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

Seaborn be gud

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-27 15:53:04 +02:00
parent d3686c8b0a
commit a88af62166
2 changed files with 37 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
py_scripts/engineer.py
View File

@@ -1,7 +1,14 @@
# Visualisations for Data # Visualisations for Data
import matplotlib.pyplot as plt
import seaborn as sns import seaborn as sns
import gunner import gunner
from numpy import count_nonzero
sns.set()
plt.xticks(rotation=90)
games_vis = gunner.game_sales_NA games_vis = gunner.game_sales_NA
sns.relplot(data = games_vis, x = "Year", y = "NA_Sales") games_fig = sns.barplot(data = games_vis, x = games_vis["Year"], y = games_vis["NA_Sales"], estimator = count_nonzero)
plt.show()

37
py_scripts/gunner.py
View File

@@ -11,20 +11,34 @@ global games_dat
global game_sales_NA global game_sales_NA
# Sales Globally # Sales Globally
global game_sales_GLO global game_sales_GLO
# Crime Recorded in The US
global crime_US
# Crime Recorded in Canada
global crime_CA
# Loading Datasets # Loading Datasets
game_sales2019_dat = pd.read_csv('datasets/videogames/vgsales-12-4-2019-short.csv') game_sales_dat = pd.read_csv('datasets/videogames/vgsales-12-4-2019-short.csv')
games_dat = pd.read_csv('datasets/videogames/Games.xls') games_dat = pd.read_csv('datasets/videogames/Games.xls')
crime_CA = pd.read_excel('datasets/crime/clean_crime_canada_dataset.xlsx')
crime_US = pd.read_csv('datasets/crime/report.csv')
# Printing information regarding datasets # Printing information regarding datasets
print("Data Sets' Info:\n") print("Game Datasets' Info:\n")
game_sales2019_dat.info() game_sales_dat.info()
games_dat.info() games_dat.info()
print("Crime Datasets' Info:\n")
crime_US.info()
crime_CA.info()
# Printing First n values (index start: 0) # Printing First n values (index start: 0)
print("Game Sale Data:\n", game_sales2019_dat.head(10)) print("Game Sale Data:\n", game_sales_dat.head(10))
print("Game Scores:\n", games_dat.head(10)) print("Game Scores:\n", games_dat.head(10))
print("US Crime Data:\n", crime_US.head(10))
print("CA Crime Data:\n", crime_CA.head(10))
# Regarding the Games.xls dataset: # Regarding the Games.xls dataset:
# Coercing the non-numeric values will result in NaN # Coercing the non-numeric values will result in NaN
# thus allowing easier removal through `.notnull()` # thus allowing easier removal through `.notnull()`
@@ -41,8 +55,15 @@ games_dat.info()
NA_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'Global_Sales'] NA_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'Global_Sales']
GLO_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'NA_Sales'] GLO_col_list = ['PAL_Sales', 'JP_Sales', 'Other_Sales', 'NA_Sales']
game_sales_NA = game_sales2019_dat.drop(columns = NA_col_list, axis = 1) game_sales_NA = game_sales_dat.drop(columns = NA_col_list, axis = 1)
game_sales_GLO = game_sales2019_dat.drop(columns = GLO_col_list, axis = 1) game_sales_GLO = game_sales_dat.drop(columns = GLO_col_list, axis = 1)
print("Game Sales for NA:\n", game_sales_NA.head(10)) print(f"Game Sales for NA:\n{game_sales_NA.head(10)} \nWith minimum year being: {game_sales_NA['Year'].min()}")
print("Game Sales Globally:\n", game_sales_GLO.head(10)) print(f"Game Sales Globally:\n{game_sales_GLO.head(10)}\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())
crime_year_max = min(crime_US['report_year'].max(), crime_CA['year'].max())
crime_CA = crime_CA[(crime_CA['year'] >= crime_year_min) & (crime_CA['year'] <= crime_year_max)]
crime_US = crime_US[(crime_US['report_year'] >= crime_year_min) & (crime_US['report_year'] <= crime_year_max)]