Comments (6)
I have no Data Science skills and experience, so I need more details here. It's very likely I would need serious DS training to get into it, and I can't be productive in this domain yet.
from rforestry.
I see your concerns. I shared some additional context via Slack, but IIUC you don't have access or to email for the next two weeks, is that correct? This request stems from an exploration of sklearn compatibility by others that I've uploaded here. I think running check_estimator()
in the example then addressing pure syntax changes could be an appropriate starting point. Let me know if you run into specific issues or continue to have concerns.
from rforestry.
I still have no idea of what's going on in that code and what the goal is. No idea what sklearn/ray is too, I have no exposure to ds frameworks at all.
DS is not something I can jump in just like that, without any theoretical knowledge. I'm sorry but you'll have to reassign this task to someone else.
from rforestry.
Thanks for sharing the context. I shared some details earlier over Slack, but realize you may not have access. Let's chat tomorrow about the best path forward!
from rforestry.
Chatted about this, appreciate you taking the time to sync. Documenting some of the additional context discussed here.
The Python package was originally developed with the intention of natively following an interface called "scikit-learn", but deltas have been introduced over time. The interface defines some requirements for class initialization, function naming, and parameter. Adhering to this interface allows easy integration with many other Python libraries that can parallelize model training or improve performance. The fixes should be syntactical and be limited to appropriately extending class requirements. However, if any errors touch model logic, requires data science context, or if any questions arise at all, please tag me and I'll resolve those myself as soon as I can.
The starting step is to run and eventually pass the following check:
from random_forestry import RandomForest
from sklearn.utils.estimator_checks import check_estimator
check_estimator(RandomForest())
The checks can be found in estimator_checks.py() with details outlined in the documentation starting from this section and below. The bulk of the change should be the following:
- Renaming getter and setter methods to
get_params
andset_params
- Explicitly define
__init__()
that aligns with params - Functions with the data frame argument
newdata
should be renamedX
Other changes may be class specific so as mentioned above, let's work closely on this if questions arise!
from rforestry.
Created PR #146
from rforestry.
Related Issues (20)
- Getting weights variables HOT 1
- Clean up README for Python Package
- Training data column with only NAs
- `has_nas` method defined, but not used
- Export model to JSON string
- Add coverage report for unittests
- `seed` same in different objects HOT 3
- :no_good: Branch `bptest/test` has an incorrect name
- Implement Custom Sampling in Python
- Allow all NA or same value columns with scaling HOT 1
- Change linFeats to be 1-indexed instead of 0-indexed
- Python package documentation is outdated
- Fix authentication issue preventing python build pipeline to access docker image
- Build R package and upload it as pipeline artifact
- R release on CRAN - resolve std::cout?
- Add pipeline step for cross language tests / Python pipeline
- Floating point imprecision HOT 3
- Python Predictions not being rescaled when forest is trained with scale = True
- segmentation faults when splitratio = 0.5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rforestry.