From a06ad0800f435d7e475c30d0e8740599b0826103 Mon Sep 17 00:00:00 2001
From: junos <junos.lukan@ijs.si>
Date: Mon, 9 Aug 2021 16:02:23 +0200
Subject: [PATCH] Explore missing application categories.

---
 exploration/expl_app_categories.py | 63 ++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 exploration/expl_app_categories.py

diff --git a/exploration/expl_app_categories.py b/exploration/expl_app_categories.py
new file mode 100644
index 0000000..c5cf744
--- /dev/null
+++ b/exploration/expl_app_categories.py
@@ -0,0 +1,63 @@
+# ---
+# jupyter:
+#   jupytext:
+#     formats: ipynb,py:percent
+#     text_representation:
+#       extension: .py
+#       format_name: percent
+#       format_version: '1.3'
+#       jupytext_version: 1.11.4
+#   kernelspec:
+#     display_name: straw2analysis
+#     language: python
+#     name: straw2analysis
+# ---
+
+# %%
+# %matplotlib inline
+import os
+import sys
+
+import matplotlib.pyplot as plt
+import pandas as pd
+import seaborn as sns
+
+nb_dir = os.path.split(os.getcwd())[0]
+if nb_dir not in sys.path:
+    sys.path.append(nb_dir)
+
+# %%
+from config.models import AppCategories, Participant
+from setup import db_engine, session
+
+# %%
+query_app_categories = session.query(AppCategories)
+with db_engine.connect() as connection:
+        df_app_categories = pd.read_sql(query_app_categories.statement, connection)
+
+# %%
+df_app_categories.head()
+
+# %%
+df_app_categories["play_store_genre"].value_counts()
+
+# %%
+df_category_not_found = df_app_categories[df_app_categories["play_store_genre"] == "not_found"]
+
+# %%
+df_category_not_found["play_store_response"].value_counts()
+
+# %%
+df_category_not_found["package_name"].value_counts()
+
+# %%
+manufacturers = ["samsung","oneplus","huawei","xiaomi","lge","motorola","miui","lenovo","oppo","mediatek"]
+custom_rom = ["coloros","lineageos","myos","cyanogenmod", "foundation.e"]
+other = ["android", "wssyncmldm"]
+rows_os_manufacturer = df_category_not_found["package_name"].str.contains("|".join(manufacturers + custom_rom + other), case=False)
+
+# %%
+with pd.option_context(
+    "display.max_rows", None, "display.max_columns", None
+): 
+    display(df_category_not_found.loc[~rows_os_manufacturer])