I noticed that plotting different time scales causes the opacity of my overlaid bar chart to fade. How do I correct this? In the first image, I plotted over a range of 2 years and in the second I plotted a 1 year time range. Notice that the former has a significantly faded bar chart, I would expect that these two charts to be the same regardless of range.
Sidenote: I am "hacking" the chart to center on the primary axis, if anyone can help me figure out how to directly set the y-axis range of the secondary axis that would be very helpful as well.
import plotly.graph_objects as go
from plotly.subplots import make_subplots
filtered = df[(df['date'] > '2017-1-24') & (df['date'] <= '2018-1-24')]
fig = make_subplots(specs=[[{"secondary_y": True}]])
fig.add_trace(
go.Bar(
x=filtered['date'],
y=filtered['divergence'],
opacity=0.5
)
)
fig.add_trace(
go.Scatter(
x=filtered['date'],
y=filtered['price'],
mode="lines"
),
secondary_y=True
)
fig.update_layout(yaxis_range=[-9, 9])
fig.show()
Opacity lower than expected:
Opacity normal:
Short answer:
This has nothing to do with opacity. For some more details take a look below at the complete answer. To obtain consisteny between a figures with many and few observations, you'll have to set the width of the bar line to zero, and set bargap to zero like in the next code snippet. Using a color like rgba(0,0,250,0) you can also select any opacity you'd like through the last digit.
fig.update_traces(marker_color = 'rgba(0,0,250, 0.5)',
marker_line_width = 0,
selector=dict(type="bar"))
fig.update_layout(bargap=0,
bargroupgap = 0,
)
Plot 1a - Few observations
Plot 1b - Many observations
The details:
This has nothing to do with opacity. You're asking plotly to build a bar-plot, and apparently barplots according to plotly must have a space between the bars. So for a few observations you'll get this:
And for many observations, as you have demonstrated, you'll get this:
The color of the bars has not changed, but it seems like it since plolty squeezes in a bit of space for many more observations.
I initially thought this would be amendable through:
fig.update_layout(bargap=0,
bargroupgap = 0,
)
But no:
In order to increase consistency between smaller and larger selectoins, you'll have to select the same color for the bar fill as for the line color of the bar, like blue.
fig.update_traces(marker_color='blue',
marker_line_color='blue',
selector=dict(type="bar"))
But there's still a little color difference between the bars if you zoom in:
And this becomes clearer for lighter colors:
But the best solution turned out to be setting marker_line_width = 0 like described at the beginning of the answer.
End result:
Complete code:
import numpy as np
import pandas as pd
import plotly.graph_objects as go
import plotly.express as px
import datetime
from plotly.subplots import make_subplots
pd.set_option('display.max_rows', None)
# data sample
nperiods = 50
np.random.seed(123)
df = pd.DataFrame(np.random.randint(-10, 12, size=(nperiods, 2)),
columns=['price', 'divergence'])
datelist = pd.date_range(datetime.datetime(2017, 1, 1).strftime('%Y-%m-%d'),periods=nperiods).tolist()
df['date'] = datelist
df = df.set_index(['date'])
df.index = pd.to_datetime(df.index)
# df.iloc[0] =1000
# df = df.cumsum().reset_index()
df.reset_index(inplace=True)
df['price'] = df['price'].cumsum()
df['divergence'] = df['divergence'].cumsum()
filtered = df[(df['date'] > '2017-1-24') & (df['date'] <= '2018-1-24')]
fig = make_subplots(specs=[[{"secondary_y": True}]])
fig.add_trace(
go.Bar(
x=filtered['date'],
y=filtered['divergence'],
#opacity=0.5
)
)
fig.add_trace(
go.Scatter(
x=filtered['date'],
y=filtered['price'],
mode="lines"
),
secondary_y=True
)
fig.update_traces(marker_color = 'rgba(0,0,250, 0.5)',
marker_line_width = 0,
selector=dict(type="bar"))
fig.update_layout(bargap=0,
bargroupgap = 0,
)
fig.show()
It is not changing opacity, but it is trying to plot large number of bars in given plot area. try zooming in and see the difference. also try changing width of the plot with :
fig.update_layout(width=2500)
to change secondary axis range use :
fig.update_layout(yaxis2_range=[lower_range,upper_range])
Related
Is it possible to align two Y-axis by two different values? I would like to align my yaxis1 at zero with my yaxis2 at 1, like in the picture
picture
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import pandas as pd
df = pd.DataFrame(dict(months=['jan','feb','mar','apr','may','jun'],
assets = [60,20,-25,-35,20,80],
liabilities = [70,75,80,90,70,50]))
# calculate ratio
df['ratio'] = df['assets'] / df['liabilities']
fig = make_subplots(specs=[[{"secondary_y": True}]])
fig.add_trace(go.Bar(x=df['months'], y=df['assets'], marker_color='green'))
fig.add_trace(go.Bar(x=df['months'], y=df['liabilities'], marker_color='red'))
fig.add_trace(go.Scatter(x=df['months'], y=df['ratio'], marker_color='orange'), secondary_y=True)
fig.update_yaxes(showgrid=False, secondary_y=True)
fig.show()
To set the range of the 2nd y-axis, set the range in the layout. The manual adjustment of the second y-axis affected the scale of the first y-axis, which was corrected at the same time. If it is not the intended scale, you are responsible for correcting it.
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import pandas as pd
df = pd.DataFrame(dict(months=['jan','feb','mar','apr','may','jun'],
assets = [60,20,-25,-35,20,80],
liabilities = [70,75,80,90,70,50]))
# calculate ratio
df['ratio'] = df['assets'] / df['liabilities']
fig = make_subplots(specs=[[{"secondary_y": True}]])
fig.add_trace(go.Bar(x=df['months'], y=df['assets'], marker_color='green',name='assets'))
fig.add_trace(go.Bar(x=df['months'], y=df['liabilities'], marker_color='red',name='liabilities'))
fig.add_trace(go.Scatter(x=df['months'], y=df['ratio'], marker_color='orange',name='ratio'), secondary_y=True)
fig.update_yaxes(showgrid=False, secondary_y=True),
fig.update_layout(autosize=True, yaxis=dict(range=[-50,150]), yaxis2=dict(range=[0,4]))#height=600,
fig.show()
Here is CDF visualization I have:
fig_cdf = px.ecdf(df['Timespan'], color_discrete_sequence=['blue'],ecdfnorm='probability', orientation='h')
fig_cdf.add_hline(y=90, line_width=2, line_color="red", name='90%', visible=True)
fig_cdf.add_hline(y=30, line_width=2, line_color="red", name='75%', visible=True)
fig_cdf.update_layout(width=500, height=500)
The problem here is that i want horizontal lines' names to be visible and appear as 2nd and 3rd legends. For this, I tried to add visible=True. However, it seems not to work. What's wrong?
This is one way of doing it...
Add the two lines to the dataframe as new columns
Use color_discrete_sequence to identify the colors you want
I am using some random dummy data, which you can replace with your data
import plotly.express as px
df = pd.DataFrame({'firstline': random.sample(range(1, 500), 20),'myX' : range(20)}) #My dummy data
#Add the two lines to dataframe
df['90%'] = [90] * 20
df['75%'] = [75] * 20
fig = px.line(df,
y = ['firstline', '90%', '75%'], x= 'myX', color_discrete_sequence=["blue", "red", "red"])
fig.update_layout(legend_title_text='Legend Heading') #Update Legend header if you dont like 'variable'
fig.show()
Output graph
This is my first experience with this graph, but to add it to the legend, you can use the line mode of the scatter plot. So I took the maximum x-axis value used in the first graph and set the legend name Average using the appropriate y-axis value. This example is taken from the official reference.
import plotly.express as px
import plotly.graph_objects as go
df = px.data.tips()
fig = px.ecdf(df, x=["total_bill", "tip"])
xmax = max(fig.data[0]['x'])
#print(xmax)
fig.add_trace(go.Scatter(
x=[0,xmax],
y=[0.6,0.6],
mode='lines',
line_color='red',
name='mean',
showlegend=True
))
fig.show()
So, I have this simplified data frame and I'm using plotly.graph_objects to plot a stacked bar chart with text annotations.
I got the text as I wanted from the Salary column but I can't get the same for the Age column where the values are significantly lower. I would like these annotations to be the same size and on top of each bar.
How can I get the text annotations to be visible for the Age column as well?
Please find my code below:
data = {'Name':['Tom', 'Nick', 'Jack'],
'Age':[18, 21, 19],
'Salary':[500, 700, 900]}
df_new=pd.DataFrame(data)
fig = go.Figure(go.Bar(x = df_new["Name"],
y = df_new["Age"],name='Age',text=df_new["Age"],
textposition='outside'))
fig.add_bar(x = df_new["Name"],
y = df_new["Salary"],name='Salary',text=df_new["Salary"],
textposition='outside')
fig.update_layout(barmode='stack',
title = 'Age - Salary',
xaxis_title="Name",
yaxis_title="Age / Salary")
Thanks in advance!
I think you have to choose from 2 possible solutions. First of all, by using the barmode = stack argument, you are stacking and thus summing the values of age and salary. The height of bars will be age + salary, such that the height of Tom's bar will be 500 + 18 = 518. I'd advise against this, as the height should reflect the callout value in my opinion.
Solution 1 - grouped bars
This solution is based on changing the barmode to barmode = group. This will make two separate bars, which have their own callout and heights reflecting their values.
I've also added the width argument to make prettier aspect ratios.
fig = go.Figure()
fig.add_bar(x = df_new["Name"],
y = df_new["Age"],name='Age',text=df_new["Age"],
width = [0.3]*len(df_new),
)
fig.add_bar(x = df_new["Name"],
y = df_new["Salary"],name='Salary',text=df_new["Salary"],
width = [0.3]*len(df_new)
)
fig.update_layout(barmode='group',
title = 'Age - Salary',
xaxis_title="Name",
yaxis_title="Age / Salary"
)
fig.update_traces(
textposition='outside'
)
fig.update_yaxes(range=[0,1000])
Solution 2 - add secondary y-axis
I prefer this solution, as the relative size of the two categories can each be scaled to their own domain; which makes the chart a lot more readable. This uses make_subplots to create two axes and the secondary_y argument. I've made both bars visible by playing around with the widths and ranges of the axes.
Based on the data you'd have to manually rescale to your liking. You could also incorporate opacity for look-through bars, but you'd still have the risk of overlapping data callouts.
from plotly.subplots import make_subplots
fig = make_subplots(specs=[[{"secondary_y": True}]])
fig.add_bar(
x=df_new["Name"],
y=df_new["Age"],
name="Age",
text=df_new["Age"],
width=[0.3] * len(df_new),
secondary_y=True,
textposition="outside"
)
fig.add_bar(
x=df_new["Name"],
y=df_new["Salary"],
name="Salary",
text=df_new["Salary"],
width=[0.5] * len(df_new),
secondary_y=False,
textposition="outside"
)
fig.update_yaxes(range=[0, 1000], title='Salary', secondary_y=False)
fig.update_yaxes(range=[0, 45], title='Age', secondary_y=True)
fig.update_layout(title="Age and Salary", xaxis_title="Name")
this is my first foray into Plotly. I love the ease of use compared to matplotlib and bokeh. However I'm stuck on some basic questions on how to beautify my plot. First, this is the code below (its fully functional, just copy and paste!):
import plotly.express as px
from plotly.subplots import make_subplots
import plotly as py
import pandas as pd
from plotly import tools
d = {'Mkt_cd': ['Mkt1','Mkt2','Mkt3','Mkt4','Mkt5','Mkt1','Mkt2','Mkt3','Mkt4','Mkt5'],
'Category': ['Apple','Orange','Grape','Mango','Orange','Mango','Apple','Grape','Apple','Orange'],
'CategoryKey': ['Mkt1Apple','Mkt2Orange','Mkt3Grape','Mkt4Mango','Mkt5Orange','Mkt1Mango','Mkt2Apple','Mkt3Grape','Mkt4Apple','Mkt5Orange'],
'Current': [15,9,20,10,20,8,10,21,18,14],
'Goal': [50,35,21,44,20,24,14,29,28,19]
}
dataset = pd.DataFrame(d)
grouped = dataset.groupby('Category', as_index=False).sum()
data = grouped.to_dict(orient='list')
v_cat = grouped['Category'].tolist()
v_current = grouped['Current']
v_goal = grouped['Goal']
fig1 = px.bar(dataset, x = v_current, y = v_cat, orientation = 'h',
color_discrete_sequence = ["#ff0000"],height=10)
fig2 = px.bar(dataset, x = v_goal, y = v_cat, orientation = 'h',height=15)
trace1 = fig1['data'][0]
trace2 = fig2['data'][0]
fig = make_subplots(rows = 1, cols = 1, shared_xaxes=True, shared_yaxes=True)
fig.add_trace(trace2, 1, 1)
fig.add_trace(trace1, 1, 1)
fig.update_layout(barmode = 'overlay')
fig.show()
Here is the Output:
Question1: how do I make the width of v_current (shown in red bar) smaller? As in, it should be smaller in height since this is a horizontal bar. I added the height as 10 for trace1 and 15 for trace2, but they are still showing at the same heights.
Question2: Is there a way to make the v_goal (shown in blue bar) only show it's right edge, instead of a filled out bar? Something like this:
If you noticed, I also added a line under each of the category. Is there a quick way to add this as well? Not a deal breaker, just a bonus. Other things I'm trying to do is add animation, etc but that's for some other time!
Thanks in advance for answering!
Running plotly.express wil return a plotly.graph_objs._figure.Figure object. The same goes for plotly.graph_objects running go.Figure() together with, for example, go.Bar(). So after building a figure using plotly express, you can add lines or traces through references directly to the figure, like:
fig['data'][0].width = 0.4
Which is exactly what you need to set the width of your bars. And you can easily use this in combination with plotly express:
Code 1
fig = px.bar(grouped, y='Category', x = ['Current'],
orientation = 'h', barmode='overlay', opacity = 1,
color_discrete_sequence = px.colors.qualitative.Plotly[1:])
fig['data'][0].width = 0.4
Plot 1
In order to get the bars or shapes to indicate the goal levels, you can use the approach described by DerekO, or you can use:
for i, g in enumerate(grouped.Goal):
fig.add_shape(type="rect",
x0=g+1, y0=grouped.Category[i], x1=g, y1=grouped.Category[i],
line=dict(color='#636EFA', width = 28))
Complete code:
import plotly.express as px
from plotly.subplots import make_subplots
import plotly as py
import pandas as pd
from plotly import tools
d = {'Mkt_cd': ['Mkt1','Mkt2','Mkt3','Mkt4','Mkt5','Mkt1','Mkt2','Mkt3','Mkt4','Mkt5'],
'Category': ['Apple','Orange','Grape','Mango','Orange','Mango','Apple','Grape','Apple','Orange'],
'CategoryKey': ['Mkt1Apple','Mkt2Orange','Mkt3Grape','Mkt4Mango','Mkt5Orange','Mkt1Mango','Mkt2Apple','Mkt3Grape','Mkt4Apple','Mkt5Orange'],
'Current': [15,9,20,10,20,8,10,21,18,14],
'Goal': [50,35,21,44,20,24,14,29,28,19]
}
dataset = pd.DataFrame(d)
grouped = dataset.groupby('Category', as_index=False).sum()
fig = px.bar(grouped, y='Category', x = ['Current'],
orientation = 'h', barmode='overlay', opacity = 1,
color_discrete_sequence = px.colors.qualitative.Plotly[1:])
fig['data'][0].width = 0.4
fig['data'][0].marker.line.width = 0
for i, g in enumerate(grouped.Goal):
fig.add_shape(type="rect",
x0=g+1, y0=grouped.Category[i], x1=g, y1=grouped.Category[i],
line=dict(color='#636EFA', width = 28))
f = fig.full_figure_for_development(warn=False)
fig.show()
You can use Plotly Express and then directly access the figure object as #vestland described, but personally I prefer to use graph_objects to make all of the changes in one place.
I'll also point out that since you are stacking bars in one chart, you don't need subplots. You can create a graph_object with fig = go.Figure() and add traces to get stacked bars, similar to what you already did.
For question 1, if you are using go.Bar(), you can pass a width parameter. However, this is in units of the position axis, and since your y-axis is categorical, width=1 will fill the entire category, so I have chosen width=0.25 for the red bar, and width=0.3 (slightly larger) for the blue bar since that seems like it was your intention.
For question 2, the only thing that comes to mind is a hack. Split the bars into two sections (one with height = original height - 1), and set its opacity to 0 so that it is transparent. Then place down bars of height 1 on top of the transparent bars.
If you don't want the traces to show up in the legend, you can set this individually for each bar by passing showlegend=False to fig.add_trace, or hide the legend entirely by passing showlegend=False to the fig.update_layout method.
import plotly.express as px
import plotly.graph_objects as go
# from plotly.subplots import make_subplots
import plotly as py
import pandas as pd
from plotly import tools
d = {'Mkt_cd': ['Mkt1','Mkt2','Mkt3','Mkt4','Mkt5','Mkt1','Mkt2','Mkt3','Mkt4','Mkt5'],
'Category': ['Apple','Orange','Grape','Mango','Orange','Mango','Apple','Grape','Apple','Orange'],
'CategoryKey': ['Mkt1Apple','Mkt2Orange','Mkt3Grape','Mkt4Mango','Mkt5Orange','Mkt1Mango','Mkt2Apple','Mkt3Grape','Mkt4Apple','Mkt5Orange'],
'Current': [15,9,20,10,20,8,10,21,18,14],
'Goal': [50,35,21,44,20,24,14,29,28,19]
}
dataset = pd.DataFrame(d)
grouped = dataset.groupby('Category', as_index=False).sum()
data = grouped.to_dict(orient='list')
v_cat = grouped['Category'].tolist()
v_current = grouped['Current']
v_goal = grouped['Goal']
fig = go.Figure()
## you have a categorical plot and the units for width are in position axis units
## therefore width = 1 will take up the entire allotted space
## a width value of less than 1 will be the fraction of the allotted space
fig.add_trace(go.Bar(
x=v_current,
y=v_cat,
marker_color="#ff0000",
orientation='h',
width=0.25
))
## you can show the right edge of the bar by splitting it into two bars
## with the majority of the bar being transparent (opacity set to 0)
fig.add_trace(go.Bar(
x=v_goal-1,
y=v_cat,
marker_color="#ffffff",
opacity=0,
orientation='h',
width=0.30,
))
fig.add_trace(go.Bar(
x=[1]*len(v_cat),
y=v_cat,
marker_color="#1f77b4",
orientation='h',
width=0.30,
))
fig.update_layout(barmode='relative')
fig.show()
I use plotly package to show dynamic finance chart at python. However I didn't manage to put my all key points lines on one chart with for loop. Here is my code:
fig.update_layout(
for i in range(0,len(data)):
shapes=[
go.layout.Shape(
type="rect",
x0=data['Date'][i],
y0=data['Max_alt'][i],
x1='2019-12-31',
y1=data['Max_ust'][i],
fillcolor="LightSkyBlue",
opacity=0.5,
layer="below",
line_width=0)])
fig.show()
I have a data like below one. It is time series based EURUSD parity financial dataset. I calculated two constraits for both Local Min and Max. I wanted to draw rectangule shape to based on for each Min_alt / Min_ust and Max_alt / Max_range. I can draw for just one date like below image however I didn't manage to show all ranges in same plotly graph.
Here is the sample data set.
Here is the solution for added lines:
import datetime
colors = ["LightSkyBlue", "RoyalBlue", "forestgreen", "lightseagreen"]
ply_shapes = {}
for i in range(0, len(data1)):
ply_shapes['shape_' + str(i)]=go.layout.Shape(type="rect",
x0=data1['Date'][i].strftime('%Y-%m-%d'),
y0=data1['Max_alt'][i],
x1='2019-12-31',
y1=data1['Max_ust'][i],
fillcolor="LightSkyBlue",
opacity=0.5,
layer="below"
)
lst_shapes=list(ply_shapes.values())
fig1.update_layout(shapes=lst_shapes)
fig1.show()
However I have still problems to add traces to those lines. I mean text attribute.
Here is my code:
add_trace = {}
for i in range(0, len(data1)):
add_trace['scatter_' + str(i)] = go.Scatter(
x=['2019-12-31'],
y=[data1['Max_ust'][i]],
text=[str(data['Max_Label'][i])],
mode="text")
lst_trace = list(add_trace.values())
fig2=go.Figure(lst_trace)
fig2.show()
The answer:
For full control of each and every shape you insert, you could follow this logic:
fig = go.Figure()
#[...] data, traces and such
ply_shapes = {}
for i in range(1, len(df)):
ply_shapes['shape_' + str(i)]=go.layout.Shape()
lst_shapes=list(ply_shapes.values())
fig.update_layout(shapes=lst_shapes)
fig.show()
The details:
I'm not 100% sure what you're aimin to do here, but the following suggestion will answer your question quite literally regarding:
How to add more than one shape with loop in plotly?
Then you'll have to figure out the details regarding:
manage to put my all key points lines on one chart
Plot:
The plot itself is most likely not what you're looking for, but since you for some reason are adding a plot by the length of your data for i in range(0,len(data), I've made this:
Code:
This snippet will show how to handle all desired traces and shapes with for loops:
# Imports
import pandas as pd
#import matplotlib.pyplot as plt
import numpy as np
import plotly.graph_objects as go
#from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
# data, random sample to illustrate stocks
np.random.seed(12345)
rows = 20
x = pd.Series(np.random.randn(rows),index=pd.date_range('1/1/2020', periods=rows)).cumsum()
y = pd.Series(x-np.random.randn(rows)*5,index=pd.date_range('1/1/2020', periods=rows))
df = pd.concat([y,x], axis = 1)
df.columns = ['StockA', 'StockB']
# lines
df['keyPoints1']=np.random.randint(-5,5,len(df))
df['keyPoints2']=df['keyPoints1']*-1
# plotly traces
fig = go.Figure()
stocks = ['StockA', 'StockB']
df[stocks].tail()
traces = {}
for i in range(0, len(stocks)):
traces['trace_' + str(i)]=go.Scatter(x=df.index,
y=df[stocks[i]].values,
name=stocks[i])
data=list(traces.values())
fig=go.Figure(data)
# shapes update
colors = ["LightSkyBlue", "RoyalBlue", "forestgreen", "lightseagreen"]
ply_shapes = {}
for i in range(1, len(df)):
ply_shapes['shape_' + str(i)]=go.layout.Shape(type="line",
x0=df.index[i-1],
y0=df['keyPoints1'].iloc[i-1],
x1=df.index[i],
y1=df['keyPoints2'].iloc[i-1],
line=dict(
color=np.random.choice(colors,1)[0],
width=30),
opacity=0.5,
layer="below"
)
lst_shapes=list(ply_shapes.values())
fig.update_layout(shapes=lst_shapes)
fig.show()
Also you can use fig.add_{shape}:
fig = go.Figure()
fig.add_trace(
go.Scatter( ...)
for i in range( 1, len( vrect)):
fig.add_vrect(
x0=vrect.start.iloc[ i-1],
x1=vrect.finish.iloc[ i-1],
fillcolor=vrect.color.iloc[ i-1]],
opacity=0.25,
line_width=0)
fig.show()