kaggle-3-Appstore

appleStore.csv
"id" : App ID

"track_name": App Name

"size_bytes": Size (in Bytes)

"currency": Currency Type

"price": Price amount

"ratingcounttot": User Rating counts (for all version)

"ratingcountver": User Rating counts (for current version)

"user_rating" : Average User Rating value (for all version)

"userratingver": Average User Rating value (for current version)

"ver" : Latest version code

"cont_rating": Content Rating

"prime_genre": Primary Genre

"sup_devices.num": Number of supporting devices

"ipadSc_urls.num": Number of screenshots showed for display

"lang.num": Number of supported languages

"vpp_lic": Vpp Device Based Licensing Enabled

appleStore_description.csv
id : App ID
track_name: Application name
size_bytes: Memory size (in Bytes)
app_desc: Application description

import pandas as pd
import numpy as np
import plotly_express as px
import plotly as py
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import random

import dash
import dash_html_components as html
import dash_core_components as dcc

# 颜色的随机生成：#123456  # 加上6位数字构成
def random_color_generator(number_of_colors):
    color = ["#"+''.join([random.choice('0123456789ABCDEF') for j in range(6)])
                 for i in range(number_of_colors)]
    return color

trace = go.Bar(
    x = cnt_srs.index,
    y = cnt_srs.values,
    text = text,
    marker = dict(
        color = random_color_generator(100),
        line = dict(color='rgb(8, 48, 107)',   # 柱子的外围线条颜色和宽度
                    width = 1.5)
    ),
    opacity = 0.7   # 透明度设置
)

# 数据部分：一定是列表的形式
data = [trace]

# 布局设置
layout = go.Layout(
    title = 'Prime genre',   # 整个图的标题
    margin = dict(
        l = 100   # 左边距离
    ),
    xaxis = dict(
        title = 'Type of app'   # 2个轴的标题
    ),
    yaxis = dict(
        title = 'Count of app'
    ),
    width = 900,  # figure的宽高
    height = 500
)

fig = go.Figure(data=data, layout=layout)

fig.update_traces(textposition="outside")   # 将每个占比显示出来，也就是y轴的值

fig.show()

df_free = df[df["isNotFree"] == 0]   # free
df_NotFree = df[df["isNotFree"] == 1]  # notfree

# 颜色的随机生成：#123456  # 加上6位数字构成
def random_color_generator(number_of_colors):
    color = ["#"+''.join([random.choice('0123456789ABCDEF') for j in range(6)])
                 for i in range(number_of_colors)]
    return color


# make subplots
fig = make_subplots(rows=2, cols=2,  # 2*2的子图
                    vertical_spacing=0.25,   # 上下子图之间的间隔
                    subplot_titles=("（1）Free","（2）NotFree","（3）Group Bar of Free & notFree"),   # 每个子图的标题
                    specs=[[{"type": "xy"}, {"type": "xy"}],  # 每个子图的类型
                           [{"rowspan": 1, "colspan": 2}, None]]  # 第2行中，只有第一个位置上有图，（2，2）是空的
                   )
# single bar

# 1-free
cnt_srs1 = df_free['prime_genre'].value_counts()
text1 = ['{:.2f}%'.format(100 * (value / cnt_srs1.sum())) for value in cnt_srs1.values]
trace1 = go.Bar(
    x = cnt_srs1.index,
    y = cnt_srs1.values,
    text = text1,
    marker = dict(
        color = random_color_generator(100),
        line = dict(color='rgb(8, 48, 107)',
                    width = 1.5)
    ),
    opacity = 0.7
)


# 2-notfree
cnt_srs2 = df_NotFree['prime_genre'].value_counts()
text2 = ['{:.2f}%'.format(100 * (value / cnt_srs2.sum())) for value in cnt_srs2.values]
trace2 = go.Bar(
    x = cnt_srs2.index,
    y = cnt_srs2.values,
    text = text2,
    marker = dict(
        color = random_color_generator(100),
        line = dict(color='rgb(8, 48, 107)',
                    width = 1.5)
    ),
    opacity = 0.7
)


# group bar chart

trace3 = go.Bar(
    x = cnt_srs1.index,
    y = cnt_srs1.values,
    text = text1,
    opacity = 0.7,
#     name='Free'
)


trace4 = go.Bar(
    x = cnt_srs2.index,
    y = cnt_srs2.values,
    text = text2,
    opacity = 0.7,
#     name='Not-Free'
)

fig.add_trace(trace1,row=1,col=1)
fig.add_trace(trace2,row=1,col=2)
fig.add_trace(trace3,row=2,col=1)
fig.add_trace(trace4,row=2,col=1)

fig.update_layout(height=800,width=900,
                  title_text="Free vs NotFree",   # 整个图的标题
                  showlegend=False)   # 将右上角的图例隐藏

fig.show()

cnt_srs = df[['prime_genre', 'user_rating']].groupby('prime_genre').mean()['user_rating'].sort_values(ascending=False)   # descending

trace = go.Bar(
    x = cnt_srs.index,   # the value of x
    y = cnt_srs.values,   # the value of y
    marker = dict(
        color = random_color_generator(100),  # the style of bar
        line = dict(color='rgb(8, 48, 107)',
                    width = 1.5)
    ),
    opacity = 0.7
)
data = [trace]

layout = go.Layout(
    title = 'User rating depending on Prime genre',
    margin = dict(
        l = 100
    ),
    xaxis = dict(
        title = 'Genre'
    ),
    yaxis = dict(
        title = 'Mean User Rating'
    ),
    width = 800,
    height = 500
)

fig = go.Figure(data=data, layout=layout)
fig.show()

# how to make heatmap
df_temp = df.drop("id",axis=1)

fig = go.Figure(data=go.Heatmap(
                   z=[[1, None, 30, 50, 1], [20, 1, 60, 80, 30], [30, 60, 1, -10, 20]],
                   x=['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday'],
                   y=['Morning', 'Afternoon', 'Evening'],
                   hoverongaps = False))
fig.show()

fig = go.Figure(data=go.Heatmap(
    z=df_corr.values,
    x=df_corr.columns.values,
    y=df_corr.columns.values,
    colorscale='gnbu',
    ))

fig.update_layout(width = 800, height = 700,
                  title='Pearson Correlation of float-type features',
                  xaxis = dict(ticks=''),
                  yaxis = dict(ticks='' ),
                  margin = dict(l = 100)
                 )
fig.show()

data = [
    go.Heatmap(
        z = df_temp.corr(),
        x = df_temp.corr().columns.values,
        y = df_temp.corr().columns.values,
        colorscale='magma',   # 'deep', 'delta', 'dense', 'earth', 'edge', 'electric','emrld', 'fall', 'geyser', 'gnbu', 'gray', 'greens'
#         reversescale=False,
    )
]

layout = go.Layout(
    title='Pearson Correlation of float-type features',
    xaxis = dict(ticks=''),
    yaxis = dict(ticks='' ),
    width = 800, height = 700,
    margin = dict(
        l = 100
    )
)

fig = go.Figure(data=data, layout=layout)
fig.show()