35 lines
914 B
Python
35 lines
914 B
Python
|
#! /usr/bin/python3
|
||
|
|
|
||
|
|
import requests
|
||
|
|
url = 'https://git.wmi.amu.edu.pl/s434695/ium_434695/raw/commit/2301fb86e434734376f73503307a8f3255a75cc6/vgsales.csv'
|
||
|
|
r = requests.get(url, allow_redirects=True)
|
||
|
|
|
||
|
|
open('vgsales.csv', 'wb').write(r.content)
|
||
|
|
|
||
|
|
import pandas as pd
|
||
|
|
vgsales = pd.read_csv('vgsales.csv')
|
||
|
|
vgsales
|
||
|
|
|
||
|
|
vgsales.describe(include='all')
|
||
|
|
|
||
|
|
vgsales["Publisher"].value_counts()
|
||
|
|
|
||
|
|
vgsales["Platform"].value_counts()
|
||
|
|
|
||
|
|
vgsales["Platform"].value_counts().plot(kind="bar")
|
||
|
|
|
||
|
|
vgsales[["Platform","JP_Sales"]].groupby("Platform").mean().plot(kind="bar")
|
||
|
|
|
||
|
|
import seaborn as sns
|
||
|
|
sns.set_theme()
|
||
|
|
sns.relplot(data=vgsales, x="JP_Sales", y="NA_Sales", hue="Genre")
|
||
|
|
|
||
|
|
from sklearn.model_selection import train_test_split
|
||
|
|
vgsales_train, vgsales_test = train_test_split(vgsales, test_size = 0.6, random_state = 1)
|
||
|
|
vgsales_train["Platform"].value_counts()
|
||
|
|
|
||
|
|
vgsales_test["Platform"].value_counts()
|
||
|
|
|
||
|
|
print(vgsales_train["Platform"])
|
||
|
|
|