def _create_flt_file(self, current_year, flt_directory_in, flt_directory_out):
logger.log_status("Convert output data for ", str(current_year))
flt_directory_out = os.path.join(flt_directory_out, 'land_covers')
if not os.path.exists(flt_directory_out):
os.makedirs(flt_directory_out)
lc = LandCoverDataset(in_storage = StorageFactory().get_storage('flt_storage', storage_location = flt_directory_in))
relative_x = lc.get_attribute("relative_x")
relative_y = lc.get_attribute("relative_y")
flat_indices = relative_x * self.ncols * 1.0 + relative_y
if flat_indices[5*self.ncols:] is None or len(flat_indices[5*self.ncols:]) == 0:
offset = 0
else:
offset = 5*self.ncols
logger.start_block("Converting")
try:
for attr_name in lc.get_primary_attribute_names():
if attr_name not in ["relative_x", "relative_y"]:
attr_name = "lct" #-------------- only output lct now
logger.log_status(" ", attr_name)
attr = ma.filled(lc.get_attribute(attr_name), self.nodata_values).astype(float32)
self._create_flt_file2(os.path.join(flt_directory_out, attr_name+".lf4"), attr, flat_indices, offset)
self._create_header(os.path.join(flt_directory_out, attr_name+".hdr")) #<-- added 26 may 09 by mm
del attr
break #-------------- only output lct now
lc.load_dataset(attributes='*')
if lc.get_computed_attribute_names() is not None:
flt_directory_out = os.path.join(flt_directory_out, "computed")
if not os.path.exists(flt_directory_out):
os.makedirs(flt_directory_out)
for attr_name in lc.get_computed_attribute_names():
if attr_name not in ["_hidden_id_"]:
if attr_name[0:5] == "probs":
logger.log_status(" ", attr_name)
attr = ma.filled(lc.get_attribute(attr_name), self.nodata_values).astype(float32)
self._create_flt_file2(os.path.join(flt_directory_out, attr_name+".lf4"), attr, flat_indices, offset)
self._create_header(os.path.join(flt_directory_out, attr_name+".hdr")) #<-- added 26 may 09 by mm
del attr
finally:
# lc.flush_dataset() # added 23 jun 2009 - not tested...
logger.end_block()
#index_attribute = sys.argv[2]
index_attribute = "lc0207_100k_0"
# 4. Years - date pair of input data; year is concatenated to flt_directory_in specified in #1
#years = [1991, 1995]
#years = [1995, 1999]
#years = [2002]
#years = sys.argv[3]
years = [2007, 2007]
lc1 = LandCoverDataset(in_storage = StorageFactory().get_storage('flt_storage',
storage_location = os.path.join(flt_directory_in, str(years[0]))),
out_storage = StorageFactory().get_storage('flt_storage',
storage_location = os.path.join(flt_directory_out, str(years[0]))))
agents_index = where(lc1.get_attribute(index_attribute))[0]
lc1subset = DatasetSubset(lc1, agents_index)
print "Writing set 1:"
for attr in lc1.get_primary_attribute_names():
print " ", attr
lc1subset.write_dataset(attributes=[attr], out_table_name="land_covers")
lc1.delete_one_attribute(attr) # leaving this line in causes the processing of every other input data file; commenting it causes memory error
lc2 = LandCoverDataset(in_storage = StorageFactory().get_storage('flt_storage',
storage_location = os.path.join(flt_directory_in, str(years[1]))),
out_storage = StorageFactory().get_storage('flt_storage',
storage_location = os.path.join(flt_directory_out, str(years[1]))))
lc2subset = DatasetSubset(lc2, agents_index)
print "Writing set 2:"
for attr in lc2.get_primary_attribute_names():
class LCCMEstimator(Estimator):
def __init__(self, **kargs):
# Estimator.__init__(self, settings=None, run_land_price_model_before_estimation=False, **kargs) # <-- old __init__
# Estimator.__init__(self, config=None, save_estimation_results=True) # <-- new __init__ doesn't work, but not needed
parent_dir_path = package().get_package_parent_path()
package_path = OpusPackage().get_path_for_package("biocomplexity")
self.storage = StorageFactory().get_storage(
'tab_storage', storage_location=os.path.join(package_path, 'data'))
## 1. directory path of full (4 county spatial extent) dataset
flt_directory = os.path.join(parent_dir_path, "biocomplexity", "data",
"LCCM_4County")
## 2. select (uncomment) from one the following choices of directory pathes of subsetted sample input data/variables
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "LCCM_small_test_set_opus")
flt_directory_est = os.path.join(parent_dir_path, "biocomplexity",
"data", "data_for_estimation_all")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_estimation_all_orig")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_suburban_orig")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_urban")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_urban_orig")
## note - must rename lct-forusewith91sample.Float32 to lct.lf4 if doing 1991-1995
## note - must rename lct-forusewith95sample.Float32 to lct.lf4 if doing 1995-1999
## 3. select (uncomment) from one the following choices of land cover data (input data) date pairs (years)
# years = [1991, 1995]
years = [1995, 1999]
# years = [1999, 2002]
self.lc1 = LandCoverDataset(in_storage=StorageFactory().get_storage(
"flt_storage",
storage_location=os.path.join(flt_directory_est, str(years[0]))),
resources=Resources({"lowercase": 1}))
self.lc2 = LandCoverDataset(in_storage=StorageFactory().get_storage(
"flt_storage",
storage_location=os.path.join(flt_directory_est, str(years[1]))),
resources=Resources({"lowercase": 1}))
self.lc1_all = LandCoverDataset(
in_storage=StorageFactory().get_storage(
"flt_storage",
storage_location=os.path.join(flt_directory, str(years[0]))),
resources=Resources({"lowercase": 1}))
self.lc1_all.flush_dataset()
self.lc2_all = LandCoverDataset(
in_storage=StorageFactory().get_storage(
"flt_storage",
storage_location=os.path.join(flt_directory, str(years[1]))),
resources=Resources({"lowercase": 1}))
self.lc2_all.flush_dataset()
def estimate(self, spec_py=None, spec_var=None, spec_file=None):
t1 = time()
if spec_py is not None:
reload(spec_py)
spec_var = spec_py.specification
if spec_var is not None:
self.specification, variables, coefficents, equations, submodels = \
self.load_specification_from_variable(spec_var)
elif spec_file is not None:
self.specification = EquationSpecification(in_storage=self.storage)
self.specification.load(in_table_name=spec_file)
self.specification.set_dataset_name_of_variables("land_cover")
self.model_name = "land_cover_change_model"
choices = range(1, 15)
lccm = LandCoverChangeModel(choices, submodel_string="lct")
## 4. select (uncomment) from one the following choices of subsetted sampling files (agents_index)
# agents_index = where(self.lc1.get_attribute("sall_91_95_0"))[0]
agents_index = where(self.lc1.get_attribute("sall_95_99_0"))[0]
# agents_index = where(self.lc1.get_attribute("sall_99_02_0b"))[0]
# agents_index = where(self.lc1.get_attribute("sa9902_9195_0"))[0]
# agents_index = where(self.lc1.get_attribute("sa9902_9599_0"))[0]
# agents_index = where(self.lc1.get_attribute("suburb91_95sample0"))[0]
# agents_index = where(self.lc1.get_attribute("suburb95_99sample0"))[0]
# agents_index = where(self.lc1.get_attribute("up91x95_old_samp0"))[0]
# agents_index = where(self.lc1.get_attribute("urbsamp95_99_0"))[0]
## need to include agents_index_all seperate for the calibration portion
## when using the dataset at the full extent, agents_index_all is needed as it is
## created from the lc1_all agents_set and matches the size of the input data
## 5. select (uncomment) from one the following choices of sampling files (agents_index) at full spatial extent
# agents_index_all = where(self.lc1_all.get_attribute("sall_91_95_0"))[0]
agents_index_all = where(self.lc1_all.get_attribute("sall_95_99_0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("sall_99_02_0b"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("sa9902_9195_0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("sa9902_9599_0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("suburb91_95sample0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("suburb95_99sample0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("up91x95_old_samp0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("urbsamp95_99_0"))[0]
coef, results = lccm.estimate(self.specification,
self.lc1,
self.lc2,
agents_index=agents_index,
debuglevel=4)
new_coef = lccm.calibrate(self.lc1_all, self.lc2_all, agents_index_all)
specification = lccm.specification
#save estimation results
# out_suffix = spec_py.__name__[len(spec_py.__name__) - 11:]
out_suffix = spec_py.__name__[30:]
specification.write(out_storage=self.storage,
out_table_name='lccm_specification_%sc' %
out_suffix)
new_coef.write(out_storage=self.storage,
out_table_name='lccm_coefficients_%sc' % out_suffix)
logger.log_status("Estimation done. %s s" % str(time() - t1))
def load_specification_from_variable(self, spec_var):
variables = []
coefficients = []
equations = []
submodels = []
try:
for sub_model, submodel_spec in spec_var.items():
if not isinstance(submodel_spec, dict):
raise ValueError, "Wrong specification format"
if submodel_spec.has_key("equation_ids"):
equation_ids = submodel_spec[
"equation_ids"] ## this retrieves eq_ids from spec.py - they're stored in equations then passed to the equation specifications
del submodel_spec["equation_ids"]
else:
equation_ids = None
for var, coefs in submodel_spec.items():
if not equation_ids:
equation_ids = range(1, len(coeffs) + 1)
for i in range(len(coefs)):
if coefs[i] != 0:
variables.append(var)
coefficients.append(coefs[i])
equations.append(equation_ids[i])
submodels.append(sub_model)
except:
raise ValueError, "Wrong specification format for submodel variable."
specification = EquationSpecification(variables=variables,
coefficients=coefficients,
equations=equations,
submodels=submodels)
return (specification, variables, coefficients, equations, submodels)
test_flag = options.test_flag
flt_directory_in = options.input
flt_directory_out = options.output
logger.log_status("Convert output data for ", str(current_year))
#todo: how to get 'land_covers' from dataset?
flt_directory_out = os.path.join(flt_directory_out, 'land_covers')
if not os.path.exists(flt_directory_out):
os.makedirs(flt_directory_out)
lc = LandCoverDataset(in_storage = StorageFactory().get_storage('flt_storage', storage_location = flt_directory_in))
relative_x = lc.get_attribute("relative_x")
relative_y = lc.get_attribute("relative_y")
flat_indices = relative_x * ncols * 1.0 + relative_y
if flat_indices[5*ncols:] is None or len(flat_indices[5*ncols:]) == 0:
offset = 0
else:
offset = 5*ncols
#if os.path.exists("indices.lf4"):
# os.remove("indices.lf4")
#flat_indices.tofile("indices.lf4")
logger.start_block("Converting")
try:
for attr_name in lc.get_primary_attribute_names():
def _create_flt_file(self, current_year, flt_directory_in,
flt_directory_out):
logger.log_status("Convert output data for ", str(current_year))
flt_directory_out = os.path.join(flt_directory_out, 'land_covers')
if not os.path.exists(flt_directory_out):
os.makedirs(flt_directory_out)
lc = LandCoverDataset(in_storage=StorageFactory().get_storage(
'flt_storage', storage_location=flt_directory_in))
relative_x = lc.get_attribute("relative_x")
relative_y = lc.get_attribute("relative_y")
flat_indices = relative_x * self.ncols * 1.0 + relative_y
if flat_indices[5 * self.ncols:] is None or len(
flat_indices[5 * self.ncols:]) == 0:
offset = 0
else:
offset = 5 * self.ncols
logger.start_block("Converting")
try:
for attr_name in lc.get_primary_attribute_names():
if attr_name not in ["relative_x", "relative_y"]:
attr_name = "lct" #-------------- only output lct now
logger.log_status(" ", attr_name)
attr = ma.filled(lc.get_attribute(attr_name),
self.nodata_values).astype(float32)
self._create_flt_file2(
os.path.join(flt_directory_out, attr_name + ".lf4"),
attr, flat_indices, offset)
self._create_header(
os.path.join(flt_directory_out, attr_name +
".hdr")) #<-- added 26 may 09 by mm
del attr
break #-------------- only output lct now
lc.load_dataset(attributes='*')
if lc.get_computed_attribute_names() is not None:
flt_directory_out = os.path.join(flt_directory_out, "computed")
if not os.path.exists(flt_directory_out):
os.makedirs(flt_directory_out)
for attr_name in lc.get_computed_attribute_names():
if attr_name not in ["_hidden_id_"]:
if attr_name[0:5] == "probs":
logger.log_status(" ", attr_name)
attr = ma.filled(
lc.get_attribute(attr_name),
self.nodata_values).astype(float32)
self._create_flt_file2(
os.path.join(flt_directory_out,
attr_name + ".lf4"), attr,
flat_indices, offset)
self._create_header(
os.path.join(
flt_directory_out, attr_name +
".hdr")) #<-- added 26 may 09 by mm
del attr
finally:
# lc.flush_dataset() # added 23 jun 2009 - not tested...
logger.end_block()
# 4. Years - date pair of input data; year is concatenated to flt_directory_in specified in #1
#years = [1991, 1995]
#years = [1995, 1999]
#years = [2002]
#years = sys.argv[3]
years = [2007, 2007]
lc1 = LandCoverDataset(in_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=os.path.join(flt_directory_in, str(years[0]))),
out_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=os.path.join(
flt_directory_out, str(years[0]))))
agents_index = where(lc1.get_attribute(index_attribute))[0]
lc1subset = DatasetSubset(lc1, agents_index)
print "Writing set 1:"
for attr in lc1.get_primary_attribute_names():
print " ", attr
lc1subset.write_dataset(attributes=[attr], out_table_name="land_covers")
lc1.delete_one_attribute(
attr
) # leaving this line in causes the processing of every other input data file; commenting it causes memory error
lc2 = LandCoverDataset(in_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=os.path.join(flt_directory_in, str(years[1]))),
out_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=os.path.join(
class LCCMEstimator(Estimator):
def __init__(self, **kargs):
# Estimator.__init__(self, settings=None, run_land_price_model_before_estimation=False, **kargs) # <-- old __init__
# Estimator.__init__(self, config=None, save_estimation_results=True) # <-- new __init__ doesn't work, but not needed
parent_dir_path = package().get_package_parent_path()
package_path = OpusPackage().get_path_for_package("biocomplexity")
self.storage = StorageFactory().get_storage('tab_storage',
storage_location=os.path.join(package_path, 'data'))
## 1. directory path of full (4 county spatial extent) dataset
flt_directory = os.path.join(parent_dir_path, "biocomplexity", "data", "LCCM_4County")
## 2. select (uncomment) from one the following choices of directory pathes of subsetted sample input data/variables
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "LCCM_small_test_set_opus")
flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_estimation_all")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_estimation_all_orig")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_suburban_orig")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_urban")
# flt_directory_est = os.path.join(parent_dir_path, "biocomplexity", "data", "data_for_urban_orig")
## note - must rename lct-forusewith91sample.Float32 to lct.lf4 if doing 1991-1995
## note - must rename lct-forusewith95sample.Float32 to lct.lf4 if doing 1995-1999
## 3. select (uncomment) from one the following choices of land cover data (input data) date pairs (years)
# years = [1991, 1995]
years = [1995, 1999]
# years = [1999, 2002]
self.lc1 = LandCoverDataset(in_storage = StorageFactory().get_storage("flt_storage",
storage_location = os.path.join(flt_directory_est, str(years[0]))),
resources=Resources({"lowercase":1}))
self.lc2 = LandCoverDataset(in_storage = StorageFactory().get_storage("flt_storage",
storage_location = os.path.join(flt_directory_est, str(years[1]))),
resources=Resources({"lowercase":1}))
self.lc1_all = LandCoverDataset(in_storage = StorageFactory().get_storage("flt_storage",
storage_location = os.path.join(flt_directory, str(years[0]))),
resources=Resources({"lowercase":1}))
self.lc1_all.flush_dataset()
self.lc2_all = LandCoverDataset(in_storage = StorageFactory().get_storage("flt_storage",
storage_location = os.path.join(flt_directory, str(years[1]))),
resources=Resources({"lowercase":1}))
self.lc2_all.flush_dataset()
def estimate(self, spec_py=None, spec_var=None, spec_file=None):
t1 = time()
if spec_py is not None:
reload(spec_py)
spec_var = spec_py.specification
if spec_var is not None:
self.specification, variables, coefficents, equations, submodels = \
self.load_specification_from_variable(spec_var)
elif spec_file is not None:
self.specification = EquationSpecification(in_storage=self.storage)
self.specification.load(in_table_name=spec_file)
self.specification.set_dataset_name_of_variables("land_cover")
self.model_name = "land_cover_change_model"
choices = range(1,15)
lccm = LandCoverChangeModel(choices, submodel_string="lct")
## 4. select (uncomment) from one the following choices of subsetted sampling files (agents_index)
# agents_index = where(self.lc1.get_attribute("sall_91_95_0"))[0]
agents_index = where(self.lc1.get_attribute("sall_95_99_0"))[0]
# agents_index = where(self.lc1.get_attribute("sall_99_02_0b"))[0]
# agents_index = where(self.lc1.get_attribute("sa9902_9195_0"))[0]
# agents_index = where(self.lc1.get_attribute("sa9902_9599_0"))[0]
# agents_index = where(self.lc1.get_attribute("suburb91_95sample0"))[0]
# agents_index = where(self.lc1.get_attribute("suburb95_99sample0"))[0]
# agents_index = where(self.lc1.get_attribute("up91x95_old_samp0"))[0]
# agents_index = where(self.lc1.get_attribute("urbsamp95_99_0"))[0]
## need to include agents_index_all seperate for the calibration portion
## when using the dataset at the full extent, agents_index_all is needed as it is
## created from the lc1_all agents_set and matches the size of the input data
## 5. select (uncomment) from one the following choices of sampling files (agents_index) at full spatial extent
# agents_index_all = where(self.lc1_all.get_attribute("sall_91_95_0"))[0]
agents_index_all = where(self.lc1_all.get_attribute("sall_95_99_0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("sall_99_02_0b"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("sa9902_9195_0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("sa9902_9599_0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("suburb91_95sample0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("suburb95_99sample0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("up91x95_old_samp0"))[0]
# agents_index_all = where(self.lc1_all.get_attribute("urbsamp95_99_0"))[0]
coef, results = lccm.estimate(self.specification, self.lc1, self.lc2, agents_index=agents_index, debuglevel=4)
new_coef = lccm.calibrate(self.lc1_all, self.lc2_all, agents_index_all)
specification = lccm.specification
#save estimation results
# out_suffix = spec_py.__name__[len(spec_py.__name__) - 11:]
out_suffix = spec_py.__name__[30:]
specification.write(out_storage=self.storage, out_table_name='lccm_specification_%sc' % out_suffix)
new_coef.write(out_storage=self.storage, out_table_name='lccm_coefficients_%sc' % out_suffix)
logger.log_status("Estimation done. %s s" % str(time()-t1))
def load_specification_from_variable(self, spec_var):
variables = []
coefficients = []
equations = []
submodels = []
try:
for sub_model, submodel_spec in spec_var.items():
if not isinstance(submodel_spec, dict):
raise ValueError, "Wrong specification format"
if submodel_spec.has_key("equation_ids"):
equation_ids = submodel_spec["equation_ids"] ## this retrieves eq_ids from spec.py - they're stored in equations then passed to the equation specifications
del submodel_spec["equation_ids"]
else:
equation_ids = None
for var, coefs in submodel_spec.items():
if not equation_ids:
equation_ids = range(1, len(coeffs)+1)
for i in range(len(coefs)):
if coefs[i] != 0:
variables.append(var)
coefficients.append(coefs[i])
equations.append(equation_ids[i])
submodels.append(sub_model)
except:
raise ValueError, "Wrong specification format for submodel variable."
specification = EquationSpecification(variables=variables,
coefficients=coefficients,
equations = equations,
submodels=submodels)
return (specification, variables, coefficients, equations, submodels)
test_flag = options.test_flag
flt_directory_in = options.input
flt_directory_out = options.output
logger.log_status("Convert output data for ", str(current_year))
#todo: how to get 'land_covers' from dataset?
flt_directory_out = os.path.join(flt_directory_out, 'land_covers')
if not os.path.exists(flt_directory_out):
os.makedirs(flt_directory_out)
lc = LandCoverDataset(in_storage=StorageFactory().get_storage(
'flt_storage', storage_location=flt_directory_in))
relative_x = lc.get_attribute("relative_x")
relative_y = lc.get_attribute("relative_y")
flat_indices = relative_x * ncols * 1.0 + relative_y
if flat_indices[5 * ncols:] is None or len(flat_indices[5 * ncols:]) == 0:
offset = 0
else:
offset = 5 * ncols
#if os.path.exists("indices.lf4"):
# os.remove("indices.lf4")
#flat_indices.tofile("indices.lf4")
logger.start_block("Converting")
try:
for attr_name in lc.get_primary_attribute_names():
def do_test_on_expected_data(self, input_variables_list, input_resources=None,
element_atol=None, sum_atol=None):
from biocomplexity.datasets.land_cover_dataset import LandCoverDataset
from biocomplexity.tests.utils.land_cover_tests_utils import make_input_data
import os
package_dir_path = package().get_package_path()
flt_directory = os.path.join(package_dir_path, "data", "small_test_set_opus", "1995")
#flt_directory = r"C:\eclipse\LCCM_small_test_set_converted\1991"
expected_lc = LandCoverDataset(in_storage = StorageFactory().get_storage('flt_storage', storage_location = flt_directory))
expected_lc.load_dataset()
temp_dir = make_input_data(flt_directory, input_variables_list)
try:
lc = LandCoverDataset(in_storage = StorageFactory().get_storage(
'flt_storage',
storage_location=temp_dir),
out_storage = StorageFactory().get_storage('flt_storage', storage_location = r"c:/tmp"))
lc.load_dataset()
dataset_pool = DatasetPool(
package_order=['biocomplexity'],
storage=StorageFactory().get_storage('flt_storage', storage_location=temp_dir))
dataset_pool._add_dataset('land_cover', lc)
lc.compute_variables(self.variable_name, resources=input_resources,
dataset_pool=dataset_pool)
#lc.write_dataset(attributes='*')
lc_values = lc.get_attribute(self.variable_name)
expected_values = expected_lc.get_attribute(self.variable_name)
if sum_atol is None: sum_atol = 1e-8
if element_atol is None: element_atol = 1e-8
if (not ma.allclose(lc_values, expected_values, atol=element_atol)):
logger.log_status("comparision using element-atol=%f, sum-atol=%f" % (element_atol, sum_atol))
logger.log_status(" computed expected");
logger.log_status("sum: ", lc_values.sum(), expected_values.sum())
logger.log_status("max: ", max(lc_values), max(expected_values))
logger.log_status("min: ", min(lc_values), min(expected_values))
c1 = 0
c2 = 0
for (i,j) in zip(lc_values, expected_values):
if i != 0:
c1 = c1 + 1
if j != 0:
c2 = c2 + 1
logger.log_status("# non-zeros values: ", c1, c2)
logger.log_status("max distance between 2 elements: %f" %
self._max_distance_between_two_elements(lc_values,expected_values))
logger.log_status(lc_values, expected_values)
count = 0
total = 0
for (i,j) in zip(lc_values, expected_values):
if i != j:
count = count + 1
total = total + 1
logger.log_status("# different elements = %d, over %d, with a %f percentage" \
% (count, total, count*1.0/total))
#self.assert_(ma.allclose(lc_values.sum(), expected_values.sum(), atol=sum_atol))
self.assert_(ma.allclose(lc_values, expected_values, atol=element_atol))
finally:
if os.path.exists(temp_dir):
rmtree(temp_dir)
def do_test_on_expected_data(self,
input_variables_list,
input_resources=None,
element_atol=None,
sum_atol=None):
from biocomplexity.datasets.land_cover_dataset import LandCoverDataset
from biocomplexity.tests.utils.land_cover_tests_utils import make_input_data
import os
package_dir_path = package().get_package_path()
flt_directory = os.path.join(package_dir_path, "data",
"small_test_set_opus", "1995")
#flt_directory = r"C:\eclipse\LCCM_small_test_set_converted\1991"
expected_lc = LandCoverDataset(in_storage=StorageFactory().get_storage(
'flt_storage', storage_location=flt_directory))
expected_lc.load_dataset()
temp_dir = make_input_data(flt_directory, input_variables_list)
try:
lc = LandCoverDataset(in_storage=StorageFactory().get_storage(
'flt_storage', storage_location=temp_dir),
out_storage=StorageFactory().get_storage(
'flt_storage',
storage_location=r"c:/tmp"))
lc.load_dataset()
dataset_pool = DatasetPool(package_order=['biocomplexity'],
storage=StorageFactory().get_storage(
'flt_storage',
storage_location=temp_dir))
dataset_pool._add_dataset('land_cover', lc)
lc.compute_variables(self.variable_name,
resources=input_resources,
dataset_pool=dataset_pool)
#lc.write_dataset(attributes='*')
lc_values = lc.get_attribute(self.variable_name)
expected_values = expected_lc.get_attribute(self.variable_name)
if sum_atol is None: sum_atol = 1e-8
if element_atol is None: element_atol = 1e-8
if (not ma.allclose(lc_values, expected_values,
atol=element_atol)):
logger.log_status(
"comparision using element-atol=%f, sum-atol=%f" %
(element_atol, sum_atol))
logger.log_status(" computed expected")
logger.log_status("sum: ", lc_values.sum(),
expected_values.sum())
logger.log_status("max: ", max(lc_values),
max(expected_values))
logger.log_status("min: ", min(lc_values),
min(expected_values))
c1 = 0
c2 = 0
for (i, j) in zip(lc_values, expected_values):
if i != 0:
c1 = c1 + 1
if j != 0:
c2 = c2 + 1
logger.log_status("# non-zeros values: ", c1, c2)
logger.log_status("max distance between 2 elements: %f" %
self._max_distance_between_two_elements(
lc_values, expected_values))
logger.log_status(lc_values, expected_values)
count = 0
total = 0
for (i, j) in zip(lc_values, expected_values):
if i != j:
count = count + 1
total = total + 1
logger.log_status("# different elements = %d, over %d, with a %f percentage" \
% (count, total, count*1.0/total))
#self.assert_(ma.allclose(lc_values.sum(), expected_values.sum(), atol=sum_atol))
self.assert_(
ma.allclose(lc_values, expected_values, atol=element_atol))
finally:
if os.path.exists(temp_dir):
rmtree(temp_dir)
