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()
I am trying to go a step further by creating a radar plot like this question states. I using the same source code that the previous question was using, except I'm trying to implement this using pandas dataframe and pivot tables.
import numpy as np
import pandas as pd
from StringIO import StringIO
import matplotlib.pyplot as plt
from matplotlib.projections.polar import PolarAxes
from matplotlib.projections import register_projection
def radar_factory(num_vars, frame='circle'):
"""Create a radar chart with `num_vars` axes."""
# calculate evenly-spaced axis angles
theta = 2 * np.pi * np.linspace(0, 1 - 1. / num_vars, num_vars)
# rotate theta such that the first axis is at the top
theta += np.pi / 2
def draw_poly_frame(self, x0, y0, r):
# TODO: use transforms to convert (x, y) to (r, theta)
verts = [(r * np.cos(t) + x0, r * np.sin(t) + y0) for t in theta]
return plt.Polygon(verts, closed=True, edgecolor='k')
def draw_circle_frame(self, x0, y0, r):
return plt.Circle((x0, y0), r)
frame_dict = {'polygon': draw_poly_frame, 'circle': draw_circle_frame}
if frame not in frame_dict:
raise ValueError, 'unknown value for `frame`: %s' % frame
class RadarAxes(PolarAxes):
"""Class for creating a radar chart (a.k.a. a spider or star chart)
http://en.wikipedia.org/wiki/Radar_chart
"""
name = 'radar'
# use 1 line segment to connect specified points
RESOLUTION = 1
# define draw_frame method
draw_frame = frame_dict[frame]
def fill(self, *args, **kwargs):
"""Override fill so that line is closed by default"""
closed = kwargs.pop('closed', True)
return super(RadarAxes, self).fill(closed=closed, *args, **kwargs)
def plot(self, *args, **kwargs):
"""Override plot so that line is closed by default"""
lines = super(RadarAxes, self).plot(*args, **kwargs)
for line in lines:
self._close_line(line)
def _close_line(self, line):
x, y = line.get_data()
# FIXME: markers at x[0], y[0] get doubled-up
if x[0] != x[-1]:
x = np.concatenate((x, [x[0]]))
y = np.concatenate((y, [y[0]]))
line.set_data(x, y)
def set_varlabels(self, labels):
self.set_thetagrids(theta * 180 / np.pi, labels)
def _gen_axes_patch(self):
x0, y0 = (0.5, 0.5)
r = 0.5
return self.draw_frame(x0, y0, r)
register_projection(RadarAxes)
return theta
def day_radar_plot(df):
fig = plt.figure(figsize=(6,6))
#adjust spacing around the subplots
fig.subplots_adjust(wspace=0.25,hspace=0.20,top=0.85,bottom=0.05)
ldo,rup = 0.1,0.8 #leftdown and right up normalized
ax = fig.add_axes([ldo,ldo,rup,rup],polar=True)
N = len(df['Group1'].unique())
theta = radar_factory(N)
polar_df = pd.DataFrame(df.groupby([df['Group1'],df['Type'],df['Vote']]).size())
polar_df.columns = ['Count']
radii = polar_df['Count'].get_values()
names = polar_df.index.get_values()
#get the number of unique colors needed
num_colors_needed = len(names)
#Create the list of unique colors needed for red and blue shades
Rcolors = []
Gcolors = []
for i in range(num_colors_needed):
ri=1-(float(i)/float(num_colors_needed))
gi=0.
bi=0.
Rcolors.append((ri,gi,bi))
for i in range(num_colors_needed):
ri=0.
gi=1-(float(i)/float(num_colors_needed))
bi=0.
Gcolors.append((ri,gi,bi))
from_x = np.linspace(0,0.95,num_colors_needed)
to_x = from_x + 0.05
i = 0
for d,f,R,G in zip(radii,polar_df.index,Rcolors,Gcolors):
i = i+1
if f[2].lower() == 'no':
ax.plot(theta,d,color=R)
ax.fill(theta,d,facecolor=R,alpha=0.25)
#this is where I think i have the issue
ax.axvspan(from_x[i],to_x[i],color=R)
elif f[2].lower() == 'yes':
ax.plot(theta,d,color=G)
ax.fill(theta,d,facecolor=G,alpha=0.25)
#this is where I think i have the issue
ax.axvspan(from_x[i],to_x[i],color=G)
plt.show()
So, let's say I have this StringIO that has a list of Group1 voting either yes or no and they are from a numbered type..these numbers are arbitrary in labeling but just as an example..
fakefile = StringIO("""\
Group1,Type,Vote
James,7,YES\nRachael,7,YES\nChris,2,YES\nRachael,9,NO
Chris,2,YES\nChris,7,NO\nRachael,9,NO\nJames,2,NO
James,7,NO\nJames,9,YES\nRachael,9,NO
Chris,2,YES\nChris,2,YES\nRachael,7,NO
Rachael,7,YES\nJames,9,YES\nJames,9,NO
Rachael,2,NO\nChris,2,YES\nRachael,7,YES
Rachael,9,NO\nChris,9,NO\nJames,7,NO
James,2,YES\nChris,2,NO\nRachael,9,YES
Rachael,9,YES\nRachael,2,NO\nChris,7,YES
James,7,YES\nChris,9,NO\nRachael,9,NO\n
Chris,9,YES
""")
record = pd.read_csv(fakefile, header=0)
day_radar_plot(record)
The error I get is Value Error: x and y must have same first dimension.
As I indicated in my script, I thought I had a solution for it but apparently I'm going by it the wrong way. Does anyone have any advice or guidance?
Since I'm completely lost in what you are trying to do, I will simply provide a solution on how to draw a radar chart from the given data.
It will answer the question how often have people voted Yes or No.
import pandas as pd
import numpy as np
from StringIO import StringIO
import matplotlib.pyplot as plt
fakefile = StringIO("""\
Group1,Type,Vote
James,7,YES\nRachael,7,YES\nChris,2,YES\nRachael,9,NO
Chris,2,YES\nChris,7,NO\nRachael,9,NO\nJames,2,NO
James,7,NO\nJames,9,YES\nRachael,9,NO
Chris,2,YES\nChris,2,YES\nRachael,7,NO
Rachael,7,YES\nJames,9,YES\nJames,9,NO
Rachael,2,NO\nChris,2,YES\nRachael,7,YES
Rachael,9,NO\nChris,9,NO\nJames,7,NO
James,2,YES\nChris,2,NO\nRachael,9,YES
Rachael,9,YES\nRachael,2,NO\nChris,7,YES
James,7,YES\nChris,9,NO\nRachael,9,NO\n
Chris,9,YES""")
df = pd.read_csv(fakefile, header=0)
df["cnt"] = np.ones(len(df))
pt = pd.pivot_table(df, values='cnt', index=['Group1'],
columns=['Vote'], aggfunc=np.sum)
fig = plt.figure()
ax = fig.add_subplot(111, projection="polar")
theta = np.arange(len(pt))/float(len(pt))*2.*np.pi
l1, = ax.plot(theta, pt["YES"], color="C2", marker="o", label="YES")
l2, = ax.plot(theta, pt["NO"], color="C3", marker="o", label="NO")
def _closeline(line):
x, y = line.get_data()
x = np.concatenate((x, [x[0]]))
y = np.concatenate((y, [y[0]]))
line.set_data(x, y)
[_closeline(l) for l in [l1,l2]]
ax.set_xticks(theta)
ax.set_xticklabels(pt.index)
plt.legend()
plt.title("How often have people votes Yes or No?")
plt.show()
I want to add a kind of "spheres" to my data cluster.
My data cluster is this, which does not have ""spheres".
And this is my code
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
style.use('ggplot')
import pandas as pd
from sklearn.cluster import KMeans
MY_FILE='total_watt.csv'
date = []
consumption = []
df = pd.read_csv(MY_FILE, parse_dates=[0], index_col=[0])
df = df.resample('1D', how='sum')
df = df.dropna()
date = df.index.tolist()
date = [x.strftime('%Y-%m-%d') for x in date]
from sklearn.preprocessing import LabelEncoder
encoder = LabelEncoder()
date_numeric = encoder.fit_transform(date)
consumption = df[df.columns[0]].values
X = np.array([date_numeric, consumption]).T
kmeans = KMeans(n_clusters=3)
kmeans.fit(X)
centroids = kmeans.cluster_centers_
labels = kmeans.labels_
print(centroids)
print(labels)
fig, ax = plt.subplots(figsize=(10,8))
rect = fig.patch
rect.set_facecolor('#2D2B2B')
colors = ["b.","r.","g."]
for i in range(len(X)):
print("coordinate:",encoder.inverse_transform(X[i,0].astype(int)), X[i,1], "label:", labels[i])
ax.plot(X[i][0], X[i][1], colors[labels[i]], markersize = 10)
ax.scatter(centroids[:, 0],centroids[:, 1], marker = "x", s=150, linewidths = 5, zorder = 10)
a = np.arange(0, len(X), 5)
ax.set_xticks(a)
ax.set_xticklabels(encoder.inverse_transform(a.astype(int)))
ax.tick_params(axis='x', colors='lightseagreen')
ax.tick_params(axis='y', colors='lightseagreen')
plt.scatter(centroids[:, 0],centroids[:, 1], marker = "x", s=100, c="black", linewidths = 5, zorder = 10)
ax.set_title('Energy consumptions Clusters (high/medium/low)', color='gold')
ax.set_xlabel('time', color='gold')
ax.set_ylabel('date(year 2011)', color='gold')
plt.show()
"Spheres" is area which surroundings plot(cluster), as this picture.
I tried to google it.
But when I type "matplotlib spheres", I could not get any result..
The sample graph in your post looks like resulting from Generalized Gaussian Mixture where each sphere is a Gaussian 2-d density.
I'll write up a sample code shortly to demonstrate how to use GMM on your dataset and do this kind of plotting.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
style.use('ggplot')
import pandas as pd
# code changes here
# ===========================================
from sklearn.mixture import GMM
# ===========================================
from sklearn.preprocessing import LabelEncoder
# replace it with you file path
MY_FILE='/home/Jian/Downloads/total_watt.csv'
df = pd.read_csv(MY_FILE, parse_dates=[0], index_col=[0])
df = df.resample('1D', how='sum')
df = df.dropna()
date = df.index.tolist()
date = [x.strftime('%Y-%m-%d') for x in date]
encoder = LabelEncoder()
date_numeric = encoder.fit_transform(date)
consumption = df[df.columns[0]].values
X = np.array([date_numeric, consumption]).T
# code changes here
# ===========================================
gmm = GMM(n_components=3, random_state=0)
gmm.fit(X)
y_pred = gmm.predict(X)
# the center is given by mean
gmm.means_
# ===========================================
import matplotlib as mpl
fig, ax = plt.subplots(figsize=(10,8))
for i, color in enumerate('rgb'):
# sphere background
width, height = 2 * 1.96 * np.sqrt(np.diagonal(gmm._get_covars()[i]))
ell = mpl.patches.Ellipse(gmm.means_[i], width, height, color=color)
ell.set_alpha(0.1)
ax.add_artist(ell)
# data points
X_data = X[y_pred == i]
ax.scatter(X_data[:,0], X_data[:,1], color=color)
# center
ax.scatter(gmm.means_[i][0], gmm.means_[i][1], marker='x', s=100, c=color)
ax.set_title('Energy consumptions Clusters (high/medium/low)', color='gold')
ax.set_xlabel('time', color='gold')
ax.set_ylabel('date(year 2011)', color='gold')
a = np.arange(0, len(X), 5)
ax.set_xticks(a)
ax.set_xticklabels(encoder.inverse_transform(a.astype(int)))
ax.tick_params(axis='x', colors='lightseagreen')
ax.tick_params(axis='y', colors='lightseagreen')