made documentation strict

.github/workflows/publish.yml

@@ -29,6 +29,13 @@ jobs:
       - name: Unit testing
         run: |
           poetry run python -m pytest
+      - name: Setup Quarto
+        uses: quarto-dev/quarto-actions/setup@v2
+      - name: View Quarto version
+        run:
+          quarto --version
+      - name: Build Notebooks
+        run: bash docs/render_nbs.bash
       - name: Deploy Docs
         run: |
           poetry run python -m mkdocs gh-deploy --strict --force

.github/workflows/test.yml

@@ -39,5 +39,12 @@ jobs:
         run: poetry run isort . --check
       - name: Pytest
         run: poetry run python -m pytest
+      - name: Setup Quarto
+        uses: quarto-dev/quarto-actions/setup@v2
+      - name: View Quarto version
+        run:
+          quarto --version
+      - name: Build Notebooks
+        run: bash docs/render_nbs.bash
       - name: mkdocs
-        run: poetry run python -m mkdocs build
+        run: poetry run python -m mkdocs build --strict

.gitignore

@@ -32,3 +32,10 @@ benchmarking_workflow/prosit_in
 
 notebooks/*.csv
 .Rproj.user
+
+notebooks/**.html
+docs/notebooks/**
+docs/notebooks/**files
+docs/**files/
+site/**
+notebooks/**/**.html

.pre-commit-config.yaml

@@ -48,3 +48,15 @@ repos:
         language: system
         pass_filenames: false
         always_run: true
+      - id: build_nbs
+        name: build_nbs
+        entry: bash docs/render_nbs.bash
+        language: system
+        pass_filenames: false
+        always_run: true
+      - id: build_docs
+        name: build_docs
+        entry: poetry run python -m mkdocs build --strict
+        language: system
+        pass_filenames: false
+        always_run: true

docs/render_nbs.bash

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+set -e
+set -x
+# It is meant to be run from the root of the repository
+
+OUTDIR=docs/notebooks
+rm -rf ${OUTDIR}
+mkdir -p ${OUTDIR}
+
+
+for NOTEBOOK_NAME in $(find notebooks/docs -name '*.qmd'); do
+   bn=$(basename $NOTEBOOK_NAME .qmd)
+   poetry run quarto render ${NOTEBOOK_NAME} --to gfm --output docs/notebooks/${bn}.md $@
+
+   # Manually move the images ... this should be fixed in a future release of quarto ...
+   mv notebooks/docs/${bn}_files docs/notebooks/${bn}_files
+done

elfragmentador/nn_encoding.py

@@ -4,25 +4,19 @@
 learnable embeddings for the aminoacids and ions.
 """
 
-try:
-    from typing import Literal, Union
-
-    LiteralFalse = Literal[False]
-except ImportError:
-    # Python pre-3.8 compatibility
-    from typing import NewType, Union
-
-    LiteralFalse = NewType("LiteralFalse", bool)
-
 import math
+from typing import Literal, Tuple, Union
 
 import pandas as pd
 import torch
 import torch.nn.functional as F
+from pandas import DataFrame
 from torch import Tensor, nn
 
 from elfragmentador import constants
 
+LiteralFalse = Literal[False]
+
 
 class SeqPositionalEmbed(torch.nn.Module):
     def __init__(self, dims_add: int = 10, max_len: int = 30, inverted=True):
@@ -313,7 +307,7 @@ def forward(self, seq, mods):
 
         return seq
 
-    def as_DataFrames(self):
+    def as_DataFrames(self) -> Tuple[DataFrame, DataFrame]:
         """
         Returns the weights as data frames.
 

notebooks/docs/visualize_attention.qmd

@@ -1,6 +1,4 @@
-______________________________________________________________________
-
-## jupyter: python3 format: gfm
+# "Visualize Attention of the default checkpoint"
 
 ```{python}
 from matplotlib import pyplot as plt

notebooks/docs/visualize_embeddings.qmd

@@ -1,6 +1,4 @@
-______________________________________________________________________
-
-## jupyter: python3 format: gfm
+# "Visualize The embeddings of the default checkpoint"
 
 ```{python}
 import elfragmentador

tests/dataset_tests/test_spectronaut_dataset.py

@@ -1,5 +1,4 @@
 import pandas as pd
-import torch
 from pandas import DataFrame
 from torch.utils.data import DataLoader