请教条和谣言检测 (#1211)

* 微博谣言预测

* 请教条

* Update module.py

* Update module.py

* Update module.py

* Update README.md

* Update README.md

Author: 1084667371

modules/text/text_generation/Rumor_prediction/README.md

@@ -0,0 +1,50 @@
+## 概述
+
+
+Rumor_prediction是预测语句是否为谣言的模型。
+
+## 命令行预测
+
+```shell
+$ hub run Rumor_prediction --input_text='兴仁县今天抢小孩没抢走，把孩子母亲捅了一刀，看见这车的注意了，真事，车牌号辽HFM055！！！！！赶紧散播！ 都别带孩子出去瞎转悠了 尤其别让老人自己带孩子出去 太危险了 注意了！！！！辽HFM055北京现代朗动，在各学校门口抢小孩！！！110已经 证实！！全市通缉！！'
+```
+
+## API
+
+```python
+def Rumor(texts, use_gpu=False):
+```
+
+预测API，预测语句是否为谣言。
+
+**参数**
+
+* texts (list\[str\]): 想要预测是否为谣言的语句；
+* use\_gpu (bool): 是否使用 GPU；**若使用GPU，请先设置CUDA\_VISIBLE\_DEVICES环境变量**；
+
+**返回**
+
+* results (list[dict]): 预测结果的列表，列表中每一个元素为 dict，各字段为：
+
+    - content(str):输入文本内容
+    - prediction(str):预测结果
+    - probability(float):预测结果概率
+
+**代码示例**
+
+```python
+import paddlehub as hub
+
+module = hub.Module(name="Rumor_prediction")
+
+test_texts = ['兴仁县今天抢小孩没抢走，把孩子母亲捅了一刀，看见这车的注意了，真事，车牌号辽HFM055！！！！！赶紧散播！ 都别带孩子出去瞎转悠了 尤其别让老人自己带孩子出去 太危险了 注意了！！！！辽HFM055北京现代朗动，在各学校门口抢小孩！！！110已经 证实！！全市通缉！！']
+results = module.Rumor(texts=test_texts, use_gpu=True)
+print(results)
+```
+
+
+### 依赖
+
+paddlepaddle >= 2.0.0rc1
+
+paddlehub >= 2.0.0rc0

modules/text/text_generation/Rumor_prediction/dict.txt

@@ -0,0 +1,152 @@
+# coding:utf-8
+#
+# 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.
+import argparse
+import ast
+import os
+import math
+import six
+import time
+from pathlib import Path
+
+from paddle.fluid.core import PaddleTensor, AnalysisConfig, create_paddle_predictor
+from paddlehub.module.module import runnable, serving, moduleinfo
+from paddlehub.io.parser import txt_parser
+from paddlehub.compat.module.nlp_module import DataFormatError
+import numpy as np
+import paddle
+import paddlehub as hub
+
+@moduleinfo(
+    name="Rumor_prediction",
+    version="1.0.0",
+    type="nlp/semantic_model",
+    summary=
+    "Is the input text prediction a rumor",
+    author="彭兆帅，郑博培",
+    author_email="1084667371@qq.com，2733821739@qq.com")
+class Rumorprediction(hub.Module):
+    def _initialize(self):
+        """
+        Initialize with the necessary elements
+        """
+        # 加载模型路径
+        self.default_pretrained_model_path = os.path.join(self.directory, "infer_model")
+    
+    def Rumor(self, texts, use_gpu=False):
+        """
+        Get the input and program of the infer model
+
+        Args:
+             image (list(numpy.ndarray)): images data, shape of each is [H, W, C], the color space is BGR.
+             use_gpu(bool): Weather to use gpu
+        """
+        # 获取数据
+        def get_data(sentence):
+            # 读取数据字典
+            with open(self.directory + '/dict.txt', 'r', encoding='utf-8') as f_data:
+                dict_txt = eval(f_data.readlines()[0])
+            dict_txt = dict(dict_txt)
+            # 把字符串数据转换成列表数据
+            keys = dict_txt.keys()
+            data = []
+            for s in sentence:
+                # 判断是否存在未知字符
+                if not s in keys:
+                    s = '<unk>'
+                data.append(int(dict_txt[s]))
+            return data
+        data = []
+        for text in texts:
+            text = get_data(text)
+            data.append(text)
+        base_shape = [[len(c) for c in data]]
+        paddle.enable_static()
+        place = paddle.CUDAPlace(0) if use_gpu else paddle.CPUPlace()
+        exe = paddle.static.Executor(place)
+        exe.run(paddle.static.default_startup_program())
+        [infer_program, feeded_var_names, target_var] = paddle.fluid.io.load_inference_model(dirname=self.default_pretrained_model_path, executor=exe)
+        # 生成预测数据
+        tensor_words = paddle.fluid.create_lod_tensor(data, base_shape, place)
+        # 执行预测
+        result = exe.run(program=infer_program,
+                        feed={feeded_var_names[0]: tensor_words},
+                        fetch_list=target_var)
+        # 分类名称
+        names = [ '谣言', '非谣言']
+
+
+        results = []
+
+        # 获取结果概率最大的label
+        for i in range(len(data)):
+            content = texts[i]
+            lab = np.argsort(result)[0][i][-1]
+
+            alltext = {
+                'content': content,
+                'prediction': names[lab],
+                'probability': result[0][i][lab]
+            }
+            alltext = [alltext]
+            results = results + alltext
+            
+        return results
+
+    
+    def add_module_config_arg(self):
+        """
+        Add the command config options
+        """
+        self.arg_config_group.add_argument(
+            '--use_gpu',
+            type=ast.literal_eval,
+            default=False,
+            help="whether use GPU for prediction")
+
+    def add_module_input_arg(self):
+        """
+        Add the command input options
+        """
+        self.arg_input_group.add_argument(
+            '--input_text',
+            type=str,
+            default=None,
+            help="input_text is str")
+    @runnable
+    def run_cmd(self, argvs):
+        """
+        Run as a command
+        """
+        self.parser = argparse.ArgumentParser(
+            description='Run the %s module.' % self.name,
+            prog='hub run %s' % self.name,
+            usage='%(prog)s',
+            add_help=True)
+
+        self.arg_input_group = self.parser.add_argument_group(
+            title="Input options", description="Input data. Required")
+        self.arg_config_group = self.parser.add_argument_group(
+            title="Config options",
+            description=
+            "Run configuration for controlling module behavior, optional.")
+
+        self.add_module_config_arg()
+        self.add_module_input_arg()
+
+        args = self.parser.parse_args(argvs)
+        input_text = [args.input_text]
+        results = self.Rumor(
+            texts=input_text, use_gpu=args.use_gpu)
+
+        return results

modules/text/text_generation/Rumor_prediction/module.py

@@ -0,0 +1,52 @@
+## 概述
+
+
+ernie_gen_leave是基于ERNIE-GEN进行微调的模型，该模型的主要功能为生成请假条。输出一个关键词，给出你的请假理由。
+
+## 命令行预测
+
+```shell
+$ hub run ernie_gen_leave --input_text="理由" --use_gpu True --beam_width 5
+```
+
+## API
+
+```python
+def generate(texts, use_gpu=False, beam_width=5):
+```
+
+预测API，输入关键字给出请假理由。
+
+**参数**
+
+* texts (list\[str\]): 请假关键字；
+* use\_gpu (bool): 是否使用 GPU；**若使用GPU，请先设置CUDA\_VISIBLE\_DEVICES环境变量**；
+* beam\_width: beam search宽度，决定输出多少理由的数量。
+
+**返回**
+
+* results (list\[list\]\[str\]): 输出请假理由。
+
+**代码示例**
+
+```python
+import paddlehub as hub
+
+module = hub.Module(name="ernie_gen_leave")
+
+test_texts = ["理由"]
+results = module.generate(texts=test_texts, use_gpu=False, beam_width=2)
+for result in results:
+    print(result)
+```
+
+
+## 查看代码
+
+https://github.com/PaddlePaddle/PaddleHub/tree/release/v2.0.0-rc/modules/text/text_generation/ernie_gen_leave
+
+### 依赖
+
+paddlepaddle >= 2.0.0rc1
+
+paddlehub >= 2.0.0rc0