def test_fit(self):
print('test fit')
mgs, poolayer, concat_layer, auto_cascade = self._init()
model = Graph()
model.add(mgs)
model.add(poolayer)
model.add(concat_layer)
model.add(auto_cascade)
model.fit(self.x_train, self.y_train)
def test_fit_transform_full(self):
print("test fit_transform_full")
mgs, poolayer, concat_layer, auto_cascade = self._init()
model = Graph()
model.add(mgs)
model.add(poolayer)
model.add(concat_layer)
model.add(auto_cascade)
model.fit_transform(self.x_train, self.y_train, self.x_test,
self.y_test)
def test_graph_transform(self):
print('test graph transform')
gc, agc = self._init()
agc.keep_in_mem = True
model = Graph()
model.add(agc)
model.fit(self.x_train, self.y_train)
model.transform(self.x_test)
def test_graph_fit_evaluate(self):
print('test fit and evaluate')
gc, agc = self._init()
agc.keep_in_mem = True
model = Graph()
model.add(agc)
model.fit(self.x_train, self.y_train)
model.evaluate(self.x_test, self.y_test)
print('x_test.shape: {}'.format(x_test.shape))
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'uci_yeast')
model_save_dir = osp.join(get_model_save_base(), 'uci_yeast')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=10,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=False,
seed=0)
model = Graph()
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
print("time cost: {}".format(time.time() - start_time))
rf2 = RandomForestConfig(n_folds=3, min_samples_leaf=10)
est_for_windows = [[rf1, rf2], [rf1, rf2], [rf1, rf2]]
mgs = MultiGrainScanLayer(windows=windows,
est_for_windows=est_for_windows,
n_class=6)
pools = [[MeanPooling(), MeanPooling()], [MeanPooling(),
MeanPooling()],
[MeanPooling(), MeanPooling()]]
pool_layer = PoolingLayer(pools=pools)
concat_layer = ConcatLayer()
est_configs = Basic4x2()
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=6,
look_index_cycle=[[0, 1], [2, 3],
[4, 5]])
model = Graph()
model.add(mgs)
model.add(pool_layer)
# model.add(concat_layer)
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
def test_fit_evaluate(self):
print("test fit and evaluate")
mgs, poolayer, concat_layer, auto_cascade = self._init()
mgs.keep_in_mem = True
auto_cascade.keep_in_mem = True
model = Graph()
model.add(mgs)
model.add(poolayer)
model.add(concat_layer)
model.add(auto_cascade)
model.fit(self.x_train, self.y_train)
model.evaluate(self.x_test, self.y_test)
def test_transform(self):
print("test transform")
mgs, poolayer, concat_layer, auto_cascade = self._init()
mgs.keep_in_mem = True
auto_cascade.keep_in_mem = True
model = Graph()
model.add(mgs)
model.add(poolayer)
model.add(concat_layer)
model.add(auto_cascade)
model.fit(self.x_train, self.y_train)
model.transform(self.x_test)
def test_graph_summary(self):
model = Graph()
model.add(self.mgs, self.poolayer, self.concat_layer, self.auto_cascade)
model.summary()
def test_uci_graph(self):
print('test uci_graph')
gc, agc = self._init()
model = Graph()
model.add(agc)
model.fit_transform(self.x_train, self.y_train, self.x_test, self.y_test)