def _get_feature_names_at_node(self,
node,
input_features=None,
entry=False):
""" main function to make the feature go down the graphpipleine and retrieve the features at a given node
Parameter
---------
node : string or ..
name of the node
input_features : None or list
if not None, the list of feature (at the input of the graphpipeline)
entry : boolean, default = False
if True will retrieve the feature at the ENTRY of a given model, otherwise the feature at the EXIT of a given model
Returns
-------
list of features for the given node, or None
"""
if not self._already_fitted:
raise NotFittedError("Please fit the model before")
if input_features is None:
input_features = self._Xinput_features
feature_dico = {}
for n in self._nodes_order:
predecessors = list(self.complete_graph.predecessors(n))
if len(predecessors) == 0:
last_features = input_features
elif len(predecessors) == 1:
last_features = feature_dico[predecessors[0]]
else:
predecessors = self._all_concat_order[n]
all_last_features = [
feature_dico[predecessor] for predecessor in predecessors
]
if all_last_features is None or None in all_last_features:
last_features = None
else:
last_features = unlist(all_last_features)
model = self._models[n]
if last_features is None or None in last_features:
last_features = None
if n != node:
feature_dico[n] = try_to_find_features_names(
model, input_features=last_features)
if feature_dico[n] is not None:
feature_dico[n] = list(feature_dico[n])
else:
if entry:
# Entry, I'll return the features at the entry of the node
return last_features
else:
# Otherwise I'll return the features at the exit of the node
feature_dico[n] = try_to_find_features_names(
model, input_features=last_features)
if feature_dico[n] is not None:
feature_dico[n] = list(feature_dico[n])
return feature_dico[n]
raise ValueError("node %s isn't in the graph" % node)
def test_try_to_find_features_names():
list_of_words = ["aa bb", "bb bb cc", "dd aa cc", "ee"]
vec = CountVectorizer()
vec.fit_transform(list_of_words)
assert try_to_find_features_names(vec) == ["aa", "bb", "cc", "dd", "ee"]
pipe = Pipeline([("nothing", DebugPassThrough()),
("vec", CountVectorizer())])
pipe.fit_transform(list_of_words)
assert try_to_find_features_names(pipe) == ["aa", "bb", "cc", "dd", "ee"]
union = FeatureUnion(transformer_list=[(
"bagword",
CountVectorizer()), ("bagchar", CountVectorizer(analyzer="char"))])
union.fit_transform(list_of_words)
assert try_to_find_features_names(union) == [
"bagword__aa",
"bagword__bb",
"bagword__cc",
"bagword__dd",
"bagword__ee",
"bagchar__ ",
"bagchar__a",
"bagchar__b",
"bagchar__c",
"bagchar__d",
"bagchar__e",
]
pipe1 = Pipeline([("nothing", DebugPassThrough()),
("vec", CountVectorizer())])
pipe2 = Pipeline([("nothing", DebugPassThrough()),
("vec", CountVectorizer(analyzer="char"))])
union = FeatureUnion(transformer_list=[("bagword",
pipe1), ("bagchar", pipe2)])
union.fit_transform(list_of_words)
assert try_to_find_features_names(union) == [
"bagword__aa",
"bagword__bb",
"bagword__cc",
"bagword__dd",
"bagword__ee",
"bagchar__ ",
"bagchar__a",
"bagchar__b",
"bagchar__c",
"bagchar__d",
"bagchar__e",
]
class DummyModelAcceptInputFeature(object):
def get_feature_names(self, input_features=None):
if input_features is None:
return [0, 1, 2, 3]
else:
return input_features
class DummyModelDontInputFeature(object):
def get_feature_names(self):
return [0, 1, 2, 3]
class DummyModelDoesntHaveGetFeatures(object):
pass
m = DummyModelAcceptInputFeature()
assert try_to_find_features_names(m) == [0, 1, 2, 3]
assert try_to_find_features_names(
m, input_features=["a", "b", "c", "d"]) == ["a", "b", "c", "d"]
m = DummyModelDontInputFeature()
assert try_to_find_features_names(m) == [0, 1, 2, 3]
assert try_to_find_features_names(m, input_features=["a", "b", "c",
"d"]) == [0, 1, 2, 3]
m = DummyModelDoesntHaveGetFeatures()
assert try_to_find_features_names(m) is None
assert try_to_find_features_names(m, input_features=["a", "b", "c", "d"
]) is None
def _fit_transform(self,
X,
y=None,
groups=None,
method=None,
fit_params=None):
""" main method of GraphPipeline, handles the fit and predict of object """
do_fit = method in ("fit", "fit_transform", "fit_predict")
if not self._already_fitted and not do_fit:
raise NotFittedError("Please fit the model before")
# Split fit_params into a 'step-by-step' dictionnary
fit_params_step = {name: {} for name in self.complete_graph.nodes}
if fit_params is not None:
for key, value in fit_params.items():
step, param = key.split("__", 1)
fit_params_step[step][param] = value
data_dico = {} # Will contain transformed blocks at each node
feature_dico = {} # Will contain the get_feature_names() of each node
if do_fit:
input_features = getattr(X, "columns", None)
if input_features is not None:
input_features = list(input_features)
self._Xinput_features = input_features
else:
input_features = self._Xinput_features
nodes_done = set()
for node in self._nodes_order:
nodes_done.add(node)
if self.verbose:
print("start processing node %s ..." % node)
### Debugging Help ###
if (getattr(self, "_return_before_node", None) is not None
and getattr(self, "_return_before_node", None) == node):
return data_dico
model = self._models[node]
predecessors = list(self.complete_graph.predecessors(node))
# Carefull : here it is not necessary always in the same order
#### I'll use the order in which the edges were given
# Concatenation : alphabetical order
concat_at_this_node = self.no_concat_nodes is None or node not in self.no_concat_nodes
if len(predecessors) == 0:
#########################
### No predecessors ###
#########################
if concat_at_this_node:
lastX = X
else:
lastX = {"_data": X}
# ==> Apply on original data
last_features = input_features
elif len(predecessors) == 1:
########################
### One predecessor ###
########################
# ==> Apply on data coming out of last node
if concat_at_this_node:
lastX = data_dico[predecessors[0]]
else:
lastX = {
predecessor: data_dico[predecessor]
for predecessor in predecessors
}
last_features = feature_dico[predecessors[0]]
elif len(predecessors) > 1:
#######################
### More than one ###
#######################
# ==> concat all the predecessors node and apply it
### Fix concatenation order ###
if do_fit:
edges_number = self._get_edges_number(predecessors, node)
predecessors = sorted(predecessors,
key=lambda p:
(edges_number.get(p, -1), p))
self._all_concat_order[node] = predecessors
else:
predecessors = self._all_concat_order[node]
all_lastX = [
data_dico[predecessor] for predecessor in predecessors
]
all_last_features = [
feature_dico[predecessor] for predecessor in predecessors
]
if all_last_features is None or None in all_last_features:
last_features = None
else:
last_features = unlist(all_last_features)
# all_columns_names = [try_to_find_features_names( self._models[predecessor], input_features = input_features)
# for predecessor, input_features in zip(predecessors, all_last_features)]
# for predecessor, input_features in zip(predecessors,all_last_features):
# try_to_find_features_names( self._models[predecessor], input_features = input_features)
if self.verbose:
print("start aggregation...")
if do_fit:
output_type = guess_output_type(all_lastX)
self._all_concat_type[node] = output_type
else:
output_type = self._all_concat_type[node]
if concat_at_this_node:
lastX = generic_hstack(all_lastX,
output_type=output_type,
all_columns_names=all_last_features)
else:
lastX = {
predecessor: data_dico[predecessor]
for predecessor in predecessors
}
if node != self._terminal_node:
# This is not the end of the graph
if do_fit:
if groups is not None and function_has_named_argument(
model.fit_transform, "groups"):
data_dico[node] = model.fit_transform(
lastX, y, groups=groups, **fit_params_step[node])
else:
data_dico[node] = model.fit_transform(
lastX, y, **fit_params_step[node])
# ICI : on pourrait sauté le fit pour certains models dans le fit params
# Quelque-chose comme :
# if node in preffited_models:
#
# self._model[node] = preffited_models[node]
# model = preffited_models[node]
# + copy model into pipeline
# data_dico[node] = model.transform(lastX, y)
# else:
# data_dico[node] = model.fit_transform(lastX, y, **fit_params_step[node] )
else:
data_dico[node] = model.transform(lastX)
feature_dico[node] = try_to_find_features_names(
model, input_features=last_features)
else:
# This is the last node of the Graph
if method == "fit":
if groups is not None and function_has_named_argument(
model.fit, "groups"):
model.fit(lastX, y, groups, **fit_params_step[node])
else:
model.fit(lastX, y, **fit_params_step[node])
result = self
elif method == "fit_predict":
if groups is not None and function_has_named_argument(
model.fit_predict, "groups"):
result = model.fit_predict(lastX, y, groups,
**fit_params_step[node])
else:
result = model.fit_predict(lastX, y,
**fit_params_step[node])
elif method == "fit_transform":
if groups is not None and function_has_named_argument(
model.fit_transform, "groups"):
result = model.fit_transform(lastX, y, groups,
**fit_params_step[node])
else:
result = model.fit_transform(lastX, y,
**fit_params_step[node])
elif method == "transform":
result = model.transform(lastX)
elif method == "predict":
result = model.predict(lastX)
elif method == "predict_proba":
result = model.predict_proba(lastX)
elif method == "predict_log_proba":
result = model.predict_log_proba(lastX)
elif method == "decision_function":
result = model.decision_function(lastX)
elif method == "score":
result = model.score(lastX, y)
else:
raise ValueError("I don't know that kind of method '%s' " %
method)
feature_dico[node] = try_to_find_features_names(
model, input_features=last_features)
return result
#######################
#### Dico cleaning ####
#######################
# I'll do a step of cleaning to remove useless blocks in memory
# I need to remove data in nodes that wont be accessed anymore
still_usefull = set()
for n in self.complete_graph.nodes:
if n in nodes_done:
continue
p = list(self.complete_graph.predecessors(n))
still_usefull.update(p)
for n in data_dico.keys():
if data_dico[n] is None:
continue
if n not in still_usefull:
if self.verbose:
print("deleting useless node %s" % n)
data_dico[n] = None
