def build_result_collection(self, exp):
rc = ResultsContainer(
base_dir=exp.get_data_folder(),
base_filename="%s" % self.uuid
)
res_seq = self.res_seq
axis_meta_block = self.base_name
axis_meta_block_labels = self.get_fold_labels()
def create_new_dim_rc(local_rc):
local_rc.axis_list = [axis_meta_block]
local_rc.labels_dict[axis_meta_block] = axis_meta_block_labels
local_rc.init_ar()
local_rc.update_label_index()
# WARNING: We only support homogeneous results, so we only check first element
res_seq_field_name, data_type = res_seq.fields.iteritems().next()
if data_type == "ClassifierResult":
single_rc_list = []
for field_name in res_seq.fields:
rc_single = ResultsContainer("", "")
create_new_dim_rc(rc_single)
for idx, res_seq_cell in enumerate(res_seq.sequence):
rc_single.ar[idx] = res_seq_cell[field_name]
single_rc_list.append(rc_single)
rc.add_dim_layer(single_rc_list, self.collector_spec.label, res_seq.fields.keys())
elif data_type == "ResultsContainer":
if len(res_seq.fields) > 1:
raise Exception("Meta block only support single output of type ResultsContainer")
else:
rc_list = []
for cell in res_seq.sequence:
sub_rc = cell[res_seq_field_name]
sub_rc.load()
rc_list.append(sub_rc)
rc.add_dim_layer(rc_list, self.base_name, self.get_fold_labels())
elif data_type == "SequenceContainer":
# TODO remove this check
pass
else:
raise Exception("Meta blocks only support ClassifierResult "
"or ResultsContainer in the output collection. "
" Instead got: %s" % data_type)
rc.store()
rc.ar = None
self.set_out_var("results_container", rc)
def build_result_collection(self, exp):
if settings.CELERY_DEBUG:
import sys
sys.path.append('/Migration/skola/phd/projects/miXGENE/mixgene_project/wrappers/pycharm-debug.egg')
import pydevd
pydevd.settrace('localhost', port=6901, stdoutToServer=True, stderrToServer=True)
rc = ResultsContainer(
base_dir=exp.get_data_folder(),
base_filename="%s" % self.uuid
)
res_seq = self.res_seq
axis_meta_block = self.base_name
axis_meta_block_labels = self.get_fold_labels()
def create_new_dim_rc(local_rc):
local_rc.axis_list = [axis_meta_block]
local_rc.labels_dict[axis_meta_block] = axis_meta_block_labels
local_rc.init_ar()
local_rc.update_label_index()
# WARNING: We only support homogeneous results, so we only check first element
res_seq_field_name, data_type = res_seq.fields.iteritems().next()
if data_type == "ClassifierResult":
single_rc_list = []
for field_name in res_seq.fields:
rc_single = ResultsContainer("", "")
create_new_dim_rc(rc_single)
for idx, res_seq_cell in enumerate(res_seq.sequence):
rc_single.ar[idx] = res_seq_cell[field_name]
single_rc_list.append(rc_single)
rc.add_dim_layer(single_rc_list, self.collector_spec.label, res_seq.fields.keys())
elif data_type == "ResultsContainer":
if len(res_seq.fields) > 1:
raise Exception("Meta block only support single output of type ResultsContainer")
else:
rc_list = []
for cell in res_seq.sequence:
sub_rc = cell[res_seq_field_name]
sub_rc.load()
rc_list.append(sub_rc)
rc.add_dim_layer(rc_list, self.base_name, self.get_fold_labels())
elif data_type == "SequenceContainer":
# TODO remove this check
pass
else:
raise Exception("Meta blocks only support ClassifierResult "
"or ResultsContainer in the output collection. "
" Instead got: %s" % data_type)
rc.store()
rc.ar = None
self.set_out_var("results_container", rc)
def main(base_dir, base_filename):
rc1 = ResultsContainer("", "")
rc1.ar = np.empty(shape=(2, ), dtype=object)
rc1.axis_list = ["classifiers"]
rc1.labels_dict["classifiers"] = ["svm", "dt"]
from environment.structures import ClassifierResult
c1 = ClassifierResult("", "")
c1.scores["accuracy"] = 0.8
c2 = ClassifierResult("", "")
c2.scores["accuracy"] = 0.95
rc1.ar[0] = c1
rc1.ar[1] = c2
rc2 = copy.deepcopy(rc1)
rc3 = copy.deepcopy(rc1)
rc4 = copy.deepcopy(rc1)
d2_rc = ResultsContainer("", "")
d2_rc.add_dim_layer([rc1, rc2, rc3, rc4], "cv_folds",
["f1", "f2", "f3", "f4"])
d2rc1 = copy.deepcopy(d2_rc)
d2rc2 = copy.deepcopy(d2_rc)
d2rc3 = copy.deepcopy(d2_rc)
d3_rc = ResultsContainer(base_dir, base_filename)
d3_rc.add_dim_layer([d2rc1, d2rc2, d2rc3], "fenotype_features",
["age", "sex", "tissue"])
return d3_rc
rc2 = copy.deepcopy(rc1)
rc3 = copy.deepcopy(rc1)
rc4 = copy.deepcopy(rc1)
d2_rc = ResultsContainer("", "")
d2_rc.add_dim_layer([rc1, rc2, rc3, rc4], "cv_folds",
["f1", "f2", "f3", "f4"])
d2rc1 = copy.deepcopy(d2_rc)
d2rc2 = copy.deepcopy(d2_rc)
d2rc3 = copy.deepcopy(d2_rc)
d3_rc = ResultsContainer(base_dir, base_filename)
d3_rc.add_dim_layer([d2rc1, d2rc2, d2rc3], "fenotype_features",
["age", "sex", "tissue"])
return d3_rc
if __name__ == "__main__":
r = main(".", "tmp.gz")
r.store()
r2 = ResultsContainer(".", "tmp.gz")
r2.load()
print r2.to_dict()
print r2.ar
#print r2.({"cv_folds": ("f2",)})
def build_result_collection(self, exp):
rc = ResultsContainer(base_dir=exp.get_data_folder(),
base_filename="%s" % self.uuid)
res_seq = self.res_seq
axis_meta_block = self.base_name
axis_meta_block_labels = self.get_fold_labels()
def create_new_dim_rc(local_rc):
local_rc.axis_list = [axis_meta_block]
local_rc.labels_dict[axis_meta_block] = axis_meta_block_labels
local_rc.init_ar()
local_rc.update_label_index()
# WARNING: We only support homogeneous results, so we only check first element
res_seq_field_name, data_type = res_seq.fields.iteritems().next()
if data_type == "ClassifierResult":
single_rc_list = []
for field_name in res_seq.fields:
rc_single = ResultsContainer("", "")
create_new_dim_rc(rc_single)
for idx, res_seq_cell in enumerate(res_seq.sequence):
rc_single.ar[idx] = res_seq_cell[field_name]
single_rc_list.append(rc_single)
rc.add_dim_layer(single_rc_list, self.collector_spec.label,
res_seq.fields.keys())
elif data_type == "ResultsContainer":
if len(res_seq.fields) > 1:
raise Exception(
"Meta block only support single output of type ResultsContainer"
)
else:
rc_list = []
for cell in res_seq.sequence:
sub_rc = cell[res_seq_field_name]
sub_rc.load()
rc_list.append(sub_rc)
rc.add_dim_layer(rc_list, self.base_name,
self.get_fold_labels())
elif data_type == "SequenceContainer":
# TODO remove this check
pass
else:
raise Exception("Meta blocks only support ClassifierResult "
"or ResultsContainer in the output collection. "
" Instead got: %s" % data_type)
rc.store()
rc.ar = None
self.set_out_var("results_container", rc)
def main(base_dir, base_filename):
rc1 = ResultsContainer("", "")
rc1.ar = np.empty(shape=(2,), dtype=object)
rc1.axis_list = ["classifiers"]
rc1.labels_dict["classifiers"] = ["svm", "dt"]
from environment.structures import ClassifierResult
c1 = ClassifierResult("", "")
c1.scores["accuracy"] = 0.8
c2 = ClassifierResult("", "")
c2.scores["accuracy"] = 0.95
rc1.ar[0] = c1
rc1.ar[1] = c2
rc2 = copy.deepcopy(rc1)
rc3 = copy.deepcopy(rc1)
rc4 = copy.deepcopy(rc1)
d2_rc = ResultsContainer("", "")
d2_rc.add_dim_layer([rc1, rc2, rc3, rc4], "cv_folds", ["f1", "f2", "f3", "f4"])
d2rc1 = copy.deepcopy(d2_rc)
d2rc2 = copy.deepcopy(d2_rc)
d2rc3 = copy.deepcopy(d2_rc)
d3_rc = ResultsContainer(base_dir, base_filename)
d3_rc.add_dim_layer([d2rc1, d2rc2, d2rc3], "fenotype_features",
["age", "sex", "tissue"])
return d3_rc
rc2 = copy.deepcopy(rc1)
rc3 = copy.deepcopy(rc1)
rc4 = copy.deepcopy(rc1)
d2_rc = ResultsContainer("", "")
d2_rc.add_dim_layer([rc1, rc2, rc3, rc4], "cv_folds", ["f1", "f2", "f3", "f4"])
d2rc1 = copy.deepcopy(d2_rc)
d2rc2 = copy.deepcopy(d2_rc)
d2rc3 = copy.deepcopy(d2_rc)
d3_rc = ResultsContainer(base_dir, base_filename)
d3_rc.add_dim_layer([d2rc1, d2rc2, d2rc3], "fenotype_features",
["age", "sex", "tissue"])
return d3_rc
if __name__ == "__main__":
r = main(".", "tmp.gz")
r.store()
r2 = ResultsContainer(".", "tmp.gz")
r2.load()
print r2.to_dict()
print r2.ar
#print r2.({"cv_folds": ("f2",)})
