fix code style

.travis.yml

@@ -28,4 +28,3 @@ notifications:
   email:
     on_success: change
     on_failure: always
-

core/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

core/engine/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

core/engine/cluster/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

core/modules/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

core/modules/coding/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

core/modules/modul/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

core/reader.py

@@ -11,9 +11,9 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 from __future__ import print_function
 
-import sys
 import abc
 import os
 
@@ -64,7 +64,11 @@ class SlotReader(dg.MultiSlotDataGenerator):
         from operator import mul
         self.sparse_slots = sparse_slots.strip().split(" ")
         self.dense_slots = dense_slots.strip().split(" ")
-        self.dense_slots_shape = [reduce(mul, [int(j) for j in i.split(":")[1].strip("[]").split(",")]) for i in self.dense_slots]
+        self.dense_slots_shape = [
+            reduce(mul,
+                   [int(j) for j in i.split(":")[1].strip("[]").split(",")])
+            for i in self.dense_slots
+        ]
         self.dense_slots = [i.split(":")[0] for i in self.dense_slots]
         self.slots = self.dense_slots + self.sparse_slots
         self.slot2index = {}
@@ -93,10 +97,13 @@ class SlotReader(dg.MultiSlotDataGenerator):
                 slot = i
                 if not self.visit[slot]:
                     if i in self.dense_slots:
-                        output[self.slot2index[i]][1].extend([self.padding] * self.dense_slots_shape[self.slot2index[i]])
+                        output[self.slot2index[i]][1].extend(
+                            [self.padding] *
+                            self.dense_slots_shape[self.slot2index[i]])
                     else:
                         output[self.slot2index[i]][1].extend([self.padding])
                 else:
                     self.visit[slot] = False
             yield output
+
         return reader

core/utils/fs.py

@@ -18,7 +18,7 @@ from paddle.fluid.incubate.fleet.utils.hdfs import HDFSClient
 
 
 def is_afs_path(path):
-    """R 
+    """is_afs_path
     """
     if path.startswith("afs") or path.startswith("hdfs"):
         return True
@@ -133,8 +133,9 @@ class FileHandler(object):
             if mode.find('a') >= 0:
                 org_content = self._hdfs_client.cat(dest_path)
             content = content + org_content
-            self._local_fs_client.write(content, temp_local_file,
-                                        mode)  # fleet hdfs_client only support upload, so write tmp file
+            self._local_fs_client.write(
+                content, temp_local_file, mode
+            )  # fleet hdfs_client only support upload, so write tmp file
             self._hdfs_client.delete(dest_path + ".tmp")
             self._hdfs_client.upload(dest_path + ".tmp", temp_local_file)
             self._hdfs_client.delete(dest_path + ".bak")
@@ -158,7 +159,8 @@ class FileHandler(object):
         files = []
         if is_afs_path(path):
             files = self._hdfs_client.ls(path)
-            files = [path + '/' + self.get_file_name(fi) for fi in files]  # absulte path
+            files = [path + '/' + self.get_file_name(fi)
+                     for fi in files]  # absulte path
         else:
             files = self._local_fs_client.ls(path)
             files = [path + '/' + fi for fi in files]  # absulte path

doc/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

models/contentunderstanding/tagspace/model.py

@@ -26,8 +26,10 @@ class Model(ModelBase):
         ModelBase.__init__(self, config)
         self.cost = None
         self.metrics = {}
-        self.vocab_text_size = envs.get_global_env("vocab_text_size", None, self._namespace)
-        self.vocab_tag_size = envs.get_global_env("vocab_tag_size", None, self._namespace)
+        self.vocab_text_size = envs.get_global_env("vocab_text_size", None,
+                                                   self._namespace)
+        self.vocab_tag_size = envs.get_global_env("vocab_tag_size", None,
+                                                  self._namespace)
         self.emb_dim = envs.get_global_env("emb_dim", None, self._namespace)
         self.hid_dim = envs.get_global_env("hid_dim", None, self._namespace)
         self.win_size = envs.get_global_env("win_size", None, self._namespace)
@@ -35,8 +37,9 @@ class Model(ModelBase):
         self.neg_size = envs.get_global_env("neg_size", None, self._namespace)
 
     def train_net(self):
-        """ network definition """
-        text = fluid.data(name="text", shape=[None, 1], lod_level=1, dtype='int64')
+        """ network"""
+        text = fluid.data(
+            name="text", shape=[None, 1], lod_level=1, dtype='int64')
         pos_tag = fluid.data(
             name="pos_tag", shape=[None, 1], lod_level=1, dtype='int64')
         neg_tag = fluid.data(
@@ -45,13 +48,19 @@ class Model(ModelBase):
         self._data_var = [text, pos_tag, neg_tag]
 
         text_emb = fluid.embedding(
-            input=text, size=[self.vocab_text_size, self.emb_dim], param_attr="text_emb")
+            input=text,
+            size=[self.vocab_text_size, self.emb_dim],
+            param_attr="text_emb")
         text_emb = fluid.layers.squeeze(input=text_emb, axes=[1])
         pos_tag_emb = fluid.embedding(
-            input=pos_tag, size=[self.vocab_tag_size, self.emb_dim], param_attr="tag_emb")
+            input=pos_tag,
+            size=[self.vocab_tag_size, self.emb_dim],
+            param_attr="tag_emb")
         pos_tag_emb = fluid.layers.squeeze(input=pos_tag_emb, axes=[1])
         neg_tag_emb = fluid.embedding(
-            input=neg_tag, size=[self.vocab_tag_size, self.emb_dim], param_attr="tag_emb")
+            input=neg_tag,
+            size=[self.vocab_tag_size, self.emb_dim],
+            param_attr="tag_emb")
         neg_tag_emb = fluid.layers.squeeze(input=neg_tag_emb, axes=[1])
 
         conv_1d = fluid.nets.sequence_conv_pool(
@@ -65,7 +74,8 @@ class Model(ModelBase):
                                    size=self.emb_dim,
                                    param_attr="text_hid")
         cos_pos = nn.cos_sim(pos_tag_emb, text_hid)
-        mul_text_hid = fluid.layers.sequence_expand_as(x=text_hid, y=neg_tag_emb)
+        mul_text_hid = fluid.layers.sequence_expand_as(
+            x=text_hid, y=neg_tag_emb)
         mul_cos_neg = nn.cos_sim(neg_tag_emb, mul_text_hid)
         cos_neg_all = fluid.layers.sequence_reshape(
             input=mul_cos_neg, new_dim=self.neg_size)
@@ -74,7 +84,10 @@ class Model(ModelBase):
         #calculate hinge loss
         loss_part1 = nn.elementwise_sub(
             tensor.fill_constant_batch_size_like(
-                input=cos_pos, shape=[-1, 1], value=self.margin, dtype='float32'),
+                input=cos_pos,
+                shape=[-1, 1],
+                value=self.margin,
+                dtype='float32'),
             cos_pos)
         loss_part2 = nn.elementwise_add(loss_part1, cos_neg)
         loss_part3 = nn.elementwise_max(
@@ -85,7 +98,7 @@ class Model(ModelBase):
         less = tensor.cast(cf.less_than(cos_neg, cos_pos), dtype='float32')
         correct = nn.reduce_sum(less)
         self.cost = avg_cost
-        
+
         self.metrics["correct"] = correct
         self.metrics["cos_pos"] = cos_pos
 
@@ -96,7 +109,8 @@ class Model(ModelBase):
         return self.metrics
 
     def optimizer(self):
-        learning_rate = envs.get_global_env("hyper_parameters.base_lr", None, self._namespace)
+        learning_rate = envs.get_global_env("hyper_parameters.base_lr", None,
+                                            self._namespace)
         sgd_optimizer = fluid.optimizer.Adagrad(learning_rate=learning_rate)
         return sgd_optimizer
 

models/contentunderstanding/tagspace/reader.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import sys
 
 import numpy as np

models/match/dssm/model.py

@@ -23,13 +23,26 @@ class Model(ModelBase):
         ModelBase.__init__(self, config)
 
     def input(self):
-        TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D", None, self._namespace)
-        Neg = envs.get_global_env("hyper_parameters.NEG", None, self._namespace)
-
-        self.query = fluid.data(name="query", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
-        self.doc_pos = fluid.data(name="doc_pos", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
-        self.doc_negs = [fluid.data(name="doc_neg_" + str(i), shape=[-1, TRIGRAM_D], dtype="float32", lod_level=0) for i
-                         in range(Neg)]
+        TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D", None,
+                                        self._namespace)
+
+        Neg = envs.get_global_env("hyper_parameters.NEG", None,
+                                  self._namespace)
+
+        self.query = fluid.data(
+            name="query", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
+        self.doc_pos = fluid.data(
+            name="doc_pos",
+            shape=[-1, TRIGRAM_D],
+            dtype='float32',
+            lod_level=0)
+        self.doc_negs = [
+            fluid.data(
+                name="doc_neg_" + str(i),
+                shape=[-1, TRIGRAM_D],
+                dtype="float32",
+                lod_level=0) for i in range(Neg)
+        ]
         self._data_var.append(self.query)
         self._data_var.append(self.doc_pos)
         for input in self.doc_negs:
@@ -37,16 +50,24 @@ class Model(ModelBase):
 
         if self._platform != "LINUX":
             self._data_loader = fluid.io.DataLoader.from_generator(
-                feed_list=self._data_var, capacity=64, use_double_buffer=False, iterable=False)
+                feed_list=self._data_var,
+                capacity=64,
+                use_double_buffer=False,
+                iterable=False)
 
     def net(self, is_infer=False):
-        hidden_layers = envs.get_global_env("hyper_parameters.fc_sizes", None, self._namespace)
-        hidden_acts = envs.get_global_env("hyper_parameters.fc_acts", None, self._namespace)
+        hidden_layers = envs.get_global_env("hyper_parameters.fc_sizes", None,
+                                            self._namespace)
+        hidden_acts = envs.get_global_env("hyper_parameters.fc_acts", None,
+                                          self._namespace)
 
         def fc(data, hidden_layers, hidden_acts, names):
             fc_inputs = [data]
             for i in range(len(hidden_layers)):
-                xavier = fluid.initializer.Xavier(uniform=True, fan_in=fc_inputs[-1].shape[1], fan_out=hidden_layers[i])
+                xavier = fluid.initializer.Xavier(
+                    uniform=True,
+                    fan_in=fc_inputs[-1].shape[1],
+                    fan_out=hidden_layers[i])
                 out = fluid.layers.fc(input=fc_inputs[-1],
                                       size=hidden_layers[i],
                                       act=hidden_acts[i],
@@ -56,8 +77,10 @@ class Model(ModelBase):
                 fc_inputs.append(out)
             return fc_inputs[-1]
 
-        query_fc = fc(self.query, hidden_layers, hidden_acts, ['query_l1', 'query_l2', 'query_l3'])
-        doc_pos_fc = fc(self.doc_pos, hidden_layers, hidden_acts, ['doc_pos_l1', 'doc_pos_l2', 'doc_pos_l3'])
+        query_fc = fc(self.query, hidden_layers, hidden_acts,
+                      ['query_l1', 'query_l2', 'query_l3'])
+        doc_pos_fc = fc(self.doc_pos, hidden_layers, hidden_acts,
+                        ['doc_pos_l1', 'doc_pos_l2', 'doc_pos_l3'])
         self.R_Q_D_p = fluid.layers.cos_sim(query_fc, doc_pos_fc)
 
         if is_infer:
@@ -65,13 +88,17 @@ class Model(ModelBase):
 
         R_Q_D_ns = []
         for i, doc_neg in enumerate(self.doc_negs):
-            doc_neg_fc_i = fc(doc_neg, hidden_layers, hidden_acts,
-                              ['doc_neg_l1_' + str(i), 'doc_neg_l2_' + str(i), 'doc_neg_l3_' + str(i)])
+            doc_neg_fc_i = fc(doc_neg, hidden_layers, hidden_acts, [
+                'doc_neg_l1_' + str(i), 'doc_neg_l2_' + str(i),
+                'doc_neg_l3_' + str(i)
+            ])
             R_Q_D_ns.append(fluid.layers.cos_sim(query_fc, doc_neg_fc_i))
-        concat_Rs = fluid.layers.concat(input=[self.R_Q_D_p] + R_Q_D_ns, axis=-1)
+        concat_Rs = fluid.layers.concat(
+            input=[self.R_Q_D_p] + R_Q_D_ns, axis=-1)
         prob = fluid.layers.softmax(concat_Rs, axis=1)
 
-        hit_prob = fluid.layers.slice(prob, axes=[0, 1], starts=[0, 0], ends=[4, 1])
+        hit_prob = fluid.layers.slice(
+            prob, axes=[0, 1], starts=[0, 0], ends=[4, 1])
         loss = -fluid.layers.reduce_sum(fluid.layers.log(hit_prob))
         self.avg_cost = fluid.layers.mean(x=loss)
 
@@ -91,18 +118,28 @@ class Model(ModelBase):
         self.metrics()
 
     def optimizer(self):
-        learning_rate = envs.get_global_env("hyper_parameters.learning_rate", None, self._namespace)
+        learning_rate = envs.get_global_env("hyper_parameters.learning_rate",
+                                            None, self._namespace)
         optimizer = fluid.optimizer.SGD(learning_rate)
         return optimizer
 
     def infer_input(self):
-        TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D", None, self._namespace)
-        self.query = fluid.data(name="query", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
-        self.doc_pos = fluid.data(name="doc_pos", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
+        TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D", None,
+                                        self._namespace)
+        self.query = fluid.data(
+            name="query", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
+        self.doc_pos = fluid.data(
+            name="doc_pos",
+            shape=[-1, TRIGRAM_D],
+            dtype='float32',
+            lod_level=0)
         self._infer_data_var = [self.query, self.doc_pos]
 
         self._infer_data_loader = fluid.io.DataLoader.from_generator(
-            feed_list=self._infer_data_var, capacity=64, use_double_buffer=False, iterable=False)
+            feed_list=self._infer_data_var,
+            capacity=64,
+            use_double_buffer=False,
+            iterable=False)
 
     def infer_net(self):
         self.infer_input()

models/recall/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

models/treebased/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

models/treebased/tdm/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

tests/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.

tools/__init__.py

+# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.