feat: add collect info (#233)

* add collect info

* fix isort error

* optimize code

* fix black error

* Update rdagent/app/cli.py

* Modify the code according to the comments

* fix isort error

* add docker info

* docs: update contributors (#230)

* fix: package dependency. (#234)

* fix package

* fix lint

* docs: Update development.rst (#235)

* feat: add cross validation for kaggle scenario (#236)

* update cross validation for kaggle scenario

* CI Issues

* delete useless file

* CI issues

* docs: Update README.md (#245)

* docs: refine the README (#244)

* init a scenario for kaggle feature engineering

* update the readme

* Delete rdagent/app/kaggle_feature/conf.py

* update some pictures

* Delete rdagent/app/kaggle_feature/model.py

* change a photo

* add pics to docs

* update the readme

* update the README

* for a try

* for another try

* change the style of the pictures in readme

* fix a small bug

* update the readme and the docs

* update the docs

* fix a typo

* change a website url

* change some styles

* fix a typo

* change the size of the logo

* change two urls

* Update README.md

* Update README.md

* Update README.md

* Update README.md

---------

Co-authored-by: Linlang <[email protected]>

* move the component to other files

* last container

* optimize rdagent info

* format with isort

* format with black

* format_with_black

* fix pip error

* format with isort

* change requirements

* fix pip error

* fix_pip_error

* fix pip error

* format with black

* fix pip error

---------

Co-authored-by: you-n-g <[email protected]>
Co-authored-by: Haotian Chen <[email protected]>
Co-authored-by: Haoran Pan <[email protected]>
Co-authored-by: Way2Learn <[email protected]>
Co-authored-by: WinstonLiyt <[email protected]>
Co-authored-by: Young <[email protected]>

Author: 6 people

.github/ISSUE_TEMPLATE/bug-report.md

@@ -27,11 +27,24 @@ Steps to reproduce the behavior:
 <!-- A screenshot of the error message or anything shouldn't appear-->
 
 ## Environment
-<!-- TODO: We may provide a more automatic way to get the information -->
- - RD-Agent version:
+
+**Note**: Users can run `rdagent collect_info` to get system information and paste it directly here.
+
+ - Name of current operating system:
+ - Processor architecture:
+ - System, version, and hardware information:
+ - Version number of the system:
  - Python version:
- - OS: Linux
- - Commit number (optional, please provide it if you are using the dev version):
+ - Container ID:
+ - Container Name:
+ - Container Status:
+ - Image ID used by the container:
+ - Image tag used by the container:
+ - Container port mapping:
+ - Container Label:
+ - Startup Commands:
+ - RD-Agent version:
+ - Package version:
 
 ## Additional Notes
 

README.md

@@ -10,6 +10,7 @@
 [![Lint PR Title](https://github.com/microsoft/RD-Agent/actions/workflows/pr.yml/badge.svg)](https://github.com/microsoft/RD-Agent/actions/workflows/pr.yml)
 [![Readthedocs Preview](https://github.com/microsoft/RD-Agent/actions/workflows/readthedocs-preview.yml/badge.svg)](https://github.com/microsoft/RD-Agent/actions/workflows/readthedocs-preview.yml)
 [![Release.yml](https://github.com/microsoft/RD-Agent/actions/workflows/release.yml/badge.svg)](https://github.com/microsoft/RD-Agent/actions/workflows/release.yml)
+[![Platform](https://img.shields.io/badge/platform-Linux-blue)](https://pypi.org/project/rdagent/#files)
 [![PyPI](https://img.shields.io/pypi/v/rdagent)](https://pypi.org/project/rdagent/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/rdagent)](https://pypi.org/project/rdagent/)
 [![Release](https://img.shields.io/github/v/release/microsoft/RD-Agent)](https://github.com/microsoft/RD-Agent/releases)

rdagent/app/cli.py

@@ -18,6 +18,7 @@
 from rdagent.app.qlib_rd_loop.factor import main as fin_factor
 from rdagent.app.qlib_rd_loop.factor_from_report import main as fin_factor_report
 from rdagent.app.qlib_rd_loop.model import main as fin_model
+from rdagent.app.utils.info import collect_info
 
 load_dotenv()
 
@@ -46,5 +47,6 @@ def app():
             "med_model": med_model,
             "general_model": general_model,
             "ui": ui,
+            "collect_info": collect_info,
         }
     )

rdagent/app/utils/info.py

@@ -0,0 +1,86 @@
+import importlib.metadata
+import platform
+import sys
+from pathlib import Path
+
+import docker
+import requests
+from setuptools_scm import get_version
+
+from rdagent.log import rdagent_logger as logger
+
+
+def sys_info():
+    """collect system related info"""
+    method_list = [
+        ["Name of current operating system: ", "system"],
+        ["Processor architecture: ", "machine"],
+        ["System, version, and hardware information: ", "platform"],
+        ["Version number of the system: ", "version"],
+    ]
+    for method in method_list:
+        logger.info(f"{method[0]}{getattr(platform, method[1])()}")
+    return None
+
+
+def python_info():
+    """collect Python related info"""
+    python_version = sys.version.replace("\n", " ")
+    logger.info(f"Python version: {python_version}")
+    return None
+
+
+def docker_info():
+    client = docker.from_env()
+    containers = client.containers.list(all=True)
+    if containers:
+        containers.sort(key=lambda c: c.attrs["Created"])
+        last_container = containers[-1]
+        logger.info(f"Container ID: {last_container.id}")
+        logger.info(f"Container Name: {last_container.name}")
+        logger.info(f"Container Status: {last_container.status}")
+        logger.info(f"Image ID used by the container: {last_container.image.id}")
+        logger.info(f"Image tag used by the container: {last_container.image.tags}")
+        logger.info(f"Container port mapping: {last_container.ports}")
+        logger.info(f"Container Label: {last_container.labels}")
+        logger.info(f"Startup Commands: {' '.join(client.containers.get(last_container.id).attrs['Config']['Cmd'])}")
+    else:
+        logger.info(f"No run containers.")
+
+
+def rdagent_info():
+    """collect rdagent related info"""
+    current_version = importlib.metadata.version("rdagent")
+    logger.info(f"RD-Agent version: {current_version}")
+    api_url = f"https://api.github.com/repos/microsoft/RD-Agent/contents/requirements.txt?ref=main"
+    response = requests.get(api_url)
+    if response.status_code == 200:
+        files = response.json()
+        file_url = files["download_url"]
+        file_response = requests.get(file_url)
+        if file_response.status_code == 200:
+            all_file_contents = file_response.text.split("\n")
+        else:
+            logger.warning(f"Failed to retrieve {files['name']}, status code: {file_response.status_code}")
+    else:
+        logger.warning(f"Failed to retrieve files in folder, status code: {response.status_code}")
+    package_list = [
+        item.split("#")[0].strip() for item in all_file_contents if item.strip() and not item.startswith("#")
+    ]
+    package_version_list = []
+    for package in package_list:
+        if package == "typer[all]":
+            package = "typer"
+        version = importlib.metadata.version(package)
+        package_version_list.append(f"{package}=={version}")
+    logger.info(f"Package version: {package_version_list}")
+    return None
+
+
+def collect_info():
+    """Prints information about the system and the installed packages."""
+    sys_info()
+    python_info()
+    docker_info()
+    rdagent_info()
+    return None

requirements.txt

@@ -28,7 +28,7 @@ tiktoken
 pymupdf  # Extract shotsreens from pdf
 
 # azure identity related
-azure.identity
+azure-identity
 
 # PDF related
 pypdf
@@ -39,17 +39,9 @@ azure-ai-formrecognizer
 # I think it is for running insteading of implementing. The dependency should be in 
 statsmodels
 
-# PDF related
-pypdf
-azure-core
-azure-ai-formrecognizer
-
 # factor implementations
 tables
 
-# azure identity related
-azure.identity
-
 # CI Fix Tool
 tree-sitter-python
 tree-sitter
@@ -72,6 +64,7 @@ selenium
 kaggle
 
 seaborn
+setuptools-scm
 
 # This is a temporary package installed to pass the test_import test
 xgboost