I've looked at the documentation, but I can't seem to figure out if this is possible -
I have a dataset, with x and y values and discrete z values. Multiple pairs of (x,y) share the same z value. What I want to do is when I mouseover one point with a particular z value, the alpha of all the points with the same z values goes to 1 - i.e., If all the alpha values are initially 0.5, I'd like only the points with the same z value to go to 1.
Here's a minimal working example to illustrate what I'm talking about :
#! /usr/bin/env python
import numpy as np
import matplotlib.pyplot as plt
x = np.random.randn(100)
y = np.random.randn(100)
z = np.arange(0, 10, 1)
z = np.repeat(z, 10)
im = plt.scatter(x, y, c=z, alpha = 0.5)
plt.colorbar(im)
plt.show()
You can probably fake what you want to achieve using a second plot:
import numpy as np
import matplotlib.pyplot as plt
Z = np.zeros(1000, dtype = [("Z", int), ("P", float, 2)])
Z["P"] = np.random.uniform(0.0,1.0,(len(Z),2))
Z["Z"] = np.random.randint(0,50,len(Z))
def on_pick(event):
z = Z[event.ind[0]]['Z']
P = Z[np.where(Z["Z"] == z)]["P"]
selection_plot.set_data(P[:,0],P[:,1])
plt.draw()
fig = plt.figure(figsize=(10,10), facecolor='white')
fig.canvas.mpl_connect('pick_event', on_pick)
ax = plt.subplot(111, aspect=1)
ax.plot(Z['P'][:,0], Z['P'][:,1], 'o', color='k', alpha=0.1, picker=5)
selection_plot, = ax.plot([],[], 'o', color='black', alpha=1.0, zorder=10)
plt.show()
Related
I did a test code brigging something I saw on stack on different topic, and try to assemble it to make what I need : a filled curve with gradient.
After validate this test code I will make a subplot (4 plots for 4 weeks) with the same min/max for all plot (it's a power consumption).
My code :
from matplotlib import pyplot as plt
import numpy as np
# random x
x = range(100)
# smooth random y
y = 0
result = []
for _ in x:
result.append(y)
y += np.random.normal(loc=0, scale=1)#, size=len(x))
y = result
y = list(map(abs, y))
# creation of z for contour
z1 = min(y)
z3 = max(y)/(len(x)+1)
z2 = max(y)-z3
z = [[z] * len(x) for z in np.arange(z1,z2,z3)]
num_bars = len(x) # more bars = smoother gradient
# plt.contourf(x, y, z, num_bars, cmap='greys')
plt.contourf(x, y, z, num_bars, cmap='cool', levels=101)
background_color = 'w'
plt.fill_between(
x,
y,
y2=max(y),
color=background_color
)
But everytime I make the code run, the result display a different gradient scale, that is not smooth neither even straight right.
AND sometime the code is in error : TypeError: Length of y (100) must match number of rows in z (101)
I'm on it since too many time, turning around, and can't figure where I'm wrong...
I finally find something particularly cool, how to :
have both filled gradient curves in a different color (thanks to JohanC in this topic)
use x axis with datetime (thanks to Ffisegydd in this topic)
Here the code :
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import matplotlib.dates as mdates
np.random.seed(2022)
st_date = '2022-11-01 00:00:00'
st_date = pd.to_datetime(st_date)
en_date = st_date + pd.DateOffset(days=7)
x = pd.date_range(start=st_date,end=en_date,freq='30min')
x = mdates.date2num(x)
y = np.random.normal(0.01, 1, len(x)).cumsum()
fig, ax = plt.subplots(figsize=(18, 5))
ax.plot(x, y, color='grey')
########################
# positives fill
#######################
grad1 = ax.imshow(
np.linspace(0, 1, 256).reshape(-1, 1),
cmap='Blues',
vmin=-0.5,
aspect='auto',
extent=[x.min(), x.max(), 0, y.max()],
# extent=[x[0], x[1], 0, y.max()],
origin='lower'
)
poly_pos = ax.fill_between(x, y.min(), y, alpha=0.1)
grad1.set_clip_path(
poly_pos.get_paths()[0],
transform=ax.transData
)
poly_pos.remove()
########################
# negatives fill
#######################
grad2 = ax.imshow(
np.linspace(0, 1, 256).reshape(-1, 1),
cmap='Reds',
vmin=-0.5,
aspect='auto',
extent=[x.min(), x.max(), y.min(), 0],
origin='upper'
)
poly_neg = ax.fill_between(x, y, y.max(), alpha=0.1)
grad2.set_clip_path(
poly_neg.get_paths()[0],
transform=ax.transData
)
poly_neg.remove()
########################
# decorations and formatting plot
########################
ax.xaxis_date()
date_format = mdates.DateFormatter('%d-%b %H:%M')
ax.xaxis.set_major_formatter(date_format)
fig.autofmt_xdate()
ax.grid(True)
I want to plot some equation in Matplotlib. But it has different result from Wolframalpha.
This is the equation:
y = 10yt + y^2t + 20
The plot result in wolframalpha is:
But when I want to plot it in the matplotlib with these code
# Creating vectors X and Y
x = np.linspace(-2, 2, 100)
# Assuming α is 10
y = ((10*y*x)+((y**2)*x)+20)
# Create the plot
fig = plt.figure(figsize = (10, 5))
plt.plot(x, y)
The result is:
Any suggestion to modify to code so it has similar plot result as wolframalpha? Thank you
As #Him has suggested in the comments, y = ((10*y*x)+((y**2)*x)+20) won't describe a relationship, so much as make an assignment, so the fact that y appears on both sides of the equation makes this difficult.
It's not trivial to express y cleanly in terms of x, but it's relatively easy to express x in terms of y, and then graph that relationship, like so:
import numpy as np
import matplotlib.pyplot as plt
y = np.linspace(-40, 40, 2000)
x = (y-20)*(((10*y)+(y**2))**-1)
fig, ax = plt.subplots()
ax.plot(x, y, linestyle = 'None', marker = '.')
ax.set_xlim(left = -4, right = 4)
ax.grid()
ax.set_xlabel('x')
ax.set_ylabel('y')
Which produces the following result:
If you tried to plot this with a line instead of points, you'll get a big discontinuity as the asymptotic limbs try to join up
So you'd have to define the same function and evaluate it in three different ranges and plot them all so you don't get any crossovers.
import numpy as np
import matplotlib.pyplot as plt
y1 = np.linspace(-40, -10, 2000)
y2 = np.linspace(-10, 0, 2000)
y3 = np.linspace(0, 40, 2000)
x = lambda y: (y-20)*(((10*y)+(y**2))**-1)
y = np.hstack([y1, y2, y3])
fig, ax = plt.subplots()
ax.plot(x(y), y, linestyle = '-', color = 'b')
ax.set_xlim(left = -4, right = 4)
ax.grid()
ax.set_xlabel('x')
ax.set_ylabel('y')
Which produces this result, that you were after:
I am trying to get my 3D python plot into 3 different colors based on the value of Z from a CSV file. I am trying to color a point one specific color, and then points below one color and points above one color. I can get the plot into a color above and below the point, but I can't seem to figure out how to get it into 3 colors.
I have tried to split the Z value into 3 different 3 subsets, but when I tried to plot the plot was just empty. I also tried to write it through an if statement assigning Z to the color but that did not work either. This is the code that works for the 2 color:
import matplotlib.pyplot as plt
import numpy as np
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D
import pandas as pd
headers = ['name','ra','x rads','x par','dec','y rads','Parallax','Parallax Error','central distance','Z Max','Z Min']
mergeddata = pd.read_csv(r'C:\Users\GregL\Downloads\mergedata - no neg parallax #s (2).csv')
mergeddata.z = mergeddata['central distance']
mergeddata.x = mergeddata['x par']
mergeddata.y = mergeddata['y rads']
x= mergeddata.x
y= mergeddata.y
z = mergeddata.z
colors = [z <= 1956.783590]
fig = plt.figure(figsize=(10,10))
ax = fig.add_subplot(111, projection='3d')
surf=ax.scatter3D(x,y,z,c=colors, cmap='coolwarm',s=.5,marker='^')
ax.set_title('3D Data Distance Plot')
ax.set_zlim(-100,10000)
ax.set_xlim(-50,50)
ax.set_ylim(-50,50)
ax.set_xlabel('RA')
ax.set_ylabel('DEC')
ax.set_zlabel('CENTRAL DISTANCE')
plt.show()
Which gives me this plot
As mentioned by Claudio on the comment, you can create a color value and then assign a proper colormap. Here, I'm going to create a discrete color map based on Matplotlib's Tab10:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import matplotlib.colors as col
fig = plt.figure()
ax = plt.axes(projection ='3d')
z = np.linspace(0, 1, 100)
x = z * np.sin(25 * z)
y = z * np.cos(25 * z)
# values for color
c = [int(zv / 0.4) for zv in z]
# discrete colormap with 3 colors
cmap=col.ListedColormap(cm.tab10.colors[:len(np.unique(c))])
ax.scatter(x, y, z, c=c, cmap=cmap)
plt.show()
Alternatively, you can create multiple ax.scatter commands, each one plotting a subset. The advantage of this approach is that you can set custom labels or rendering properties to each subset:
fig = plt.figure()
ax = plt.axes(projection ='3d')
i1 = z < 0.3
i2 = (z >= 0.3) & (z < 0.6)
i3 = z >= 0.6
ax.scatter(x[i1], y[i1], z[i1], label="a")
ax.scatter(x[i2], y[i2], z[i2], label="b")
ax.scatter(x[i3], y[i3], z[i3], label="c")
ax.legend()
plt.show()
I'd like to make a scatter plot where each point is colored by the spatial density of nearby points.
I've come across a very similar question, which shows an example of this using R:
R Scatter Plot: symbol color represents number of overlapping points
What's the best way to accomplish something similar in python using matplotlib?
In addition to hist2d or hexbin as #askewchan suggested, you can use the same method that the accepted answer in the question you linked to uses.
If you want to do that:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
# Generate fake data
x = np.random.normal(size=1000)
y = x * 3 + np.random.normal(size=1000)
# Calculate the point density
xy = np.vstack([x,y])
z = gaussian_kde(xy)(xy)
fig, ax = plt.subplots()
ax.scatter(x, y, c=z, s=100)
plt.show()
If you'd like the points to be plotted in order of density so that the densest points are always on top (similar to the linked example), just sort them by the z-values. I'm also going to use a smaller marker size here as it looks a bit better:
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde
# Generate fake data
x = np.random.normal(size=1000)
y = x * 3 + np.random.normal(size=1000)
# Calculate the point density
xy = np.vstack([x,y])
z = gaussian_kde(xy)(xy)
# Sort the points by density, so that the densest points are plotted last
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]
fig, ax = plt.subplots()
ax.scatter(x, y, c=z, s=50)
plt.show()
Plotting >100k data points?
The accepted answer, using gaussian_kde() will take a lot of time. On my machine, 100k rows took about 11 minutes. Here I will add two alternative methods (mpl-scatter-density and datashader) and compare the given answers with same dataset.
In the following, I used a test data set of 100k rows:
import matplotlib.pyplot as plt
import numpy as np
# Fake data for testing
x = np.random.normal(size=100000)
y = x * 3 + np.random.normal(size=100000)
Output & computation time comparison
Below is a comparison of different methods.
1: mpl-scatter-density
Installation
pip install mpl-scatter-density
Example code
import mpl_scatter_density # adds projection='scatter_density'
from matplotlib.colors import LinearSegmentedColormap
# "Viridis-like" colormap with white background
white_viridis = LinearSegmentedColormap.from_list('white_viridis', [
(0, '#ffffff'),
(1e-20, '#440053'),
(0.2, '#404388'),
(0.4, '#2a788e'),
(0.6, '#21a784'),
(0.8, '#78d151'),
(1, '#fde624'),
], N=256)
def using_mpl_scatter_density(fig, x, y):
ax = fig.add_subplot(1, 1, 1, projection='scatter_density')
density = ax.scatter_density(x, y, cmap=white_viridis)
fig.colorbar(density, label='Number of points per pixel')
fig = plt.figure()
using_mpl_scatter_density(fig, x, y)
plt.show()
Drawing this took 0.05 seconds:
And the zoom-in looks quite nice:
2: datashader
Datashader is an interesting project. It has added support for matplotlib in datashader 0.12.
Installation
pip install datashader
Code (source & parameterer listing for dsshow):
import datashader as ds
from datashader.mpl_ext import dsshow
import pandas as pd
def using_datashader(ax, x, y):
df = pd.DataFrame(dict(x=x, y=y))
dsartist = dsshow(
df,
ds.Point("x", "y"),
ds.count(),
vmin=0,
vmax=35,
norm="linear",
aspect="auto",
ax=ax,
)
plt.colorbar(dsartist)
fig, ax = plt.subplots()
using_datashader(ax, x, y)
plt.show()
It took 0.83 s to draw this:
There is also possibility to colorize by third variable. The third parameter for dsshow controls the coloring. See more examples here and the source for dsshow here.
3: scatter_with_gaussian_kde
def scatter_with_gaussian_kde(ax, x, y):
# https://stackoverflow.com/a/20107592/3015186
# Answer by Joel Kington
xy = np.vstack([x, y])
z = gaussian_kde(xy)(xy)
ax.scatter(x, y, c=z, s=100, edgecolor='')
It took 11 minutes to draw this:
4: using_hist2d
import matplotlib.pyplot as plt
def using_hist2d(ax, x, y, bins=(50, 50)):
# https://stackoverflow.com/a/20105673/3015186
# Answer by askewchan
ax.hist2d(x, y, bins, cmap=plt.cm.jet)
It took 0.021 s to draw this bins=(50,50):
It took 0.173 s to draw this bins=(1000,1000):
Cons: The zoomed-in data does not look as good as in with mpl-scatter-density or datashader. Also you have to determine the number of bins yourself.
5: density_scatter
The code is as in the answer by Guillaume.
It took 0.073 s to draw this with bins=(50,50):
It took 0.368 s to draw this with bins=(1000,1000):
Also, if the number of point makes KDE calculation too slow, color can be interpolated in np.histogram2d [Update in response to comments: If you wish to show the colorbar, use plt.scatter() instead of ax.scatter() followed by plt.colorbar()]:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm
from matplotlib.colors import Normalize
from scipy.interpolate import interpn
def density_scatter( x , y, ax = None, sort = True, bins = 20, **kwargs ) :
"""
Scatter plot colored by 2d histogram
"""
if ax is None :
fig , ax = plt.subplots()
data , x_e, y_e = np.histogram2d( x, y, bins = bins, density = True )
z = interpn( ( 0.5*(x_e[1:] + x_e[:-1]) , 0.5*(y_e[1:]+y_e[:-1]) ) , data , np.vstack([x,y]).T , method = "splinef2d", bounds_error = False)
#To be sure to plot all data
z[np.where(np.isnan(z))] = 0.0
# Sort the points by density, so that the densest points are plotted last
if sort :
idx = z.argsort()
x, y, z = x[idx], y[idx], z[idx]
ax.scatter( x, y, c=z, **kwargs )
norm = Normalize(vmin = np.min(z), vmax = np.max(z))
cbar = fig.colorbar(cm.ScalarMappable(norm = norm), ax=ax)
cbar.ax.set_ylabel('Density')
return ax
if "__main__" == __name__ :
x = np.random.normal(size=100000)
y = x * 3 + np.random.normal(size=100000)
density_scatter( x, y, bins = [30,30] )
You could make a histogram:
import numpy as np
import matplotlib.pyplot as plt
# fake data:
a = np.random.normal(size=1000)
b = a*3 + np.random.normal(size=1000)
plt.hist2d(a, b, (50, 50), cmap=plt.cm.jet)
plt.colorbar()
How would I make a countour grid in python using matplotlib.pyplot, where the grid is one colour where the z variable is below zero and another when z is equal to or larger than zero? I'm not very familiar with matplotlib so if anyone can give me a simple way of doing this, that would be great.
So far I have:
x= np.arange(0,361)
y= np.arange(0,91)
X,Y = np.meshgrid(x,y)
area = funcarea(L,D,H,W,X,Y) #L,D,H and W are all constants defined elsewhere.
plt.figure()
plt.contourf(X,Y,area)
plt.show()
You can do this using the levels keyword in contourf.
import numpy as np
import matplotlib.pyplot as plt
fig, axs = plt.subplots(1,2)
x = np.linspace(0, 1, 100)
X, Y = np.meshgrid(x, x)
Z = np.sin(X)*np.sin(Y)
levels = np.linspace(-1, 1, 40)
zdata = np.sin(8*X)*np.sin(8*Y)
cs = axs[0].contourf(X, Y, zdata, levels=levels)
fig.colorbar(cs, ax=axs[0], format="%.2f")
cs = axs[1].contourf(X, Y, zdata, levels=[-1,0,1])
fig.colorbar(cs, ax=axs[1])
plt.show()
You can change the colors by choosing and different colormap; using vmin, vmax; etc.