junos
/
stress_at_work_analysis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Export categories and add csv.

rapids
junos 2021-12-15 18:26:20 +01:00
parent 7e8e922d71
commit de10269d36
2 changed files with 1046 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1019
data/app_categories.csv 100644
View File

File diff suppressed because it is too large Load Diff

28
exploration/expl_app_categories.py
View File

@ -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)
# %%