Add basic size analysis

popcorn.py

@@ -16,3 +16,64 @@ def _():
     mo.md(r"""# Void Linux 'Popcorn' package repository stat analysis""")
     return
 
+
+@app.cell
+def _():
+    def parse_size(size_str):
+        try:
+            return float(re.search(r"(\d+.?\d+) kB", size_str).group(1))
+        except AttributeError:
+            return None
+
+    sizes_df = (
+        pl.read_csv("data/file_sizes.csv")
+        .with_columns(
+            pl.col("name")
+            .str.replace(r"data/(\d{4}-\d{2}-\d{2}).json", "${1}")
+            .str.to_date()
+            .alias("date"),
+            pl.col("size").map_elements(lambda x: parse_size(x), return_dtype=pl.Float32).alias("size_num")
+        )
+        .select(["date", "size_num", "size", "modified"])
+    )
+    sizes_df_null = sizes_df.filter(pl.col("size_num").is_null())
+    sizes_df = sizes_df.filter(pl.col("size").is_not_null())
+    return
+
+
+@app.cell
+def _(sizes_df_null):
+    sizes_df_null.select(["date", "size"]).style.tab_header(
+        title="Missing Days",
+        subtitle="Days with 0B size due to missing on the popcorn server.",
+    )
+
+
+@app.cell
+def _(sizes_df):
+    (
+        lp.ggplot(sizes_df, lp.aes(x="date", y="size"))
+        + lp.geom_point()
+        + lp.labs(
+            title="File sizes",
+            subtitle="Size of daily popcorn files over time",
+            caption="Raw json file size, without any formatting, removal of markers, characters or newlines.",
+        )
+    )
+
+
+@app.cell
+def _(sizes_df):
+    (
+        lp.ggplot(sizes_df, lp.aes(x="date", y="size"))
+        + lp.geom_dotplot()
+        + lp.labs(
+            title="",
+            subtitle="",
+            caption="",
+        )
+    )
+
+
+if __name__ == "__main__":
+    app.run()