Python库 Bokeh 数据可视化实用指南

目录

• 什么是 Bokeh
• 在哪使用 Bokeh 图
• 安装Bokeh库
• 导入Bokeh库
• 绘制图表的语法
• 使用Bokeh库主题
• 图表样式
• Python 中的 Bokeh用例
  • 数据
  • 数据说明
  • 饼形图
  • 圆环图
  • 散点图
  • 简单直方图
  • 堆积直方图
• 不同类型的条形图
  • 简单条形图
  • 堆积条形图
  • 堆积垂直条形图
  • 双向条形图
  • 折线图
  • 棒棒糖图表
  • 面积图
  • Bokeh库的布局功能
• 技术交流

pip install pandas-Bokeh

conda install -c patrikhlobil pandas-Bokeh

import pandas as pd
# pip install pandas_Bokeh
import pandas_Bokeh
from Bokeh.io import show, output_notebook
from Bokeh.plotting import figure
pandas_Bokeh.output_notebook()
pd.set_option("plotting.backend", "pandas_Bokeh")

from Bokeh.plotting import figure

from Bokeh.io import show, output_notebook

pandas_Bokeh.output_notebook()

pandas_bokeh.output_file（文件名）

from Bokeh.models import HoverTool, ColumnDataSource

dataframe.plot_Bokeh()

fig = figure()
"""
自定义绘图代码
"""
show(fig)

output_file("abc.html")

fig = figure(background_fill_color="#fafafa")

fig = figure(height=350, width=500)

fig.axis.visible=False

fig.grid.grid_line_color = None

fig.background_fill_alpha=0.3

fig = figure(title="abc")

fig.xaxis.axis_label="X-axis"
fig.yaxis.axis_label="Y-axis"

x = list(range(11))
y0 = x

fig = figure(width=500, height=250,title="Title",background_fill_color="#fafafa")

fig.circle(x, y0, size=12, color="#53777a", alpha=0.8)
fig.grid.grid_line_color = None
fig.xaxis.axis_label="X-axis"
fig.yaxis.axis_label="Y-axis"

show(fig)

import glob
path = "archive" 
all_files = glob.glob(path + "/*.csv")
li = []
usr=0
for filename in all_files:
    usr+=1
    df = pd.read_csv(filename, index_col=None, header=0)
    df["User ID"]=usr
    li.append(df)
df = pd.concat(li, axis=0, ignore_index=True)
df[:2]

df.describe(include="O")

df["Min"] = df.apply(lambda x : x["Game Length"].split(" ")[0] , axis = 1)
df["Min"] = df["Min"].replace("m", "", regex=True)
df["Min"][:2]

0    07
1    16
Name: Min, dtype: object

df["Murdered"].replace(["No", "Yes", "-"], ["Not Murdered", "Murdered", "Missing"],inplace=True)

1. df_team = df.Team.value_counts() 
2. df_team.plot_Bokeh(kind="pie", title="Ration of Mposter vs Crewmate") 

from math import pi
df_mur = df.Murdered.value_counts().reset_index().rename(columns={"index": "Murdered", "Murdered": "Value"})
df_mur["Angle"] = df_mur["Value"]/df_mur["Value"].sum() * 2*pi
df_mur["Color"] = ["#3182bd", "#6baed6", "#9ecae1"]

df_mur

from Bokeh.transform import cumsum

fig = figure(plot_height=350,             toolbar_location=None,

tools="hover", tooltips="@Murdered: @Value", x_range=(-.5, .5))
fig.annular_wedge(x=0, y=1, inner_radius=0.15, 
                  outer_radius=0.25, direction="anticlock",

start_angle=cumsum("Angle", include_zero=True),
                  end_angle=cumsum("Angle"),

line_color="white", fill_color="Color", legend_label="Murdered", source=df_mur)

fig.axis.axis_label=None
fig.axis.visible=False
fig.grid.grid_line_color = None
show(fig)

df_min = pd.crosstab(df["Min"], df["Sabotages Fixed"]).reset_index()
df_min = df_min.rename(columns={0.0:"0T", 1.0:"1T",
                       2.0:"2T",3.0:"3T",4.0:"4T",5.0:"5T"
                    })
df_min[:2]

df_0 = df_min[["Min", "0T"]]
df_1 = df_min[["Min", "1T"]]
df_2 = df_min[["Min", "2T"]]

df_min.plot_Bokeh.scatter(x="Min", y="1T")

fig = figure(title="Sabotages Fixed vs Minutes", 
             tools= "hover", 
             toolbar_location="above", 
             toolbar_sticky=False)
fig.circle(x="Min",y="0T", 
         size=12, alpha=0.5, 
         color="#F78888", 
         legend_label="0T", 
         source=df_0),
fig.circle(x="Min",y="1T", 
         size=12, alpha=0.5, 
         color="blue", 
         legend_label="1T", 
         source=df_1),
fig.circle(x="Min",y="2T", 
         size=12, alpha=0.5, 
         color="#626262", 
         legend_label="2T", 
         source=df_2),
show(fig)

1. df_minutes = df["Min"].astype("int64") 
2. df_minutes.plot_Bokeh(kind="hist", title="Distribution of Minutes") 

df_gm_te = pd.crosstab(df["Game Length"], df["Team"])
df_gm_te

df_gm_te.plot_Bokeh.hist(title="Gamelegth vs Imposter/Crewmate", figsize=(750, 350))

1. df_tc = pd.DataFrame(df["Task Completed"].value_counts())[1:].sort_index().rename(columns={"Task Completed": "Count"}) 
2. df_tc.plot_Bokeh(kind="bar", y="Count", title="How many people have completed given task?", figsize=(750, 350)) 

df1 = pd.crosstab(df["Team"], df["Outcome"])
df1.plot_Bokeh.bar(title="Who wins: Imposter or Crewmates",stacked=True,
figsize=(550, 350))

df["All Tasks Completed"].replace(["Yes","No"], ["Tasks Completed","Tasks Not Completed"], inplace=True)

df2 = pd.crosstab(df["Outcome"], df["All Tasks Completed"])
df2.plot_Bokeh.barh(title="Completeing task: win or loss", stacked=True,
figsize=(650, 350))

df_user = pd.crosstab(df["User ID"], df["Outcome"]).reset_index()
df_user["Loss"] = df_user["Loss"]*-1
df_user["User ID"] = (df_user.index+1).astype(str) + " User"
df_user = df_user.set_index("User ID")
df_user[:2]

df_user.plot_Bokeh.barh(title="Users: Won or Defeat")

df_crewmate = df[df["Team"] == "Crewmate"]
df_t_ej = pd.crosstab(df_crewmate["User ID"], df_crewmate["Ejected"]).reset_index()
df_t_ej = df_t_ej[["No","Yes"]]
df_t_ej.plot_Bokeh.line(title="Cremates Memebers: Ejected vs Minutes", figsize=(750, 350))

df_user_new = pd.crosstab(df["User ID"], df["Outcome"]).reset_index().sort_values(by="Win", ascending=False)[:10]
df_user_new["User ID"] = (df_user_new.index+1).astype(str) + " User"
df_user_new[:2]

x = df_user_new["Win"]

factors = df_user_new["User ID"] #.values
fig = figure(title="Top 10 Users: Win", toolbar_location=None,tools="hover", tooltips="@x",
y_range=factors, x_range=[0,75],
plot_width=750, plot_height=350)

fig.segment(0, factors, x, factors, line_width=2, line_color="#3182bd")
fig.circle(x, factors, size=15, fill_color="#9ecae1", line_color="#3182bd", line_width=3)
fig.xgrid.grid_line_color = None
fig.ygrid.grid_line_color = None
show(fig)

1. from Bokeh.models import ColumnDataSource 
2. from Bokeh.plotting import figure, output_file, show 
3.  
4. # data 
5. df_min = pd.crosstab(df["Min"], df["Sabotages Fixed"]).reset_index() 
6. df_min = df_min.rename(columns={0.0:"0T", 1.0:"1T",2.0:"2T",3.0:"3T",4.0:"4T",5.0:"5T"}) 
7.  
8. # chart 
9. names = ["0T","1T"] 
10. source = ColumnDataSource(data=dict(x = df_min.Min, 
11.                                     y0 = df_min["0T"], 
12.                                     y1 = df_min["1T"])) 
13.  
14. fig = figure(width=400, height=400, title="Sabotages Fied vs Minutes") 
15. fig.varea_stack(["y0","y1"], x="x", color=("grey", "lightgrey"),legend_label=names, source=source) 
16.  
17. fig.grid.grid_line_color = None 
18. fig.xaxis.axis_label="Minutes" 
19.  
20. show(fig) 

from Bokeh.io import output_file, show
from Bokeh.layouts import row,column
from Bokeh.plotting import figure
output_file("layout.html")
x = list(range(11))
y0 = x
y1 = [10 - i for i in x]
y2 = [abs(i - 5) for i in x]
# create three plots
s1 = figure(width=250, height=250, background_fill_color="#fafafa")
s1.circle(x, y0, size=12, color="#53777a", alpha=0.8)
s2 = figure(width=250, height=250, background_fill_color="#fafafa")
s2.triangle(x, y1, size=12, color="#c02942", alpha=0.8)
s3 = figure(width=250, height=250, background_fill_color="#fafafa")
s3.square(x, y2, size=12, color="#d95b43", alpha=0.8)

show(column(s1, s2, s3))

# 将结果排成一行并显示
show(row(s1, s2, s3))

layout = grid([[fig1],
               [fig2, fig3]])

from Bokeh.io import output_file, show
from Bokeh.plotting import figure
from Bokeh.layouts import column, grid
# 1 layout
df_user_new = pd.crosstab(df["User ID"], df["Outcome"]).reset_index().sort_values(by="Win", ascending=False)[:10]
df_user_new["User ID"] = (df_user_new.index+1).astype(str) + " User"
x = df_user_new["Win"]
factors = df_user_new["User ID"] 
fig1 = figure(title="Top 10 Users: Win", toolbar_location=None,
              tools="hover", tooltips="@x",
              y_range=factors, x_range=[0,75], 
              width=700, height=250)
fig1.segment(0, factors, x, factors, line_width=2, line_color="#3182bd")
fig1.circle(x, factors, size=15, fill_color="#9ecae1", line_color="#3182bd", line_width=3)
# 2 layout
df_mur = df.Murdered.value_counts().reset_index().rename(columns={"index": "Murdered", "Murdered": "Value"})
df_mur["Angle"] = df_mur["Value"]/df_mur["Value"].sum() * 2*pi
df_mur["Color"] = ["#3182bd", "#6baed6", "#9ecae1"]
fig2 = figure(height=300,width=400,              toolbar_location=None, tools="hover", tooltips="@Murdered: @Value", x_range=(-.5, .5))
fig2.annular_wedge(x=0, y=1,  inner_radius=0.15, outer_radius=0.25, direction="anticlock",
                   start_angle=cumsum("Angle", include_zero=True), end_angle=cumsum("Angle"),
                   line_color="white", fill_color="Color", legend_label="Murdered", source=df_mur)
# 3 layout
df_team = pd.DataFrame(df.Team.value_counts()).reset_index().rename(columns={"index": "Team", "Team": "Value"})
df_team["Angle"] = df_team["Value"]/df_team["Value"].sum() * 2*pi
df_team["Color"] = ["#3182bd", "#6baed6"]

fig3 = figure(height=300, width=300, 
              toolbar_location=None, tools="hover", tooltips="@Team: @Value", x_range=(-.5, .5))
fig3.annular_wedge(x=0, y=1,  inner_radius=0.15, outer_radius=0.25, direction="anticlock",
                   start_angle=cumsum("Angle", include_zero=True), end_angle=cumsum("Angle"),
                   line_color="white", fill_color="Color", legend_label="Team", source=df_team)
# Styling
for fig in [fig1, fig2, fig3]:
        fig.grid.grid_line_color = None
for fig in [fig2, fig3]:
        fig.axis.visible=False
        fig.axis.axis_label=None
layout = grid([
                [fig1],
                [fig2, fig3]
       ])
show(layout)