Start transferring to quarto file

notebooks/popcorn.py

@@ -83,7 +83,7 @@ def plt_filesize(sizes_df):
         + lp.geom_smooth(method="lm")
         + lp.labs(
             title="Size growth",
-            subtitle="Size of daily popcorn statistics files over time",
+            subtitle="Cumulative filesize of daily popcorn statistics over time",
             caption="Raw json file size, without any formatting, removal of markers, characters or newlines.",
             y="filesize in kB",
         )
@@ -115,7 +115,7 @@ def _():
 
 
 @app.cell
-def _():
+def tab_pkg():
     df_versions_lazy = pl.scan_csv(
         f"{DATA_DIR}/packages.csv",
         schema={
@@ -157,7 +157,7 @@ def _():
 
 
 @app.cell
-def _(df_pkg_lazy: pl.LazyFrame):
+def plt_weekly_packages(df_pkg_lazy: pl.LazyFrame):
     pkg_per_day = df_pkg_lazy.group_by("date").agg(pl.col("count").sum()).sort("date")
 
     def _():
@@ -222,7 +222,7 @@ def _():
 
 
 @app.cell
-def _(df_pkg_lazy: pl.LazyFrame):
+def plt_weekday_packages(df_pkg_lazy: pl.LazyFrame):
     def _():
         weekday_downloads = (
             df_pkg_lazy.with_columns(
@@ -261,7 +261,8 @@ def _(df_pkg_lazy: pl.LazyFrame):
 
 
 @app.cell
-def _(df_pkg_lazy: pl.LazyFrame):
+def plt_month_packages(df_pkg_lazy: pl.LazyFrame):
+    # FIXME: should be cut off after exact 12 months, or counts some months double
     def _():
         month_agg_downloads = (
             df_pkg_lazy.with_columns(pl.col("date").dt.month().alias("month"))
@@ -285,7 +286,7 @@ def _(df_pkg_lazy: pl.LazyFrame):
 
 
 @app.cell
-def _():
+def plt_unique_installs():
     df_unique_installs = pl.read_csv(
         f"{DATA_DIR}/unique_installs.csv",
         schema={"date": pl.Date, "unique": pl.UInt16},
@@ -306,7 +307,7 @@ def _():
 
 
 @app.cell
-def _(df_pkg_lazy: pl.LazyFrame):
+def plt_top_packages(df_pkg_lazy: pl.LazyFrame):
     df_pkg_dl = df_pkg_lazy.group_by("package").agg(pl.col("count").sum())
 
     def _():
@@ -346,7 +347,7 @@ def _(df_pkg_lazy: pl.LazyFrame):
 
 
 @app.cell(hide_code=True)
-def _(df_pkg_dl: pl.LazyFrame):
+def plt_package_distribution(df_pkg_dl: pl.LazyFrame):
     def _():
         return (
             lp.ggplot(df_pkg_dl.collect(engine="streaming"), lp.aes("count"))
@@ -360,39 +361,6 @@ def _(df_pkg_dl: pl.LazyFrame):
     return
 
 
-@app.cell(hide_code=True)
-def _(df_pkg_dl: pl.LazyFrame):
-    # TODO: this is horrible performance-wise
-    def _():
-        def get_num(df: pl.LazyFrame) -> int:
-            return df.count().collect(engine="streaming").item(0, 0)
-
-        one_ten_installs = df_pkg_dl.sort("count", descending=False).filter(
-            (pl.col("count") >= 1) & (pl.col("count") < 10)
-        )
-        ten_twenty_installs = df_pkg_dl.sort("count", descending=False).filter(
-            (pl.col("count") >= 10) & (pl.col("count") < 20)
-        )
-        twenty_thirty = df_pkg_dl.sort("count", descending=False).filter(
-            (pl.col("count") >= 20) & (pl.col("count") < 30)
-        )
-        thirty_plus = df_pkg_dl.sort("count", descending=False).filter(
-            (pl.col("count") >= 30)
-        )
-        # TODO: Fix for new filters above
-        return mo.md(rf"""
-
-        There are {get_num(one_ten_installs):,} packages which have between one
-        and ten installations in the data, {get_num(ten_twenty_installs):,}
-        packages between eleven and 20 installations, and
-        {get_num(twenty_thirty):,} packages between 21 and 30 installations.
-        {get_num(thirty_plus):,} packages have over 30 installations.
-
-        """)
-
-    _()
-    return
-
 
 @app.cell(hide_code=True)
 def _():
@@ -402,7 +370,7 @@ def _():
 
 # - which kernels have been DL when? (simplified for semver)
 @app.cell
-def _():
+def plt_kernel_versions():
     kernel_df_lazy = (
         pl.scan_csv(
             f"{DATA_DIR}/kernels.csv",
@@ -468,7 +436,7 @@ def _(kernel_df_v99: pl.DataFrame):
 
 
 @app.cell
-def _(kernel_df_lazy: pl.LazyFrame):
+def plt_kernel_timeline(kernel_df_lazy: pl.LazyFrame):
     weekly_kernel_df = (
         kernel_df_lazy.with_columns(pl.col("major_ver").cast(pl.String))
         .select(["date", "major_ver", "downloads"])
@@ -535,7 +503,7 @@ def _():
 
 
 @app.cell
-def _(sizes_df: pl.DataFrame):
+def tab_missing_days(sizes_df: pl.DataFrame):
     date_range = pl.date_range(
         sizes_df.select("date").min().item(), sizes_df.select("date").max().item()
     )
@@ -550,7 +518,7 @@ def _(sizes_df: pl.DataFrame):
 
 
 @app.cell
-def _(sizes_df):
+def plt_modified_times(sizes_df):
     def _():
         different_modification_date = sizes_df.filter(
             pl.col("date") != pl.col("modified").dt.date()