def reduce(self, store_results=True):
# Terminaison (leaf) node return results
if not self.children:
return self.load_state(name="results")
# 1) Build sub-aggregates over children
children_results = [child.reduce(store_results=False) for
child in self.children]
result_set = ResultSet(*children_results)
if not self.reducer:
return result_set
# Group by key, without consideration of the fold/permutation number
# which is the head of the key
# use OrderedDict to preserve runing order
from collections import OrderedDict
groups = OrderedDict()
for result in result_set:
# remove the head of the key
_, key_tail = key_pop(result["key"], index=0)
result["key"] = key_tail
key_tail = result["key"]
if not key_tail in groups:
groups[key_tail] = list()
groups[key_tail].append(result)
# For each key, stack results
reduced = ResultSet()
for key in groups:
result_stacked = Result.stack(*groups[key])
reduced.add(self.reducer.reduce(result_stacked))
return reduced
def reduce(self, store_results=True):
# Terminaison (leaf) node return results
if not self.children:
return self.load_state(name="results")
# 1) Build sub-aggregates over children
children_results = [
child.reduce(store_results=False) for child in self.children
]
result_set = ResultSet(*children_results)
if not self.reducer:
return result_set
# Group by key, without consideration of the fold/permutation number
# which is the head of the key
# use OrderedDict to preserve runing order
from collections import OrderedDict
groups = OrderedDict()
for result in result_set:
# remove the head of the key
_, key_tail = key_pop(result["key"], index=0)
result["key"] = key_tail
key_tail = result["key"]
if not key_tail in groups:
groups[key_tail] = list()
groups[key_tail].append(result)
# For each key, stack results
reduced = ResultSet()
for key in groups:
result_stacked = Result.stack(*groups[key])
reduced.add(self.reducer.reduce(result_stacked))
return reduced
def reduce(self, store_results=True):
children_results = [
child.reduce(store_results=False) for child in self.children
]
results = ResultSet(*children_results)
if self.reducer:
to_refit, best_params = self.reducer.reduce(results)
Xy = self.load_results()
Xy = self._results2dict(**Xy)
self.refited = to_refit
self.best_params = best_params
out = self.refited.top_down(**Xy)
out[conf.BEST_PARAMS] = best_params
result = Result(key=self.get_signature(), **out)
return ResultSet(result)
return results
def reduce(self, store_results=True):
# 1) Build sub-aggregates over children
children_results = [
child.reduce(store_results=False) for child in self.children
]
results = ResultSet(*children_results)
return results
def reduce(self, store_results=True):
# 1) Build sub-aggregates over children
children_result_set = [child.reduce(store_results=False) for
child in self.children]
result_set = ResultSet(*children_result_set)
# Append node signature in the keys
for result in result_set:
result["key"] = key_push(self.get_signature(), result["key"])
return result_set
def transform(self, **Xy):
Xy_train, Xy_test = train_test_split(Xy)
result = Result(key=self.get_signature(), **Xy)
if not self.store:
self.store = StoreMem()
self.save_results(ResultSet(result))
if Xy_train is Xy_test:
return Xy
else:
return Xy_train
def reduce(self, result_set):
# if you want to a remote execution of your code, import should be done
# within methods
from epac.utils import train_test_split
from epac.map_reduce.results import ResultSet
outputs = list() # output result is a dictonary
for result in result_set:
output = dict() # output result is a dictonary
result_train, result_test = train_test_split(result)
if result_train is result_test:
accuracy = accuracy_score(result['y/true'], result['y/pred'])
output["acc/y"] = accuracy
else:
accuracy = accuracy_score(result_test['y/true'], result_test['y/pred'])
output["acc/y/test"] = accuracy
output["acc/y/train"] = accuracy_score(result_train['y/true'], result_train['y/pred'])
outputs.append(Result(key=result['key'], **output))
return ResultSet(*outputs)
def top_down(self, **Xy):
"""Top-down data processing method
This method does nothing more that recursively call
parent/children func_name. Most of time, it should be re-defined.
Parameters
----------
func_name: str
the name of the function to be called
recursion: boolean
if True recursively call parent/children func_name. If the
current node is the root of the tree call the children.
This way the whole tree is executed.
If it is a leaf, then recursively call the parent before
being executed. This a pipeline made of the path from the
leaf to the root is executed.
**Xy: dict
the keyword dictionnary of data-flow
Return
------
A dictionnary of processed data
"""
if conf.TRACE_TOPDOWN:
print self.get_key()
if debug.DEBUG:
debug.current = self
debug.Xy = Xy
if not self.parent:
self.initialization(**Xy) ## Performe some initialization
Xy = self.transform(**Xy)
if self.children:
# Call children func_name down to leaves
ret = [child.top_down(**Xy) for child in self.get_children_top_down()]
Xy = ret[0] if len(ret) == 1 else ret
else:
result = Result(key=self.get_signature(), **Xy)
self.save_state(ResultSet(result), name="result_set")
return Xy
def top_down(self, **Xy):
"""Top-down data processing method
This method does nothing more that recursively call
parent/children func_name. Most of time, it should be re-defined.
Parameters
----------
func_name: str
the name of the function to be called
recursion: boolean
if True recursively call parent/children func_name. If the
current node is the root of the tree call the children.
This way the whole tree is executed.
If it is a leaf, then recursively call the parent before
being executed. This a pipeline made of the path from the
leaf to the root is executed.
**Xy: dict
the keyword dictionnary of data-flow
Return
------
A dictionnary of processed data
Example
-------
>>> from epac import Methods
>>> from sklearn.svm import SVC
>>> from sklearn import datasets
>>> X, y = datasets.make_classification(n_samples=12,
... n_features=10,
... n_informative=2,
... random_state=1)
>>> methods = Methods(*[SVC(C=1), SVC(C=2)])
>>> methods.top_down(X=X, y=y)
[{'y/true': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1]), 'y/pred': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1])}, {'y/true': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1]), 'y/pred': array([1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 1])}]
"""
if conf.TRACE_TOPDOWN:
print(self.get_key())
if debug.DEBUG:
debug.current = self
debug.Xy = Xy
if not self.parent:
self.initialization(**Xy) # Performe some initialization
Xy = self.transform(**Xy)
if not self.stop_top_down:
if self.children:
# Call children func_name down to leaves
ret = [
child.top_down(**Xy)
for child in self.get_children_top_down()
]
Xy = ret[0] if len(ret) == 1 else ret
else:
result = Result(key=self.get_signature(), **Xy)
self.save_results(ResultSet(result))
return Xy
def reduce(self, store_results=True):
results = ResultSet(self.children[0].reduce(store_results=False))
for result in results:
result["key"] = key_push(self.get_signature(), result["key"])
return results