I hacked together this code to plot lat and lon coordinates on a map, and the code works pretty darn well, but I can't seem to get the legend displayed, so it's hard to tell what I'm actually looking at.
import pandas as pd
import pandas_bokeh
import matplotlib.pyplot as plt
import pgeocode
import geopandas as gpd
from shapely.geometry import Point
from geopandas import GeoDataFrame
pandas_bokeh.output_notebook()
import plotly.graph_objects as go
nomi = pgeocode.Nominatim('us')
df_melted['Latitude'] = (nomi.query_postal_code(df_melted['my_zip'].tolist()).latitude)
df_melted['Longitude'] = (nomi.query_postal_code(df_melted['my_zip'].tolist()).longitude)
df_melted['colors'] = df_melted['value'].groupby(df_melted['value']).transform('count')
print(df_melted.shape)
print(df_melted.head())
import plotly.express as px
import plotly.graph_objects as go
import pandas as pd
fig = go.Figure(data=go.Scattergeo(
lon = df_melted['Longitude'],
lat = df_melted['Latitude'],
text = df_melted['value'],
marker_color = df_melted['colors']
))
fig.update_layout(
autosize=False,
width=1000,
height=1000,
title = 'Footprints Compared Based on Lat & Lon Coordinates)',
geo_scope='usa',
showlegend=True
)
fig.update_layout(legend=dict(
orientation="h",
yanchor="bottom",
y=1.02,
xanchor="right",
x=1
))
fig.show()
When I run the code, I see a nice map of the US, but there is not legend, even though I'm using this small script directly below, which came straight from the Plotly documentation.
legend=True & showlegend=True
Both gave me errors. Any idea how to get the legend to show up here?
have used earthquake data to be able to simulate df_melted with compatible columns
there really is only one missing parameter: marker_coloraxis="coloraxis"
also changed showlegend=False
full working example using OP plotting code
import pandas as pd
import matplotlib.pyplot as plt
import geopandas as gpd
from shapely.geometry import Point
from geopandas import GeoDataFrame
import plotly.graph_objects as go
import requests
res = requests.get(
"https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/2.5_week.geojson"
)
us = (
gpd.read_file(gpd.datasets.get_path("naturalearth_lowres"))
.loc[lambda d: d["iso_a3"].eq("USA"), "geometry"]
.values[0]
)
gdf = gpd.GeoDataFrame.from_features(res.json(), crs="epsg:4386").loc[
lambda d: d.intersects(us)
]
df_melted = pd.DataFrame(
{
"Latitude": gdf["geometry"].y,
"Longitude": gdf["geometry"].x,
"colors": gdf["mag"],
"value": gdf["place"],
}
)
fig = go.Figure(
data=go.Scattergeo(
lon=df_melted["Longitude"],
lat=df_melted["Latitude"],
text=df_melted["value"],
marker_color=df_melted["colors"],
marker_coloraxis="coloraxis",
)
)
fig.update_layout(
autosize=False,
width=400,
height=400,
title="Footprints Compared Based on Lat & Lon Coordinates)",
geo_scope="usa",
showlegend=False,
)
fig.update_layout(
legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1)
)
fig.show()
The code is running well; however, in my dataset, there is a column SD in my custom dataset. I would like the size of these markers should be based on SD and I did it in the seaborn library, it is running well. However, I get errors here.
%Error is
Did you mean "line"?
Bad property path:
size
^^^^
Code is
df=pd.read_csv("Lifecycle.csv")
df1=df[df["Specie"]=="pot_marigold"]
df1
df2=df[df["Specie"]=="Sunflowers"]
df2
trace=go.Scatter(x=df1["Days"], y=df1["Lifecycle"],text=df1["Specie"],marker={"color":"green"}, size=df1[SD],
mode="lines+markers")
trace1=go.Scatter(x=df2["Days"], y=df2["Lifecycle"],text=df2["Specie"],marker={"color":"red"},
mode="lines+markers")
data=[trace,trace1]
layout=go.Layout(
title="Lifecycle",
xaxis={"title":"Days"},
yaxis={"title":"Lifecycle"})
fig=go.Figure(data=data,layout=layout)
pyo.plot(fig)
you have not provided sample data, so I have simulated based on what I can imply from your code
simply you can set marker_size within framework you have used
this type of plot is far simpler with Plotly Express have also shown code for this
import pandas as pd
import numpy as np
import plotly.graph_objects as go
# df=pd.read_csv("Lifecycle.csv")
df = pd.DataFrame(
{
"Specie": np.repeat(["pot_marigold", "Sunflowers"], 10),
"Days": np.tile(np.arange(1, 11, 1), 2),
"Lifecycle": np.concatenate(
[np.sort(np.random.uniform(1, 5, 10)).astype(int) for _ in range(2)]
),
"SD": np.random.randint(1, 8, 20),
}
)
df1 = df[df["Specie"] == "pot_marigold"]
df2 = df[df["Specie"] == "Sunflowers"]
trace = go.Scatter(
x=df1["Days"],
y=df1["Lifecycle"],
text=df1["Specie"],
marker={"color": "green"},
marker_size=df1["SD"],
mode="lines+markers",
)
trace1 = go.Scatter(
x=df2["Days"],
y=df2["Lifecycle"],
text=df2["Specie"],
marker={"color": "red"},
mode="lines+markers",
)
data = [trace, trace1]
layout = go.Layout(
title="Lifecycle", xaxis={"title": "Days"}, yaxis={"title": "Lifecycle"}
)
fig = go.Figure(data=data, layout=layout)
fig
Plotly Express
import plotly.express as px
px.scatter(
df,
x="Days",
y="Lifecycle",
color="Specie",
size="SD",
color_discrete_map={"pot_marigold": "green", "Sunflowers": "red"},
).update_traces(mode="lines+markers")
You can use plotly.express instead:
import plotly.express as px
trace=px.scatter(df, x="Days", y="Lifecycle", text="Specie", marker="SD")
I need to change stacked barchart width to be overlapped.
I found this question and solution How to plot a superimposed bar chart using matplotlib in python? and I would like to reproduce the same chart on DASH Plotly python framework.
The code is as below:
import matplotlib.pyplot as plt
import numpy as np
width = 0.8
highPower = [1184.53,1523.48,1521.05,1517.88,1519.88,1414.98,
1419.34,1415.13,1182.70,1165.17]
lowPower = [1000.95,1233.37, 1198.97,1198.01,1214.29,1130.86,
1138.70,1104.12,1012.95,1000.36]
indices = np.arange(len(highPower))
plt.bar(indices, highPower, width=width,
color='b', label='Max Power in mW')
plt.bar([i+0.25*width for i in indices], lowPower,
width=0.5*width, color='r', alpha=0.5, label='Min Power in mW')
plt.xticks(indices+width/2.,
['T{}'.format(i) for i in range(len(highPower))] )
plt.legend()
plt.show()
Question: How to edit to accomodate DASH principles?
For instance, on Dash, bar doesn't accept width=0.5*width adn alpha=0.5
Thanks.
My own code is as below:
from plotly.offline import init_notebook_mode, iplot
from plotly import graph_objs as go
init_notebook_mode(connected = True)
import pandas as pd
import numpy as np
dfb=pd.read_csv('https://www.dropbox.com/s/90y07129zn351z9/test_data.csv?dl=1', encoding="latin-1", infer_datetime_format=True, parse_dates=['date'], skipinitialspace=True)
dfb["date"]=pd.to_datetime(dfb['date'])
dfb["site"]=dfb["site"].astype("category")
cm_inc=dfb[dfb.site == 5].pivot_table(index='date', values = 'site', aggfunc = { 'site' : 'count' } )
dfb['cm_target'] = [40]*len(dfb)
dfb.to_csv('test_data.csv', index=False)
data = [
go.Bar(x=cm_inc.index, y=cm_inc['site'], name='Enroll Site A',
#base=0
),
go.Bar(x=cm_inc.index, y=dfb['cm_target'], name='Target Site A',
#base=0,
#width=0.5
)]
layout = go.Layout(
barmode='stack',
)
fig = dict(data = data, layout = layout)
iplot(fig, show_link=False)
The proposed solution by #Teoretic to use base=0 on both traces and to use barmode='stack' is not working.
Thanks.
EDIT edited answer to use new data that was added to the question
You can do overlapped barchart in Plotly by doing these 2 steps:
1) setting barmode in layout to 'stack'
2) setting base of every barchart to 0
3) small numeric value to set to X values
Also you might want to play around with:
1) Setting "width" parameter of the second barchart to the value that suits you
2) Making labels of "X" axis data more suitable to you
Sample code (run in Jupyter Notebook):
from plotly.offline import init_notebook_mode, iplot
from plotly import graph_objs as go
init_notebook_mode(connected = True)
import pandas as pd
import numpy as np
dfb=pd.read_csv('https://www.dropbox.com/s/90y07129zn351z9/test_data.csv?dl=1', encoding="latin-1", infer_datetime_format=True, parse_dates=['date'], skipinitialspace=True)
dfb["date"]=pd.to_datetime(dfb['date'])
dfb["site"]=dfb["site"].astype("category")
cm_inc=dfb[dfb.site == 5].pivot_table(index='date', values = 'site', aggfunc = { 'site' : 'count' } )
dfb['cm_target'] = [40]*len(dfb)
dfb.to_csv('test_data.csv', index=False)
# You need small int indexes for "width" and "base" = 0 trick to work
indexes = [int(i.timestamp()) / 10000 for i in cm_inc.index]
# For string dates labels
dates_indexes = [str(i) for i in cm_inc.index]
data = [
go.Bar(x=indexes,
y=dfb['cm_target'],
name='Target Site A',
base=0
),
go.Bar(x=indexes,
y=cm_inc['site'],
name='Enroll Site A',
base=0,
width=5 # Width value varies depending on number of samples in data
)
]
layout = go.Layout(
barmode='stack',
xaxis=dict(
showticklabels=True,
ticktext=dates_indexes,
tickvals=[i for i in indexes],
)
)
fig = dict(data = data, layout = layout)
iplot(fig, show_link=False)
from plotly.offline import init_notebook_mode, iplot
from plotly import graph_objs as go
init_notebook_mode(connected = True)
import pandas as pd
import numpy as np
from datetime import timedelta, datetime, tzinfo
import time
from datetime import datetime as dt
dfb=pd.read_csv('https://www.dropbox.com/s/90y07129zn351z9/test_data.csv?dl=1', encoding="latin-1", infer_datetime_format=True, parse_dates=['date'], skipinitialspace=True)
dfb["date"]=pd.to_datetime(dfb['date'])
dfb["site"]=dfb["site"].astype("category")
cm_inc=dfb[dfb.site == 5].pivot_table(index='date', values = 'site', aggfunc = { 'site' : 'count' } )
dfb['cm_target'] = [40]*len(dfb)
dfb.to_csv('test_data.csv', index=False)
# You need small int indexes for "width" and "base" = 0 trick to work
#indexes = [int(i.timestamp()) / 10000 for i in cm_inc.index]
indexes =pd.to_datetime(cm_inc.index)
# For string dates labels
#dates_indexes = [str(i) for i in cm_inc.index]
dates_indexes = pd.to_datetime(cm_inc.index)
data = [
go.Bar(x=indexes,
y=dfb['cm_target'],
name='Target Site A',
base=0
),
go.Bar(x=indexes,
y=cm_inc['site'],
name='Enroll Site A',
base=0,
#width=2 # Width value varies depending on number of samples in data
)
]
layout = go.Layout(
barmode='stack',
xaxis=dict(
showticklabels=True,
ticktext=dates_indexes,
tickvals=[i for i in indexes],
)
)
fig = dict(data = data, layout = layout)
iplot(fig, show_link=False)
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')