Undraft references #75
Conversation
| @@ -257,6 +257,16 @@ ctx-after-train | |||
| ;; So now we can add more operations to the pipeline, | |||
| ;; and nothing else changes, for example drop columns. | |||
|
|
|||
| ;; While most metamorph compliant operations behave the same in | |||
There was a problem hiding this comment.
This is a bit abstract.
How are :fit and :transform different from a certain notion of "fit" and "transform"?
I think this paragraph leaves the reader confused.
There was a problem hiding this comment.
I have no idea how to express the concept of the metamorph context in simple words.
There was a problem hiding this comment.
It is the concept of "keeping state", while still have pure functions.
combined with "transformers" which (might !) behave different in the "two passes" over a pipeline,
in "train" and "predict" (= :fit and :transform)
There was a problem hiding this comment.
combined with the concept that existing dataset->dataset functions can be "lifted automatically by a macro" to become "context"->"context" functions, so we don't need to rewrite tablecloth to become "metamorh compliant"
This is "not simple"
There was a problem hiding this comment.
combined with the fact that we can avoid pipelines as well,
or split it into a dataset transformation pipeline (= using a normal threading macro)
and a metamorph pipeline in most cases.
|
|
||
| ;; These libraries do not have any functions for the models they contain. | ||
| ;; `metamorph.ml` has instead of funtcions per model the concept of each model having a | ||
| ;; unique `key`, the :model-type , which needs to be given when calling |
There was a problem hiding this comment.
It would be good to consistently use backticks for keywords
:model-type, etc.
| ;;`metamorph.ml/train` | ||
| ;; | ||
| ;; The model libraries register their models under these keys, when their main ns | ||
| ;; is `require`d. (and the model keys get printed on screen when getting registered) |
There was a problem hiding this comment.
Some periods (.) are missing at the end of sentences.
|
|
||
| ;; ML tutorial |
| ;; Instead we provide in the the last chapters of the Noj book a complete list | ||
| ;; of all models (and their keys) incl. the parameters they take with a description. | ||
| ;; For some models this reference documentation contains as well code examples. | ||
| ;; This can be used to browse or search for models and their parameters. |
| @@ -6,7 +6,20 @@ | |||
| [scicloj.ml.smile.projections] | |||
| [noj-book.utils.render-tools :refer [render-key-info]])) | |||
|
|
|||
| ;; ## Smile other models reference - DRAFT 🛠 | |||
| ;; ## Smile other models reference | |||
There was a problem hiding this comment.
More context is needed, like the above.
| @@ -13,7 +13,16 @@ | |||
| ^:kindly/hide-code | |||
| (require '[scicloj.ml.smile.regression]) | |||
|
|
|||
| ;; ## Smile regression models reference - DRAFT 🛠 | |||
| ;; ## Smile regression models reference | |||
There was a problem hiding this comment.
More context is needed, like the above.
| @@ -29,7 +32,7 @@ | |||
| (kind/md "----------------------------------------------------------")])))) | |||
|
|
|||
|
|
|||
| ;; ## Transformer reference - DRAFT 🛠 | |||
| ;; ## Transformer reference | |||
There was a problem hiding this comment.
More context is needed, like the above.
We cannot expect the reader to know what Transformers are, even if that was mentioned in a paragraph many chapters ago.
This is especially important, since Transformers have different meanings nowadays.
|
|
||
|
|
||
| ;; ## Tribuo reference - DRAFT 🛠 | ||
| ;; ## Tribuo reference |
There was a problem hiding this comment.
More context is needed, like the above.
| @@ -5,6 +5,15 @@ | |||
| [noj-book.utils.render-tools :refer [render-key-info]])) | |||
|
|
|||
|
|
|||
| ;; ## Xgboost model reference - DRAFT 🛠 | |||
| ;; ## Xgboost model reference | |||
There was a problem hiding this comment.
More context is needed, like the above.
What is XGBoost, etc.
|
You ask for quite some changes, so I somehow believe it is not very efficient if I do them myself and we ping-pong here back and forward. This seems more efficient. |
|
Sure, thanks |
|
Just to mention it. and they are the same thing, just "functional" and "stateless". |
|
Differently to "metamorph transformers", sklearn pipelines cannot have directly "pandas ds->ds operations". But user could create a "custom transformer" which internally executes pandas operations. |
I added explanantions in the references and in
the ml notebooks I added pointers to the reference.
So to me, the "draft" can be removed.