RDAgent aims to automate the most critical and valuable aspects of the industrial R&D process, and we begin with focusing on the data-driven scenarios to streamline the development of models and data.
Methodologically, we have identified a framework with two key components: 'R' for proposing new ideas and 'D' for implementing them.
@@ -29,23 +36,21 @@ We believe that the automatic evolution of R&D will lead to solutions of signifi
R&D is a very general scenario. The advent of RDAgent can be your
-- π Automatic Quant Factory [(π₯demo)](https://rdagent.azurewebsites.net/factor_loop)
-- π€ Data Mining Agent: iteratively proposing data [(π₯demo)](https://rdagent.azurewebsites.net/dmm) & models [(π₯demo)](https://rdagent.azurewebsites.net/model_loop) and implementing them by gaining knowledge from data.
-- π¦Ύ Research Copilot: Auto read research papers [(π₯demo)](https://rdagent.azurewebsites.net/report_model) / financial reports [(π₯demo)](https://rdagent.azurewebsites.net/report_factor) and implement model structures or building datasets.
+- π° **Automatic Quant Factory** [(π₯Demo Video)](https://rdagent.azurewebsites.net/factor_loop)
+- π€ **Data Mining Agent:** Iteratively proposing data [(π₯Demo Video)](https://rdagent.azurewebsites.net/dmm) & models [(π₯Demo Video)](https://rdagent.azurewebsites.net/model_loop) and implementing them by gaining knowledge from data.
+- π¦Ύ **Research Copilot:** Auto read research papers [(π₯Demo Video)](https://rdagent.azurewebsites.net/report_model) / financial reports [(π₯Demo Video)](https://rdagent.azurewebsites.net/report_factor) and implement model structures or building datasets.
- ...
-You can click the π₯ [link](https://rdagent.azurewebsites.net) above to view the demo. More methods and scenarios are being added to the project to empower your R&D processes and boost productivity.
-
-
- [](https://rdagent.azurewebsites.net/)
-
+You can click the links above to view the demo. We're continuously adding more methods and scenarios to the project to enhance your R&D processes and boost productivity.
+
+Additionally, you can take a closer look at the examples in our **[π₯οΈ Live Demo](https://rdagent.azurewebsites.net/)**.
+
+
Automating the R&D process in data science is a highly valuable yet underexplored area in industry. We propose a framework to push the boundaries of this important research field.
@@ -166,18 +181,18 @@ Automating the R&D process in data science is a highly valuable yet underexplore
The research questions within this framework can be divided into three main categories:
| Research Area | Paper/Work List |
|--------------------|-----------------|
-| Benchmark the R&D abilities | [Benchmark](#benchmark) |
-| Idea proposal: Explore new ideas or refine existing ones | [Research](#research) |
-| Ability to realize ideas: Implement and execute ideas | [Development](#development) |
+| **Benchmark the R&D abilities** | [Benchmark](#benchmark) |
+| **Idea proposal:** Explore new ideas or refine existing ones | [Research](#research) |
+| **Ability to realize ideas:** Implement and execute ideas | [Development](#development) |
We believe that the key to delivering high-quality solutions lies in the ability to evolve R&D capabilities. Agents should learn like human experts, continuously improving their R&D skills.
-More documents can be found in the [πreadthedocs](https://rdagent.readthedocs.io/).
+More documents can be found in the **[π readthedocs](https://rdagent.readthedocs.io/)**.
# π Paper/Work list
## π Benchmark
-- [Towards Data-Centric Automatic R&D](https://arxiv.org/abs/2404.11276);
+- [Towards Data-Centric Automatic R&D](https://arxiv.org/abs/2404.11276)
```BibTeX
@misc{chen2024datacentric,
title={Towards Data-Centric Automatic R&D},
@@ -196,7 +211,7 @@ In a data mining expert's daily research and development process, they propose a
Based on the principles above, we have established a basic method framework that continuously proposes hypotheses, verifies them, and gets feedback from the real-world practice. This is the first scientific research automation framework that supports linking with real-world verification.
-For more detail, please refer to our [Demos page](https://rdagent.azurewebsites.net).
+For more detail, please refer to our **[π₯οΈ Live Demo page](https://rdagent.azurewebsites.net)**.
## π οΈ Development
diff --git a/docs/_static/Framework-RDAgent.png b/docs/_static/Framework-RDAgent.png
new file mode 100644
index 00000000..10a20f22
Binary files /dev/null and b/docs/_static/Framework-RDAgent.png differ
diff --git a/docs/_static/demo.png b/docs/_static/demo.png
new file mode 100644
index 00000000..54a9e0e4
Binary files /dev/null and b/docs/_static/demo.png differ
diff --git a/docs/_static/favicon.ico b/docs/_static/favicon.ico
new file mode 100644
index 00000000..99688ed8
Binary files /dev/null and b/docs/_static/favicon.ico differ
diff --git a/docs/_static/logo.png b/docs/_static/logo.png
new file mode 100644
index 00000000..ec1b644f
Binary files /dev/null and b/docs/_static/logo.png differ
diff --git a/docs/_static/scen.png b/docs/_static/scen.png
new file mode 100644
index 00000000..4c438ebb
Binary files /dev/null and b/docs/_static/scen.png differ
diff --git a/docs/conf.py b/docs/conf.py
index 4e8e069e..a1fea424 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -61,7 +61,9 @@ try:
except ImportError:
html_theme = "default"
+html_logo = "_static/logo.png"
html_static_path = ["_static"]
+html_favicon = "_static/favicon.ico"
html_theme_options = {
"source_repository": "https://github.com/microsoft/RD-Agent",
diff --git a/docs/index.rst b/docs/index.rst
index 69f6d00d..850cd57f 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -6,6 +6,9 @@
Welcome to RDAgent's documentation!
===================================
+.. image:: _static/logo.png
+ :alt: RD-Agent Logo
+
.. toctree::
:maxdepth: 3
:caption: Doctree:
diff --git a/docs/introduction.rst b/docs/introduction.rst
index 22adbf66..9cb2172a 100644
--- a/docs/introduction.rst
+++ b/docs/introduction.rst
@@ -6,7 +6,7 @@ Introduction
In modern industry, research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automate these high-value generic R&D processes through our open source R&D automation tool RDAgent, which let AI drive data-driven AI.
-.. image:: _static/scen.jpg
+.. image:: _static/scen.png
:alt: Our focused scenario
diff --git a/docs/project_framework_introduction.rst b/docs/project_framework_introduction.rst
index bfe7052d..e3b78ec9 100644
--- a/docs/project_framework_introduction.rst
+++ b/docs/project_framework_introduction.rst
@@ -7,7 +7,7 @@ Framework & Components
.. NOTE: This depends on the correctness of `c-v` of github.
-.. image:: https://github.com/user-attachments/assets/98fce923-77ab-4982-93c8-a7a01aece766
+.. image:: _static/Framework-RDAgent.png
:alt: Components & Feature Level
The image above shows the overall framework of RDAgent.
diff --git a/docs/scens/data_agent_fin.rst b/docs/scens/data_agent_fin.rst
index 1c957c16..30e807aa 100644
--- a/docs/scens/data_agent_fin.rst
+++ b/docs/scens/data_agent_fin.rst
@@ -20,14 +20,14 @@ And this is where the **Finance Model Agent** comes into play.
π₯ `Demo `_
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-.. https://rdagent.azurewebsites.net:443/media/54d59c2bf85211de6a7cd2bd3c57d3b56c36cf9795a31111a9111ddb.mp4
-
.. raw:: html
-
+
+
+
π Introduction
@@ -88,26 +88,31 @@ Please refer to the installation part in :doc:`../installation_and_configuration
You can try our demo by running the following command:
- π Create a Conda Environment
- - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
-
- .. code-block:: sh
+
+ - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ .. code-block:: sh
conda create -n rdagent python=3.10
- - Activate the environment:
+ - Activate the environment:
- .. code-block:: sh
+ .. code-block:: sh
- conda activate rdagent
+ conda activate rdagent
- π¦ Install the RDAgent
- - You can directly install the RDAgent package from PyPI:
+
+ - You can install the RDAgent package from PyPI:
- .. code-block:: sh
+ .. code-block:: sh
- pip install rdagent
+ pip install rdagent
- π Run the Application
+
+ - You can directly run the application by using the following command:
+
.. code-block:: sh
rdagent fin_factor
diff --git a/docs/scens/data_copilot_fin.rst b/docs/scens/data_copilot_fin.rst
index 88c4e852..9d5bfc43 100644
--- a/docs/scens/data_copilot_fin.rst
+++ b/docs/scens/data_copilot_fin.rst
@@ -25,11 +25,12 @@ And this is where the **Finance Data Copilot** steps in.
.. raw:: html
-
-
+
+
+
π Introduction
@@ -88,41 +89,59 @@ Please refer to the installation part in :doc:`../installation_and_configuration
You can try our demo by running the following command:
- π Create a Conda Environment
- - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
- .. code-block:: sh
-
- conda create -n rdagent python=3.10
+ - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ .. code-block:: sh
+
+ conda create -n rdagent python=3.10
- - Activate the environment:
+ - Activate the environment:
- .. code-block:: sh
+ .. code-block:: sh
- conda activate rdagent
+ conda activate rdagent
- π¦ Install the RDAgent
- - You can directly install the RDAgent package from PyPI:
+
+ - You can install the RDAgent package from PyPI:
- .. code-block:: sh
+ .. code-block:: sh
- pip install rdagent
+ pip install rdagent
- π Run the Application
- - Store the factors you want to extract from the financial reports in your desired folder. Then, save the paths of the reports in the `report_result_json_file_path`. The format should be as follows:
-
- .. code-block:: json
-
- [
- "git_ignore_folder/report/fin_report1.pdf",
- "git_ignore_folder/report/fin_report2.pdf",
- "git_ignore_folder/report/fin_report3.pdf"
- ]
-
- - Run the application using the following command:
- .. code-block:: sh
+ - Download the financial reports you wish to extract factors from and store them in your preferred folder.
- rdagent fin_factor_report
+ - Specifically, you can follow this example, or use your own method:
+
+ .. code-block:: sh
+
+ wget https://github.com/SunsetWolf/rdagent_resource/releases/download/reports/all_reports.zip
+ unzip all_reports.zip -d git_ignore_folder/reports
+
+ - Run the application with the following command:
+
+ .. code-block:: sh
+
+ rdagent fin_factor_report --report_folder=git_ignore_folder/reports
+
+ - Alternatively, you can store the paths of the reports in `report_result_json_file_path`. The format should be:
+
+ .. code-block:: json
+
+ [
+ "git_ignore_folder/report/fin_report1.pdf",
+ "git_ignore_folder/report/fin_report2.pdf",
+ "git_ignore_folder/report/fin_report3.pdf"
+ ]
+
+ - Then, run the application using the following command:
+
+ .. code-block:: sh
+
+ rdagent fin_factor_report
π οΈ Usage of modules
~~~~~~~~~~~~~~~~~~~~~
diff --git a/docs/scens/model_agent_fin.rst b/docs/scens/model_agent_fin.rst
index 43e9262b..e9ffaef6 100644
--- a/docs/scens/model_agent_fin.rst
+++ b/docs/scens/model_agent_fin.rst
@@ -22,14 +22,12 @@ And this is where the **Finance Model Agent** steps in.
.. raw:: html
-
-
-
-
-
+
+
+
π Introduction
@@ -90,26 +88,31 @@ Please refer to the installation part in :doc:`../installation_and_configuration
You can try our demo by running the following command:
- π Create a Conda Environment
- - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ .. code-block:: sh
- .. code-block:: sh
-
- conda create -n rdagent python=3.10
+ conda create -n rdagent python=3.10
- - Activate the environment:
+ - Activate the environment:
- .. code-block:: sh
+ .. code-block:: sh
- conda activate rdagent
+ conda activate rdagent
- π¦ Install the RDAgent
- - You can directly install the RDAgent package from PyPI:
+
+ - You can install the RDAgent package from PyPI:
- .. code-block:: sh
+ .. code-block:: sh
- pip install rdagent
+ pip install rdagent
- π Run the Application
+
+ - You can directly run the application by using the following command:
+
.. code-block:: sh
rdagent fin_model
diff --git a/docs/scens/model_agent_med.rst b/docs/scens/model_agent_med.rst
index 25f000da..0f4bc839 100644
--- a/docs/scens/model_agent_med.rst
+++ b/docs/scens/model_agent_med.rst
@@ -17,10 +17,12 @@ In this task, we aim at predicting the whether the patients will suffer from Acu
.. raw:: html
-
+
+
+
π Introduction
@@ -69,32 +71,38 @@ Please refer to the installation part in :doc:`../installation_and_configuration
You can try our demo by running the following command:
- π Create a Conda Environment
- - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ .. code-block:: sh
- .. code-block:: sh
-
- conda create -n rdagent python=3.10
+ conda create -n rdagent python=3.10
- - Activate the environment:
+ - Activate the environment:
- .. code-block:: sh
+ .. code-block:: sh
- conda activate rdagent
+ conda activate rdagent
- π¦ Install the RDAgent
- - You can directly install the RDAgent package from PyPI:
+
+ - You can install the RDAgent package from PyPI:
- .. code-block:: sh
+ .. code-block:: sh
- pip install rdagent
+ pip install rdagent
- π¦ Request PhysioNet Account
- - Apply for an account at `PhysioNet `_.
- - Request access to FIDDLE preprocessed data: `FIDDLE Dataset `_.
- - Place your username and password in `.rdagent.app.data_mining.conf`.
+
+ - Apply for an account at `PhysioNet `_.
+ - Request access to FIDDLE preprocessed data: `FIDDLE Dataset `_.
+ - Place your username and password in `.rdagent.app.data_mining.conf`.
- π Run the Application
+
+ - You can directly run the application by using the following command:
+
.. code-block:: sh
rdagent med_model
diff --git a/docs/scens/model_copilot_general.rst b/docs/scens/model_copilot_general.rst
index 11160252..bafdf11f 100644
--- a/docs/scens/model_copilot_general.rst
+++ b/docs/scens/model_copilot_general.rst
@@ -20,10 +20,12 @@ And this is where the **General Model Copilot** steps in.
.. raw:: html
-
+
+
+
π Introduction
~~~~~~~~~~~~~~~~
@@ -60,35 +62,38 @@ Please refer to the installation part in :doc:`../installation_and_configuration
You can try our demo by running the following command:
- π Create a Conda Environment
- - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ - Create a new conda environment with Python (3.10 and 3.11 are well tested in our CI):
+
+ .. code-block:: sh
- .. code-block:: sh
-
- conda create -n rdagent python=3.10
+ conda create -n rdagent python=3.10
- - Activate the environment:
+ - Activate the environment:
- .. code-block:: sh
+ .. code-block:: sh
- conda activate rdagent
+ conda activate rdagent
- π¦ Install the RDAgent
- - You can directly install the RDAgent package from PyPI:
+
+ - You can install the RDAgent package from PyPI:
- .. code-block:: sh
+ .. code-block:: sh
- pip install rdagent
+ pip install rdagent
- π Run the Application
- - Prepare relevant files (in pdf format) by uploading papers to the directory below and copy the path as report_file_path.
+
+ - Prepare relevant files (in pdf format) by uploading papers to the directory below and copy the path as report_file_path.
- .. code-block:: sh
+ .. code-block:: sh
- rdagent/scenarios/general_model
+ rdagent/scenarios/general_model
- - Run the following command in your terminal within the same virtual environment:
-
- .. code-block:: sh
+ - Run the following command in your terminal within the same virtual environment:
+
+ .. code-block:: sh
- rdagent general_model --report_file_path=
+ rdagent general_model --report_file_path=
diff --git a/rdagent/app/qlib_rd_loop/factor_from_report.py b/rdagent/app/qlib_rd_loop/factor_from_report.py
index 81fa8998..cff11408 100644
--- a/rdagent/app/qlib_rd_loop/factor_from_report.py
+++ b/rdagent/app/qlib_rd_loop/factor_from_report.py
@@ -110,7 +110,7 @@ class FactorReportLoop(FactorRDLoop, metaclass=LoopMeta):
open(FACTOR_FROM_REPORT_PROP_SETTING.report_result_json_file_path, "r")
)
else:
- self.judge_pdf_data_items = Path(report_folder).rglob("*.pdf")
+ self.judge_pdf_data_items = [i for i in Path(report_folder).rglob("*.pdf")]
self.pdf_file_index = 0
self.valid_pdf_file_count = 0
@@ -146,21 +146,22 @@ class FactorReportLoop(FactorRDLoop, metaclass=LoopMeta):
return self.current_loop_exp
-def main(path=None, step_n=None):
+def main(report_folder=None, path=None, step_n=None):
"""
- Auto R&D Evolving loop for fintech factors (the factors are extracted from finance report).
-
- You can continue running session by
-
- .. code-block:: python
-
- dotenv run -- python rdagent/app/qlib_rd_loop/factor_from_report.py $LOG_PATH/__session__/1/0_propose --step_n 1 # `step_n` is a optional parameter
+ Auto R&D Evolving loop for fintech factors (the factors are extracted from finance reports).
+ Args:
+ report_folder (str, optional): The folder contains the report PDF files. Reports will be loaded from this folder.
+ path (str, optional): The path for loading a session. If provided, the session will be loaded.
+ step_n (int, optional): Step number to continue running a session.
"""
- if path is None:
- model_loop = FactorReportLoop(FACTOR_FROM_REPORT_PROP_SETTING)
- else:
+ if path is None and report_folder is None:
+ model_loop = FactorReportLoop()
+ elif path is not None:
model_loop = FactorReportLoop.load(path)
+ else:
+ model_loop = FactorReportLoop(report_folder=report_folder)
+
model_loop.run(step_n=step_n)
diff --git a/rdagent/log/ui/web.py b/rdagent/log/ui/web.py
index 99a2f755..f9cff7b5 100644
--- a/rdagent/log/ui/web.py
+++ b/rdagent/log/ui/web.py
@@ -586,7 +586,7 @@ class TraceWindow(StWindow):
self.show_llm = show_llm
self.show_common_logs = show_common_logs
image_c, scen_c = container.columns([2, 3], vertical_alignment="center")
- image_c.image("scen.jpg")
+ image_c.image("scen.png")
scen_c.container(border=True).markdown(QlibModelScenario().rich_style_description)
top_container = container.container()
col1, col2 = top_container.columns([2, 3])
+
+ π₯οΈ Live Demo | π₯ Demo Video | π Documentation
+
+
+
+
+