apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-06-11 15:15:18 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

add aide.py update README

Browse source
This commit is contained in:
duyipan 2024-09-10 16:27:29 +08:00
parent af41f1f1cf
commit 923109e882
2 changed files with 33 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

34
expo/README.md
View file

@ -169,38 +169,8 @@ #### Run
运行下面脚本获取运行结果，在当前目录下将生成一个 log 文件夹以及 workspace 文件夹
log 文件夹中将包含实验使用配置以及生成方案记录，workspace 文件夹下将保存 aide 最后生成的结果文件
```python
import aide
import os
import time
os.environ["OPENAI_API_KEY"] = "sk-xxx"
os.environ["OPENAI_BASE_URL"] = "your url"
start_time = time.time()
data_dir = "xxx/data/titanic"
goal = f"""
# User requirement
({data_dir}, 'This is a 04_titanic dataset. Your goal is to predict the target column `Survived`.\nPerform data analysis, data preprocessing, feature engineering, and modeling to predict the target. \nReport f1 on the eval data. Do not plot or make any visualizations.\n')
# Data dir
training (with labels): train.csv
testing (without labels): test.csv
dataset description: dataset_info.json (You can use this file to get additional information about the dataset)"""
exp = aide.Experiment(
data_dir=data_dir, # replace this with your own directory
goal=goal,
eval="f1", # replace with your own evaluation metric
)
best_solution = exp.run(steps=10)
print(f"Best solution has validation metric: {best_solution.valid_metric}")
print(f"Best solution code: {best_solution.code}")
end_time = time.time()
execution_time = end_time - start_time
print(f"run time : {execution_time} seconds")
```
python experimenter/aide.py
```
### Autogluon

31
expo/experimenter/aide.py Normal file
View file

@ -0,0 +1,31 @@
import aide
import os
import time
os.environ["OPENAI_API_KEY"] = "sk-xxx"
os.environ["OPENAI_BASE_URL"] = "your url"
start_time = time.time()
data_dir = "xxx/data/titanic"
goal = f"""
# User requirement
({data_dir}, 'This is a 04_titanic dataset. Your goal is to predict the target column `Survived`.\nPerform data analysis, data preprocessing, feature engineering, and modeling to predict the target. \nReport f1 on the eval data. Do not plot or make any visualizations.\n')
# Data dir
training (with labels): train.csv
testing (without labels): test.csv
dataset description: dataset_info.json (You can use this file to get additional information about the dataset)"""
exp = aide.Experiment(
data_dir=data_dir, # replace this with your own directory
goal=goal,
eval="f1", # replace with your own evaluation metric
)
best_solution = exp.run(steps=10)
print(f"Best solution has validation metric: {best_solution.valid_metric}")
print(f"Best solution code: {best_solution.code}")
end_time = time.time()
execution_time = end_time - start_time
print(f"run time : {execution_time} seconds")