Initial docs generation #32

ppdebreuck · 2021-02-18T16:09:47Z

Modnet documentation automatically generated by sphinx apidoc.

To be discussed:

What files should exactly be tracked by GitHub ? (everything has bee committed)
Is the overall structure of the docs understandable, make it more fancy (some extra sections)?
Host it somewhere, preferentially automatically generated and updated

davidwaroquiers · 2021-02-18T17:11:48Z

Hi guys,

Thank you for the hard work you've been doing with MODNet, which I haven't been able to follow up very much. Just one general comment on documentation, it would be good to get off on the right foot from the beginning (of course :D). I've seen this blog and there is a nice talk from the guy at a pycon conference: https://documentation.divio.com/

Everything does not need to be there from the beginning but if the structure is laid out nicely from the beginning it will for sure help for the future.

The "part" of the documentation that is covered by this pull request is mainly about the API reference from what I understand. As you can see in the blog above (and the pycon conference), there are 3 other parts that have other goals.

David

ml-evs · 2021-02-18T17:17:57Z

Just to put my suggestions to @ppdebreuck in public:

we could use readthedocs to host the sphinx docs, that would be built on every push to master. It allows you to have versioned documentation which is nice.
we could "self-host" on github pages, by committing the docs to a gh_pages branch in this repository (and hitting a switch in the settings); we could then have a CI task that rebuilds the docs and commits them to the gh_pages branch automatically (so only the build files would need to be committed to master)

ppdebreuck · 2021-03-03T15:43:27Z

Update:

Added other sections (mainly Install + Tutorials). Will look how to integrate the other sections recommended by David.
Individual pages for MODData and MODNetModel's specifications
Only track source files+ makefile
Hosting will be done on RTD
Included README update in this PR

ml-evs · 2021-03-05T11:42:10Z

README.md

@@ -19,9 +20,13 @@

 <a name="introduction"></a>
 ## Introduction
-This repository contains the python package implementing the Material Optimal Descriptor Network (MODNet). It is a supervised machine learning framework for **learning material properties** from the **crystal structure**. The framework is well suited for **limited datasets** and can be used for learning *multiple* properties together by using **joint transfer learning**.
+This repository contains the python package implementing the Material Optimal Descriptor Network (MODNet).


Suggested change

This repository contains the python package implementing the Material Optimal Descriptor Network (MODNet).

This repository contains the Python (3.8+) package implementing the Material Optimal Descriptor Network (MODNet).

ml-evs · 2021-03-05T11:43:17Z

README.md

+This repository contains the python package implementing the Material Optimal Descriptor Network (MODNet).
+It is a supervised machine learning framework for **learning material properties** from
+either the **composition** or  **crystal structure**. The framework is well suited for **limited datasets**
+and can be used for learning *multiple* properties together by using **joint transfer learning**.


I would suggest that joint and transfer learning are two separate techniques?

Suggested change

and can be used for learning *multiple* properties together by using **joint transfer learning**.

and can be used for learning *multiple* properties together by using **joint learning**.

ml-evs · 2021-03-05T11:43:31Z

README.md

+This repository also contains two pretrained models that can be used for predicting
+the refractive index and vibrational thermodynamics from any crystal structure.


(Just removing the linebreak)

Suggested change

This repository also contains two pretrained models that can be used for predicting

the refractive index and vibrational thermodynamics from any crystal structure.

This repository also contains two pretrained models that can be used for predicting the refractive index and vibrational thermodynamics from any crystal structure.

ml-evs · 2021-03-05T11:44:36Z

README.md

@@ -34,7 +39,7 @@ See the MODNet papers and repositories below for more details:


 <p align='center'>
-<img src="img/MODNet_schematic.PNG" alt="MODNet schematic" />
+<img src="img/MODNet_schematic.png" alt="MODNet schematic" />


This image does not render for me when I "view file"

(just need to either revert this change or fix the image file extension)

ml-evs · 2021-03-05T11:45:48Z

README.md

+The MP MODData on [figshare](https://figshare.com/articles/dataset/Materials_Project_MP_2018_6_MODData/12834275)
+(MP_2018.6) is very usefull for predicting a learned property on all structures from the Materials Project:


Do we release the MP model too? The example line then shows model predictions...

Suggested change

The MP MODData on [figshare](https://figshare.com/articles/dataset/Materials_Project_MP_2018_6_MODData/12834275)

(MP_2018.6) is very usefull for predicting a learned property on all structures from the Materials Project:

The MP MODData on [figshare](https://figshare.com/articles/dataset/Materials_Project_MP_2018_6_MODData/12834275) (MP_2018.6) is very useful for predicting a learned property on all structures from the Materials Project:

ml-evs · 2021-03-05T11:46:19Z

README.md


+Especially, carefully read the two main classes, `MODData` and `MODNetModel` found in preprocessing and models modules.
+A `MODData` instance is used for representing a particular dataset. It contains a list of structures and corresponding properties:


Suggested change

A `MODData` instance is used for representing a particular dataset. It contains a list of structures and corresponding properties:

A `MODData` instance is used for representing a particular dataset. It contains a list of structures and corresponding properties.

ml-evs · 2021-03-05T11:48:05Z

README.md

@@ -173,7 +197,7 @@ from modnet.preprocessing import MODData
 data = MODData.load('path/dataname')
 ```

-Both the save and load methods use pandas `.read_pickle(...)` and `.load_pickle(...)` which will try to compress/decompress files according to their file extensions (e.g. `".zip"`, `".tgz"` and `".bz2"`.
+Both the save and load methods use pandas `.read_pickle(...)` and `.load_pickle(...)` which will try to compress/decompress files according to their file extensions (e.g. `".zip"`, `".tgz"` and `".bz2").


Suggested change

Both the save and load methods use pandas `.read_pickle(...)` and `.load_pickle(...)` which will try to compress/decompress files according to their file extensions (e.g. `".zip"`, `".tgz"` and `".bz2").

Both the save and load methods use pandas `.read_pickle(...)` and `.load_pickle(...)` which will try to compress/decompress files according to their file extensions (e.g. `".zip"`, `".tgz"` and `".bz2").

Please note that this method is **unsafe** can load arbitrary Python objects. Care has been taken to check the hashes of data that is automatically loaded from Figshare; if you rely on this feature for your own data then we recommend you do the same.

ml-evs · 2021-03-05T11:48:43Z

README.md

+model = MODNetModel(targets,
+                    weights,
+                    num_classes = None  # only needed for classification, e.g. num_classes = {'is_metal':2}
+                    num_neurons=[[64],[32],[16],[16]],
+                    n_feat=300,
+                    act='relu',
+                    )


Suggested change

model = MODNetModel(targets,

weights,

num_classes = None # only needed for classification, e.g. num_classes = {'is_metal':2}

num_neurons=[[64],[32],[16],[16]],

n_feat=300,

act='relu',

)

model = MODNetModel(

targets,

weights,

num_classes = None # only needed for classification, e.g. num_classes = {'is_metal':2}

num_neurons=[[64],[32],[16],[16]],

n_feat=300,

act='relu',

)

ml-evs · 2021-03-05T11:49:19Z

README.md

+model.fit(data,
+          val_fraction = 0.0,
+          val_data = None,
+          val_key = None,
+          lr=0.001,
+          epochs = 200,
+          batch_size = 128,
+          xscale='minmax',
+          loss='mse',
+          )


Suggested change

model.fit(data,

val_fraction = 0.0,

val_data = None,

val_key = None,

lr=0.001,

epochs = 200,

batch_size = 128,

xscale='minmax',

loss='mse',

)

model.fit(

data,

val_fraction = 0.0,

val_data = None,

val_key = None,

lr=0.001,

epochs = 200,

batch_size = 128,

xscale='minmax',

loss='mse',

)

- install - getting-started - support

ppdebreuck requested a review from ml-evs February 18, 2021 16:09

github-pages bot deployed to github-pages February 22, 2021 21:39 View deployment

ppdebreuck force-pushed the create_docs branch from ba36f9b to 3563aff Compare March 3, 2021 15:36

github-pages bot deployed to github-pages March 3, 2021 15:36 View deployment

ml-evs reviewed Mar 5, 2021

View reviewed changes

github-pages bot deployed to github-pages March 8, 2021 16:12 View deployment

github-pages bot deployed to github-pages March 8, 2021 16:33 View deployment

github-pages bot deployed to github-pages March 8, 2021 21:25 View deployment

github-pages bot deployed to github-pages March 8, 2021 21:49 View deployment

github-pages bot deployed to github-pages March 8, 2021 21:51 View deployment

github-pages bot deployed to github-pages March 8, 2021 21:57 View deployment

github-pages bot deployed to github-pages March 8, 2021 21:58 View deployment

github-pages bot deployed to github-pages March 8, 2021 22:01 View deployment

github-pages bot deployed to github-pages March 8, 2021 22:02 View deployment

ppdebreuck marked this pull request as ready for review March 10, 2021 12:05

ppdebreuck force-pushed the create_docs branch from fcfa222 to 1d15476 Compare March 10, 2021 12:07

ppdebreuck added 11 commits March 10, 2021 13:09

README update

86e593a

img update

c39451f

Initial docs generation

3f84aa4

untrack build files

39b4274

restructured docs in separate build and source

d7fea12

reformat API +

3cde2e2

- install - getting-started - support

README update

334091f

add yaml for RTD

9fdde4b

yaml update

c82dc49

change install_requires versions

dde72a1

install_requires fix

3135688

ppdebreuck added 6 commits March 10, 2021 13:09

doc setup test

122e030

doc setup test fix

b6f95cd

doc setup test fix

4ee90b7

doc setup test fix

fd5322f

doc setup test fix

b6d16e9

img update

700ea70

ppdebreuck force-pushed the create_docs branch from 1d15476 to 700ea70 Compare March 10, 2021 12:10

add documentation links in readme and setup

82606f2

ppdebreuck merged commit 4aae4af into master Mar 10, 2021

ml-evs deleted the create_docs branch August 9, 2021 10:21

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Initial docs generation #32

Initial docs generation #32

ppdebreuck commented Feb 18, 2021

davidwaroquiers commented Feb 18, 2021 •

edited

Loading

ml-evs commented Feb 18, 2021

ppdebreuck commented Mar 3, 2021 •

edited

Loading

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

ml-evs Mar 5, 2021

	This repository contains the python package implementing the Material Optimal Descriptor Network (MODNet).
	This repository contains the Python (3.8+) package implementing the Material Optimal Descriptor Network (MODNet).

	and can be used for learning multiple properties together by using joint transfer learning.
	and can be used for learning multiple properties together by using joint learning.

		This repository also contains two pretrained models that can be used for predicting
		the refractive index and vibrational thermodynamics from any crystal structure.

		The MP MODData on [figshare](https://figshare.com/articles/dataset/Materials_Project_MP_2018_6_MODData/12834275)
		(MP_2018.6) is very usefull for predicting a learned property on all structures from the Materials Project:


		Especially, carefully read the two main classes, `MODData` and `MODNetModel` found in preprocessing and models modules.
		A `MODData` instance is used for representing a particular dataset. It contains a list of structures and corresponding properties:

	Both the save and load methods use pandas `.read_pickle(...)` and `.load_pickle(...)` which will try to compress/decompress files according to their file extensions (e.g. `".zip"`, `".tgz"` and `".bz2").
	Both the save and load methods use pandas `.read_pickle(...)` and `.load_pickle(...)` which will try to compress/decompress files according to their file extensions (e.g. `".zip"`, `".tgz"` and `".bz2").
	Please note that this method is unsafe can load arbitrary Python objects. Care has been taken to check the hashes of data that is automatically loaded from Figshare; if you rely on this feature for your own data then we recommend you do the same.

Initial docs generation #32

Initial docs generation #32

Conversation

ppdebreuck commented Feb 18, 2021

davidwaroquiers commented Feb 18, 2021 • edited Loading

ml-evs commented Feb 18, 2021

ppdebreuck commented Mar 3, 2021 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

davidwaroquiers commented Feb 18, 2021 •

edited

Loading

ppdebreuck commented Mar 3, 2021 •

edited

Loading