Continuous error band with Plotly Express in Python [duplicate] - python

This question already has answers here:
Plotly: How to make a figure with multiple lines and shaded area for standard deviations?
(4 answers)
Closed 1 year ago.
I need to plot data with continuous error bands. I would like to use Plotly Express in the same way as plotly.express.scatter, but instead of error bars to get continuous error bands. With "continuous error bands" I am talking about this:

I wrote the following function to extend plotly.express.line with the same high level interface of Plotly Express. In case it is useful to other people, this is the function:
import plotly.express as px
import plotly.graph_objs as go
def line(error_y_mode=None, **kwargs):
"""Extension of `plotly.express.line` to use error bands."""
ERROR_MODES = {'bar','band','bars','bands',None}
if error_y_mode not in ERROR_MODES:
raise ValueError(f"'error_y_mode' must be one of {ERROR_MODES}, received {repr(error_y_mode)}.")
if error_y_mode in {'bar','bars',None}:
fig = px.line(**kwargs)
elif error_y_mode in {'band','bands'}:
if 'error_y' not in kwargs:
raise ValueError(f"If you provide argument 'error_y_mode' you must also provide 'error_y'.")
figure_with_error_bars = px.line(**kwargs)
fig = px.line(**{arg: val for arg,val in kwargs.items() if arg != 'error_y'})
for data in figure_with_error_bars.data:
x = list(data['x'])
y_upper = list(data['y'] + data['error_y']['array'])
y_lower = list(data['y'] - data['error_y']['array'] if data['error_y']['arrayminus'] is None else data['y'] - data['error_y']['arrayminus'])
color = f"rgba({tuple(int(data['line']['color'].lstrip('#')[i:i+2], 16) for i in (0, 2, 4))},.3)".replace('((','(').replace('),',',').replace(' ','')
fig.add_trace(
go.Scatter(
x = x+x[::-1],
y = y_upper+y_lower[::-1],
fill = 'toself',
fillcolor = color,
line = dict(
color = 'rgba(255,255,255,0)'
),
hoverinfo = "skip",
showlegend = False,
legendgroup = data['legendgroup'],
xaxis = data['xaxis'],
yaxis = data['yaxis'],
)
)
# Reorder data as said here: https://stackoverflow.com/a/66854398/8849755
reordered_data = []
for i in range(int(len(fig.data)/2)):
reordered_data.append(fig.data[i+int(len(fig.data)/2)])
reordered_data.append(fig.data[i])
fig.data = tuple(reordered_data)
return fig
and this is an usage example:
import plotly.express as px
import pandas
df = px.data.gapminder().query('continent=="Americas"')
df = df[df['country'].isin({'Argentina','Brazil','Colombia'})]
df['lifeExp std'] = df['lifeExp']*.1 # Invent some error data...
for error_y_mode in {'band', 'bar'}:
fig = line(
data_frame = df,
x = 'year',
y = 'lifeExp',
error_y = 'lifeExp std',
error_y_mode = error_y_mode,
color = 'country',
title = f'Using error {error_y_mode}',
markers = '.',
)
fig.show()
which should produce the following two plots:

Related

How to highlight a single data point on a scatter plot using plotly express

In a scatter plot created using px.scatter, how do I mark one data point with a red star?
fig = px.scatter(df, x="sepal_width", y="sepal_length")
# Now set a single data point to color="red", symbol="star".
This isn't really highlighting an already existing data point within a trace you've already produced, but rather adding another one with a different visual appearance. But it does exactly what you're looking for:
fig.add_trace(go.Scatter(x=[3.5], y=[6.5], mode = 'markers',
marker_symbol = 'star',
marker_size = 15))
Plot:
Complete code:
import plotly.express as px
import pandas as pd
import plotly.graph_objects as go
df = px.data.iris() # iris is a pandas DataFrame
fig = px.scatter(df, x="sepal_width", y="sepal_length")
fig.add_trace(go.Scatter(x=[3.5], y=[6.5], mode = 'markers',
marker_symbol = 'star',
marker_size = 15))
fig.show()
This directly modifies the Scatter trace's Marker itself:
import plotly.express as px
df = px.data.iris()
fig = px.scatter(df, x="sepal_width", y="sepal_length")
trace = next(fig.select_traces())
# Modify kth point.
n = len(trace.x)
k = 136
color = [trace.marker.color] * n
color[k] = "red"
size = [8] * n
size[k] = 15
symbol = [trace.marker.symbol] * n
symbol[k] = "star"
# Update trace.
trace.marker.color = color
trace.marker.size = size
trace.marker.symbol = symbol
# Alternatively, call:
# fig.update_traces(marker=dict(color=color, size=size, symbol=symbol))
fig.show()

How to create secondary y-axes from a plotly express facetted figure?

I would like to modify a facetted plotly.express figure so that each trace has its own secondary y-axis. I don't want to re-create the figure from scratch using the standard Plotly-python api if possible. See exmaple below.
import plotly.express as px
input_df = px.data.tips()
fig = px.scatter(input_df,
x = 'total_bill',
y = 'tip',
color = 'day',
facet_row = 'smoker',
facet_col = 'sex',
)
fig.layout.width = 800
fig.show()
I would like to convert the above so each trace (or color) has its own secondary y-axis. So in this case, I would like 3 additional y-axes for each facet. This is my attempt but it doesn't work. There must be a better way. I would appreciate any ideas.
import plotly.graph_objects as go
yaxes = []
for trace in fig.data:
yaxisLabel = trace['yaxis']
if trace['yaxis'] in yaxes:
if yaxisLabel == 'y':
axisnumber = 0
else:
axisnumber = int(trace['yaxis'][1:])
newAxis_num = axisnumber + 100 * yaxes.count(yaxisLabel)
exec(f"fig.layout.update(yaxis{newAxis_num} = go.layout.YAxis(overlaying='y', side='right'))")
trace.update({'yaxis': f'y{newAxis_num}'})
yaxes.append(yaxisLabel)

Plotly: How to annotate end of multiple lines with text and marker colors that match the lines?

The post Plotly: Annotate marker at the last value in line chart
shows how to annotate end of lines with text and an individual marker. But how can you do the same thing for multiple lines and at the same time set the associated text and markers to match the color of all lines?
Example plot:
Code with sample dataset:
# imports
import pandas as pd
import plotly.express as px
# data
df = px.data.stocks()
colors = px.colors.qualitative.T10
# plotly
fig = px.line(df,
x = 'date',
y = [c for c in df.columns if c != 'date'],
template = 'plotly_dark',
color_discrete_sequence = colors,
title = 'Stocks',
)
fig.show()
You can address the features of each trace and build new traces for your end markers and text through:
for i, d in enumerate(fig.data):
fig.add_scatter(x=[d.x[-1]], y = [d.y[-1]], [...])
If you've specified colors when building your figure you can also retrieve trace colors and set colors for markers and fonts like this:
textfont = dict(color=d.line.color),
marker = dict(color = d.line.color, size = 12)
Plot:
The figure was being a bit crowded so I dropped one of the stocks. I also made room for the annotations by changing the position of the legend through fig.layout.legend.x = -0.3
Complete code:
# imports
import pandas as pd
import plotly.express as px
# data
df = px.data.stocks()
df = df.drop('AMZN', axis = 1)
colors = px.colors.qualitative.T10
# plotly
fig = px.line(df,
x = 'date',
y = [c for c in df.columns if c != 'date'],
template = 'plotly_dark',
color_discrete_sequence = colors,
title = 'Stocks',
)
# move legend
fig.layout.legend.x = -0.3
# add traces for annotations and text for end of lines
for i, d in enumerate(fig.data):
fig.add_scatter(x=[d.x[-1]], y = [d.y[-1]],
mode = 'markers+text',
text = d.y[-1],
textfont = dict(color=d.line.color),
textposition='middle right',
marker = dict(color = d.line.color, size = 12),
legendgroup = d.name,
showlegend=False)
fig.show()

how to plot a range with a line in the center with Plotly, in Python [duplicate]

How can I use Plotly to produce a line plot with a shaded standard deviation? I am trying to achieve something similar to seaborn.tsplot. Any help is appreciated.
The following approach is fully flexible with regards to the number of columns in a pandas dataframe and uses the default color cycle of plotly. If the number of lines exceed the number of colors, the colors will be re-used from the start. As of now px.colors.qualitative.Plotly can be replaced with any hex color sequence that you can find using px.colors.qualitative:
Alphabet = ['#AA0DFE', '#3283FE', '#85660D', '#782AB6', '#565656', '#1...
Alphabet_r = ['#FA0087', '#FBE426', '#B00068', '#FC1CBF', '#C075A6', '...
[...]
Complete code:
# imports
import plotly.graph_objs as go
import plotly.express as px
import pandas as pd
import numpy as np
# sample data in a pandas dataframe
np.random.seed(1)
df=pd.DataFrame(dict(A=np.random.uniform(low=-1, high=2, size=25).tolist(),
B=np.random.uniform(low=-4, high=3, size=25).tolist(),
C=np.random.uniform(low=-1, high=3, size=25).tolist(),
))
df = df.cumsum()
# define colors as a list
colors = px.colors.qualitative.Plotly
# convert plotly hex colors to rgba to enable transparency adjustments
def hex_rgba(hex, transparency):
col_hex = hex.lstrip('#')
col_rgb = list(int(col_hex[i:i+2], 16) for i in (0, 2, 4))
col_rgb.extend([transparency])
areacol = tuple(col_rgb)
return areacol
rgba = [hex_rgba(c, transparency=0.2) for c in colors]
colCycle = ['rgba'+str(elem) for elem in rgba]
# Make sure the colors run in cycles if there are more lines than colors
def next_col(cols):
while True:
for col in cols:
yield col
line_color=next_col(cols=colCycle)
# plotly figure
fig = go.Figure()
# add line and shaded area for each series and standards deviation
for i, col in enumerate(df):
new_col = next(line_color)
x = list(df.index.values+1)
y1 = df[col]
y1_upper = [(y + np.std(df[col])) for y in df[col]]
y1_lower = [(y - np.std(df[col])) for y in df[col]]
y1_lower = y1_lower[::-1]
# standard deviation area
fig.add_traces(go.Scatter(x=x+x[::-1],
y=y1_upper+y1_lower,
fill='tozerox',
fillcolor=new_col,
line=dict(color='rgba(255,255,255,0)'),
showlegend=False,
name=col))
# line trace
fig.add_traces(go.Scatter(x=x,
y=y1,
line=dict(color=new_col, width=2.5),
mode='lines',
name=col)
)
# set x-axis
fig.update_layout(xaxis=dict(range=[1,len(df)]))
fig.show()
I was able to come up with something similar. I post the code here to be used by someone else or for any suggestions for improvements.
import matplotlib
import random
import plotly.graph_objects as go
import numpy as np
#random color generation in plotly
hex_colors_dic = {}
rgb_colors_dic = {}
hex_colors_only = []
for name, hex in matplotlib.colors.cnames.items():
hex_colors_only.append(hex)
hex_colors_dic[name] = hex
rgb_colors_dic[name] = matplotlib.colors.to_rgb(hex)
data = [[1, 3, 5, 4],
[2, 3, 5, 4],
[1, 1, 4, 5],
[2, 3, 5, 4]]
#calculating mean and standard deviation
mean=np.mean(data,axis=0)
std=np.std(data,axis=0)
#draw figure
fig = go.Figure()
c = random.choice(hex_colors_only)
fig.add_trace(go.Scatter(x=np.arange(4), y=mean+std,
mode='lines',
line=dict(color=c,width =0.1),
name='upper bound'))
fig.add_trace(go.Scatter(x=np.arange(4), y=mean,
mode='lines',
line=dict(color=c),
fill='tonexty',
name='mean'))
fig.add_trace(go.Scatter(x=np.arange(4), y=mean-std,
mode='lines',
line=dict(color=c, width =0.1),
fill='tonexty',
name='lower bound'))
fig.show()
Great custom responses posted by others. In case someone is interested in code from the official plotly website, see here: https://plotly.com/python/continuous-error-bars/
I wrote a function to extend plotly.express.line with the same high level interface of Plotly Express. The line function (source code below) is used in the same exact way as plotly.express.line but allows for continuous error bands with the flag argument error_y_mode which can be either 'band' or 'bar'. In the second case it produces the same result as the original plotly.express.line. Here is an usage example:
import plotly.express as px
df = px.data.gapminder().query('continent=="Americas"')
df = df[df['country'].isin({'Argentina','Brazil','Colombia'})]
df['lifeExp std'] = df['lifeExp']*.1 # Invent some error data...
for error_y_mode in {'band', 'bar'}:
fig = line(
data_frame = df,
x = 'year',
y = 'lifeExp',
error_y = 'lifeExp std',
error_y_mode = error_y_mode, # Here you say `band` or `bar`.
color = 'country',
title = f'Using error {error_y_mode}',
markers = '.',
)
fig.show()
which produces the following two plots:
The source code of the line function that extends plotly.express.line is this:
import plotly.express as px
import plotly.graph_objs as go
def line(error_y_mode=None, **kwargs):
"""Extension of `plotly.express.line` to use error bands."""
ERROR_MODES = {'bar','band','bars','bands',None}
if error_y_mode not in ERROR_MODES:
raise ValueError(f"'error_y_mode' must be one of {ERROR_MODES}, received {repr(error_y_mode)}.")
if error_y_mode in {'bar','bars',None}:
fig = px.line(**kwargs)
elif error_y_mode in {'band','bands'}:
if 'error_y' not in kwargs:
raise ValueError(f"If you provide argument 'error_y_mode' you must also provide 'error_y'.")
figure_with_error_bars = px.line(**kwargs)
fig = px.line(**{arg: val for arg,val in kwargs.items() if arg != 'error_y'})
for data in figure_with_error_bars.data:
x = list(data['x'])
y_upper = list(data['y'] + data['error_y']['array'])
y_lower = list(data['y'] - data['error_y']['array'] if data['error_y']['arrayminus'] is None else data['y'] - data['error_y']['arrayminus'])
color = f"rgba({tuple(int(data['line']['color'].lstrip('#')[i:i+2], 16) for i in (0, 2, 4))},.3)".replace('((','(').replace('),',',').replace(' ','')
fig.add_trace(
go.Scatter(
x = x+x[::-1],
y = y_upper+y_lower[::-1],
fill = 'toself',
fillcolor = color,
line = dict(
color = 'rgba(255,255,255,0)'
),
hoverinfo = "skip",
showlegend = False,
legendgroup = data['legendgroup'],
xaxis = data['xaxis'],
yaxis = data['yaxis'],
)
)
# Reorder data as said here: https://stackoverflow.com/a/66854398/8849755
reordered_data = []
for i in range(int(len(fig.data)/2)):
reordered_data.append(fig.data[i+int(len(fig.data)/2)])
reordered_data.append(fig.data[i])
fig.data = tuple(reordered_data)
return fig

Making a Legend in a Scattergeo Plot in Plotly

I'm plotting some data similar to the first example found here (the US airports map). However, rather than plotting a scale I'm plotting binary features (let's say one color is over 15k flights and one color is under 15k flights). I've looked at the documentation but can't find a way to do a legend if I wanted to do this sort of plot. Does anyone know how?
You could specify the color according to your condition, e.g.
color = np.where(df['Set'] > 15000, 'red', 'green')
but then you wouldn't have a nice legend.
An alternative approach would be to add two plots, one for each condition.
import pandas as pd
import plotly
df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/2011_february_us_airport_traffic.csv')
data = dict(
type = 'scattergeo',
locationmode = 'USA-states',
mode = 'markers'
)
data_high = data.copy()
data_high['lon'] = df[df['cnt'] > 10000 ]['long']
data_high['lat'] = df[df['cnt'] > 10000 ]['lat']
data_high['marker'] = dict(color = 'red')
data_high['name'] = '> 10000'
data_low = data.copy()
data_low['lon'] = df[df['cnt'] <= 10000 ]['long']
data_low['lat'] = df[df['cnt'] <= 10000 ]['lat']
data_low['marker'] = dict(color = 'green')
data_low['name'] = '<= 10000'
layout = dict(
geo = dict(
scope = 'usa',
projection = dict(type='albers usa'),
),
)
fig = dict(data=[data_high, data_low], layout=layout)
plotly.offline.plot(fig)

Categories