Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
oliverwang15 authored Aug 23, 2023
1 parent 8174943 commit b6c0116
Showing 1 changed file with 4 additions and 4 deletions.
8 changes: 4 additions & 4 deletions fingpt/FinGPT-v1/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,11 @@
## Let's obtain our own FinGPT by finetuning Llama2 and ChatGLM2 with LoRA

### Ⅰ. Data Preparations
#### 1. [Download Titles](./data_preparations/download_titles.py)
#### 1. Download Titles [code](./data_preparations/download_titles.py)
* In this file, we downloaded the financial news titles and URLs from [eastmoney(东方财富)](https://www.eastmoney.com/)
#### 2. [Download Content](./data_preparations/download_contents.py)
#### 2. Download Content [code](./data_preparations/download_contents.py)
* In this file, we downloaded the financial news Contents from [eastmoney(东方财富)](https://www.eastmoney.com/)
#### 3. [Add labels](./data_preparations/add_labels.py)
#### 3. Add labels [code](./data_preparations/add_labels.py)
* In this file, we add the label for news titles and contents.
* The labels are determined by the change pct between the stock price of today and 5-days later
* change pct >= 0.06 : `very positive`
Expand All @@ -17,7 +17,7 @@

### Ⅱ. Making Dataset

1. [Make dataset_by_date](./making_dataset/make_dataset_by_date.py)
1. Make dataset_by_date [code](./making_dataset/make_dataset_by_date.py)
* You may run this notebook to generate the dataset file in alpaca format

2. Please run the following two files respectively to generate the dataset in hugging face dataset format.
Expand Down

0 comments on commit b6c0116

Please sign in to comment.