From 28e1c182bad1757a36cbfe527ed851aadde07fcd Mon Sep 17 00:00:00 2001
From: Supermjork <markehabaziz@gmail.com>
Date: Tue, 28 Mar 2023 13:13:07 +0200
Subject: [PATCH] Circular bad

---
 .gitignore              |  1 +
 py_scripts/engineer.py  |  8 ++++----
 py_scripts/gunner.py    | 11 ++++++-----
 py_scripts/mining_hq.py | 30 ++++++++++++++++++++++++++++--
 4 files changed, 39 insertions(+), 11 deletions(-)

diff --git a/.gitignore b/.gitignore
index 948496b..dc7b073 100644
--- a/.gitignore
+++ b/.gitignore
@@ -131,3 +131,4 @@ dmypy.json
 .vscode/
 jupyter-notes/merged_games.csv
 datasets/videogames/vgsales.csv
+datasets/videogames/games_merged.csv
diff --git a/py_scripts/engineer.py b/py_scripts/engineer.py
index 9c93815..ab22516 100644
--- a/py_scripts/engineer.py
+++ b/py_scripts/engineer.py
@@ -1,15 +1,15 @@
 # Visualisations for Data
 import matplotlib.pyplot as plt
 import seaborn as sns
-import gunner
+import mining_hq
 from numpy import count_nonzero
 
 sns.set()
 plt.xticks(rotation = 90)
 
-games_pre = gunner.game_sales_NA_pre
-games_dur = gunner.game_sales_NA_dur
-games_pos = gunner.game_sales_NA_pos
+games_pre = mining_hq.games_sales_split_pre
+games_dur = mining_hq.games_sales_split_dur
+games_pos = mining_hq.games_sales_split_pos
 
 games_fig_pre = sns.barplot(data = games_pre, x = "Year", y = "NA_Sales", estimator = count_nonzero)
 plt.show()
diff --git a/py_scripts/gunner.py b/py_scripts/gunner.py
index 238f872..44b1773 100644
--- a/py_scripts/gunner.py
+++ b/py_scripts/gunner.py
@@ -3,6 +3,7 @@
 
 import pandas as pd
 import numpy as np
+import mining_hq
 
 # Sharing the dataset variables
 # Games' data
@@ -22,7 +23,7 @@ global crime_US
 global crime_CA
 
 # Loading Datasets
-games_merged = pd.read_csv('datasets/videogames/merged_games.csv')
+games_merged = mining_hq.games_merged_dat
 
 crime_CA = pd.read_excel('datasets/crime/clean_crime_canada_dataset.xlsx')
 crime_US = pd.read_csv('datasets/crime/report.csv')
@@ -54,14 +55,14 @@ games_merged.info()
 # 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
-NA_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'Global_Sales']
-GLO_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'NA_Sales']
+NA_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'Global_Sales', 'User_Score', 'GameName', 'Review', '']
+GLO_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'NA_Sales', 'User_Score', 'GameName', 'Review', '']
 
 game_sales_NA = games_merged.drop(columns = NA_col_list, axis = 1)
 game_sales_GLO = games_merged.drop(columns = GLO_col_list, axis = 1)
 
-print(f"Game Sales for NA:\n{game_sales_NA.head(10)} \nWith minimum year being: {game_sales_NA['Year'].min()}")
-print(f"Game Sales Globally:\n{game_sales_GLO.head(10)}\nWith minimum year being: {game_sales_GLO['Year'].min()}")
+print(f"Game Sales for NA:\n{game_sales_NA.head(5)} \nWith minimum year being: {game_sales_NA['Year'].min()}")
+print(f"Game Sales Globally:\n{game_sales_GLO.head(5)}\nWith minimum year being: {game_sales_GLO['Year'].min()}")
 
 # Getting the range of years which both datasets share
 crime_year_min = max(crime_US['report_year'].min(), crime_CA['year'].min())
diff --git a/py_scripts/mining_hq.py b/py_scripts/mining_hq.py
index 10b4f12..540666e 100644
--- a/py_scripts/mining_hq.py
+++ b/py_scripts/mining_hq.py
@@ -4,14 +4,40 @@ import pandas as pd
 import numpy as np
 import seaborn as sns
 import digger
-
-import pandas as pd
 from tkinter.filedialog import askopenfilename
 
+# Instantiating globals to be used in other files
+global games_merged_dat
+global games_sales_split_pre
+global games_sales_split_dur
+global games_sales_split_pos
+
 games_review = pd.read_csv("datasets/videogames/Games.xls")
 games_sales = pd.read_csv("datasets/videogames/vgsales-12-4-2019-short.csv")
 
 games_review_phase1 = digger.slice_column(games_review, "GameName", "Review")
 games_review_final = digger.slice_column(games_review, "GameName", "(Import)")
+
 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
+# Collecting Split-Up Datasets
+games_sales_split_pre = gunner.game_sales_NA_pre
+
+games_sales_split_dur = gunner.game_sales_NA_dur
+
+games_sales_split_pos = gunner.game_sales_NA_pos
+
+# 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("Dataset Info:\n")
+games_sales_split_pre.info()
+games_sales_split_dur.info()
+games_sales_split_pos.info()