文章目录
一、数据来源二、导入数据三、散点图Scatter四、堆积柱状图Stacked Bar五、饼图六、旭日图Sunburst七、分布图Distplot八、箱线图Boxplot九、热点图Heatmap十、.时间序列图 Time Series(使用时间序列选择器)十一、多子图十二、多图表Table and Chart Subplots十三、k线图十四、代码+数据集获取一、数据来源
整理之前的代码，发现了之前使用plotly做数据可视化的代码，贴上来做个记录。
数据集为美国不同地区各个超市的不同商品的销量数据。
需要这份数据集的可以见文末的下载地址。
本文只列举了部分图形的可视化方法，更多的可以参看Plotly官方文档
二、导入数据
import pandas as pdimport plotly as pyimport plotly.graph_objs as goimport numpy as npdata=pd.read_excel('Sample - Superstore.xls')data.head()
一共有21个特征值，具体的含义不做过多的描述，看字段名基本都能明白。
三、散点图Scatter
展示不同种类商品Category的售价Sales和利润Profit的关系
#Q1.散点图Scatter#展示不同种类商品Category的售价Sales和利润Profit的关系colors=['#393E46','#2BCDC2','#F66095']labels=data['Category'].drop_duplicates(inplace=False)#获取种类数X=[]Y=[]for i in labels:X.append(data[data['Category']==i]['Sales'])Y.append(data[data['Category']==i]['Profit'])fig=go.Figure()py.offline.init_notebook_mode()for s,p,c,l in zip(X,Y,colors,labels):fig.add_trace(go.Scatter(x=s,y=p,mode='markers',marker_color=c,name=l))fig.update_layout(title='Sales & Profit of each Category',xaxis=dict(title='Sales'),yaxis=dict(title='Profit'),)py.offline.iplot(fig)
四、堆积柱状图Stacked Bar
#Q2.堆积柱状图Stacked Bar#展示不同商品子类的Sub-Category中不同客户类别Segment的利润总和data2=data.groupby(['Segment','Sub-Category'])['Profit'].sum()fig=go.Figure()for sg,cl in zip(data2.index.levels[0],colors):fig.add_trace(go.Bar(x=data2[sg].index,y=data2[sg].values,name=sg,marker=dict(color=cl,opacity=0.65)))fig.update(layout=dict(title='Profit by Sub-Category & Segment',xaxis=dict(title='Sub-Category'),yaxis=dict(title='Profit'),barmode='stack',))py.offline.iplot(fig)
五、饼图
展示不同商品类的Category利润Profit占比
#Q3.饼图#展示不同商品类的Category利润Profit占比colors = ['gold', 'mediumturquoise', 'darkorange', 'lightgreen']data3=data.groupby(['Category'])['Profit'].sum()fig = go.Figure(data=[go.Pie(labels=data3.index,values=data3)])fig.update_traces(title='The Percentage of Profit in each Category',hoverinfo='label+percent+value', textfont_size=15,marker=dict(colors=colors, line=dict(color='#000000', width=2)))py.offline.iplot(fig)
六、旭日图Sunburst
展现美国各个地区Region各个州State的利润情况
#Q4.旭日图Sunburst#展现美国各个地区Region各个州State的利润情况Labels=['United States','South','West','East','Central']Region=['South','West','East','Central']Parents=['','United States','United States','United States','United States']data4=data[['Region','State','Profit']]data4_1=np.array(data4)Values=[data4['Profit'].sum(),data4[data4['Region']=='South']['Profit'].sum(),data4[data4['Region']=='West']['Profit'].sum(),data4[data4['Region']=='East']['Profit'].sum(),data4[data4['Region']=='Central']['Profit'].sum()]for i in data4_1:if i[1] not in Labels:Labels.append(i[1])Parents.append(i[0])Values.append(data4[data4['State']==i[1]]['Profit'].sum())fig=go.Figure(go.Sunburst(labels=Labels,parents=Parents,values=Values,))fig.update_layout(margin = dict(t=1, l=1, r=1, b=10))py.offline.iplot(fig)
七、分布图Distplot
展现商品类别Category的质量Quantity分布情况
#Q5.分布图Distplot#展现商品类别Category的质量Quantity分布情况import plotly.figure_factory as ffCategory=data['Category'].drop_duplicates(inplace=False).tolist()# Add histogram datax1 =data[data['Category']==Category[0]]['Quantity']x2 = data[data['Category']==Category[1]]['Quantity']x3 = data[data['Category']==Category[2]]['Quantity']# Group data togetherhist_data = [x1, x2, x3]group_labels = Category# Create distplot with custom bin_sizefig = ff.create_distplot(hist_data, group_labels, bin_size=[.1, .25, .5])fig.update(layout=dict(title='The Quanlity of Each Category ',))py.offline.iplot(fig)
八、箱线图Boxplot
展现商品类别Category的折扣Discount分布情况
#Q6.箱线图Boxplot#展现商品类别Category的折扣Discount分布情况fig = go.Figure()for i in Category:fig.add_trace(go.Box(y=data[data['Category']==i]['Discount'],name=i))fig.update(layout=dict(title='Dicount Distribution ',))py.offline.iplot(fig)
九、热点图Heatmap
展现商品类别Category在不同地区Region的利润Profit的相关性
#Q7.热点图Heatmap#展现商品类别Category在不同地区Region的利润Profit的相关性Z=[]for i in Category:Y=[]data_0=data[data['Category']==i]for j in Region:Y.append(data_0[data_0['Region']==j]['Profit'].sum())Z.append(Y)fig = go.Figure(data=go.Heatmap(z=Z,x=Region,y=Category,hoverongaps = False))fig.update(layout=dict(title='Profit in Different Regions of Three Categories ',))py.offline.iplot(fig)
十、.时间序列图 Time Series(使用时间序列选择器)
展现各个年份每月的利润Profit情况。底部的时间序列选择器可以通过拖动展示指定时间区间的数据。
#Q9 .时间序列图 Time Series(使用时间序列选择器)#展现各个年份每月的利润Profit情况fig = go.Figure()for value,year,color in zip(Y,Year,colors):fig.add_trace(go.Scatter(x=Month,y=value, name=year,line_color=color))fig.update_layout(title_text='Time Series with Rangeslider',xaxis=dict(title='Month'),yaxis=dict(title='Profit'),xaxis_rangeslider_visible=True)py.offline.iplot(fig)
十一、多子图
各个商品子类Sub-Category的利润Profit
#Q10.多子图Subplots#各个商品子类Sub-Category的利润Profitfig = go.Figure()trace1 = go.Bar(x=data2[sg].index,y=data.groupby(['Sub-Category'])['Sales'].sum(),name='Sales')trace2 = go.Scatter(x=data2[sg].index,y=data.groupby(['Sub-Category'])['Profit'].sum(),name='Profit',xaxis='x', )data = [trace1, trace2]layout = go.Layout(title='Profit & Sales of each Sub-Category',yaxis2=dict(anchor='x', overlaying='y', side='right')#设置坐标轴的格式，一般次坐标轴在右侧)fig=go.Figure(data=data,layout=layout)py.offline.iplot(fig)
十二、多图表Table and Chart Subplots
表格展现订单时间Order Date销售的物品名称Product Name以及对应的利润Profit
#Q11.多图表Table and Chart Subplots#表格展现订单时间Order Date销售的物品名称Product Name以及对应的利润Profitfrom plotly.subplots import make_subplotsdata11=data[['Order Date','Product Name','Profit']]va=data11.sort_values('Order Date')fig = make_subplots(rows=2, cols=1,shared_xaxes=True,vertical_spacing=0.03,specs=[[{"type": "table"}],[{"type": "scatter"}]])fig.add_trace(go.Scatter(x=va["Order Date"],y=va["Profit"],mode="lines",name="hash-rate-TH/s"),row=2, col=1)fig.add_trace(go.Table(header=dict(values=['Order ID','Product Name','Profit'],font=dict(size=10),align="left"),cells=dict(values=[va[k].tolist() for k in va.columns],align = "left")),row=1, col=1)fig.update_layout(height=800,showlegend=False,title_text="Profits from to ",xaxis=dict(title='Year'),yaxis=dict(title='Profit'),)fig.show()
十三、k线图
十四、代码+数据集获取
关注以下公众号回复"0040"即可get√
Python数据可视化——Plotly绘制散点图 堆积柱状图 饼图 旭日图 分布图 箱线图 时间序列图 多子图 k线图
