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

R visualisation better

Browse Source
This commit is contained in:
Weaponised Autism
2023-03-28 20:41:46 +02:00
parent ca748eb57e
commit 300ce67b60
2 changed files with 27 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
py_scripts/engineer.py
View File

@@ -5,19 +5,30 @@ import mining_hq
from numpy import count_nonzero
sns.set()
plt.xticks(rotation = 90)
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)
crime_US = mining_hq.crime_US_intersect
crime_CA = mining_hq.crime_CA_intersect
plt.xticks(rotation = 90)
games_fig_pre = sns.histplot(data = games_pre, x = "Year", palette = sns.color_palette("flare"), kde = True)
plt.show()
plt.xticks(rotation = 90)
games_fig_dur = sns.barplot(data = games_dur, x = "Year", y = "NA_Sales", estimator = count_nonzero)
games_fig2_pre = sns.histplot(data = games_pre, x = "Year", hue = "Genre", multiple = "stack", shrink = 0.65)
plt.show()
plt.xticks(rotation = 90)
games_fig_pos = sns.barplot(data = games_pos, x = "Year", y = "NA_Sales", estimator = count_nonzero)
games_fig_dur = sns.barplot(data = games_dur, x = "Year", y = "NA_Sales")
plt.show()
plt.xticks(rotation = 90)
games_fig_pos = sns.barplot(data = games_pos, x = "Year", y = "NA_Sales")
plt.show()
plt.xticks(rotation = 90)
crime_CA_fig = sns.barplot(data = crime_CA, x = "year", y = "incidents")
plt.show()

25
py_scripts/mining_hq.py
View File

@@ -3,8 +3,7 @@
import pandas as pd
import numpy as np
import seaborn as sns
import digger
import gunner
import digger, gunner
# Instantiating globals to be used in other files
global games_merged_dat
@@ -24,7 +23,7 @@ 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
print(games_merged_dat.isnull())
print(games_merged_dat.count())
games_merged_dat.to_csv("datasets/videogames/games_merged.csv")
# Loading Crime Datasets
@@ -70,22 +69,22 @@ games_merged_dat = gunner.drop_kick(NA_col_list, games_merged_dat)
sale_tri_split = gunner.trisect_by_year(games_merged_dat, 'Year', year_interval)
game_sales_split_pre = sale_tri_split[0]
game_sales_split_dur = sale_tri_split[1]
game_sales_split_pos = sale_tri_split[2]
games_sales_split_pre = sale_tri_split[0]
games_sales_split_dur = sale_tri_split[1]
games_sales_split_pos = sale_tri_split[2]
# Displaying Acquired Data
print("Acquired Datasets:\n")
print(game_sales_split_pre.head(5),
game_sales_split_dur.head(5),
game_sales_split_pos.head(5))
print(games_sales_split_pre.head(5),
games_sales_split_dur.head(5),
games_sales_split_pos.head(5))
print("Dataset Info:\n")
game_sales_split_pre.info()
game_sales_split_dur.info()
game_sales_split_pos.info()
games_sales_split_pre.info()
games_sales_split_dur.info()
games_sales_split_pos.info()
print(game_sales_split_dur.describe())
print(games_sales_split_dur.describe())
# Required to use binning for cleaning, idk
# https://towardsdatascience.com/data-preprocessing-with-python-pandas-part-5-binning-c5bd5fd1b950