Comments (15)
Indeed, if I look again at above visualisation, it looks 'scattered'. I will adjust it to the vertical stack version. Let's see how it'll look ;)
from dtreeviz.
Looks pretty cool! I think our goal, though, is to show the path from root to predictor leaf in a big tree as tightly as possible. I wonder what it looks like as a vertical stack of just the decision nodes entered and then the leaf. That would be the smallest footprint, which I think is kind of the goal here. what do you think?
from dtreeviz.
from dtreeviz.
heh, nice work! I like it. Does it work horizontally too? I think we have an option for that.
from dtreeviz.
cool. By horizontally.... do you mean a horizontal stack instead of vertical stack ?
from dtreeviz.
yep, left to right
from dtreeviz.
wouldn't be a problem if the prediction path is very deep ? I think we will end with a 'crowdy' plot.
from dtreeviz.
well, sometimes you want very tall and sometimes very wide. seems like original code can change orientation so this should inherit that; i assume you just cut/paste, right?
from dtreeviz.
I wanted to use as much functionality as possible from dtreeviz(), so I didn't cut/paste. I will take a look for horizontal view. There is little work left also for vertical view, I made a little 'hack' to create the visualisation with vertical view for decision nodes only :)
from dtreeviz.
We can skip horizontal if it gets messy in the code :)
from dtreeviz.
For horizontal view I didn't have to do any extra logic, it was already in dtreeviz() code ;)
Should I make a PR ?
from dtreeviz.
Looks great! Only question is, how do we activate this? Seems like it should be an arg to existing tree viz functions. Oh, I see you have show_just_path
. Sounds good! Please do make a PR. Does it work for regression trees too?
from dtreeviz.
I didn't try it on regression trees. I will try it tomorrow.
from dtreeviz.
yey, it works also for regression trees. I will create a PR for this.
from dtreeviz.
great job!
from dtreeviz.
Related Issues (20)
- from dtreeviz.trees import * Import necessary libraries HOT 1
- Color keyword argument - Value error HOT 14
- Add support for TensorFlow GradientBoostedTreesModel model
- _regr_leaf_viz calculates the mean for prediction value.
- WARNING:matplotlib.font_manager:findfont: Font family 'Arial' not found. HOT 2
- Decision Tree visualize wrong path HOT 1
- When using dataset that is different from the training for trees models - does not draw HOT 1
- Support for RandomForest HOT 5
- Visualize custom decision tree HOT 1
- how to use dtreeviz in streamlit HOT 2
- VisualisationNotYetSupportedError: get_min_samples_leaf() is not implemented yet for XGBoost. HOT 4
- TypeError: list indices must be integers or slices, not numpy.float64 HOT 5
- Crash when leaf nodes have no samples HOT 1
- Out of memory when calling viz.view() HOT 2
- Integrate AI explanation
- CatBoost need to be supported. HOT 1
- AttributeError: module 'dtreeviz' has no attribute 'model' on Windows platform, works fine on Google colab
- tfdf.keras.CartModel support? HOT 1
- TypeError: 'int' object is not subscriptable HOT 3
- Development requirement in `setup.py` HOT 1
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 dtreeviz.