
{
'id': 'substrates',
'class': self.dao.schema['sources']['Substrate'],
'mappings': [
{'source': 'id', 'target': 'id'},
{'source': 'label', 'target': 'label'},
{'source': 'description', 'target': 'description'},
]
},
{
'id': 'energies',
'class': self.dao.schema['sources']['Energy'],
'mappings': [
{'source': 'id', 'target': 'id'},
{'source': 'label', 'target': 'label'},
{'source': 'description', 'target': 'description'},
]
},
{
'id': 'feature_categories',
'class': self.dao.schema['sources']['FeatureCategory'],
'mappings': [
{'source': 'id', 'target': 'id'},
{'source': 'label', 'target': 'label'},
{'source': 'description', 'target': 'description'},
]
},
{
'id': 'features',
'class': self.dao.schema['sources']['Feature'],
'mappings': [
{'source': 'id', 'target': 'id'},
{'source': 'category', 'target': 'category'},
{'source': 'label', 'target': 'label'},
{'source': 'description', 'target': 'description'},
]
},
{
'id': 'gears',
'class': self.dao.schema['sources']['Gear'],
'mappings': [
{'source': 'id', 'target': 'id'},
{'source': 'generic_id', 'target': 'generic_id'},
{'source': 'is_generic', 'target': 'is_generic',
'processor': parse_bool},
{'source': 'label', 'target': 'label'},
{'source': 'description', 'target': 'description'},
{'source': 'min_depth', 'processor': robust_float},
{'source': 'max_depth', 'processor': robust_float},
]
},
{
'id': 'va',
'class': self.dao.schema['sources']['VA'],
'mappings': [
{'source': 'gear_id', 'target': 'gear_id'},
{'source': 'feature_id', 'target': 'feature_id'},
{'source': 'substrate_id', 'target': 'substrate_id'},
{'source': 'energy_id', 'target': 'energy_id'},
{'source': 's', 'target': 's', 'processor': robust_int},
{'source': 'r', 'target': 'r', 'processor': robust_int},
]
},
{
'id': 'fishing_efforts',
'optional': True,
'class': self.dao.schema['sources']['Effort'],
'mappings': [
{'source': 'cell_id', 'target':'cell_id',
'processor': robust_int},
{'source': 'time', 'target': 'time',
'processor': robust_int},
'gear_id',
# note: we assume a is already in km^2.
{'source': 'a', 'processor': robust_float},
{'source': 'hours_fished', 'processor': robust_float},
{'source': 'value', 'processor': robust_float},
]
},
{
'id': 'model_parameters',
'class': self.dao.schema['sources']['ModelParameters'],
'mappings': [
'time_start',
'time_end',
'time_step',
{'source': 't_0', 'target': 't_0',
'processor': robust_float},
{'source': 't_1', 'target': 't_1',
'processor': robust_float},
{'source': 't_2', 'target': 't_2',
'processor': robust_float},
{'source': 't_3', 'target': 't_3',
'processor': robust_float},
{'source': 'w_0', 'target': 'w_0',
'processor': robust_float},
{'source': 'w_1', 'target': 'w_1',
'processor': robust_float},
{'source': 'w_2', 'target': 'w_2',
'processor': robust_float},
{'source': 'w_3', 'target': 'w_3',
'processor': robust_float},
{'source': 'effort_model', 'default': 'nominal'},
{'source': 'projection', 'target': 'projection',
# Use the mollweide projection as the default.
'default': gis_util.get_default_geographic_crs(),
}
],
},
]
for section in csv_sections:
self.ingest_csv_section(section)
# Convenience shortcuts.
self.model_parameters = self.dao.query('__ModelParameters').fetchone()
self.geographic_crs = self.model_parameters.projection
self.ingest_grid()
self.ingest_habitats()
self.post_ingest()
def ingest_csv_section(self, section):
csv_file = os.path.join(self.data_dir, "%s.csv" % section['id'])
if not os.path.isfile(csv_file):
if not section.get('optional'):
raise Exception(
("Error ingesting '%s': "
"File '%s' is required and was not found.") %
(section['id'], csv_file)
)
else:
return
base_msg = "Ingesting '%s'..." % section['id']
self.logger.info(base_msg)
section_config = self.config.get('sections', {}).get(
section['id'], {})
Ingestor(
reader=CSVReader(csv_file=csv_file),
processors=[
ClassMapper(clazz=section['class'],
mappings=section['mappings']),
DAOWriter(dao=self.dao, commit_interval=self.commit_interval),
],
logger=self.get_section_logger(section['id'], base_msg),
limit=section_config.get('limit'),
).ingest()
self.dao.commit()
def ingest_grid(self):
base_msg = "Ingesting 'grid'..."
self.logger.info(base_msg)
grid_logger = self.get_section_logger('grid', base_msg)
self.cells = {}
grid_file = os.path.join(self.data_dir, 'grid', "grid.shp")
grid_config = self.config.get('sections', {}).get('grid', {})
Ingestor(
reader=ShapefileReader(
shp_file=grid_file,
reproject_to='EPSG:4326',
),
processors=[
ClassMapper(
clazz=self.dao.schema['sources']['Cell'],
mappings=[
{'source': 'ID', 'target': 'id', 'processor': int},
{'source': '__shape', 'target': 'shape'},
{'source': '__shape', 'target': 'geom_wkt',
'processor': gis_util.shape_to_wkt}
]
),
self.add_area_mbr,
DictWriter(dict_=self.cells),
],
logger=grid_logger,
limit=grid_config.get('limit'),
).ingest()
def ingest_habitats(self):
base_msg = "Ingesting 'habitats'..."
self.logger.info(base_msg)
habs_logger=self.get_section_logger('habs', base_msg)
self.habs = {}
self.habs_spatial_hash = SpatialHash(cell_size=self.hash_cell_size)
habs_file = os.path.join(self.data_dir, 'habitats', "habitats.shp")
habs_config = self.config.get('sections', {}).get('habitats', {})
def add_to_habs_spatial_hash(data=None, **kwargs):
self.habs_spatial_hash.add_rect(data.mbr, data)
return data
def process_neg_depth(neg_depth):
if neg_depth is not None:
depth = -1.0 * float(neg_depth)
return depth
Ingestor(
reader=ShapefileReader(
shp_file=habs_file,
reproject_to='EPSG:4326',
),
processors=[
ClassMapper(
clazz=self.dao.schema['sources']['Habitat'],
mappings=[
{'source': 'SUBSTRATE', 'target': 'substrate_id'},
{'source': 'ENERGY', 'target': 'energy_id'},
{'source': 'Z', 'target': 'depth',
'processor': process_neg_depth},
{'source': '__shape', 'target': 'shape'},
]
),
self.add_area_mbr,
add_to_habs_spatial_hash,
DictWriter(dict_=self.habs),
],
logger=habs_logger,
limit=habs_config.get('limit'),
).ingest()
def get_section_logger(self, section_id, base_msg):
logger = logging.getLogger("%s_%s" % (id(self), section_id))
formatter = logging.Formatter(base_msg + ' %(message)s.')
log_handler = LoggerLogHandler(self.logger)
log_handler.setFormatter(formatter)
logger.addHandler(log_handler)
logger.setLevel(self.logger.level)
return logger
def post_ingest(self):
self.post_process_cells()
# Allow for cells and habs to be garbage collected.
self.cells = None
self.habs = None
self.habs_spatial_hash = None
def post_process_cells(self, log_interval=1000):
base_msg = 'Calculating cell compositions...'
self.logger.info(base_msg)
logger = self.get_section_logger('habitat_areas', base_msg)
num_cells = len(self.cells)
counter = 0
for cell in self.cells.values():
counter += 1
if (counter % log_interval) == 0:
logger.info(" %d of %d (%.1f%%)" % (
counter, num_cells, 1.0 * counter/num_cells* 100))
composition = {}
cell.depth = 0
# Get candidate intersecting habitats.
candidate_habs = self.habs_spatial_hash.items_for_rect(cell.mbr)
for hab in candidate_habs:
intersection = gis_util.get_intersection(cell.shape, hab.shape)
if not intersection:
continue
intersection_area = gis_util.get_shape_area(
intersection,
target_crs=self.geographic_crs,
)
hab_key = (hab.substrate_id, hab.energy_id,)
pct_area = intersection_area/cell.area
composition[hab_key] = composition.get(hab_key, 0) + pct_area
cell.depth += pct_area * hab.depth
cell.habitat_composition = composition
# Convert cell area to km^2.
cell.area = cell.area/(1000.0**2)
self.dao.save(cell, commit=False)
self.dao.commit()
# Define processor for adding area, mbr to geom entities.
def add_area_mbr(self, data=None, **kwargs):
data.area = gis_util.get_shape_area(
data.shape, target_crs=self.geographic_crs)
data.mbr = gis_util.get_shape_mbr(data.shape)
return data
class SASI_Ingestor(object):
def __init__(self,
data_dir=None,
dao=None,
logger=logging.getLogger(),
config={},
hash_cell_size=.1,
**kwargs):
self.data_dir = data_dir
self.dao = dao
self.logger = logger
self.hash_cell_size = hash_cell_size
self.config = config
self.commit_interval = config.get('commit_interval', 1e4)
def ingest(self):
# Define generic CSV ingests.
csv_sections = [
{
'id':
'substrates',
'class':
self.dao.schema['sources']['Substrate'],
'mappings': [
{
'source': 'id',
'target': 'id'
},
{
'source': 'label',
'target': 'label'
},
{
'source': 'description',
'target': 'description'
},
]
},
{
'id':
'energies',
'class':
self.dao.schema['sources']['Energy'],
'mappings': [
{
'source': 'id',
'target': 'id'
},
{
'source': 'label',
'target': 'label'
},
{
'source': 'description',
'target': 'description'
},
]
},
{
'id':
'feature_categories',
'class':
self.dao.schema['sources']['FeatureCategory'],
'mappings': [
{
'source': 'id',
'target': 'id'
},
{
'source': 'label',
'target': 'label'
},
{
'source': 'description',
'target': 'description'
},
]
},
{
'id':
'features',
'class':
self.dao.schema['sources']['Feature'],
'mappings': [
{
'source': 'id',
'target': 'id'
},
{
'source': 'category',
'target': 'category'
},
{
'source': 'label',
'target': 'label'
},
{
'source': 'description',
'target': 'description'
},
]
},
{
'id':
'gears',
'class':
self.dao.schema['sources']['Gear'],
'mappings': [
{
'source': 'id',
'target': 'id'
},
{
'source': 'generic_id',
'target': 'generic_id'
},
{
'source': 'is_generic',
'target': 'is_generic',
'processor': parse_bool
},
{
'source': 'label',
'target': 'label'
},
{
'source': 'description',
'target': 'description'
},
{
'source': 'min_depth',
'processor': robust_float
},
{
'source': 'max_depth',
'processor': robust_float
},
]
},
{
'id':
'va',
'class':
self.dao.schema['sources']['VA'],
'mappings': [
{
'source': 'gear_id',
'target': 'gear_id'
},
{
'source': 'feature_id',
'target': 'feature_id'
},
{
'source': 'substrate_id',
'target': 'substrate_id'
},
{
'source': 'energy_id',
'target': 'energy_id'
},
{
'source': 's',
'target': 's',
'processor': robust_int
},
{
'source': 'r',
'target': 'r',
'processor': robust_int
},
]
},
{
'id':
'fishing_efforts',
'optional':
True,
'class':
self.dao.schema['sources']['Effort'],
'mappings': [
{
'source': 'cell_id',
'target': 'cell_id',
'processor': robust_int
},
{
'source': 'time',
'target': 'time',
'processor': robust_int
},
'gear_id',
# note: we assume a is already in km^2.
{
'source': 'a',
'processor': robust_float
},
{
'source': 'hours_fished',
'processor': robust_float
},
{
'source': 'value',
'processor': robust_float
},
]
},
{
'id':
'model_parameters',
'class':
self.dao.schema['sources']['ModelParameters'],
'mappings': [
'time_start',
'time_end',
'time_step',
{
'source': 't_0',
'target': 't_0',
'processor': robust_float
},
{
'source': 't_1',
'target': 't_1',
'processor': robust_float
},
{
'source': 't_2',
'target': 't_2',
'processor': robust_float
},
{
'source': 't_3',
'target': 't_3',
'processor': robust_float
},
{
'source': 'w_0',
'target': 'w_0',
'processor': robust_float
},
{
'source': 'w_1',
'target': 'w_1',
'processor': robust_float
},
{
'source': 'w_2',
'target': 'w_2',
'processor': robust_float
},
{
'source': 'w_3',
'target': 'w_3',
'processor': robust_float
},
{
'source': 'effort_model',
'default': 'nominal'
},
{
'source': 'projection',
'target': 'projection',
# Use the mollweide projection as the default.
'default': gis_util.get_default_geographic_crs(),
}
],
},
]
for section in csv_sections:
self.ingest_csv_section(section)
# Convenience shortcuts.
self.model_parameters = self.dao.query('__ModelParameters').fetchone()
self.geographic_crs = self.model_parameters.projection
self.ingest_grid()
self.ingest_habitats()
self.post_ingest()
def ingest_csv_section(self, section):
csv_file = os.path.join(self.data_dir, "%s.csv" % section['id'])
if not os.path.isfile(csv_file):
if not section.get('optional'):
raise Exception(("Error ingesting '%s': "
"File '%s' is required and was not found.") %
(section['id'], csv_file))
else:
return
base_msg = "Ingesting '%s'..." % section['id']
self.logger.info(base_msg)
section_config = self.config.get('sections', {}).get(section['id'], {})
Ingestor(
reader=CSVReader(csv_file=csv_file),
processors=[
ClassMapper(clazz=section['class'],
mappings=section['mappings']),
DAOWriter(dao=self.dao, commit_interval=self.commit_interval),
],
logger=self.get_section_logger(section['id'], base_msg),
limit=section_config.get('limit'),
).ingest()
self.dao.commit()
def ingest_grid(self):
base_msg = "Ingesting 'grid'..."
self.logger.info(base_msg)
grid_logger = self.get_section_logger('grid', base_msg)
self.cells = {}
grid_file = os.path.join(self.data_dir, 'grid', "grid.shp")
grid_config = self.config.get('sections', {}).get('grid', {})
Ingestor(
reader=ShapefileReader(
shp_file=grid_file,
reproject_to='EPSG:4326',
),
processors=[
ClassMapper(clazz=self.dao.schema['sources']['Cell'],
mappings=[{
'source': 'ID',
'target': 'id',
'processor': int
}, {
'source': '__shape',
'target': 'shape'
}, {
'source': '__shape',
'target': 'geom_wkt',
'processor': gis_util.shape_to_wkt
}]),
self.add_area_mbr,
DictWriter(dict_=self.cells),
],
logger=grid_logger,
limit=grid_config.get('limit'),
).ingest()
def ingest_habitats(self):
base_msg = "Ingesting 'habitats'..."
self.logger.info(base_msg)
habs_logger = self.get_section_logger('habs', base_msg)
self.habs = {}
self.habs_spatial_hash = SpatialHash(cell_size=self.hash_cell_size)
habs_file = os.path.join(self.data_dir, 'habitats', "habitats.shp")
habs_config = self.config.get('sections', {}).get('habitats', {})
def add_to_habs_spatial_hash(data=None, **kwargs):
self.habs_spatial_hash.add_rect(data.mbr, data)
return data
def process_neg_depth(neg_depth):
if neg_depth is not None:
depth = -1.0 * float(neg_depth)
return depth
Ingestor(
reader=ShapefileReader(
shp_file=habs_file,
reproject_to='EPSG:4326',
),
processors=[
ClassMapper(clazz=self.dao.schema['sources']['Habitat'],
mappings=[
{
'source': 'SUBSTRATE',
'target': 'substrate_id'
},
{
'source': 'ENERGY',
'target': 'energy_id'
},
{
'source': 'Z',
'target': 'depth',
'processor': process_neg_depth
},
{
'source': '__shape',
'target': 'shape'
},
]),
self.add_area_mbr,
add_to_habs_spatial_hash,
DictWriter(dict_=self.habs),
],
logger=habs_logger,
limit=habs_config.get('limit'),
).ingest()
def get_section_logger(self, section_id, base_msg):
logger = logging.getLogger("%s_%s" % (id(self), section_id))
formatter = logging.Formatter(base_msg + ' %(message)s.')
log_handler = LoggerLogHandler(self.logger)
log_handler.setFormatter(formatter)
logger.addHandler(log_handler)
logger.setLevel(self.logger.level)
return logger
def post_ingest(self):
self.post_process_cells()
# Allow for cells and habs to be garbage collected.
self.cells = None
self.habs = None
self.habs_spatial_hash = None
def post_process_cells(self, log_interval=1000):
base_msg = 'Calculating cell compositions...'
self.logger.info(base_msg)
logger = self.get_section_logger('habitat_areas', base_msg)
num_cells = len(self.cells)
counter = 0
for cell in self.cells.values():
counter += 1
if (counter % log_interval) == 0:
logger.info(
" %d of %d (%.1f%%)" %
(counter, num_cells, 1.0 * counter / num_cells * 100))
composition = {}
cell.depth = 0
# Get candidate intersecting habitats.
candidate_habs = self.habs_spatial_hash.items_for_rect(cell.mbr)
for hab in candidate_habs:
intersection = gis_util.get_intersection(cell.shape, hab.shape)
if not intersection:
continue
intersection_area = gis_util.get_shape_area(
intersection,
target_crs=self.geographic_crs,
)
hab_key = (
hab.substrate_id,
hab.energy_id,
)
pct_area = intersection_area / cell.area
composition[hab_key] = composition.get(hab_key, 0) + pct_area
cell.depth += pct_area * hab.depth
cell.habitat_composition = composition
# Convert cell area to km^2.
cell.area = cell.area / (1000.0**2)
self.dao.save(cell, commit=False)
self.dao.commit()
# Define processor for adding area, mbr to geom entities.
def add_area_mbr(self, data=None, **kwargs):
data.area = gis_util.get_shape_area(data.shape,
target_crs=self.geographic_crs)
data.mbr = gis_util.get_shape_mbr(data.shape)
return data
class SASIGridderTask(task_manager.Task):
def __init__(self, config={}, data={}, **kwargs):
super(SASIGridderTask, self).__init__(**kwargs)
self.logger.debug("RunSasiTask.__init__")
self.data = data
self.config = config
self.value_attrs = models.Effort.value_attrs
self.key_attrs = ['gear_id', 'time']
# Define trip type to gear code mappings.
self.trip_type_gear_mappings = kwargs.get('gear_mappings', {
'hy_drg': 'GC30',
'otter': 'GC10',
'sca-gc': 'GC21',
'sca-la': 'GC20',
'shrimp': 'GC11',
'squid': 'GC12',
'raised': 'GC13',
'trap': 'GC60',
'gillne': 'GC50',
'longli': 'GC40',
})
for kwarg in ['raw_efforts_path', 'grid_path', 'stat_areas_path',
'output_path', 'effort_limit']:
setattr(self, kwarg, kwargs.get(kwarg))
if not self.output_path:
os_hndl, self.output_path = tempfile.mkstemp(
prefix="gridded_efforts.", suffix='.csv')
self.message_logger = logging.getLogger("Task%s_msglogger" % id(self))
main_log_handler = LoggerLogHandler(self.logger)
main_log_handler.setFormatter(
logging.Formatter('%(message)s'))
self.message_logger.addHandler(main_log_handler)
self.message_logger.setLevel(self.logger.level)
def call(self):
self.progress = 1
self.message_logger.info("Starting...")
# Create build dir.
build_dir = tempfile.mkdtemp(prefix="gridderWork.")
# Read in data.
base_msg = "Ingesting..."
ingest_logger = self.get_logger_logger('ingest', base_msg,
self.logger)
self.message_logger.info(base_msg)
# Read in cells.
self.ingest_cells(parent_logger=ingest_logger, limit=None)
# Read in stat_areas.
self.ingest_stat_areas(parent_logger=ingest_logger)
#
# Main part of the gridding task.
#
base_msg = "Gridding."
gridding_logger = self.get_logger_logger('gridding', base_msg,
self.logger)
self.message_logger.info(base_msg)
#
# 0. Terms used here:
# 'clean' efforts can be assigned to a cell.
# 'kinda_dirty' efforts can be assigned to a stat_area.
# 'super_dirty' efforts can not be assigned to a cell or a stat_area.
#
# Running example:
# We start with two cells, 'C1' and 'C2', and one stat_area , 'StatArea1'.
# 'StatArea1' contains 50% of 'C1', and 100% of 'C2'.
#
#
# 1. Assign 'clean' efforts to cells, assign kinda-dirty efforts to
# stat areas, and save super-dirty efforts to the super-dirty efforts list.
#
# Running example:
# We have 100 points of clean effort which can be assigned to 'C1',
# 100 points of clean effort which can be assigned to 'C2',
# 100 points of kinda-dirty effort which can be assigned to 'StatArea1',
# and 100 points of super-dirty effort which can't be assigned to anything.
# After this first step, both 'C1' and 'C2' will have 100 points of effort assigned
# from clean efforts.
#
# Do the first pass on efforts
# as we read them in.
base_msg = "Assigning raw efforts to cells/stat_areas ... "
fp_logger = self.get_logger_logger('first_pass', base_msg,
gridding_logger)
fp_logger.info(base_msg)
unassigned = {}
logging_interval = 1e4
# Define functions to handle raw effort columns
def trip_type_to_gear_id(trip_type):
return self.trip_type_gear_mappings.get(trip_type)
def float_w_empty_dot(value):
if value == '.' or value == '':
return None
elif value is not None:
return float(value)
# Define function to execute after each raw effort is mapped to an
# effort column. This is the first pass described above.
def first_pass(data=None, **kwargs):
#effort = data
#if (effort_counter % 1e3) == 0:
# print ["%s: %.3e" % (k, v) for k,v in c_.items()]
# If effort has lat and lon...
if data.lat is not None and data.lon is not None:
# Can effort can be assigned to cell?
cell = self.get_cell_for_pos(data.lat, data.lon)
if cell:
self.add_effort_to_cell(cell, data)
return
# Otherwise can effort can be assigned to statarea?
stat_area = self.get_stat_area_for_pos(
data.lat, data.lon)
if stat_area:
self.add_effort_to_stat_area(stat_area, data)
return
# Otherwise add to unassigned.
else:
self.add_effort_to_unassigned(unassigned, data)
return
# Otherwise if effort has a stat area...
elif data.stat_area_id is not None:
stat_area = self.stat_areas.get(data.stat_area_id)
if not stat_area:
self.add_effort_to_unassigned(unassigned, data)
return
else:
self.add_effort_to_stat_area(stat_area, data)
return
# Otherwise add to unassigned list.
else:
self.add_effort_to_unassigned(unassigned, data)
return
# Create and run effort ingestor.
ingestor = Ingestor(
reader=CSVReader(csv_file=self.raw_efforts_path),
processors=[
ClassMapper(
clazz=models.Effort,
mappings=[
{'source': 'trip_type', 'target': 'gear_id',
'processor': trip_type_to_gear_id},
{'source': 'year', 'target': 'time',
'processor': float_w_empty_dot},
{'source': 'nemarea', 'target': 'stat_area_id',
'processor': float_w_empty_dot},
{'source': 'A', 'target': 'a',
'processor': float_w_empty_dot},
{'source': 'value', 'target': 'value',
'processor': float_w_empty_dot},
{'source': 'hours_fished', 'target': 'hours_fished',
'processor': float_w_empty_dot},
{'source': 'lat', 'target': 'lat',
'processor': float_w_empty_dot},
{'source': 'lon', 'target': 'lon',
'processor': float_w_empty_dot}
],
),
first_pass,
],
logger=fp_logger,
get_count=True,
limit=self.effort_limit,
).ingest()
#
# 2. For each effort assigned to a stat area,
# distribute values across cracked cells in that stat area.
# We distribute values in proportion to the amount of value
# contained in the cracked cell relative to the total amount
# of 'clean' value the stat area already contains.
#
# Running Example:
# We now distribute the 100 points of kinda effort which can be assigned to 'StatArea1'.
# We distribute the effort proportionally to the cracked cells,
# so that 'C1' gets 33 additional effort points, and 'C2' gets 66 additional effort points.
#
base_msg = "Distributing stat_area values to cells ... "
sa_logger = self.get_logger_logger('stat_areas', base_msg,
gridding_logger)
sa_logger.info(base_msg)
num_stat_areas = len(self.stat_areas)
logging_interval = 1
sa_counter = 0
for stat_area in self.stat_areas.values():
sa_counter += 1
if (sa_counter % logging_interval) == 0:
sa_logger.info("stat_area %s of %s (%.1f%%)" % (
sa_counter, num_stat_areas,
100.0 * sa_counter/num_stat_areas))
# Get stat area values.
sa_keyed_values = self.sa_values.setdefault(stat_area.id, {})
# Get list of cracked cells.
cracked_cells = self.get_cracked_cells_for_stat_area(stat_area)
# Calculate totals for values across cracked cells.
ccell_totals = {}
for ccell in cracked_cells:
for effort_key, ccell_values in ccell.keyed_values.items():
ccell_totals_values = ccell_totals.setdefault(
effort_key,
self.new_values_dict()
)
for attr, ccell_value in ccell_values.items():
ccell_totals_values[attr] += ccell_value
# Distribute the stat area's values across the cracked
# cells, in proportion to the cracked cell's values as a
# percentage of the stat area's cracked cell totals.
for ccell in cracked_cells:
pcell_keyed_values = self.c_values[ccell.parent_cell.id]
for effort_key, sa_values in sa_keyed_values.items():
ccell_totals_values = ccell_totals.get(effort_key)
ccell_values = ccell.keyed_values.get(effort_key)
pcell_values = pcell_keyed_values.setdefault(
effort_key, self.new_values_dict())
if not ccell_totals_values or not ccell_values:
continue
for attr, sa_value in sa_values.items():
# Don't add anything for empty values.
# This also avoids division by zero errors.
if not sa_value:
continue
ccell_value = ccell_values.get(attr, 0.0)
ccell_totals_value = ccell_totals_values.get(attr, 0.0)
if not ccell_value or not ccell_totals_value:
continue
pct_value = ccell_value/ccell_totals_value
# Add proportional value to cracked cell's parent
# cell.
pcell_values[attr] += sa_value * pct_value
#
# 3. For efforts which could not be assigned to a cell or a stat area
# ('super-dirty' efforts), distribute the efforts across all cells,
# such that the amount of effort each cell is receives is proportional to the cell's
# total contribution to the overall total.
#
# Running Example:
# We start cells 'C1' and 'C2'.
# 'C1' starts with 133 effort points from clean efforts + kinda-dirty efforts.
# Likewise 'C1' starts with 166 effort points from clean efforts + kinda-dirty efforts.
# Our overall total is 133 + 166 = 300.
# 'C1' is responsible for 133/300 = 45% of the total effort.
# 'C2' is responsible for 166/300 = 55% of the total effort.
# We then have 100 additional points of super-dirty effort which could not be assigned to any cell
# or stat area.
# We distributed the effort proportionally to the cells so that
# 'C1' gets 45 additional effort points, and 'C2' gets 55 additional effort points.
# Our final result is that 'C1' has 133 + 45 = 178 effort points, and
# 'C2' has 166 + 55 = 221 effort points.
base_msg = "Distributing unassigned values to cells ... "
unassigned_logger = self.get_logger_logger('unassigned', base_msg,
gridding_logger)
unassigned_logger.info(base_msg)
# Calculate totals across all cells.
totals = {}
num_cells = len(self.cells)
for cell in self.cells.values():
cell_keyed_values = self.c_values[cell.id]
for effort_key, cell_values in cell_keyed_values.items():
totals_values = totals.setdefault(
effort_key,
self.new_values_dict()
)
for attr, cell_value in cell_values.items():
totals_values[attr] += cell_value
# Distribute unassigned efforts across all cells,
# in proportion to the cell's values as a percentage of the total.
logging_interval = 1e3
cell_counter = 0
for cell in self.cells.values():
cell_counter += 1
if (cell_counter % logging_interval) == 0:
unassigned_logger.info("cell %s of %s (%.1f%%)" % (
cell_counter, num_cells, 100.0 * cell_counter/num_cells))
cell_keyed_values = self.c_values[cell.id]
for effort_key, unassigned_values in unassigned.items():
cell_values = cell_keyed_values.get(effort_key)
if not cell_values:
continue
for attr, unassigned_value in unassigned_values.items():
if not unassigned_value:
continue
cell_value = cell_values.get(attr, 0.0)
pct_value = cell_value/unassigned_value
cell_values[attr] += unassigned_value * pct_value
# Done with gridding. At this point the effort has been distributed.
# Note that there may be some efforts which are not included.
# For example, if an unassigned effort has an effort_key which is
# not used by any effort assigned to a cell or a stat_area, then
# no cell will have a non-zero pct_value for that effort_key.
#
# Output gridded efforts.
#
with open(self.output_path, "w") as f:
w = csv.writer(f)
fields = ['cell_id'] + self.key_attrs + self.value_attrs
w.writerow(fields)
for cell in self.cells.values():
cell_keyed_values = self.c_values[cell.id]
for keys, values in cell_keyed_values.items():
row_dict = {
'cell_id': cell.id
}
for i in range(len(self.key_attrs)):
row_dict[self.key_attrs[i]] = keys[i]
row_dict.update(values)
w.writerow([row_dict[f] for f in fields])
shutil.rmtree(build_dir)
self.progress = 100
self.message_logger.info("Gridding completed, output file is:'%s'" % (
self.output_path))
self.data['output_file'] = self.output_path
self.status = 'resolved'
def get_logger_logger(self, name=None, base_msg=None, parent_logger=None):
logger = logging.getLogger("%s_%s" % (id(self), name))
formatter = logging.Formatter(base_msg + ' %(message)s.')
log_handler = LoggerLogHandler(parent_logger)
log_handler.setFormatter(formatter)
logger.addHandler(log_handler)
logger.setLevel(self.message_logger.level)
return logger
def get_cell_for_pos(self, lat, lon):
"""
Get cell which contains given point, via
spatial hash.
"""
pos_wkt = 'POINT(%s %s)' % (lon, lat)
pnt_shp = gis_util.wkt_to_shape(pos_wkt)
candidates = self.cell_spatial_hash.items_for_point((lon,lat))
for c in candidates:
if gis_util.get_intersection(c.shape, pnt_shp):
return c
return None
def get_stat_area_for_pos(self, lat, lon):
pos_wkt = 'POINT(%s %s)' % (lon, lat)
pnt_shp = gis_util.wkt_to_shape(pos_wkt)
candidates = self.sa_spatial_hash.items_for_point((lon,lat))
for c in candidates:
if gis_util.get_intersection(c.shape, pnt_shp):
return c
return None
def new_values_dict(self):
return dict(zip(self.value_attrs, [0.0] * len(self.value_attrs)))
def update_values_dict(self, values_dict, effort):
for k in values_dict.keys():
effort_value = getattr(effort, k, 0.0)
if effort_value is None:
effort_value = 0.0
values_dict[k] += effort_value
def add_effort_to_keyed_values_dict(self, kvd, effort):
values = kvd.setdefault(
self.get_effort_key(effort),
self.new_values_dict()
)
self.update_values_dict(values, effort)
def add_effort_to_cell(self, cell, effort):
cell_keyed_values = self.c_values[cell.id]
self.add_effort_to_keyed_values_dict(cell_keyed_values, effort)
def add_effort_to_stat_area(self, stat_area, effort):
sa_keyed_values = self.sa_values.setdefault(stat_area.id, {})
self.add_effort_to_keyed_values_dict(sa_keyed_values, effort)
def add_effort_to_unassigned(self, unassigned, effort):
self.add_effort_to_keyed_values_dict(unassigned, effort)
def get_effort_key(self, effort):
""" Key for grouping values by effort types. """
return tuple([getattr(effort, attr, None) for attr in self.key_attrs])
def ingest_cells(self, parent_logger=None, limit=None):
self.cells = {}
self.cell_spatial_hash = SpatialHash(cell_size=.1)
self.c_values = {}
logger = self.get_logger_logger(
name='cell_ingest',
base_msg='Ingesting cells...',
parent_logger=parent_logger
)
Ingestor(
reader=ShapefileReader(shp_file=self.grid_path,
reproject_to='EPSG:4326'),
processors=[
ClassMapper(
clazz=models.Cell,
mappings=[{'source': 'ID', 'target': 'id'},
{'source': '__shape', 'target': 'shape'},],
),
DictWriter(dict_=self.cells, key_func=lambda c: c.id),
],
logger=logger,
limit=limit
).ingest()
# Calculate cell areas and add cells to spatial hash,
# and initialize c_values.
for cell in self.cells.values():
cell.area = gis_util.get_shape_area(cell.shape)
cell.mbr = gis_util.get_shape_mbr(cell.shape)
self.cell_spatial_hash.add_rect(cell.mbr, cell)
self.c_values[cell.id] = {}
def ingest_stat_areas(self, parent_logger=None, limit=None):
self.stat_areas = {}
self.sa_spatial_hash = SpatialHash(cell_size=.1)
self.sa_values = {}
logger = self.get_logger_logger(
name='stat_area_ingest',
base_msg='Ingesting stat_areas...',
parent_logger=parent_logger
)
Ingestor(
reader=ShapefileReader(shp_file=self.stat_areas_path,
reproject_to='EPSG:4326'),
processors=[
ClassMapper(
clazz=models.StatArea,
mappings=[{'source': 'SAREA', 'target': 'id'},
{'source': '__shape', 'target': 'shape'},],
),
DictWriter(dict_=self.stat_areas, key_func=lambda sa: sa.id),
],
logger=logger,
limit=limit
).ingest()
# Add to spatial hash.
for stat_area in self.stat_areas.values():
stat_area.mbr = gis_util.get_shape_mbr(stat_area.shape)
self.sa_spatial_hash.add_rect(stat_area.mbr, stat_area)
def get_cracked_cells_for_stat_area(self, stat_area):
cracked_cells = []
candidates = self.cell_spatial_hash.items_for_rect(stat_area.mbr)
for icell in candidates:
intersection = gis_util.get_intersection(stat_area.shape, icell.shape)
if not intersection:
continue
intersection_area = gis_util.get_shape_area(intersection)
pct_area = intersection_area/icell.area
# Set cracked cell values in proportion to percentage
# of parent cell's area.
ccell_keyed_values = {}
icell_keyed_values = self.c_values[icell.id]
for effort_key, icell_values in icell_keyed_values.items():
ccell_values = ccell_keyed_values.setdefault(effort_key, {})
for attr, value in icell_values.items():
ccell_values[attr] = pct_area * value
cracked_cells.append(models.CrackedCell(
parent_cell=icell,
area=intersection_area,
keyed_values=ccell_keyed_values,
))
return cracked_cells
