I want to create a multi layer graph with the same data frame from pandas.
One should be a boxplot and the other a scatter to see where the company is located.
Is there a way to combine both plots?
boxplot
scatterplot
import pandas as pd
import plotly.express as px
df = pd.read_csv("company_index.csv", sep=";", decimal=",")
print(df)
df_u9 = df.loc[df["company"].isin(["U9"])]
fig_1 = px.box(
df,
x="period",
y="index"
)
fig_2 = px.scatter(
df_u9,
x="period",
y="index"
)
fig_1.show()
fig_2.show()
company_index.csv
period;index;company
1;202,4;U1
1;226,69;U10
1;235,18;U9
1;236,49;U4
1;238,13;U2
1;244,05;U6
1;252,08;U3
1;256,68;U8
1;294,99;U5
1;299,391;U7
2;243,78;U1
2;264,26;U10
2;270,6;U2
2;272,89;U9
2;285,26;U5
2;289,29;U4
2;291,15;U6
2;291,19;U3
2;305,92;U7
2;314,65;U8
3;271,82;U1
3;278,65;U2
3;296,16;U10
3;297,21;U4
3;305,93;U6
3;308,96;U5
3;323,74;U9
3;335,93;U3
3;354,13;U8
3;381,2;U7
4;281,26;U5
4;308,5;U2
4;311,61;U1
4;334,03;U4
4;335,72;U9
4;344,32;U8
4;345,27;U6
4;355,44;U3
4;373,54;U7
4;381,68;U10
5;288,6;U1
5;305,66;U5
5;323,2;U2
5;358,46;U8
5;365,57;U3
5;366,96;U10
5;368,38;U7
5;371,23;U6
5;373,63;U4
5;422,93;U9
6;285,32;U5
6;291,65;U1
6;308,68;U2
6;372,04;U8
6;376,64;U3
6;403,55;U6
6;407,38;U4
6;420,65;U10
6;423,68;U9
6;453,09;U7
Found this solution. Works rather well.
Im still struggling to understand the ".data[0]" but i believe its referring to the first fig in use. Maybe if you have multiple graphs.
import pandas as pd
import plotly.express as px
df = pd.read_csv("company_index.csv", sep=";", decimal=",")
print(df)
df_u9 = df.loc[df["company"].isin(["U9"])].copy()
df_u9["size"] = 1
fig = px.box(
df,
x="period",
y="index"
)
fig.add_trace(px.scatter(
df_u9,
x="period",
y="index",
size="size",
size_max=15,
color_discrete_sequence=(203,153,201)
).data[0])
fig.show()
How do I utilize plotly.express to plot multiple lines on two yaxis out of one Pandas dataframe?
I find this very useful to plot all columns containing a specific substring:
fig = px.line(df, y=df.filter(regex="Linear").columns, render_mode="webgl")
as I don't want to loop over all my filtered columns and use something like:
fig.add_trace(go.Scattergl(x=df["Time"], y=df["Linear-"]))
in each iteration.
It took me some time to fiddle this out, but I feel this could be useful to some people.
# import some stuff
import plotly.express as px
from plotly.subplots import make_subplots
import pandas as pd
import numpy as np
# create some data
df = pd.DataFrame()
n = 50
df["Time"] = np.arange(n)
df["Linear-"] = np.arange(n)+np.random.rand(n)
df["Linear+"] = np.arange(n)+np.random.rand(n)
df["Log-"] = np.arange(n)+np.random.rand(n)
df["Log+"] = np.arange(n)+np.random.rand(n)
df.set_index("Time", inplace=True)
subfig = make_subplots(specs=[[{"secondary_y": True}]])
# create two independent figures with px.line each containing data from multiple columns
fig = px.line(df, y=df.filter(regex="Linear").columns, render_mode="webgl",)
fig2 = px.line(df, y=df.filter(regex="Log").columns, render_mode="webgl",)
fig2.update_traces(yaxis="y2")
subfig.add_traces(fig.data + fig2.data)
subfig.layout.xaxis.title="Time"
subfig.layout.yaxis.title="Linear Y"
subfig.layout.yaxis2.type="log"
subfig.layout.yaxis2.title="Log Y"
# recoloring is necessary otherwise lines from fig und fig2 would share each color
# e.g. Linear-, Log- = blue; Linear+, Log+ = red... we don't want this
subfig.for_each_trace(lambda t: t.update(line=dict(color=t.marker.color)))
subfig.show()
The trick with
subfig.for_each_trace(lambda t: t.update(line=dict(color=t.marker.color)))
I got from nicolaskruchten here: https://stackoverflow.com/a/60031260
Thank you derflo and vestland! I really wanted to use Plotly Express as opposed to Graph Objects with dual axis to more easily handle DataFrames with lots of columns. I dropped this into a function. Data1/2 works well as a DataFrame or Series.
import plotly.express as px
from plotly.subplots import make_subplots
import pandas as pd
def plotly_dual_axis(data1,data2, title="", y1="", y2=""):
# Create subplot with secondary axis
subplot_fig = make_subplots(specs=[[{"secondary_y": True}]])
#Put Dataframe in fig1 and fig2
fig1 = px.line(data1)
fig2 = px.line(data2)
#Change the axis for fig2
fig2.update_traces(yaxis="y2")
#Add the figs to the subplot figure
subplot_fig.add_traces(fig1.data + fig2.data)
#FORMAT subplot figure
subplot_fig.update_layout(title=title, yaxis=dict(title=y1), yaxis2=dict(title=y2))
#RECOLOR so as not to have overlapping colors
subplot_fig.for_each_trace(lambda t: t.update(line=dict(color=t.marker.color)))
return subplot_fig
I was trying to create some heatmap using plotly3.10 and I encountered one problem that the
column names are not displayed full in ylabel.
import pandas as pd
import plotly.figure_factory as ff
from plotly.offline import plot, iplot, init_notebook_mode
df = pd.util.testing.makeDataFrame()
df.columns = ['this_is_long_column_name','another_column_name','yet_another_column_name','price']
df_corr = df.corr()
z = df_corr.values
fig = ff.create_annotated_heatmap(z,showscale=True,
x=df_corr.columns.values.tolist(),
y=df_corr.columns.values.tolist()
)
iplot(fig)
I got this image:
Question
How to show the full column name in ylabels?
How to show xlabel on both top and bottom with larger fontsizes?
How to show only 2 significant numbers, like df.round(2) only in plot?
Have you tried manually specifying the margins? E.g.:
import plotly.graph_objs as go
layout = go.Layout(
margin=dict(l=80, r=80, t=100, b=80)
)
This might work for you:
import numpy as np
import pandas as pd
import plotly
import plotly.offline as py
import plotly.graph_objs as go
import plotly.figure_factory as ff
from plotly.offline import plot, iplot, init_notebook_mode
init_notebook_mode(connected=False)
df = pd.util.testing.makeDataFrame()
df.columns = ['this_is_long_column_name','another_column_name','yet_another_column_name','price']
df_corr = df.corr()
z = df_corr.round(2).values
fig = ff.create_annotated_heatmap(z,showscale=True,
x=df_corr.columns.values.tolist(),
y=df_corr.columns.values.tolist()
)
layout = go.Layout(margin=dict(l=200, r=50, t=100, b=50))
fig.layout.update(layout)
iplot(fig)
Gives:
I have a plotly-dash dashboard and I can't seem to rescale my secondary y-axis. Is there a way of doing this?
I've tried messing with the domain parameter and the range parameter in the go.Layout.
I need the volume bar chart to be scaled down and occupy maybe 10% of the height of the plot so it doesn't overlap with my candlesticks.
Thank you very much.
Any help is appreciated.
import pandas as pd
import pandas_datareader.data as web
import plotly.offline as pyo
import plotly.graph_objs as go
stock_ticker='AAPL'
start_date='2019-04-01'
end_date='2019-05-22'
data=[]
hist_stock_df = web.DataReader(stock_ticker,'iex',start_date, end_date)
data.append(go.Candlestick(x=hist_stock_df.index,
open=hist_stock_df['open'],
high=hist_stock_df['high'],
low=hist_stock_df['low'],
close=hist_stock_df['close'],
name='AAPL'))
data.append(go.Bar(x=hist_stock_df.index,
y=hist_stock_df['volume'].values,
yaxis='y2'))
#y0=1000000
layout=go.Layout(title= 'Candestick Chart of AAPL',
xaxis=dict(title='Date',rangeslider=dict(visible=False)),
yaxis=dict(title='Price'),
plot_bgcolor='#9b9b9b',
paper_bgcolor='#9b9b9b',
font=dict(color='#c4c4c4'),
yaxis2=dict(title='Volume',
overlaying='y',
side='right'))
#scaleanchor='y'))
#scaleratio=0.00000001,
#rangemode='tozero',
#constraintoward='bottom',
#domain=[0,0.1]))
fig = go.Figure(data=data, layout=layout)
pyo.iplot(fig)
I have tried messing with the commented parameters
UPDATE
With this combination of layout parameters I managed to rescale the bars, but now there are two x-axis, been trying to figure out how to bring the middle x-axis down.
layout=go.Layout(title= 'Candestick Chart of AAPL',
xaxis=dict(title='Date',rangeslider=dict(visible=False)),
yaxis=dict(title='Price'),
plot_bgcolor='#9b9b9b',
paper_bgcolor='#9b9b9b',
font=dict(color='#c4c4c4'),
yaxis2=dict(title='Volume',
overlaying='y',
side='right',
scaleanchor='y',
scaleratio=0.0000001))
Use secondary_y=True or secondary_y=False within fig.update_yaxes() to specify which axis to adjust.
Plot 1: Without manual adjustments
Plot 2: With manual adjustments
Code:
from plotly.subplots import make_subplots
import plotly.graph_objects as go
import pandas as pd
import numpy as np
import datetime
# data
np.random.seed(1234)
numdays=20
dates = pd.date_range('1/1/2020', periods=numdays)
A = (np.random.randint(low=-10, high=10, size=numdays).cumsum()+100).tolist()
B = (np.random.randint(low=0, high=100, size=numdays).tolist())
df = pd.DataFrame({'A': A,'B':B}, index=dates)
# plotly figure setup
fig = make_subplots(specs=[[{"secondary_y": True}]])
fig.add_trace(go.Scatter(name='A', x=df.index, y=df['A'].values))
fig.add_trace(go.Bar(name='B', x=df.index, y=df['B'].values), secondary_y=True)
# plotly manual axis adjustments
fig.update_yaxes(range=[50,160], secondary_y=False)
fig.update_yaxes(range=[-10,200], secondary_y=True)
fig.show()
These resources show how to take data from a single Pandas DataFrame and plot different columns subplots on a Plotly graph. I'm interested in creating figures from separate DataFrames and plotting them to the same graph as subplots. Is this possible with Plotly?
https://plot.ly/python/subplots/
https://plot.ly/pandas/subplots/
I'm creating each figure from a dataframe like this:
import pandas as pd
import cufflinks as cf
from plotly.offline import download_plotlyjs, plot,iplot
cf.go_offline()
fig1 = df.iplot(kind='bar',barmode='stack',x='Type',
y=mylist,asFigure=True)
Edit:
Here is an example based on Naren's feedback:
Create the dataframes:
a={'catagory':['loc1','loc2','loc3'],'dogs':[1,5,6],'cats':[3,1,4],'birds':[4,12,2]}
df1 = pd.DataFrame(a)
b={'catagory':['loc1','loc2','loc3'],'dogs':[12,3,5],'cats':[4,6,1],'birds':[7,0,8]}
df2 = pd.DataFrame(b)
The plot will just show the information for the dogs, not the birds or cats:
fig = tls.make_subplots(rows=2, cols=1)
fig1 = df1.iplot(kind='bar',barmode='stack',x='catagory',
y=['dogs','cats','birds'],asFigure=True)
fig.append_trace(fig1['data'][0], 1, 1)
fig2 = df2.iplot(kind='bar',barmode='stack',x='catagory',
y=['dogs','cats','birds'],asFigure=True)
fig.append_trace(fig2['data'][0], 2, 1)
iplot(fig)
Here's a short function in a working example to save a list of figures all to a single HTML file.
def figures_to_html(figs, filename="dashboard.html"):
with open(filename, 'w') as dashboard:
dashboard.write("<html><head></head><body>" + "\n")
for fig in figs:
inner_html = fig.to_html().split('<body>')[1].split('</body>')[0]
dashboard.write(inner_html)
dashboard.write("</body></html>" + "\n")
# Example figures
import plotly.express as px
gapminder = px.data.gapminder().query("country=='Canada'")
fig1 = px.line(gapminder, x="year", y="lifeExp", title='Life expectancy in Canada')
gapminder = px.data.gapminder().query("continent=='Oceania'")
fig2 = px.line(gapminder, x="year", y="lifeExp", color='country')
gapminder = px.data.gapminder().query("continent != 'Asia'")
fig3 = px.line(gapminder, x="year", y="lifeExp", color="continent",
line_group="country", hover_name="country")
figures_to_html([fig1, fig2, fig3])
You can get a dashboard that contains several charts with legends next to each one:
import plotly
import plotly.offline as py
import plotly.graph_objs as go
fichier_html_graphs=open("DASHBOARD.html",'w')
fichier_html_graphs.write("<html><head></head><body>"+"\n")
i=0
while 1:
if i<=40:
i=i+1
#______________________________--Plotly--______________________________________
color1 = '#00bfff'
color2 = '#ff4000'
trace1 = go.Bar(
x = ['2017-09-25','2017-09-26','2017-09-27','2017-09-28','2017-09-29','2017-09-30','2017-10-01'],
y = [25,100,20,7,38,170,200],
name='Debit',
marker=dict(
color=color1
)
)
trace2 = go.Scatter(
x=['2017-09-25','2017-09-26','2017-09-27','2017-09-28','2017-09-29','2017-09-30','2017-10-01'],
y = [3,50,20,7,38,60,100],
name='Taux',
yaxis='y2'
)
data = [trace1, trace2]
layout = go.Layout(
title= ('Chart Number: '+str(i)),
titlefont=dict(
family='Courier New, monospace',
size=15,
color='#7f7f7f'
),
paper_bgcolor='rgba(0,0,0,0)',
plot_bgcolor='rgba(0,0,0,0)',
yaxis=dict(
title='Bandwidth Mbit/s',
titlefont=dict(
color=color1
),
tickfont=dict(
color=color1
)
),
yaxis2=dict(
title='Ratio %',
overlaying='y',
side='right',
titlefont=dict(
color=color2
),
tickfont=dict(
color=color2
)
)
)
fig = go.Figure(data=data, layout=layout)
plotly.offline.plot(fig, filename='Chart_'+str(i)+'.html',auto_open=False)
fichier_html_graphs.write(" <object data=\""+'Chart_'+str(i)+'.html'+"\" width=\"650\" height=\"500\"></object>"+"\n")
else:
break
fichier_html_graphs.write("</body></html>")
print("CHECK YOUR DASHBOARD.html In the current directory")
Result:
You can also try the following using cufflinks:
cf.subplots([df1.figure(kind='bar',categories='category'),
df2.figure(kind='bar',categories='category')],shape=(2,1)).iplot()
And this should give you:
New Answer:
We need to loop through each of the animals and append a new trace to generate what you need. This will give the desired output I am hoping.
import pandas as pd
import numpy as np
import cufflinks as cf
import plotly.tools as tls
from plotly.offline import download_plotlyjs, plot,iplot
cf.go_offline()
import random
def generate_random_color():
r = lambda: random.randint(0,255)
return '#%02X%02X%02X' % (r(),r(),r())
a={'catagory':['loc1','loc2','loc3'],'dogs':[1,5,6],'cats':[3,1,4],'birds':[4,12,2]}
df1 = pd.DataFrame(a)
b={'catagory':['loc1','loc2','loc3'],'dogs':[12,3,5],'cats':[4,6,1],'birds':[7,0,8]}
df2 = pd.DataFrame(b)
#shared Xaxis parameter can make this graph look even better
fig = tls.make_subplots(rows=2, cols=1)
for animal in ['dogs','cats','birds']:
animal_color = generate_random_color()
fig1 = df1.iplot(kind='bar',barmode='stack',x='catagory',
y=animal,asFigure=True,showlegend=False, color = animal_color)
fig.append_trace(fig1['data'][0], 1, 1)
fig2 = df2.iplot(kind='bar',barmode='stack',x='catagory',
y=animal,asFigure=True, showlegend=False, color = animal_color)
#if we do not use the below line there will be two legend
fig2['data'][0]['showlegend'] = False
fig.append_trace(fig2['data'][0], 2, 1)
#additional bonus
#use the below command to use the bar chart three mode
# [stack, overlay, group]
#as shown below
#fig['layout']['barmode'] = 'overlay'
iplot(fig)
Output:
Old Answer:
This will be the solution
Explanation:
Plotly tools has a subplot function to create subplots you should read the documentation for more details here. So I first use cufflinks to create a figure of the bar chart. One thing to note is cufflinks create and object with both data and layout. Plotly will only take one layout parameter as input, hence I take only the data parameter from the cufflinks figure and append_trace it to the make_suplots object. so fig.append_trace() the second parameter is row number and third parameter is column number
import pandas as pd
import cufflinks as cf
import numpy as np
import plotly.tools as tls
from plotly.offline import download_plotlyjs, plot,iplot
cf.go_offline()
fig = tls.make_subplots(rows=2, cols=1)
df = pd.DataFrame(np.random.randint(0,100,size=(100, 4)), columns=list('ABCD'))
fig1 = df.iplot(kind='bar',barmode='stack',x='A',
y='B',asFigure=True)
fig.append_trace(fig1['data'][0], 1, 1)
df2 = pd.DataFrame(np.random.randint(0,100,size=(100, 4)), columns=list('EFGH'))
fig2 = df2.iplot(kind='bar',barmode='stack',x='E',
y='F',asFigure=True)
fig.append_trace(fig2['data'][0], 2, 1)
iplot(fig)
If you want to add a common layout to the subplot I suggest that you do
fig.append_trace(fig2['data'][0], 2, 1)
fig['layout']['showlegend'] = False
iplot(fig)
or even
fig.append_trace(fig2['data'][0], 2, 1)
fig['layout'].update(fig1['layout'])
iplot(fig)
So in the first example before plotting, I access the individual parameters of the layout object and change them, you need to go through layout object properties for refernce.
In the second example before plotting, I update the layout of the figure with the cufflinks generated layout this will produce the same output as we see in cufflinks.
You've already received a few suggestions that work perfectly well. They do however require a lot of coding. Facet / trellis plots using px.bar() will let you produce the plot below using (almost) only this:
px.bar(df, x="category", y="dogs", facet_row="Source")
The only extra steps you'll have to take is to introduce a variable on which to split your data, and then gather or concatenate your dataframes like this:
df1['Source'] = 1
df2['Source'] = 2
df = pd.concat([df1, df2])
And if you'd like to include the other variables as well, just do:
fig = px.bar(df, x="category", y=["dogs", "cats", "birds"], facet_row="Source")
fig.update_layout(barmode = 'group')
Complete code:
# imports
import plotly.express as px
import pandas as pd
# data building
a={'category':['loc1','loc2','loc3'],'dogs':[1,5,6],'cats':[3,1,4],'birds':[4,12,2]}
df1 = pd.DataFrame(a)
b={'category':['loc1','loc2','loc3'],'dogs':[12,3,5],'cats':[4,6,1],'birds':[7,0,8]}
df2 = pd.DataFrame(b)
# data processing
df1['Source'] = 1
df2['Source'] = 2
df = pd.concat([df1, df2])
# plotly figure
fig = px.bar(df, x="category", y="dogs", facet_row="Source")
fig.show()
#fig = px.bar(df, x="category", y=["dogs", "cats", "birds"], facet_row="Source")
#fig.update_layout(barmode = 'group')