All Projects → vietsDeng → Stock-Prediction

vietsDeng / Stock-Prediction

Licence: other
stock predict by cnn and lstm

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Stock-Prediction

Lidc nodule detection
lidc nodule detection with CNN and LSTM network
Stars: ✭ 187 (+648%)
Mutual labels:  cnn, lstm
stylenet
A pytorch implemention of "StyleNet: Generating Attractive Visual Captions with Styles"
Stars: ✭ 58 (+132%)
Mutual labels:  cnn, lstm
Deepsleepnet
DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
Stars: ✭ 200 (+700%)
Mutual labels:  cnn, lstm
Eeg Dl
A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.
Stars: ✭ 165 (+560%)
Mutual labels:  cnn, lstm
Lightnet
Efficient, transparent deep learning in hundreds of lines of code.
Stars: ✭ 243 (+872%)
Mutual labels:  cnn, lstm
Kaggle Competition Favorita
5th place solution for Kaggle competition Favorita Grocery Sales Forecasting
Stars: ✭ 169 (+576%)
Mutual labels:  cnn, lstm
Sign Language Gesture Recognition
Sign Language Gesture Recognition From Video Sequences Using RNN And CNN
Stars: ✭ 214 (+756%)
Mutual labels:  cnn, lstm
Easyocr
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Stars: ✭ 13,379 (+53416%)
Mutual labels:  cnn, lstm
Caption generator
A modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.
Stars: ✭ 243 (+872%)
Mutual labels:  cnn, lstm
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+12736%)
Mutual labels:  cnn, lstm
Tensorflow template application
TensorFlow template application for deep learning
Stars: ✭ 1,851 (+7304%)
Mutual labels:  cnn, lstm
Base-On-Relation-Method-Extract-News-DA-RNN-Model-For-Stock-Prediction--Pytorch
基於關聯式新聞提取方法之雙階段注意力機制模型用於股票預測
Stars: ✭ 33 (+32%)
Mutual labels:  lstm, stock-prediction
Vpilot
Scripts and tools to easily communicate with DeepGTAV. In the future a self-driving agent will be implemented.
Stars: ✭ 136 (+444%)
Mutual labels:  cnn, lstm
Speech Emotion Recognition
Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别
Stars: ✭ 181 (+624%)
Mutual labels:  cnn, lstm
Ncrfpp
NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (e.g. NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components.
Stars: ✭ 1,767 (+6968%)
Mutual labels:  cnn, lstm
Screenshot To Code
A neural network that transforms a design mock-up into a static website.
Stars: ✭ 13,561 (+54144%)
Mutual labels:  cnn, lstm
Robust Lane Detection
Stars: ✭ 110 (+340%)
Mutual labels:  cnn, lstm
Pytorch convlstm
convolutional lstm implementation in pytorch
Stars: ✭ 126 (+404%)
Mutual labels:  cnn, lstm
Natural Language Processing With Tensorflow
Natural Language Processing with TensorFlow, published by Packt
Stars: ✭ 222 (+788%)
Mutual labels:  cnn, lstm
Automatic speech recognition
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Stars: ✭ 2,751 (+10904%)
Mutual labels:  cnn, lstm

《基于深度学习的财经新闻量化与股市预测研究》论文源代码说明


目录说明

  • CNN (CNN文本处理及模型)
  • Database (mysql连接类及数据库结构文件)
  • Ensemble (集成学习文本处理及模型)
  • FetchBindex (百度指数爬虫)
  • LSTM (LSTM文本处理及模型)
  • run_data (生成文件存放目录)
  • Spider (财经新闻、股票数据爬虫及自定义工具类)
  • /main.py (入口文件,含交叉验证及所有样例)
  • /ensemble_temp.bat (批处理文件,作用详见下面"缺陷")

数据爬取

  1. 财经新闻数据:Spider/NewsSpider.py
  2. 股票历史数据:Spider/StockSpider.py
  3. 百度指数数据:FetchBindex

训练集处理

  1. 数据处理:CNN/DataHelper.py、CNN/News.py(新闻词典生成)
  2. CNN训练数据集:CNN/OriginData.py
  3. LSTM训练数据集:LSTM/OriginData.py
  4. 集成学习模型训练数据集:Ensemble/Ensemble.py

模型构建

  1. CNN模型:CNN/CNNStockText.py、CNN/CNNStockNumber.py
  2. LSTM模型:LSTM/LSTMStockOrigin.py
  3. 集成学习模型:Ensemble/Ensemble.py

交叉验证

  1. 模型十折十次交叉验证:/main.py

结果分析

  1. 倾向词典分析:CNN/News.py
  2. 模型预测结果分析:Spider/Analyse.py

缺陷

  1. 利用Ensemble类的makeEnsembleData函数生成集成模型的输入集时,因内存释放问题,在生成第一个输入集后速度会变慢(需生成100个输入集),暂处理方法为加入exit()并利用批处理(即每次生成一个后退出,利用批处理来执行一百遍)

非代码相关资料

实验数据 (内含本人毕业论文、相关文献、数据库数据、实验过程数据、实验结果截图)

版权声明

开源代码对学术研究完全开放,使用时请引用出处;请勿用作商业应用,后果自行负责。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].