Export categories and add csv.

exploration/expl_app_categories.py

@@ -6,7 +6,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.11.4
+#       jupytext_version: 1.13.0
 #   kernelspec:
 #     display_name: straw2analysis
 #     language: python
@@ -74,3 +74,29 @@ rows_os_manufacturer = df_category_not_found["package_name"].str.contains(
 # %%
 with pd.option_context("display.max_rows", None, "display.max_columns", None):
     display(df_category_not_found.loc[~rows_os_manufacturer])
+
+# %% [markdown]
+# # Export categories
+
+# %% [markdown]
+# Rename all of "not_found" to "system" or "other".
+
+# %%
+df_app_categories_to_export = df_app_categories.copy()
+rows_os_manufacturer_full = (df_app_categories_to_export["package_name"].str.contains(
+    "|".join(manufacturers + custom_rom + other), case=False
+)) & (df_app_categories_to_export["play_store_genre"] == "not_found")
+df_app_categories_to_export.loc[rows_os_manufacturer_full, "play_store_genre"] = "System"
+
+# %%
+rows_not_found = (df_app_categories_to_export["play_store_genre"] == "not_found")
+df_app_categories_to_export.loc[rows_not_found, "play_store_genre"] = "Other"
+
+# %%
+df_app_categories_to_export["play_store_genre"].value_counts()
+
+# %%
+df_app_categories_to_export.rename(columns={"play_store_genre": "genre"},inplace=True)
+df_app_categories_to_export.to_csv("../data/app_categories.csv", columns=["package_hash","genre"],index=False)
+
+# %%