linly/Mining-Away
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Circular bad

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-28 13:13:07 +02:00
parent ae9ca5eee8
commit 28e1c182ba
4 changed files with 39 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
py_scripts/engineer.py
View File

@@ -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()

11
py_scripts/gunner.py
View File

@@ -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())

30
py_scripts/mining_hq.py
View File

@@ -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()