jinanzou/astock

Astock

astock's Issues

Hi! How to get train.csv from raw data?

Hi, I'm a student in PKU. I'm appreciating of your great job! Therefore, I want to research more about stock prediction based on your work. However, I meet some confusions about the file train.csv, so I hope you can give me some help. If you can share your code getting train.csv, I would really appreciate it!
Thanks!!!

backtest

Hi，which part of the code is backtest

【数据预处理】请问可以提供数据预处理脚本吗

请问可以提供数据预处理脚本吗？比如LTP的语义角色标注
已经搜不到LTP4.0以前的版本了，没有办法用简单的方法获取到作者预处理后的结果

hi，Can you provide this model，‘PRE_TRAINED_MODEL_NAME = '/home/bit/stock/model/pretrained-bert/ROBERT_4_model.bin'

new complementary tool

My name is Luis, I'm a big-data machine-learning developer, I'm a fan of your work, and I usually check your updates.

I was afraid that my savings would be eaten by inflation. I have created a powerful tool that based on past technical patterns (volatility, moving averages, statistics, trends, candlesticks, support and resistance, stock index indicators).
All the ones you know (RSI, MACD, STOCH, Bolinger Bands, SMA, DEMARK, Japanese candlesticks, ichimoku, fibonacci, williansR, balance of power, murrey math, etc) and more than 200 others.

The tool creates prediction models of correct trading points (buy signal and sell signal, every stock is good traded in time and direction).
For this I have used big data tools like pandas python, stock market libraries like: tablib, TAcharts ,pandas_ta... For data collection and calculation.
And powerful machine-learning libraries such as: Sklearn.RandomForest , Sklearn.GradientBoosting, XGBoost, Google TensorFlow and Google TensorFlow LSTM.

With the models trained with the selection of the best technical indicators, the tool is able to predict trading points (where to buy, where to sell) and send real-time alerts to Telegram or Mail. The points are calculated based on the learning of the correct trading points of the last 2 years (including the change to bear market after the rate hike).

I think it could be useful to you, to improve, I would like to share it with you, and if you are interested in improving and collaborating I am also willing, and if not file it in the box.

what is the data format of verb A0 and A1 feature ?

Thanks for your answers about previous questions very much!
In the dataset,for example "train.csv" , each Verb A0 and A1 is composed of two elements, such as (49,2) in [(0, 2), (2, 2), (49, 2), (51, 2), (53, 1), (54, 2), (56, 1), (57, 1), (71, 3)] . What do these two elements mean? My guess the "text_a" is splited into many sentences,the first element is the sentence index, and further more the each sentence is divided into many words, the sencond element is the word index. What is the real situation?
I have not found source code that pre-process the raw data for transition to training data in the project.

a little bug

There is a little bug in Pretrained_RoBERT file. In the code segment "def get_predictions(model, data_loader):", the statement ："outputs, attention_weight = model(" have two return parameters, but the "SentimentClassifier" function have only one parameter that is outputs.

Cloning repository is time-consuming due to archives

Cloning into 'Astock'...
remote: Enumerating objects: 4729, done.
remote: Counting objects: 100% (65/65), done.
remote: Compressing objects: 100% (62/62), done.
Receiving objects:   1% (52/4729), 69.83 MiB | 877.00 KiB/s 

1% for 70 MiB means repo is ~5-7gb in size which is inappropriate for cloning github repository, instead large files should be downloaded on demand after cloning the code base

If the three labels are based on the return rate after a certain number of days following the news release? I'm curious to know the specific number of days.

If the three labels are based on the return rate after a certain number of days following the news release? I'm curious to know the specific number of days.

The pretrain model has not exist

There is a statement: PRE_TRAINED_MODEL_NAME = '/home/bit/stock/model/pretrained-bert/ROBERT_4_model.bin' in source code ,but where is the ROBERT_4_model.bin file?

train/test/val encoder

Can you describe a code with which you get train.csv, i researched ltp repo https://github.com/HIT-SCIR/ltp, but i do not understand how you get train,test,val .csv