From fea7af62f69257378eb672edf245ad69d9b3b11b Mon Sep 17 00:00:00 2001
From: Supermjork <markehabaziz@gmail.com>
Date: Tue, 28 Mar 2023 14:07:50 +0200
Subject: [PATCH] Refactoring killed muh bebe

---
 py_scripts/gunner.py    | 29 +----------------------------
 py_scripts/mining_hq.py | 35 +++++++++++++++++++++--------------
 2 files changed, 22 insertions(+), 42 deletions(-)

diff --git a/py_scripts/gunner.py b/py_scripts/gunner.py
index ad454ad..0f8e503 100644
--- a/py_scripts/gunner.py
+++ b/py_scripts/gunner.py
@@ -3,34 +3,7 @@
 
 import pandas as pd
 import numpy as np
-import mining_hq
 
-# Sharing the dataset variables
-# Games' data
-
-# Loading Datasets
-games_merged = mining_hq.games_merged_dat
-
-victim1 = pd.read_excel("datasets/crime/clean_crime_canada_dataset.xlsx")
-victim2 = pd.read_csv("datasets/crime/report.csv")
-
-# Printing information regarding datasets
-print("Game Datasets' Info:\n")
-games_merged.info()
-
-print("Crime Datasets' Info:\n")
-victim2.info()
-victim1.info()
-
-
-# Regarding the Games.xls dataset:
-# Coercing the non-numeric values will result in NaN
-# thus allowing easier removal through `.notnull()`
-
-
-# Regarding the vgsales-12-4-2019 dataset
-# Considering we will be using a US (probs CA too) crime datasets
-# It wouldn't be that useful to have other columns regarding other regions
 def drop_kick(col_list, dataframe):
     return dataframe.drop(columns=col_list, axis=1)
 
@@ -38,8 +11,8 @@ def drop_kick(col_list, dataframe):
 # Getting the range of years which both datasets share
 def year_interval(victim1, victim2, col1, col2):
     return (
-        min(victim2[col2].max(), victim1[col1].max()),
         max(victim2[col2].min(), victim1[col1].min()),
+        min(victim2[col2].max(), victim1[col1].max()),
     )
 
 
diff --git a/py_scripts/mining_hq.py b/py_scripts/mining_hq.py
index 9a6854f..0c628de 100644
--- a/py_scripts/mining_hq.py
+++ b/py_scripts/mining_hq.py
@@ -4,7 +4,7 @@ import pandas as pd
 import numpy as np
 import seaborn as sns
 import digger
-from tkinter.filedialog import askopenfilename
+import gunner
 
 # Instantiating globals to be used in other files
 global games_merged_dat
@@ -23,7 +23,16 @@ games_merged_dat = digger.write_joined_df(games_sales, games_review_final)
 # Acquisition of Merged dataset
 games_merged_dat.to_csv("datasets/videogames/games_merged.csv")
 
-import gunner
+# Loading Crime Datasets
+crime_CA = pd.read_excel('datasets/crime/clean_crime_canada_dataset.xlsx')
+
+crime_US = pd.read_csv('datasets/crime/report.csv')
+
+year_interval = gunner.year_interval(crime_US, crime_CA, "report_year", "year")
+
+print(year_interval[0], year_interval[1])
+
+crime_intersect = gunner.intersect_by_year(crime_US, crime_CA, "report_year", "year")
 
 NA_col_list = [
     "PAL_Sales",
@@ -33,7 +42,6 @@ NA_col_list = [
     "User_Score",
     "GameName",
     "Review",
-    "",
 ]
 GLO_col_list = [
     "PAL_Sales",
@@ -43,22 +51,21 @@ GLO_col_list = [
     "User_Score",
     "GameName",
     "Review",
-    "",
 ]
+
+# Splitting crime datasets
 # Collecting Split-Up Datasets
-games_sales_split_pre = gunner.game_sales_NA_pre
+games_merged_dat = gunner.drop_kick(NA_col_list, games_merged_dat)
 
-games_sales_split_dur = gunner.game_sales_NA_dur
-
-games_sales_split_pos = gunner.game_sales_NA_pos
+sale_tri_split = gunner.trisect_by_year(games_merged_dat, 'Year', year_interval)
 
 # Displaying Acquired Data
 print("Acquired Datasets:\n")
-games_sales_split_pre.head(5)
-games_sales_split_dur.head(5)
-games_sales_split_pos.head(5)
+print(sale_tri_split[0].head(5),
+sale_tri_split[1].head(5),
+sale_tri_split[2].head(5))
 
 print("Dataset Info:\n")
-games_sales_split_pre.info()
-games_sales_split_dur.info()
-games_sales_split_pos.info()
+sale_tri_split[0].info()
+sale_tri_split[1].info()
+sale_tri_split[2].info()