数据可视化---plotly篇

plotly

https://plot.ly/python/ plotly是现代平台的敏捷商业智能和数据科学库，它作为一款开源的绘图库，可以应用于Python、R、MATLAB、Excel、JavaScript和jupyter等多种语言，主要使用的js进行图形绘制，实现过程中主要就是调用plotly的函数接口，底层实现完全被隐藏，便于初学者的掌握。

Basic Example

In [6]:

import plotly.plotly as py

import plotly.graph_objs as go

py . sign_in ( 'deamoncao' , '*******' ) # 注意：这里是plotly网站的用户名和密码

trace = go . Bar ( x = [ 2 , 4 , 6 ], y = [ 10 , 12 , 15 ])

data = [ trace ]

layout = go . Layout ( title = 'A Simple Plot' , width = 800 , height = 640 )

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

py . image . save_as ( fig , filename = 'a-simple-plot.png' )

from IPython.display import Image

Image ( 'a-simple-plot.png' )

Out[6]:

Basic Box Plot

https://plot.ly/python/box-plots/

In [22]:

import plotly.plotly as py

import plotly.graph_objs as go

import numpy as np

y0 = np . random . randn ( 50 ) - 1

y1 = np . random . randn ( 50 ) + 1

trace0 = go . Box (

y = y0

)

trace1 = go . Box (

y = y1

)

data = [ trace0 , trace1 ]

py . iplot ( data )

Out[22]:

Fully Styled Box Plots

In [9]:

import plotly.plotly as py

import plotly.graph_objs as go

x_data = [ 'Carmelo Anthony' , 'Dwyane Wade' ,

'Deron Williams' , 'Brook Lopez' ,

'Damian Lillard' , 'David West' ,]

y0 = np . random . randn ( 50 ) - 1

y1 = np . random . randn ( 50 ) + 1

y2 = np . random . randn ( 50 )

y3 = np . random . randn ( 50 ) + 2

y4 = np . random . randn ( 50 ) - 2

y5 = np . random . randn ( 50 ) + 3

y_data = [ y0 , y1 , y2 , y3 , y4 , y5 ]

colors = [ 'rgba(93, 164, 214, 0.5)' , 'rgba(255, 144, 14, 0.5)' , 'rgba(44, 160, 101, 0.5)' , 'rgba(255, 65, 54, 0.5)' , 'rgba(207, 114, 255, 0.5)' , 'rgba(127, 96, 0, 0.5)' ]

traces = []

for xd , yd , cls in zip ( x_data , y_data , colors ):

traces . append ( go . Box (

y = yd ,

name = xd ,

boxpoints = 'all' ,

jitter = 0.5 ,

whiskerwidth = 0.2 ,

fillcolor = cls ,

marker = dict (

size = 2 ,

),

line = dict ( width = 1 ),

))

layout = go . Layout (

title = 'Points Scored by the Top 9 Scoring NBA Players in 2012' ,

yaxis = dict (

autorange = True ,

showgrid = True ,

zeroline = True ,

dtick = 5 ,

gridcolor = 'rgb(255, 255, 255)' ,

gridwidth = 1 ,

zerolinecolor = 'rgb(255, 255, 255)' ,

zerolinewidth = 2 ,

),

margin = dict (

l = 40 ,

r = 30 ,

b = 80 ,

t = 100 ,

),

paper_bgcolor = 'rgb(243, 243, 243)' ,

plot_bgcolor = 'rgb(243, 243, 243)' ,

showlegend = False

)

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

py . iplot ( fig )

Out[9]:

US Flight Paths Map

In [23]:

import plotly.plotly as py

import pandas as pd

df_airports = pd . read_csv ( 'https://raw.githubusercontent.com/plotly/datasets/master/2011_february_us_airport_traffic.csv' )

df_airports . head ()

df_flight_paths = pd . read_csv ( 'https://raw.githubusercontent.com/plotly/datasets/master/2011_february_aa_flight_paths.csv' )

df_flight_paths . head ()

airports = [ dict (

type = 'scattergeo' ,

locationmode = 'USA-states' ,

lon = df_airports [ 'long' ],

lat = df_airports [ 'lat' ],

hoverinfo = 'text' ,

text = df_airports [ 'airport' ],

mode = 'markers' ,

marker = dict (

size = 2 ,

color = 'rgb(255, 0, 0)' ,

line = dict (

width = 3 ,

color = 'rgba(68, 68, 68, 0)'

)

))]

flight_paths = []

for i in range ( len ( df_flight_paths ) ):

flight_paths . append (

dict (

type = 'scattergeo' ,

locationmode = 'USA-states' ,

lon = [ df_flight_paths [ 'start_lon' ][ i ], df_flight_paths [ 'end_lon' ][ i ] ],

lat = [ df_flight_paths [ 'start_lat' ][ i ], df_flight_paths [ 'end_lat' ][ i ] ],

mode = 'lines' ,

line = dict (

width = 1 ,

color = 'red' ,

),

opacity = float ( df_flight_paths [ 'cnt' ][ i ]) / float ( df_flight_paths [ 'cnt' ] . max ()),

)

)

layout = dict (

title = 'Feb. 2011 American Airline flight paths
(Hover for airport names)' ,

showlegend = False ,

geo = dict (

scope = 'north america' ,

projection = dict ( type = 'azimuthal equal area' ),

showland = True ,

landcolor = 'rgb(243, 243, 243)' ,

countrycolor = 'rgb(204, 204, 204)' ,

),

)

fig = dict ( data = flight_paths + airports , layout = layout )

py . iplot ( fig , filename = 'd3-flight-paths' )

Out[23]:

Contour lines on globe

https://plot.ly/python/lines-on-maps/

In [24]:

import plotly.plotly as py

import pandas as pd

try :

# Python 2

from itertools import izip

except ImportError :

# Python 3

izip = zip

df = pd . read_csv ( 'https://raw.githubusercontent.com/plotly/datasets/master/globe_contours.csv' )

df . head ()

contours = []

scl = [ 'rgb(213,62,79)' , 'rgb(244,109,67)' , 'rgb(253,174,97)' , \

'rgb(254,224,139)' , 'rgb(255,255,191)' , 'rgb(230,245,152)' , \

'rgb(171,221,164)' , 'rgb(102,194,165)' , 'rgb(50,136,189)' ]

def pairwise ( iterable ):

a = iter ( iterable )

return izip ( a , a )

i = 0

for lat , lon in pairwise ( df . columns ):

contours . append ( dict (

type = 'scattergeo' ,

lon = df [ lon ],

lat = df [ lat ],

mode = 'lines' ,

line = dict (

width = 2 ,

color = scl [ i ]

)

) )

i = 0 if i + 1 >= len ( df . columns ) / 4 else i + 1

layout = dict (

title = 'Contour lines over globe
(Click and drag to rotate)' ,

showlegend = False ,

geo = dict (

showland = True ,

showlakes = True ,

showcountries = True ,

showocean = True ,

countrywidth = 0.5 ,

landcolor = 'rgb(230, 145, 56)' ,

lakecolor = 'rgb(0, 255, 255)' ,

oceancolor = 'rgb(0, 255, 255)' ,

projection = dict (

type = 'orthographic' ,

rotation = dict (

lon = - 100 ,

lat = 40 ,

roll = 0

)

),

lonaxis = dict (

showgrid = True ,

gridcolor = 'rgb(102, 102, 102)' ,

gridwidth = 0.5

),

lataxis = dict (

showgrid = True ,

gridcolor = 'rgb(102, 102, 102)' ,

gridwidth = 0.5

)

)

)

fig = dict ( data = contours , layout = layout )

py . iplot ( fig , validate = False , filename = 'd3-globe' )

Out[24]: