Visualizations are getting duplicated when using ipywidgets in Python jupyter notebooks - python

This is the code that I am using to output a drop down and a visualization. However with the drop down the visualization duplicates when I select a value.
def common_filtering(year):
output.clear_output()
plot_output.clear_output()
common_filter = Top_Team(year)
with output:
display(common_filter)
with plot_output:
plt.ioff
test = common_filter.player_name.tolist()
x = [10,35,30,30,35,65,65,65,100,95,95]
y = [40,10,30,50,70,20,40,60,40,60,20]
plt.style.use('ggplot')
pitch = Pitch(pitch_type='statsbomb', orientation='vertical',
pitch_color='#22312b', line_color='#c7d5cc', figsize=(16, 20),
constrained_layout=True, tight_layout=False,axis = True,label = True)
fig, ax = pitch.draw()
sc = pitch.scatter(x, y,
color ='red',edgecolors = 'black',
s=40000, ax=ax)
for i,j,k in zip(x,y,test):
pitch.annotate(k, (i,j),c='white', va='top', ha='center', size=16, weight='bold', ax=ax)
fig.set_facecolor("#22312b")
display(fig)
def dropdown_year_eventhandler(change):
common_filtering(change.new)
dropdown_year.observe(
dropdown_year_eventhandler, names='value')
display(dropdown_year) -- This is where the drop down is seen and underneath the duplicated visualizations
This is where essentially the output should be coming from and it is.
display(plot_output)
display(output)

Related

How to plot geographic data with customized legend?

Having the geographic points with values, I would like to encode the values with colormap and customize the legend position and colormap range.
Using geopandas, I have written the following function:
def plot_continuous(df, column_values, title):
fig = plt.figure()
ax = fig.add_axes([0, 0, 1, 1])
ax.axis('off')
df.plot(ax=ax, column=column_values, cmap='OrRd', legend=True);
ax.title.set_text(title)
The colorbar by default is vertical, but I would like to make it horizontal.
In order to have a horizontal colorbar, I have written the following function:
def plot_continuous(df, column_values, title, legend_title=None):
fig = plt.figure()
ax = fig.add_axes([0, 0, 1, 1])
x = np.array(df.geometry.apply(lambda x: x.x))
y = np.array(df.geometry.apply(lambda x: x.y))
vals = np.array(df[column_values])
sc = ax.scatter(x, y, c=vals, cmap='OrRd')
cbar = plt.colorbar(sc, orientation="horizontal")
if legend_title is not None:
cbar.ax.set_xlabel(legend_title)
ax.title.set_text(title)
The image width and height in the latter case, however, is not proportional so the output looks distorted.
Does anyone know how to customize the geographic plot and keep the width-height ratio undistorted?
This gets far simpler if you use geopandas customisation of plot()
This is documented: https://geopandas.org/en/stable/docs/user_guide/mapping.html
Below I show MWE using your function and then using geopandas. Later has scaled data correctly.
MWE of your code
import geopandas as gpd
import matplotlib.pyplot as plt
import numpy as np
def plot_continuous(df, column_values, title, legend_title=None):
fig = plt.figure()
ax = fig.add_axes([0, 0, 1, 1])
x = np.array(df.geometry.apply(lambda x: x.x))
y = np.array(df.geometry.apply(lambda x: x.y))
vals = np.array(df[column_values])
sc = ax.scatter(x, y, c=vals, cmap='OrRd')
cbar = plt.colorbar(sc, orientation="horizontal")
if legend_title is not None:
cbar.ax.set_xlabel(legend_title)
ax.title.set_text(title)
cities = gpd.read_file(gpd.datasets.get_path("naturalearth_cities"))
cities["color"] = np.random.randint(1,10, len(cities))
plot_continuous(cities, "color", "my title", "Color")
use geopandas
ax = cities.plot(
column="color",
cmap="OrRd",
legend=True,
legend_kwds={"label": "Color", "orientation": "horizontal"},
)
ax.set_title("my title")

Visualizing the difference between two numeric arrays

I have two numeric arrays of equal length, with one array always having the element value >= to the corresponding (same index) element in the second array.
I am trying to visualize in a single graph:
i) difference between the corresponding elements,
ii) values of the corresponding elements in the two arrays.
I have tried plotting the CDF as below:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
arr1 = np.random.uniform(1,20,[25,1])
arr2 = arr1 + np.random.uniform(1,10,[25,1])
df1 = pd.DataFrame(arr1)
df2 = pd.DataFrame(arr2)
fix, ax = plt.subplots()
sns.kdeplot(df1[0], cumulative=True, color='orange', label='arr1')
sns.kdeplot(df2[0], cumulative=True, color='b', label='arr2')
sns.kdeplot(df2[0]-df1[0], cumulative=True, color='r', label='difference')
plt.show()
which gives the following output:
However, it does not capture the difference, and values of the corresponding elements together. For example, suppose the difference between two elements is 3. The two numbers can be 2 and 5, but they can also be 15 and 18, and this can not be determined from the CDF.
Which kind of plotting can visualize both the difference between the elements and the values of the elements?
I do not wish to line plot as below because not much statistical insights can be derived from the visualization.
ax.plot(df1[0])
ax.plot(df2[0])
ax.plot(df2[0]-df1[0])
There are lots of ways to show difference between two values. It really depends on your goal for the chart, how quantitative or qualitative you want to be, or if you want to show the raw data somehow. Here are a few ideas that come to mind that do not involve simple line plots or density functions. I strongly recommend the book Better Data Visualization by Johnathan Schwabish. He discusses interesting considerations regarding data presentation.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import ticker
arr1 = np.random.uniform(1,20, size=25)
arr2 = arr1 + np.random.uniform(1,10, size=25)
df = pd.DataFrame({
'col1' : arr1,
'col2' : arr2
})
df['diff'] = df.col2 - df.col1
df['sum'] = df.col1 + df.col2
fig, axes = plt.subplots(ncols=2, nrows=3, figsize=(15,15))
axes = axes.flatten()
# Pyramid chart
df_sorted = df.sort_values(by='sum', ascending=True)
axes[0].barh(
y = np.arange(1,26),
width = -df_sorted.col1
)
axes[0].barh(
y = np.arange(1,26),
width = df_sorted.col2
)
# Style axes[0]
style_func(axes[0], 'Pyramid Chart')
# Dot Plot
axes[1].scatter(df.col1, np.arange(1, 26), label='col1')
axes[1].scatter(df.col2, np.arange(1, 26), label='col2')
axes[1].hlines(
y = np.arange(1, 26),
xmin = df.col1, xmax = df.col2,
zorder=0, linewidth=1.5, color='k'
)
# Style axes[1]
legend = axes[1].legend(ncol=2, loc='center', bbox_to_anchor=(0.14,1.025), edgecolor='w')
style_func(axes[1], 'Dot Plot')
set_xlim = axes[1].set_xlim(0,25)
# Dot Plot 2
df_sorted = df.sort_values(by=['col1', 'diff'], ascending=False)
axes[2].scatter(df_sorted.col1, np.arange(1, 26), label='col1')
axes[2].scatter(df_sorted.col2, np.arange(1, 26), label='col2')
axes[2].hlines(
y = np.arange(1, 26),
xmin = df_sorted.col1, xmax = df_sorted.col2,
zorder=0, linewidth=1.5, color='k'
)
# Style axes[2]
legend = axes[2].legend(ncol=2, loc='center', bbox_to_anchor=(0.14,1.025), edgecolor='w')
style_func(axes[2], 'Dot Plot')
set_xlim = axes[2].set_xlim(0,25)
# Dot Plot 3
df_sorted = df.sort_values(by='sum', ascending=True)
axes[3].scatter(-df_sorted.col1, np.arange(1, 26), label='col1')
axes[3].scatter(df_sorted.col2, np.arange(1, 26), label='col2')
axes[3].vlines(x=0, ymin=-1, ymax=27, linewidth=2.5, color='k')
axes[3].hlines(
y = np.arange(1, 26),
xmin = -df_sorted.col1, xmax = df_sorted.col2,
zorder=0, linewidth=2
)
# Style axes[3]
legend = axes[3].legend(ncol=2, loc='center', bbox_to_anchor=(0.14,1.025), edgecolor='w')
style_func(axes[3], 'Dot Plot')
# Strip plot
axes[4].scatter(df.col1, [4] * 25)
axes[4].scatter(df.col2, [6] * 25)
axes[4].set_ylim(0, 10)
axes[4].vlines(
x = [df.col1.mean(), df.col2.mean()],
ymin = [3.5, 5.5], ymax=[4.5,6.5],
color='black', linewidth =2
)
# Style axes[4]
axes[4].yaxis.set_major_locator(ticker.FixedLocator([4,6]))
axes[4].yaxis.set_major_formatter(ticker.FixedFormatter(['col1','col2']))
hide_spines = [axes[4].spines[x].set_visible(False) for x in ['left','top','right']]
set_title = axes[4].set_title('Strip Plot', fontweight='bold')
tick_params = axes[4].tick_params(axis='y', left=False)
grid = axes[4].grid(axis='y', dashes=(8,3), alpha=0.3, color='gray')
# Slope chart
for i in range(25):
axes[5].plot([0,1], [df.col1[i], df.col2[i]], color='k')
align = ['left', 'right']
for i in range(1,3):
axes[5].text(x = i - 1, y = 0, s = 'col' + str(i),
fontsize=14, fontweight='bold', ha=align[i-1])
set_title = axes[5].set_title('Slope chart', fontweight='bold')
axes[5].axis('off')
def style_func(ax, title):
hide_spines = [ax.spines[x].set_visible(False) for x in ['left','top','right']]
set_title = ax.set_title(title, fontweight='bold')
set_xlim = ax.set_xlim(-25,25)
x_locator = ax.xaxis.set_major_locator(ticker.MultipleLocator(5))
y_locator = ax.yaxis.set_major_locator(ticker.FixedLocator(np.arange(1,26, 2)))
spine_width = ax.spines['bottom'].set_linewidth(1.5)
x_tick_params = ax.tick_params(axis='x', length=8, width=1.5)
x_tick_params = ax.tick_params(axis='y', left=False)
What about a parallel coordinates plot with plotly? This will allow to see the distinct values of each original array but then also if they converge on the same diffrence?
https://plot.ly/python/parallel-coordinates-plot/

For loop to create multiple histogram png files

I am not sure as to why this happens. Maybe it is just a simple mistake that I cannot see, but by using this code:
for filename in glob.glob('/Users/jacob/Desktop/MERS/new/NOT COAL/gensets/statistics_per_lgu/per_lgu_files/*.csv'):
base = os.path.basename(filename)
name = os.path.splitext(base)[0]
df = pd.read_csv(filename)
# Show 4 different binwidths
for i, binwidth in enumerate([10, 20, 30, 40]):
# Set up the plot
ax = plt.subplot(2, 2, i + 1)
plt.subplots_adjust( wspace=0.5, hspace=0.5)
# Draw the plot
ax.hist(df['New Capacity based on 0.8 PF'], bins=binwidth,
color='red', edgecolor='black',alpha=0.5)
# Title and labels
ax.set_title('Histogram with Binwidth = %d' % binwidth, size=10)
ax.set_xlabel('Capacity', size=11)
ax.set_ylabel('Frequency count', size=11)
ax.axvline(x=df['New Capacity based on 0.8 PF'].median(), linestyle='dashed', alpha=0.3, color='blue')
min_ylim, max_ylim = plt.ylim()
ax.text(x=df['New Capacity based on 0.8 PF'].median(),y= max_ylim*0.9, s='Median', alpha=0.7, color='blue',fontsize = 12)
ax.axvline(x=df['New Capacity based on 0.8 PF'].mean(), linestyle='dashed', alpha=0.9, color='green')
min_ylim, max_ylim = plt.ylim()
ax.text(x=df['New Capacity based on 0.8 PF'].mean(),y= max_ylim*0.5, s='Mean', alpha=0.9, color='green',fontsize = 12)
plt.tight_layout()
plt.grid(True)
plt.savefig('/Users/jacob/Documents/Gensets_gis/historgrams/per_lgu_files/{}.png'.format(name))
I get all files created like this attached photo here.
Any ideas as to what I've done wrong?
Thanks in advance.
attached photo of one histogram output
My desired result would be something like this.
Desired output
It doesn't create new subplots but it use previous ones and then it draw new plots on old plots so you have to use clear subplot before you draw new histogram.
ax = plt.subplot(2, 2, i + 1)
ax.clear()
Example code. It gives desired output but if you remove `ax.clear() then first image will be OK but you get new plot with old plots on second and third image.
import os
import pandas as pd
import matplotlib.pyplot as plt
import random
for n in range(3):
filename = f'example_data_{n}.csv'
base = os.path.basename(filename)
name = os.path.splitext(base)[0]
df = pd.DataFrame({'New Capacity based on 0.8 PF': random.choices(list(range(1000)), k=100)})
data = df['New Capacity based on 0.8 PF']
median = data.median()
mean = data.mean()
# Show 4 different binwidths
for i, binwidth in enumerate([10, 20, 30, 40]):
# Set up the plot
ax = plt.subplot(2,2,i+1)
ax.clear() # <--- it removes previous histogram
plt.subplots_adjust( wspace=0.5, hspace=0.5)
# Draw the plot
ax.hist(data , bins=binwidth, color='red', edgecolor='black',alpha=0.5)
# Title and labels
ax.set_title('Histogram with Binwidth = %d' % binwidth, size=10)
ax.set_xlabel('Capacity', size=11)
ax.set_ylabel('Frequency count', size=11)
min_ylim, max_ylim = plt.ylim()
ax.axvline(x=median, linestyle='dashed', alpha=0.3, color='blue')
ax.text(x=median, y= max_ylim*0.9, s='Median', alpha=0.7, color='blue',fontsize = 12)
ax.axvline(x=mean, linestyle='dashed', alpha=0.9, color='green')
ax.text(x=mean, y= max_ylim*0.5, s='Mean', alpha=0.9, color='green',fontsize = 12)
plt.tight_layout()
plt.grid(True)
plt.savefig('{}.png'.format(name))

Empty plot issue

As you can see in the picture attached when I execute my code I get two graphs and one of them is empty. I only need one so what is wrong with my code below?
kmf_par_modele = KaplanMeierFitter()
duration = iot_df_2.duree
observed = iot_df_2.batterie_0
fig, axes = plt.subplots(nrows = 1, ncols = 2, sharey = True, figsize=(12,15))
for modele_capteur, ax in zip(modele_capteur, axes.flatten()):
idx = iot_df_2.modele_objet == modele_capteur
kmf_par_modele.fit(duration[idx], observed[idx])
kmf_par_modele.plot(ax=ax, legend=False)
ax.annotate("Moyenne = {:.0f} mois".format(kmf_par_modele.median_), xy = (.47, .85), xycoords = "axes fraction")
ax.set_xlabel("")
ax.set_title(modele_capteur)
ax.set_xlim(0,25)
ax.set_ylim(0,1)
fig.tight_layout()
fig.text(0.5, -0.01, "Timeline (Mois)", ha="center")
fig.text(-0.01, 0.5, "Probabilité qu'un ERS_C02 ait toujours de la batterie", va="center", rotation="vertical")
fig.suptitle("Courbe de longévité pour le capteur ERS_C02",
fontsize=20)
fig.subplots_adjust(top=0.92)
plt.show()
As I mentioned in my comments, you just need to specify one single plot (subplot) if you only need one. I am answering because you don't need to flatten your axes instance because you just use a single figure. Here is how you can do it alternatively:
fig = plt.figure(figsize=(12,15))
ax = fig.add_subplot(111) # 111 means 1 row, 1 column ad 1st subplot (here only 1)
for modele_capteur in modele_capteur: # just loop over your modele_capteur
idx = iot_df_2.modele_objet == modele_capteur
kmf_par_modele.fit(duration[idx], observed[idx])
kmf_par_modele.plot(ax=ax, legend=False)
ax.annotate("Moyenne = {:.0f} mois".format(kmf_par_modele.median_), xy = (.47, .85), xycoords = "axes fraction")
ax.set_xlabel("")
ax.set_title(modele_capteur)
ax.set_xlim(0,25)
ax.set_ylim(0,1)

How to add hovering annotations to a plot

I am using matplotlib to make scatter plots. Each point on the scatter plot is associated with a named object. I would like to be able to see the name of an object when I hover my cursor over the point on the scatter plot associated with that object. In particular, it would be nice to be able to quickly see the names of the points that are outliers. The closest thing I have been able to find while searching here is the annotate command, but that appears to create a fixed label on the plot. Unfortunately, with the number of points that I have, the scatter plot would be unreadable if I labeled each point. Does anyone know of a way to create labels that only appear when the cursor hovers in the vicinity of that point?
It seems none of the other answers here actually answer the question. So here is a code that uses a scatter and shows an annotation upon hovering over the scatter points.
import matplotlib.pyplot as plt
import numpy as np; np.random.seed(1)
x = np.random.rand(15)
y = np.random.rand(15)
names = np.array(list("ABCDEFGHIJKLMNO"))
c = np.random.randint(1,5,size=15)
norm = plt.Normalize(1,4)
cmap = plt.cm.RdYlGn
fig,ax = plt.subplots()
sc = plt.scatter(x,y,c=c, s=100, cmap=cmap, norm=norm)
annot = ax.annotate("", xy=(0,0), xytext=(20,20),textcoords="offset points",
bbox=dict(boxstyle="round", fc="w"),
arrowprops=dict(arrowstyle="->"))
annot.set_visible(False)
def update_annot(ind):
pos = sc.get_offsets()[ind["ind"][0]]
annot.xy = pos
text = "{}, {}".format(" ".join(list(map(str,ind["ind"]))),
" ".join([names[n] for n in ind["ind"]]))
annot.set_text(text)
annot.get_bbox_patch().set_facecolor(cmap(norm(c[ind["ind"][0]])))
annot.get_bbox_patch().set_alpha(0.4)
def hover(event):
vis = annot.get_visible()
if event.inaxes == ax:
cont, ind = sc.contains(event)
if cont:
update_annot(ind)
annot.set_visible(True)
fig.canvas.draw_idle()
else:
if vis:
annot.set_visible(False)
fig.canvas.draw_idle()
fig.canvas.mpl_connect("motion_notify_event", hover)
plt.show()
Because people also want to use this solution for a line plot instead of a scatter, the following would be the same solution for plot (which works slightly differently).
import matplotlib.pyplot as plt
import numpy as np; np.random.seed(1)
x = np.sort(np.random.rand(15))
y = np.sort(np.random.rand(15))
names = np.array(list("ABCDEFGHIJKLMNO"))
norm = plt.Normalize(1,4)
cmap = plt.cm.RdYlGn
fig,ax = plt.subplots()
line, = plt.plot(x,y, marker="o")
annot = ax.annotate("", xy=(0,0), xytext=(-20,20),textcoords="offset points",
bbox=dict(boxstyle="round", fc="w"),
arrowprops=dict(arrowstyle="->"))
annot.set_visible(False)
def update_annot(ind):
x,y = line.get_data()
annot.xy = (x[ind["ind"][0]], y[ind["ind"][0]])
text = "{}, {}".format(" ".join(list(map(str,ind["ind"]))),
" ".join([names[n] for n in ind["ind"]]))
annot.set_text(text)
annot.get_bbox_patch().set_alpha(0.4)
def hover(event):
vis = annot.get_visible()
if event.inaxes == ax:
cont, ind = line.contains(event)
if cont:
update_annot(ind)
annot.set_visible(True)
fig.canvas.draw_idle()
else:
if vis:
annot.set_visible(False)
fig.canvas.draw_idle()
fig.canvas.mpl_connect("motion_notify_event", hover)
plt.show()
In case someone is looking for a solution for lines in twin axes, refer to How to make labels appear when hovering over a point in multiple axis?
In case someone is looking for a solution for bar plots, please refer to e.g. this answer.
This solution works when hovering a line without the need to click it:
import matplotlib.pyplot as plt
# Need to create as global variable so our callback(on_plot_hover) can access
fig = plt.figure()
plot = fig.add_subplot(111)
# create some curves
for i in range(4):
# Giving unique ids to each data member
plot.plot(
[i*1,i*2,i*3,i*4],
gid=i)
def on_plot_hover(event):
# Iterating over each data member plotted
for curve in plot.get_lines():
# Searching which data member corresponds to current mouse position
if curve.contains(event)[0]:
print("over %s" % curve.get_gid())
fig.canvas.mpl_connect('motion_notify_event', on_plot_hover)
plt.show()
From http://matplotlib.sourceforge.net/examples/event_handling/pick_event_demo.html :
from matplotlib.pyplot import figure, show
import numpy as npy
from numpy.random import rand
if 1: # picking on a scatter plot (matplotlib.collections.RegularPolyCollection)
x, y, c, s = rand(4, 100)
def onpick3(event):
ind = event.ind
print('onpick3 scatter:', ind, npy.take(x, ind), npy.take(y, ind))
fig = figure()
ax1 = fig.add_subplot(111)
col = ax1.scatter(x, y, 100*s, c, picker=True)
#fig.savefig('pscoll.eps')
fig.canvas.mpl_connect('pick_event', onpick3)
show()
This recipe draws an annotation on picking a data point: http://scipy-cookbook.readthedocs.io/items/Matplotlib_Interactive_Plotting.html .
This recipe draws a tooltip, but it requires wxPython:
Point and line tooltips in matplotlib?
The easiest option is to use the mplcursors package.
mplcursors: read the docs
mplcursors: github
If using Anaconda, install with these instructions, otherwise use these instructions for pip.
This must be plotted in an interactive window, not inline.
For jupyter, executing something like %matplotlib qt in a cell will turn on interactive plotting. See How can I open the interactive matplotlib window in IPython notebook?
Tested in python 3.10, pandas 1.4.2, matplotlib 3.5.1, seaborn 0.11.2
import matplotlib.pyplot as plt
import pandas_datareader as web # only for test data; must be installed with conda or pip
from mplcursors import cursor # separate package must be installed
# reproducible sample data as a pandas dataframe
df = web.DataReader('aapl', data_source='yahoo', start='2021-03-09', end='2022-06-13')
plt.figure(figsize=(12, 7))
plt.plot(df.index, df.Close)
cursor(hover=True)
plt.show()
Pandas
ax = df.plot(y='Close', figsize=(10, 7))
cursor(hover=True)
plt.show()
Seaborn
Works with axes-level plots like sns.lineplot, and figure-level plots like sns.relplot.
import seaborn as sns
# load sample data
tips = sns.load_dataset('tips')
sns.relplot(data=tips, x="total_bill", y="tip", hue="day", col="time")
cursor(hover=True)
plt.show()
The other answers did not address my need for properly showing tooltips in a recent version of Jupyter inline matplotlib figure. This one works though:
import matplotlib.pyplot as plt
import numpy as np
import mplcursors
np.random.seed(42)
fig, ax = plt.subplots()
ax.scatter(*np.random.random((2, 26)))
ax.set_title("Mouse over a point")
crs = mplcursors.cursor(ax,hover=True)
crs.connect("add", lambda sel: sel.annotation.set_text(
'Point {},{}'.format(sel.target[0], sel.target[1])))
plt.show()
Leading to something like the following picture when going over a point with mouse:
A slight edit on an example provided in http://matplotlib.org/users/shell.html:
import numpy as np
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.set_title('click on points')
line, = ax.plot(np.random.rand(100), '-', picker=5) # 5 points tolerance
def onpick(event):
thisline = event.artist
xdata = thisline.get_xdata()
ydata = thisline.get_ydata()
ind = event.ind
print('onpick points:', *zip(xdata[ind], ydata[ind]))
fig.canvas.mpl_connect('pick_event', onpick)
plt.show()
This plots a straight line plot, as Sohaib was asking
mpld3 solve it for me.
EDIT (CODE ADDED):
import matplotlib.pyplot as plt
import numpy as np
import mpld3
fig, ax = plt.subplots(subplot_kw=dict(axisbg='#EEEEEE'))
N = 100
scatter = ax.scatter(np.random.normal(size=N),
np.random.normal(size=N),
c=np.random.random(size=N),
s=1000 * np.random.random(size=N),
alpha=0.3,
cmap=plt.cm.jet)
ax.grid(color='white', linestyle='solid')
ax.set_title("Scatter Plot (with tooltips!)", size=20)
labels = ['point {0}'.format(i + 1) for i in range(N)]
tooltip = mpld3.plugins.PointLabelTooltip(scatter, labels=labels)
mpld3.plugins.connect(fig, tooltip)
mpld3.show()
You can check this example
mplcursors worked for me. mplcursors provides clickable annotation for matplotlib. It is heavily inspired from mpldatacursor (https://github.com/joferkington/mpldatacursor), with a much simplified API
import matplotlib.pyplot as plt
import numpy as np
import mplcursors
data = np.outer(range(10), range(1, 5))
fig, ax = plt.subplots()
lines = ax.plot(data)
ax.set_title("Click somewhere on a line.\nRight-click to deselect.\n"
"Annotations can be dragged.")
mplcursors.cursor(lines) # or just mplcursors.cursor()
plt.show()
showing object information in matplotlib statusbar
Features
no extra libraries needed
clean plot
no overlap of labels and artists
supports multi artist labeling
can handle artists from different plotting calls (like scatter, plot, add_patch)
code in library style
Code
### imports
import matplotlib as mpl
import matplotlib.pylab as plt
import numpy as np
# https://stackoverflow.com/a/47166787/7128154
# https://matplotlib.org/3.3.3/api/collections_api.html#matplotlib.collections.PathCollection
# https://matplotlib.org/3.3.3/api/path_api.html#matplotlib.path.Path
# https://stackoverflow.com/questions/15876011/add-information-to-matplotlib-navigation-toolbar-status-bar
# https://stackoverflow.com/questions/36730261/matplotlib-path-contains-point
# https://stackoverflow.com/a/36335048/7128154
class StatusbarHoverManager:
"""
Manage hover information for mpl.axes.Axes object based on appearing
artists.
Attributes
----------
ax : mpl.axes.Axes
subplot to show status information
artists : list of mpl.artist.Artist
elements on the subplot, which react to mouse over
labels : list (list of strings) or strings
each element on the top level corresponds to an artist.
if the artist has items
(i.e. second return value of contains() has key 'ind'),
the element has to be of type list.
otherwise the element if of type string
cid : to reconnect motion_notify_event
"""
def __init__(self, ax):
assert isinstance(ax, mpl.axes.Axes)
def hover(event):
if event.inaxes != ax:
return
info = 'x={:.2f}, y={:.2f}'.format(event.xdata, event.ydata)
ax.format_coord = lambda x, y: info
cid = ax.figure.canvas.mpl_connect("motion_notify_event", hover)
self.ax = ax
self.cid = cid
self.artists = []
self.labels = []
def add_artist_labels(self, artist, label):
if isinstance(artist, list):
assert len(artist) == 1
artist = artist[0]
self.artists += [artist]
self.labels += [label]
def hover(event):
if event.inaxes != self.ax:
return
info = 'x={:.2f}, y={:.2f}'.format(event.xdata, event.ydata)
for aa, artist in enumerate(self.artists):
cont, dct = artist.contains(event)
if not cont:
continue
inds = dct.get('ind')
if inds is not None: # artist contains items
for ii in inds:
lbl = self.labels[aa][ii]
info += '; artist [{:d}, {:d}]: {:}'.format(
aa, ii, lbl)
else:
lbl = self.labels[aa]
info += '; artist [{:d}]: {:}'.format(aa, lbl)
self.ax.format_coord = lambda x, y: info
self.ax.figure.canvas.mpl_disconnect(self.cid)
self.cid = self.ax.figure.canvas.mpl_connect(
"motion_notify_event", hover)
def demo_StatusbarHoverManager():
fig, ax = plt.subplots()
shm = StatusbarHoverManager(ax)
poly = mpl.patches.Polygon(
[[0,0], [3, 5], [5, 4], [6,1]], closed=True, color='green', zorder=0)
artist = ax.add_patch(poly)
shm.add_artist_labels(artist, 'polygon')
artist = ax.scatter([2.5, 1, 2, 3], [6, 1, 1, 7], c='blue', s=10**2)
lbls = ['point ' + str(ii) for ii in range(4)]
shm.add_artist_labels(artist, lbls)
artist = ax.plot(
[0, 0, 1, 5, 3], [0, 1, 1, 0, 2], marker='o', color='red')
lbls = ['segment ' + str(ii) for ii in range(5)]
shm.add_artist_labels(artist, lbls)
plt.show()
# --- main
if __name__== "__main__":
demo_StatusbarHoverManager()
I have made a multi-line annotation system to add to: https://stackoverflow.com/a/47166787/10302020.
for the most up to date version:
https://github.com/AidenBurgess/MultiAnnotationLineGraph
Simply change the data in the bottom section.
import matplotlib.pyplot as plt
def update_annot(ind, line, annot, ydata):
x, y = line.get_data()
annot.xy = (x[ind["ind"][0]], y[ind["ind"][0]])
# Get x and y values, then format them to be displayed
x_values = " ".join(list(map(str, ind["ind"])))
y_values = " ".join(str(ydata[n]) for n in ind["ind"])
text = "{}, {}".format(x_values, y_values)
annot.set_text(text)
annot.get_bbox_patch().set_alpha(0.4)
def hover(event, line_info):
line, annot, ydata = line_info
vis = annot.get_visible()
if event.inaxes == ax:
# Draw annotations if cursor in right position
cont, ind = line.contains(event)
if cont:
update_annot(ind, line, annot, ydata)
annot.set_visible(True)
fig.canvas.draw_idle()
else:
# Don't draw annotations
if vis:
annot.set_visible(False)
fig.canvas.draw_idle()
def plot_line(x, y):
line, = plt.plot(x, y, marker="o")
# Annotation style may be changed here
annot = ax.annotate("", xy=(0, 0), xytext=(-20, 20), textcoords="offset points",
bbox=dict(boxstyle="round", fc="w"),
arrowprops=dict(arrowstyle="->"))
annot.set_visible(False)
line_info = [line, annot, y]
fig.canvas.mpl_connect("motion_notify_event",
lambda event: hover(event, line_info))
# Your data values to plot
x1 = range(21)
y1 = range(0, 21)
x2 = range(21)
y2 = range(0, 42, 2)
# Plot line graphs
fig, ax = plt.subplots()
plot_line(x1, y1)
plot_line(x2, y2)
plt.show()
Based off Markus Dutschke" and "ImportanceOfBeingErnest", I (imo) simplified the code and made it more modular.
Also this doesn't require additional packages to be installed.
import matplotlib.pylab as plt
import numpy as np
plt.close('all')
fh, ax = plt.subplots()
#Generate some data
y,x = np.histogram(np.random.randn(10000), bins=500)
x = x[:-1]
colors = ['#0000ff', '#00ff00','#ff0000']
x2, y2 = x,y/10
x3, y3 = x, np.random.randn(500)*10+40
#Plot
h1 = ax.plot(x, y, color=colors[0])
h2 = ax.plot(x2, y2, color=colors[1])
h3 = ax.scatter(x3, y3, color=colors[2], s=1)
artists = h1 + h2 + [h3] #concatenating lists
labels = [list('ABCDE'*100),list('FGHIJ'*100),list('klmno'*100)] #define labels shown
#___ Initialize annotation arrow
annot = ax.annotate("", xy=(0,0), xytext=(20,20),textcoords="offset points",
bbox=dict(boxstyle="round", fc="w"),
arrowprops=dict(arrowstyle="->"))
annot.set_visible(False)
def on_plot_hover(event):
if event.inaxes != ax: #exit if mouse is not on figure
return
is_vis = annot.get_visible() #check if an annotation is visible
# x,y = event.xdata,event.ydata #coordinates of mouse in graph
for ii, artist in enumerate(artists):
is_contained, dct = artist.contains(event)
if(is_contained):
if('get_data' in dir(artist)): #for plot
data = list(zip(*artist.get_data()))
elif('get_offsets' in dir(artist)): #for scatter
data = artist.get_offsets().data
inds = dct['ind'] #get which data-index is under the mouse
#___ Set Annotation settings
xy = data[inds[0]] #get 1st position only
annot.xy = xy
annot.set_text(f'pos={xy},text={labels[ii][inds[0]]}')
annot.get_bbox_patch().set_edgecolor(colors[ii])
annot.get_bbox_patch().set_alpha(0.7)
annot.set_visible(True)
fh.canvas.draw_idle()
else:
if is_vis:
annot.set_visible(False) #disable when not hovering
fh.canvas.draw_idle()
fh.canvas.mpl_connect('motion_notify_event', on_plot_hover)
Giving the following result:
Maybe this helps anybody, but I have adapted the #ImportanceOfBeingErnest's answer to work with patches and classes. Features:
The entire framework is contained inside of a single class, so all of the used variables are only available within their relevant scopes.
Can create multiple distinct sets of patches
Hovering over a patch prints patch collection name and patch subname
Hovering over a patch highlights all patches of that collection by changing their edge color to black
Note: For my applications, the overlap is not relevant, thus only one object's name is displayed at a time. Feel free to extend to multiple objects if you wish, it is not too hard.
Usage
fig, ax = plt.subplots(tight_layout=True)
ap = annotated_patches(fig, ax)
ap.add_patches('Azure', 'circle', 'blue', np.random.uniform(0, 1, (4,2)), 'ABCD', 0.1)
ap.add_patches('Lava', 'rect', 'red', np.random.uniform(0, 1, (3,2)), 'EFG', 0.1, 0.05)
ap.add_patches('Emerald', 'rect', 'green', np.random.uniform(0, 1, (3,2)), 'HIJ', 0.05, 0.1)
plt.axis('equal')
plt.axis('off')
plt.show()
Implementation
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
from matplotlib.collections import PatchCollection
np.random.seed(1)
class annotated_patches:
def __init__(self, fig, ax):
self.fig = fig
self.ax = ax
self.annot = self.ax.annotate("", xy=(0,0),
xytext=(20,20),
textcoords="offset points",
bbox=dict(boxstyle="round", fc="w"),
arrowprops=dict(arrowstyle="->"))
self.annot.set_visible(False)
self.collectionsDict = {}
self.coordsDict = {}
self.namesDict = {}
self.isActiveDict = {}
self.motionCallbackID = self.fig.canvas.mpl_connect("motion_notify_event", self.hover)
def add_patches(self, groupName, kind, color, xyCoords, names, *params):
if kind=='circle':
circles = [mpatches.Circle(xy, *params, ec="none") for xy in xyCoords]
thisCollection = PatchCollection(circles, facecolor=color, alpha=0.5, edgecolor=None)
ax.add_collection(thisCollection)
elif kind == 'rect':
rectangles = [mpatches.Rectangle(xy, *params, ec="none") for xy in xyCoords]
thisCollection = PatchCollection(rectangles, facecolor=color, alpha=0.5, edgecolor=None)
ax.add_collection(thisCollection)
else:
raise ValueError('Unexpected kind', kind)
self.collectionsDict[groupName] = thisCollection
self.coordsDict[groupName] = xyCoords
self.namesDict[groupName] = names
self.isActiveDict[groupName] = False
def update_annot(self, groupName, patchIdxs):
self.annot.xy = self.coordsDict[groupName][patchIdxs[0]]
self.annot.set_text(groupName + ': ' + self.namesDict[groupName][patchIdxs[0]])
# Set edge color
self.collectionsDict[groupName].set_edgecolor('black')
self.isActiveDict[groupName] = True
def hover(self, event):
vis = self.annot.get_visible()
updatedAny = False
if event.inaxes == self.ax:
for groupName, collection in self.collectionsDict.items():
cont, ind = collection.contains(event)
if cont:
self.update_annot(groupName, ind["ind"])
self.annot.set_visible(True)
self.fig.canvas.draw_idle()
updatedAny = True
else:
if self.isActiveDict[groupName]:
collection.set_edgecolor(None)
self.isActiveDict[groupName] = True
if (not updatedAny) and vis:
self.annot.set_visible(False)
self.fig.canvas.draw_idle()

Categories