Pre-commit fixes

Author: dependabot[bot]

s10_extra/documentation.md

@@ -40,7 +40,7 @@ dynamic (like video), but the site does not change (1).
 
 We are in this module going to look at [Mkdocs](https://www.mkdocs.org/), which (in my opinion) is one of the easiest
 systems to get started with because all documentation is written in markdown and the build system is written in Python.
-As an alternativ, you can consider doing the exercises in [Sphinx](https://www.sphinx-doc.org/en/master/) which is
+As an alternative, you can consider doing the exercises in [Sphinx](https://www.sphinx-doc.org/en/master/) which is
 probably the most used documentation system for Python code. Sphinx offer more customization than Mkdocs, so is
 generally preferred for larger projects with complex documentation, but for smaller projects Mkdocs should be easier to
 get started with and is sufficient.

s3_reproducibility/config_files.md

@@ -121,7 +121,7 @@ look online for your answers before looking at the solution. Remember: it's not
     ??? success "Solution"
 
         From the top of the file `batch_size`, `x_dim`, `hidden_dim` can be found as hyperparameters. Looking through
-        the code it can be seen that the `latent_dim` of the encoder and decoder, `lr` for the optimzer, and `epochs` in
+        the code it can be seen that the `latent_dim` of the encoder and decoder, `lr` for the optimizer, and `epochs` in
         the training loop are also hyperparameters. Finally, the `seed` is not included in the script but is needed to
         make the script fully reproducible, e.g. `torch.manual_seed(seed)`.
 

s7_deployment/exercise_files/onnx_simple.py

@@ -27,7 +27,7 @@
 graph = make_graph([node1, node2], "lr", [X, A, B], [Y])  # nodes  # a name  # inputs  # outputs
 
 # onnx graph
-# there is no metata in this case.
+# there is no metadata in this case.
 
 onnx_model = make_model(graph)
 

tools/to_pdf/main.py

@@ -1,15 +1,16 @@
 import os
-import requests
-from bs4 import BeautifulSoup
+import re
 from urllib.parse import urljoin, urlparse
+
 import pdfkit
+import requests
+from bs4 import BeautifulSoup
 from PyPDF2 import PdfMerger, PdfReader, PdfWriter
-import re
+
 
 def natural_key(s):
     """Turn a string into a list of ints and text, so 's10' > 's9'."""
-    return [int(text) if text.isdigit() else text.lower()
-            for text in re.split(r'(\d+)', s)]
+    return [int(text) if text.isdigit() else text.lower() for text in re.split(r"(\d+)", s)]
 
 
 def get_all_links(base_url):
@@ -47,7 +48,7 @@ def save_pages_as_pdfs(urls, output_dir="pages_pdfs"):
     os.makedirs(output_dir, exist_ok=True)
     pdf_files = []
     for i, url in enumerate(urls):
-        out_file = os.path.join(output_dir, f"page_{i+1}.pdf")
+        out_file = os.path.join(output_dir, f"page_{i + 1}.pdf")
         try:
             pdfkit.from_url(url, out_file)
             pdf_files.append(out_file)
@@ -68,17 +69,24 @@ def merge_pdfs(pdf_files, output_file="combined.pdf"):
 
 import subprocess
 
+
 def compress_pdf(input_file, output_file, quality="/ebook"):
-    subprocess.run([
-        "gs", "-sDEVICE=pdfwrite", "-dCompatibilityLevel=1.4",
-        f"-dPDFSETTINGS={quality}",
-        "-dNOPAUSE", "-dQUIET", "-dBATCH",
-        f"-sOutputFile={output_file}", input_file
-    ])
+    subprocess.run(
+        [
+            "gs",
+            "-sDEVICE=pdfwrite",
+            "-dCompatibilityLevel=1.4",
+            f"-dPDFSETTINGS={quality}",
+            "-dNOPAUSE",
+            "-dQUIET",
+            "-dBATCH",
+            f"-sOutputFile={output_file}",
+            input_file,
+        ]
+    )
     print(f"📉 Compressed {input_file} → {output_file}")
 
 
-
 def split_pdf(input_file, output_files):
     reader = PdfReader(input_file)
     total_pages = len(reader.pages)
@@ -95,21 +103,22 @@ def split_pdf(input_file, output_files):
             writer.add_page(page)
         with open(out_file, "wb") as f:
             writer.write(f)
-        print(f"✂️ Split pages {start+1}-{end} → {out_file}")
+        print(f"✂️ Split pages {start + 1}-{end} → {out_file}")
         start = end
 
 
 if __name__ == "__main__":
     base_url = "https://skaftenicki.github.io/dtu_mlops/"
     urls = get_all_links(base_url)
-    urls = sorted(urls, key=natural_key)   # 👈 use natural sort
+    urls = sorted(urls, key=natural_key)  # 👈 use natural sort
     print(f"Found {len(urls)} pages.")
 
     pdf_files = save_pages_as_pdfs(urls)
     merge_pdfs(pdf_files, "dtu_mlops_all.pdf")
-    split_pdf("dtu_mlops_all.pdf", [
-        "dtu_mlops_part1.pdf", "dtu_mlops_part2.pdf", "dtu_mlops_part3.pdf", "dtu_mlops_part4.pdf"
-    ])
+    split_pdf(
+        "dtu_mlops_all.pdf",
+        ["dtu_mlops_part1.pdf", "dtu_mlops_part2.pdf", "dtu_mlops_part3.pdf", "dtu_mlops_part4.pdf"],
+    )
     compress_pdf("dtu_mlops_part1.pdf", "dtu_mlops_part1_small.pdf")
     compress_pdf("dtu_mlops_part2.pdf", "dtu_mlops_part2_small.pdf")
     compress_pdf("dtu_mlops_part3.pdf", "dtu_mlops_part3_small.pdf")