# Packages
import pandas as pd
import numpy as np
import scipy as sp
import plotly
import plotly.plotly as py
from plotly.graph_objs import *# Plotly token
plotly.tools.set_credentials_file(username='your account', api_key='your token')df = pd.read_csv("vgsales.csv")
df[:10]| Rank | Name | Platform | Year | Genre | Publisher | NA_Sales | EU_Sales | JP_Sales | Other_Sales | Global_Sales | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1 | Wii Sports | Wii | 2006.0 | Sports | Nintendo | 41.49 | 29.02 | 3.77 | 8.46 | 82.74 |
| 1 | 2 | Super Mario Bros. | NES | 1985.0 | Platform | Nintendo | 29.08 | 3.58 | 6.81 | 0.77 | 40.24 |
| 2 | 3 | Mario Kart Wii | Wii | 2008.0 | Racing | Nintendo | 15.85 | 12.88 | 3.79 | 3.31 | 35.82 |
| 3 | 4 | Wii Sports Resort | Wii | 2009.0 | Sports | Nintendo | 15.75 | 11.01 | 3.28 | 2.96 | 33.00 |
| 4 | 5 | Pokemon Red/Pokemon Blue | GB | 1996.0 | Role-Playing | Nintendo | 11.27 | 8.89 | 10.22 | 1.00 | 31.37 |
| 5 | 6 | Tetris | GB | 1989.0 | Puzzle | Nintendo | 23.20 | 2.26 | 4.22 | 0.58 | 30.26 |
| 6 | 7 | New Super Mario Bros. | DS | 2006.0 | Platform | Nintendo | 11.38 | 9.23 | 6.50 | 2.90 | 30.01 |
| 7 | 8 | Wii Play | Wii | 2006.0 | Misc | Nintendo | 14.03 | 9.20 | 2.93 | 2.85 | 29.02 |
| 8 | 9 | New Super Mario Bros. Wii | Wii | 2009.0 | Platform | Nintendo | 14.59 | 7.06 | 4.70 | 2.26 | 28.62 |
| 9 | 10 | Duck Hunt | NES | 1984.0 | Shooter | Nintendo | 26.93 | 0.63 | 0.28 | 0.47 | 28.31 |
df.info()<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16598 entries, 0 to 16597
Data columns (total 11 columns):
Rank 16598 non-null int64
Name 16598 non-null object
Platform 16598 non-null object
Year 16327 non-null float64
Genre 16598 non-null object
Publisher 16540 non-null object
NA_Sales 16598 non-null float64
EU_Sales 16598 non-null float64
JP_Sales 16598 non-null float64
Other_Sales 16598 non-null float64
Global_Sales 16598 non-null float64
dtypes: float64(6), int64(1), object(4)
memory usage: 1.4+ MB
df.shape(16598, 11)
df.describe()| Rank | Year | NA_Sales | EU_Sales | JP_Sales | Other_Sales | Global_Sales | |
|---|---|---|---|---|---|---|---|
| count | 16598.000000 | 16327.000000 | 16598.000000 | 16598.000000 | 16598.000000 | 16598.000000 | 16598.000000 |
| mean | 8300.605254 | 2006.406443 | 0.264667 | 0.146652 | 0.077782 | 0.048063 | 0.537441 |
| std | 4791.853933 | 5.828981 | 0.816683 | 0.505351 | 0.309291 | 0.188588 | 1.555028 |
| min | 1.000000 | 1980.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.010000 |
| 25% | 4151.250000 | 2003.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 0.060000 |
| 50% | 8300.500000 | 2007.000000 | 0.080000 | 0.020000 | 0.000000 | 0.010000 | 0.170000 |
| 75% | 12449.750000 | 2010.000000 | 0.240000 | 0.110000 | 0.040000 | 0.040000 | 0.470000 |
| max | 16600.000000 | 2020.000000 | 41.490000 | 29.020000 | 10.220000 | 10.570000 | 82.740000 |
Release vs. Platform
# Platform
df.Platform = df.Platform.astype('category')
df.Platform.describe()count 16598
unique 31
top DS
freq 2163
Name: Platform, dtype: object
platform_count = df.groupby('Platform', axis=0).count().reset_index()[['Platform','Name']].sort_values(by = "Name", ascending=True)# Game counts by platform
import plotly.graph_objs as go
layout = go.Layout(
title='Total Release by Platforms',
yaxis=dict(
title='Platform'
),
xaxis=dict(
title='Count'
),
height=900, width=900
)
trace = go.Bar(
x=platform_count.Name,
y=platform_count.Platform,
orientation = 'h'
)
fig = go.Figure(data=[trace], layout=layout)
py.iplot(fig)Release by Year
year_count = df.groupby('Year', axis=0).count().reset_index()[['Year','Name']]
year_count.Year = year_count.Year.astype('int')
# remove data after 2016
year_count = year_count[year_count.Year <= 2016]trace = go.Scatter(
x = year_count.Year,
y = year_count.Name,
mode = 'lines',
name = 'lines'
)
layout = go.Layout(
title='Release by Year',
yaxis=dict(
title='Count'
),
xaxis=dict(
title='Year'
),
height=900, width=900
)
fig = go.Figure(data=[trace], layout=layout)
py.iplot(fig)Because the sales of new released games are still booming, the decreasing curve doesn't mean the market is decreasing
Release by Genre
genre_count = df.groupby('Genre', axis=0).count().reset_index()[['Genre','Name']].sort_values(by = "Name", ascending=True)
layout = go.Layout(
title='Releases by Genre',
yaxis=dict(
title='Genre'
),
xaxis=dict(
title='Releases'
),
height=400, width=900
)
trace = go.Bar(
x=genre_count.Name,
y=genre_count.Genre,
orientation = 'h'
)
fig = go.Figure(data=[trace], layout=layout)
py.iplot(fig)Action, sports and music games took top 3 in game releases.
Release by Publisher
publisher_count = df.groupby('Publisher', axis=0).count().reset_index()[['Publisher','Name']].sort_values(by = "Name", ascending=True)
publisher_count = publisher_count.tail(n=30)
layout = go.Layout(
title='Release by Publisher (Top 30)',
xaxis=dict(
title='Releases'
),
height=700, width=800,
margin=go.Margin(
l=300,
r=50,
b=100,
t=100,
pad=4
)
)
trace = go.Bar(
x=publisher_count.Name,
y=publisher_count.Publisher,
orientation = 'h'
)
fig = go.Figure(data=[trace], layout=layout)
py.iplot(fig)Sales by Publisher
publisher_sales = df.groupby('Publisher', axis=0).sum().reset_index()[['Publisher','Global_Sales']].sort_values(by = "Global_Sales", ascending=True)
publisher_sales = publisher_sales.tail(n=30)
layout = go.Layout(
title='Sales by Publisher (Top 30)',
xaxis=dict(
title='Sales (in Millions)'
),
height=700, width=800,
margin=go.Margin(
l=300,
r=50,
b=100,
t=100,
pad=4
)
)
trace = go.Bar(
x=publisher_sales.Global_Sales,
y=publisher_sales.Publisher,
orientation = 'h'
)
fig = go.Figure(data=[trace], layout=layout)
py.iplot(fig)Revenue per game by Publisher
new_df = df
new_df['Game_Count'] = 1
new_df = new_df.groupby(['Publisher']).sum().reset_index()[['Publisher', 'Global_Sales','Game_Count']]
new_df['Revenue_per_game'] = new_df.Global_Sales/new_df.Game_Count
new_df = new_df.sort_values(by = "Revenue_per_game", ascending=True).\
tail(n=30)
layout = go.Layout(
title='Revenue_per_game by Publisher (Top 30)',
xaxis=dict(
title='Revenue_per_game (in Millions)'
),
height=700, width=800,
margin=go.Margin(
l=300,
r=50,
b=100,
t=100,
pad=4
)
)
trace = go.Bar(
x=new_df.Revenue_per_game,
y=new_df.Publisher,
orientation = 'h'
)
fig = go.Figure(data=[trace], layout=layout)
py.iplot(fig)Average revenue per game shows the cashability of games published by the publishers.
Sales by Genre
sales_by_genre = df.groupby(['Genre','Name'], axis = 0).sum().reset_index()[['Genre','Name','Global_Sales']]import random
from numpy import *
genres = sales_by_genre.Genre.unique()
traces = []
c = ['hsl('+str(h)+',50%'+',50%)' for h in linspace(0, 360, len(genres))]
for i in range(len(genres)):
genre = genres[i]
df_genre = sales_by_genre[sales_by_genre.Genre == genre]
trace = go.Box(
y=np.array(df_genre.Global_Sales),
name=genre,
boxmean=True,
marker={'color': c[i]}
)
traces.append(trace)
layout = go.Layout(
title='Sales by Genre (A lot of outliers)',
showlegend=False,
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=traces, layout=layout)
py.iplot(fig)# The outliers are like:
df.groupby(['Genre','Name'], axis = 0).\
sum()[['Global_Sales']].\
sort_values(by="Global_Sales", ascending = False).\
reset_index()[:10]| Genre | Name | Global_Sales | |
|---|---|---|---|
| 0 | Sports | Wii Sports | 82.74 |
| 1 | Action | Grand Theft Auto V | 55.92 |
| 2 | Platform | Super Mario Bros. | 45.31 |
| 3 | Puzzle | Tetris | 35.84 |
| 4 | Racing | Mario Kart Wii | 35.82 |
| 5 | Sports | Wii Sports Resort | 33.00 |
| 6 | Role-Playing | Pokemon Red/Pokemon Blue | 31.37 |
| 7 | Shooter | Call of Duty: Black Ops | 31.03 |
| 8 | Shooter | Call of Duty: Modern Warfare 3 | 30.83 |
| 9 | Platform | New Super Mario Bros. | 30.01 |
# After delete outlier
PERCENTAGE = 0.95
traces = []
for i in range(len(genres)):
genre = genres[i]
df_genre = sales_by_genre[sales_by_genre.Genre == genre]
df_genre = df_genre[df_genre.Global_Sales < df_genre.Global_Sales.quantile(PERCENTAGE)]
trace = go.Box(
y=np.array(df_genre.Global_Sales),
name=genre,
boxmean=True,
marker={'color': c[i]}
)
traces.append(trace)
layout = go.Layout(
title='Sales by Genre (Less outliers)',
showlegend=False,
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=traces, layout=layout)
py.iplot(fig)Then let's check revenue distribution of TOP 1% sales of each genre
# After delete outlier
PERCENTAGE = 0.99
traces = []
for i in range(len(genres)):
genre = genres[i]
df_genre = sales_by_genre[sales_by_genre.Genre == genre]
df_genre = df_genre[df_genre.Global_Sales > df_genre.Global_Sales.quantile(PERCENTAGE)]
trace = go.Box(
y=np.array(df_genre.Global_Sales),
name=genre,
boxmean=True,
marker={'color': c[i]}
)
traces.append(trace)
layout = go.Layout(
title='Sales by Genre (TOP 1% games)',
showlegend=False,
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=traces, layout=layout)
py.iplot(fig)** Sales of games by Publisher **
top10_publishers = np.array(df.groupby('Publisher', axis=0).sum().\
reset_index()[['Publisher','Global_Sales']].\
sort_values(by = "Global_Sales", ascending=True).\
tail(n=10)['Publisher'])
top10_df = df[[pub in top10_publishers for pub in df.Publisher]]
sales_by_publisher = top10_df.groupby(['Publisher','Name']).sum().reset_index()[['Publisher','Name','Global_Sales']]PERCENTAGE = 0.9
traces = []
for i in range(len(top10_publishers)):
publisher = top10_publishers[i]
df_pub = sales_by_publisher[sales_by_publisher.Publisher == publisher]
df_pub = df_pub[df_pub.Global_Sales < df_pub.Global_Sales.quantile(PERCENTAGE)]
trace = go.Box(
y=np.array(df_pub.Global_Sales),
name=publisher,
boxmean=True,
marker={'color': c[i]}
)
traces.append(trace)
layout = go.Layout(
title='Sales by Publisher (Majority Games)',
showlegend=False,
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=traces, layout=layout)
py.iplot(fig)However, in game industry, only top games are extremely profitable, so let's see top games of these top publishers
PERCENTAGE = 0.95
traces = []
for i in range(len(top10_publishers)):
publisher = top10_publishers[i]
df_pub = sales_by_publisher[sales_by_publisher.Publisher == publisher]
df_pub = df_pub[df_pub.Global_Sales > df_pub.Global_Sales.quantile(PERCENTAGE)]
trace = go.Box(
y=np.array(df_pub.Global_Sales),
name=publisher,
boxmean=True,
marker={'color': c[i]},
boxpoints = 'all'
)
traces.append(trace)
layout = go.Layout(
title='Sales by Publisher (TOP 5% Games)',
showlegend=False,
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=traces, layout=layout)
py.iplot(fig)The masterpieces of Nintendo, Activision and Take-Two Interactive are more powerful in cashability.
sales_by_year = df.groupby('Year', axis=0).sum().reset_index()[['Year','NA_Sales','EU_Sales','JP_Sales','Other_Sales','Global_Sales']]
sales_by_year.Year = sales_by_year.Year.astype('int')sales_by_year = sales_by_year[sales_by_year.Year <= 2016]trace_Global = go.Scatter(
x = sales_by_year.Year,
y = sales_by_year.Global_Sales,
mode = 'none',
name = 'Global_Sales',
fill='tonexty',
)
trace_NA = go.Scatter(
x = sales_by_year.Year,
y = sales_by_year.NA_Sales,
mode = 'none',
fill='tonexty',
name = 'NA_Sales'
)
trace_EU = go.Scatter(
x = sales_by_year.Year,
y = sales_by_year.EU_Sales,
mode = 'none',
fill='tonexty',
name = 'EU_Sales'
)
trace_JP = go.Scatter(
x = sales_by_year.Year,
y = sales_by_year.JP_Sales,
mode = 'none',
fill='tonexty',
name = 'JP_Sales'
)
trace_Other = go.Scatter(
x = sales_by_year.Year,
y = sales_by_year.Other_Sales,
mode = 'none',
fill='tozeroy',
name = 'Other_Sales'
)
layout = go.Layout(
title='Sales by Region',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
),
height=700, width=900,
margin=go.Margin(
l=100,
r=50,
b=100,
t=100,
pad=4
)
)
fig = go.Figure(data=[trace_Other, trace_JP, trace_EU, trace_NA, trace_Global], layout=layout)
py.iplot(fig)- North America is always the biggest market for video games.
- Sales in other regions are booming
** Regional Sales by Genre across year (How genre in each region changes) **
I will use below function to get traces for plotly
# Get list of unique genres
genres = np.sort(df.Genre.unique())[::-1]
def get_traces(df, region):
regional_df = df.groupby(['Genre','Year'], axis=0).sum().reset_index()[['Genre','Year', region]]
years = range(1980,2018)
temp_dict = {}
for genre in genres:
temp_dict[genre] = {}
for year in years:
try:
temp_value = round(np.array(regional_df[(regional_df.Genre == genre) &
(regional_df.Year == year)][region])[0],2)
except:
temp_value = 0
temp_dict[genre][year] = temp_value
traces = []
for genre in genres:
trace = go.Bar(
x = years,
y = temp_dict[genre].values(),
name=genre
)
traces.append(trace)
return tracesGlobal
data = get_traces(df, 'Global_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales change in Global',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)In Global market:
- Sale of Action and Shooter games are increasing
- Sale of Music, Sports, Fighting, Racing and Puzzle games are decreasing
- Much fewer revenue were generated by Strategy, Puzzle and Racing games
In North America
data = get_traces(df, 'NA_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales change in North America',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)North America has distribution pretty similar to Global market, because it takes up most of global sales. NA market tends to prefer Action and Shooter games to other games.
In Japan
data = get_traces(df, 'JP_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales change in Japan',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)In Japan, besides Action, Role-Playing games attracts most revenue, which is quite different from NA market.
In Europe
data = get_traces(df, 'EU_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales change in Europe',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)European people tends to have similar taste with North American players.
In Other Regions
data = get_traces(df, 'Other_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales change in Other (not JP, NA, EU)',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)Sports and shooter games are booming in these regions.
- Sales Percentage of genres over time (How each market grows)
I change a little bit of the function to get traces
def get_percent_traces(df, region):
temp_df = df.groupby(['Year','Genre'], axis=0).sum()[[region]]
df_pcts = temp_df.groupby(level=0).apply(lambda x: 100 * x / float(x.sum()))
df_pcts = df_pcts.reset_index()
regional_df = df_pcts[df_pcts.Year < 2017]
years = range(1980,2018)
temp_dict = {}
for genre in genres:
temp_dict[genre] = {}
for year in years:
try:
temp_value = round(np.array(regional_df[(regional_df.Genre == genre) &
(regional_df.Year == year)][region])[0],2)
except:
temp_value = 0
temp_dict[genre][year] = temp_value
traces = []
for genre in genres:
trace = go.Bar(
x = years,
y = temp_dict[genre].values(),
name=genre
)
traces.append(trace)
return tracesGlobal
data = get_percent_traces(df, 'Global_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales Percentage of Genres over Years in Global',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)By percentage of genres:
- Action and Shooter are both increasing rapidly
- Racing, puzzle, music, and strategy games are disapearing
North America
data = get_percent_traces(df, 'NA_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales Percentage of Genres over Years in North America',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)Japan
data = get_percent_traces(df, 'JP_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales Percentage of Genres over Years in Japan',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)In Japan, RPG is always most welcome genre. And Action games are booming.
In Europe
data = get_percent_traces(df, 'EU_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales Percentage of Genres over Years in Europe',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)Europe has quite similar style with NA market
In Other regions
data = get_percent_traces(df, 'Other_Sales')
layout = go.Layout(
barmode='stack',
title = 'Sales Percentage of Genres over Years in Other regions',
xaxis=dict(
title='Year'
),
yaxis=dict(
title='Sales (in Millions)'
)
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)len(df.Publisher.unique())579
Sales by genre, publisher
# Prefered genres of top-5-sale publishers
genres = genres[::-1]
def get_traces_genre_publisher(region):
top5_publishers = np.array(df.groupby('Publisher', axis=0).sum().\
reset_index()[['Publisher', 'Global_Sales']].\
sort_values(by = 'Global_Sales', ascending=True).\
tail(n=5)['Publisher'])
top5_df = df[[pub in top5_publishers for pub in df.Publisher]]
top5_genre_df = top5_df.groupby(['Publisher','Genre']).sum().reset_index()[['Publisher','Genre',region]]
traces = []
for i in range(len(top5_publishers)):
publisher = top5_publishers[i]
temp_df = top5_genre_df[top5_genre_df.Publisher == publisher]
trace = go.Bar(
x = genres,
y = np.array(temp_df[region]),
name=publisher
)
traces.append(trace)
return traces
data = get_traces_genre_publisher('Global_Sales')
layout = go.Layout(
xaxis=dict(tickangle=-45),
yaxis=dict(title='Sales (in Millions)'),
barmode='group',
title = 'Global Sales by Genre and Publisher'
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)In global market:
- Nintendo focus more on Platform, RPG and Sports games
- EA focus more on Sports, shooter and racing games
- Activision earn money more on shooter games
Take a look at the top games of these publishers:
# Top 5 games of Nintendo
df[df.Publisher == 'Nintendo'].sort_values(by = 'Global_Sales', ascending=False)[['Publisher','Name','Global_Sales']][:5]| Publisher | Name | Global_Sales | |
|---|---|---|---|
| 0 | Nintendo | Wii Sports | 82.74 |
| 1 | Nintendo | Super Mario Bros. | 40.24 |
| 2 | Nintendo | Mario Kart Wii | 35.82 |
| 3 | Nintendo | Wii Sports Resort | 33.00 |
| 4 | Nintendo | Pokemon Red/Pokemon Blue | 31.37 |
# Top 5 games of EA
df[df.Publisher == 'Electronic Arts'].sort_values(by = 'Global_Sales', ascending=False)[['Publisher','Name','Global_Sales']][:5]| Publisher | Name | Global_Sales | |
|---|---|---|---|
| 77 | Electronic Arts | FIFA 16 | 8.49 |
| 82 | Electronic Arts | FIFA Soccer 13 | 8.24 |
| 83 | Electronic Arts | The Sims 3 | 8.11 |
| 92 | Electronic Arts | Star Wars Battlefront (2015) | 7.67 |
| 99 | Electronic Arts | Battlefield 3 | 7.34 |
# Top 5 games of Activision
df[df.Publisher == 'Activision'].sort_values(by = 'Global_Sales', ascending=False)[['Publisher','Name','Global_Sales']][:5]| Publisher | Name | Global_Sales | |
|---|---|---|---|
| 29 | Activision | Call of Duty: Modern Warfare 3 | 14.76 |
| 31 | Activision | Call of Duty: Black Ops | 14.64 |
| 33 | Activision | Call of Duty: Black Ops 3 | 14.24 |
| 34 | Activision | Call of Duty: Black Ops II | 14.03 |
| 35 | Activision | Call of Duty: Black Ops II | 13.73 |
data = get_traces_genre_publisher('NA_Sales')
layout = go.Layout(
xaxis=dict(tickangle=-45),
yaxis=dict(title='Sales (in Millions)'),
barmode='group',
title = 'North America - Sales by Genre and Publisher'
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)data = get_traces_genre_publisher('JP_Sales')
layout = go.Layout(
xaxis=dict(tickangle=-45),
yaxis=dict(title='Sales (in Millions)'),
barmode='group',
title = 'Japan - Sales by Genre and Publisher'
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)Japan is almost taken up by its local publishers, Nintendo and SONY in all genres
data = get_traces_genre_publisher('EU_Sales')
layout = go.Layout(
xaxis=dict(tickangle=-45),
yaxis=dict(title='Sales (in Millions)'),
barmode='group',
title = 'Europe - Sales by Genre and Publisher'
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)In Europe, EA's adventure games
data = get_traces_genre_publisher('Other_Sales')
layout = go.Layout(
xaxis=dict(tickangle=-45),
yaxis=dict(title='Sales (in Millions)'),
barmode='group',
title = 'Other Regions - Sales by Genre and Publisher'
)
fig = go.Figure(data=data, layout=layout)
py.iplot(fig)- Global game market is increasing
- North America and Europe have similar taste of games while Japan is different, with RPG taken up more marketshare
- TOP 5 publishers are fighting at all genre, however, they have their advantageous genres