Re-enable in-text computations

notebooks/popcorn.py

@@ -455,15 +455,9 @@ def plt_kernel_versions():
             .alias("major_ver"),
             pl.col("kernel").str.replace(r"(\d+\.\d+).*", "${1}").alias("minor_ver"),
         )
+        .filter(pl.col("major_ver") != 99)
     )
 
-    kernel_df_v99 = (
-        kernel_df_lazy.filter(pl.col("major_ver") == 99)
-        .collect(engine="streaming")
-        .select("date")
-    )
-    kernel_df_lazy = kernel_df_lazy.filter(pl.col("major_ver") != 99)
-
     (
         lp.ggplot(
             kernel_df_lazy.with_columns(pl.col("major_ver").cast(pl.String))
@@ -482,23 +476,31 @@ def plt_kernel_versions():
     return
 
 
-@app.cell(hide_code=True)
-def _(kernel_df_v99: pl.DataFrame):
-    mo.md(
-        rf"""
-
-    When looking at the kernel versions used, we see a very strong jump between major kernel version
-    4 and major kernel version 5.
-
-    For this analysis we had to exclude {kernel_df_v99.select(pl.len()).item()} rows which were
-    apparently from the future, as they were running variations of major kernel version 99. In all
-    likelihood there is a custom kernel version out there which reports its own major version as 99.
-    The strange version starts appearing on {kernel_df_v99.select("date").row(0)[0]} and shows up
-    all the way until {kernel_df_v99.select("date").row(-1)[0]}.
-
-    """
+@app.cell
+def df_kernel_v99():
+    kernel_df_v99 = (
+        pl.scan_csv(
+            f"{DATA_DIR}/kernels.csv",
+            schema={
+                "date": pl.Date,
+                "kernel": pl.String,
+                "downloads": pl.UInt16,
+            },
+        )
+        .fill_null(0)
+        .with_columns(pl.col("kernel").str.replace(r"(\d+\.\d+\.\d+).*", "${1}"))
+        .with_columns(
+            pl.col("kernel")
+            .str.replace(r"(\d+).*", "${1}")
+            .str.to_integer(dtype=pl.UInt8)
+            .alias("major_ver"),
+            pl.col("kernel").str.replace(r"(\d+\.\d+).*", "${1}").alias("minor_ver"),
+        )
+        .filter(pl.col("major_ver") == 99)
+        .collect(engine="streaming")
+        .select("date")
     )
-    return
+    kernel_df_v99
 
 
 @app.cell