I have the following code:
from mpl_toolkits.axes_grid.axislines import SubplotZero
from matplotlib.transforms import BlendedGenericTransform
import matplotlib.pyplot as plt
import numpy
if 1:
fig = plt.figure(1)
ax = SubplotZero(fig, 111)
fig.add_subplot(ax)
ax.axhline(linewidth=1.7, color="black")
ax.axvline(linewidth=1.7, color="black")
plt.xticks([1])
plt.yticks([])
ax.text(0, 1.05, 'y', transform=BlendedGenericTransform(ax.transData, ax.transAxes), ha='center')
ax.text(1.05, 0, 'x', transform=BlendedGenericTransform(ax.transAxes, ax.transData), va='center')
for direction in ["xzero", "yzero"]:
ax.axis[direction].set_axisline_style("-|>")
ax.axis[direction].set_visible(True)
for direction in ["left", "right", "bottom", "top"]:
ax.axis[direction].set_visible(False)
x = numpy.linspace(-1, 1, 10000)
ax.plot(x, numpy.tan(2*(x - numpy.pi/2)), linewidth=1.2, color="black")
plt.ylim(-5, 5)
plt.savefig('graph.png')
which produces this graph:
As you can see, not only is the tan graph sketched, but a portion of line is added to join the asymptotic regions of the tan graph, where an asymptote would normally be.
Is there some built in way to skip that section? Or will I graph separate disjoint domains of tan that are bounded by asymptotes (if you get what I mean)?
Something you could try: set a finite threshold and modify your function to provide non-finite values after those points. Practical code modification:
yy = numpy.tan(2*(x - numpy.pi/2))
threshold = 10000
yy[yy>threshold] = numpy.inf
yy[yy<-threshold] = numpy.inf
ax.plot(x, yy, linewidth=1.2, color="black")
Results in:
This code creates a figure and one subplot for tangent function. NaN are inserted when cos(x) is tending to 0 (NaN means "Not a Number" and NaNs are not plotted or connected).
matplot-fmt-pi created by k-donn(https://pypi.org/project/matplot-fmt-pi/) used to change the formatter to make x labels and ticks correspond to multiples of π/8 in fractional format.
plot formatting (grid, legend, limits, axis) is performed as commented.
import matplotlib.pyplot as plt
import numpy as np
from matplot_fmt_pi import MultiplePi
fig, ax = plt.subplots() # creates a figure and one subplot
x = np.linspace(-2 * np.pi, 2 * np.pi, 1000)
y = np.tan(x)
y[np.abs(np.cos(x)) <= np.abs(np.sin(x[1]-x[0]))] = np.nan
# This operation inserts a NaN where cos(x) is reaching 0
# NaN means "Not a Number" and NaNs are not plotted or connected
ax.plot(x, y, lw=2, color="blue", label='Tangent')
# Set up grid, legend, and limits
ax.grid(True)
ax.axhline(0, color='black', lw=.75)
ax.axvline(0, color='black', lw=.75)
ax.set_title("Trigonometric Functions")
ax.legend(frameon=False) # remove frame legend frame
# axis formatting
ax.set_xlim(-2 * np.pi, 2 * np.pi)
pi_manager = MultiplePi(8) # number= ticks between 0 - pi
ax.xaxis.set_major_locator(pi_manager.locator())
ax.xaxis.set_major_formatter(pi_manager.formatter())
plt.ylim(top=10) # y axis limit values
plt.ylim(bottom=-10)
y_ticks = np.arange(-10, 10, 1)
plt.yticks(y_ticks)
fig
[![enter image description here][1]][1]plt.show()
Related
I've seen numerous examples of 3D plots using matplotlib/seaborn in Python but can't seem to get what I'm looking for; I have 50 or so timeseries that I would like to plot cleanly as in the following example below but with the name of the series on the axis; as an example I've marked in Goog, IBM, GE, Pepsi etc. Appreciate any pointers or examples. Thank you,
Example PLOT Click Here Please
Matplotlib has very rich gallery. I found this, you can only plot it once instead of animation. And manually put y-axis legend wherever you want.
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.animation as animation
# Fixing random state for reproducibility
np.random.seed(19680801)
# Create new Figure with black background
fig = plt.figure(figsize=(12, 8))
# Add a subplot with no frame
ax = plt.subplot(111, frameon=False)
# Generate random data
data = np.random.uniform(0, 1, (64, 75))
X = np.linspace(-1, 1, data.shape[-1])
G = 1.5 * np.exp(-4 * X ** 2)
# Generate line plots
lines = []
for i in range(len(data)):
# Small reduction of the X extents to get a cheap perspective effect
xscale = 1 - i / 200.
# Same for linewidth (thicker strokes on bottom)
lw = 1.5 - i / 100.0
line, = ax.plot(xscale * X, i + G * data[i], color="b", lw=lw)
lines.append(line)
# Set y limit (or first line is cropped because of thickness)
ax.set_ylim(-1, 70)
# No ticks
ax.set_xticks([])
ax.set_yticks([])
# 2 part titles to get different font weights
ax.text(0.5, 1.0, "MATPLOTLIB ", transform=ax.transAxes,
ha="right", va="bottom", color="k",
family="sans-serif", fontweight="light", fontsize=16)
ax.text(0.5, 1.0, "UNCHAINED", transform=ax.transAxes,
ha="left", va="bottom", color="k",
family="sans-serif", fontweight="bold", fontsize=16)
def update(*args):
# Shift all data to the right
data[:, 1:] = data[:, :-1]
# Fill-in new values
data[:, 0] = np.random.uniform(0, 1, len(data))
# Update data
for i in range(len(data)):
lines[i].set_ydata(i + G * data[i])
# Return modified artists
return lines
# Construct the animation, using the update function as the animation director.
anim = animation.FuncAnimation(fig, update, interval=10)
plt.show()
I am attempting to produce a plot like this which combines a cartesian scatter plot and a polar histogram. (Radial lines optional)
A similar solution (by Nicolas Legrand) exists for looking at differences in x and y (code here), but we need to look at ratios (i.e. x/y).
More specifically, this is useful when we want to look at the relative risk measure which is the ratio of two probabilities.
The scatter plot on it's own is obviously not a problem, but the polar histogram is more advanced.
The most promising lead I have found is this central example from the matplotlib gallery here
I have attempted to do this, but have run up against the limits of my matplotlib skills. Any efforts moving towards this goal would be great.
I'm sure that others will have better suggestions, but one method that gets something like you want (without the need for extra axes artists) is to use a polar projection with a scatter and bar chart together. Something like
import matplotlib.pyplot as plt
import numpy as np
x = np.random.uniform(size=100)
y = np.random.uniform(size=100)
r = np.sqrt(x**2 + y**2)
phi = np.arctan2(y, x)
h, b = np.histogram(phi, bins=np.linspace(0, np.pi/2, 21), density=True)
colors = plt.cm.Spectral(h / h.max())
ax = plt.subplot(111, projection='polar')
ax.scatter(phi, r, marker='.')
ax.bar(b[:-1], h, width=b[1:] - b[:-1],
align='edge', bottom=np.max(r) + 0.2, color=colors)
# Cut off at 90 degrees
ax.set_thetamax(90)
# Set the r grid to cover the scatter plot
ax.set_rgrids([0, 0.5, 1])
# Let's put a line at 1 assuming we want a ratio of some sort
ax.set_thetagrids([45], [1])
which will give
It is missing axes labels and some beautification, but it might be a place to start. I hope it is helpful.
You can use two axes on top of each other:
import matplotlib.pyplot as plt
fig = plt.figure(figsize=(6,6))
ax1 = fig.add_axes([0.1,0.1,.8,.8], label="cartesian")
ax2 = fig.add_axes([0.1,0.1,.8,.8], projection="polar", label="polar")
ax2.set_rorigin(-1)
ax2.set_thetamax(90)
plt.show()
Ok. Thanks to the answer from Nicolas, and the answer from tomjn I have a working solution :)
import numpy as np
import matplotlib.pyplot as plt
# Scatter data
n = 50
x = 0.3 + np.random.randn(n)*0.1
y = 0.4 + np.random.randn(n)*0.02
def radial_corner_plot(x, y, n_hist_bins=51):
"""Scatter plot with radial histogram of x/y ratios"""
# Axis setup
fig = plt.figure(figsize=(6,6))
ax1 = fig.add_axes([0.1,0.1,.6,.6], label="cartesian")
ax2 = fig.add_axes([0.1,0.1,.8,.8], projection="polar", label="polar")
ax2.set_rorigin(-20)
ax2.set_thetamax(90)
# define useful constant
offset_in_radians = np.pi/4
def rotate_hist_axis(ax):
"""rotate so that 0 degrees is pointing up and right"""
ax.set_theta_offset(offset_in_radians)
ax.set_thetamin(-45)
ax.set_thetamax(45)
return ax
# Convert scatter data to histogram data
r = np.sqrt(x**2 + y**2)
phi = np.arctan2(y, x)
h, b = np.histogram(phi,
bins=np.linspace(0, np.pi/2, n_hist_bins),
density=True)
# SCATTER PLOT -------------------------------------------------------
ax1.scatter(x,y)
ax1.set(xlim=[0, 1], ylim=[0, 1], xlabel="x", ylabel="y")
ax1.spines['right'].set_visible(False)
ax1.spines['top'].set_visible(False)
# HISTOGRAM ----------------------------------------------------------
ax2 = rotate_hist_axis(ax2)
# rotation of axis requires rotation in bin positions
b = b - offset_in_radians
# plot the histogram
bars = ax2.bar(b[:-1], h, width=b[1:] - b[:-1], align='edge')
def update_hist_ticks(ax, desired_ratios):
"""Update tick positions and corresponding tick labels"""
x = np.ones(len(desired_ratios))
y = 1/desired_ratios
phi = np.arctan2(y,x) - offset_in_radians
# define ticklabels
xticklabels = [str(round(float(label), 2)) for label in desired_ratios]
# apply updates
ax2.set(xticks=phi, xticklabels=xticklabels)
return ax
ax2 = update_hist_ticks(ax2, np.array([1/8, 1/4, 1/2, 1, 2, 4, 8]))
# just have radial grid lines
ax2.grid(which="major", axis="y")
# remove bin count labels
ax2.set_yticks([])
return (fig, [ax1, ax2])
fig, ax = radial_corner_plot(x, y)
Thanks for the pointers!
I'd like to draw a lognormal distribution of a given bar plot.
Here's the code
import matplotlib.pyplot as plt
from matplotlib.pyplot import figure
import numpy as np; np.random.seed(1)
import scipy.stats as stats
import math
inter = 33
x = np.logspace(-2, 1, num=3*inter+1)
yaxis = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0.01,0.03,0.3,0.75,1.24,1.72,2.2,3.1,3.9,
4.3,4.9,5.3,5.6,5.87,5.96,6.01,5.83,5.42,4.97,4.60,4.15,3.66,3.07,2.58,2.19,1.90,1.54,1.24,1.08,0.85,0.73,
0.84,0.59,0.55,0.53,0.48,0.35,0.29,0.15,0.15,0.14,0.12,0.14,0.15,0.05,0.05,0.05,0.04,0.03,0.03,0.03, 0.02,
0.02,0.03,0.01,0.01,0.01,0.01,0.01,0.0,0.0,0.0,0.0,0.0,0.01,0,0]
fig, ax = plt.subplots()
ax.bar(x[:-1], yaxis, width=np.diff(x), align="center", ec='k', color='w')
ax.set_xscale('log')
plt.xlabel('Diameter (mm)', fontsize='12')
plt.ylabel('Percentage of Total Particles (%)', fontsize='12')
plt.ylim(0,8)
plt.xlim(0.01, 10)
fig.set_size_inches(12, 12)
plt.savefig("Test.png", dpi=300, bbox_inches='tight')
Resulting plot:
What I'm trying to do is to draw the Probability Density Function exactly like the one shown in red in the graph below:
An idea is to convert everything to logspace, with u = log10(x). Then draw the density histogram in there. And also calculate a kde in the same space. Everything gets drawn as y versus u. When we have u at a top twin axes, x can stay at the bottom. Both axes get aligned by setting the same xlims, but converted to logspace on the top axis. The top axis can be hidden to get the desired result.
import matplotlib.pyplot as plt
import numpy as np
from scipy import stats
inter = 33
u = np.linspace(-2, 1, num=3*inter+1)
x = 10**u
us = np.linspace(u[0], u[-1], 500)
yaxis = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0.01,0.03,0.3,0.75,1.24,1.72,2.2,3.1,3.9,
4.3,4.9,5.3,5.6,5.87,5.96,6.01,5.83,5.42,4.97,4.60,4.15,3.66,3.07,2.58,2.19,1.90,1.54,1.24,1.08,0.85,0.73,
0.84,0.59,0.55,0.53,0.48,0.35,0.29,0.15,0.15,0.14,0.12,0.14,0.15,0.05,0.05,0.05,0.04,0.03,0.03,0.03, 0.02,
0.02,0.03,0.01,0.01,0.01,0.01,0.01,0.0,0.0,0.0,0.0,0.0,0.01,0,0]
yaxis = np.array(yaxis)
# reconstruct data from the given frequencies
u_data = np.repeat((u[:-1] + u[1:]) / 2, (yaxis * 100).astype(np.int))
kde = stats.gaussian_kde((u[:-1]+u[1:])/2, weights=yaxis, bw_method=0.2)
total_area = (np.diff(u)*yaxis).sum() # total area of all bars; divide by this area to normalize
fig, ax = plt.subplots()
ax2 = ax.twiny()
ax2.bar(u[:-1], yaxis, width=np.diff(u), align="edge", ec='k', color='w', label='frequencies')
ax2.plot(us, total_area*kde(us), color='crimson', label='kde')
ax2.plot(us, total_area * stats.norm.pdf(us, u_data.mean(), u_data.std()), color='dodgerblue', label='lognormal')
ax2.legend()
ax.set_xscale('log')
ax.set_xlabel('Diameter (mm)', fontsize='12')
ax.set_ylabel('Percentage of Total Particles (%)', fontsize='12')
ax.set_ylim(0,8)
xlim = np.array([0.01,10])
ax.set_xlim(xlim)
ax2.set_xlim(np.log10(xlim))
ax2.set_xticks([]) # hide the ticks at the top
plt.tight_layout()
plt.show()
PS: Apparently this also can be achieved directly without explicitly using u (at the cost of being slightly more cryptic):
x = np.logspace(-2, 1, num=3*inter+1)
xs = np.logspace(-2, 1, 500)
total_area = (np.diff(np.log10(x))*yaxis).sum() # total area of all bars; divide by this area to normalize
kde = gaussian_kde((np.log10(x[:-1])+np.log10(x[1:]))/2, weights=yaxis, bw_method=0.2)
ax.bar(x[:-1], yaxis, width=np.diff(x), align="edge", ec='k', color='w')
ax.plot(xs, total_area*kde(np.log10(xs)), color='crimson')
ax.set_xscale('log')
Note that the bandwidth set for gaussian_kde is a somewhat arbitrarily value. Larger values give a more equalized curve, smaller values keep closer to the data. Some experimentation can help.
I have a code for ctg(x) but I don't want asymptotes or I want that they have a different color. I'm a beginner and I don't know what I can change in this code:
import matplotlib.ticker as tck
import matplotlib.pyplot as plt
import numpy as np
f,ax=plt.subplots(figsize=(8,5))
x=np.linspace(-np.pi, np.pi,100)
y=np.cos(x)/np.sin(x)
plt.ylim([-4, 4])
ax.plot(x/np.pi,y)
plt.title("f(x) = ctg(x)")
plt.xlabel("x")
plt.ylabel("y")
ax.xaxis.set_major_formatter(tck.FormatStrFormatter('%g $\pi$'))
plt.savefig('ctg')
plt.show()
It is not an asymptote being draw, but the line for the points around zero.
To overcome this you should create two plots for the positive and negative parts separately, making sure that the color (style?) for the two plots is the same (and optionally get the first default matplotlib color).
Since np.linspace() includes the extrema, these might accidentally create the same artifact.
To overcome this, it is enough to add/subtract a small number (epsilon) to the extrema.
import matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np
f,ax=plt.subplots(figsize=(8,5))
# get first default color
color = plt.rcParams['axes.prop_cycle'].by_key()['color'][0]
epsilon = 1e-7
intervals = (
(-np.pi, 0),
(0, np.pi), )
for a, b in intervals:
x=np.linspace(a + epsilon, b - epsilon, 50)
y=np.cos(x) / np.sin(x)
ax.plot(x/np.pi,y, color=color)
plt.title("f(x) = ctg(x)")
plt.xlabel("x")
plt.ylabel("y")
plt.ylim([-4, 4])
ax.xaxis.set_major_formatter(mpl.ticker.FormatStrFormatter('%g $\pi$'))
plt.savefig('ctg')
plt.show()
This code creates a figure and one subplot for cotangent function. NaN are inserted when sin(x) is tending to 0 (NaN means "Not a Number" and NaNs are not plotted or connected).
matplot-fmt-pi created by k-donn(https://pypi.org/project/matplot-fmt-pi/) used to change the formatter to make x labels and ticks correspond to multiples of π/8 in fractional format.
plot formatting (grid, legend, limits, axis) is performed as commented.
import matplotlib.pyplot as plt
import numpy as np
from matplot_fmt_pi import MultiplePi
fig, ax = plt.subplots() # creates a figure and one subplot
x = np.linspace(-2 * np.pi, 2 * np.pi, 1000)
y = 1/np.tan(x)
y[np.abs(np.sin(x)) <= np.abs(np.sin(x[1]-x[0]))] = np.nan
# This operation inserts a NaN where sin(x) is reaching 0
# NaN means "Not a Number" and NaNs are not plotted or connected
ax.plot(x, y, lw=2, color="blue", label='Cotangent')
# Set up grid, legend, and limits
ax.grid(True)
ax.axhline(0, color='black', lw=.75)
ax.axvline(0, color='black', lw=.75)
ax.set_title("Trigonometric Functions")
ax.legend(frameon=False) # remove frame legend frame
# axis formatting
ax.set_xlim(-2 * np.pi, 2 * np.pi)
pi_manager = MultiplePi(8) # number= ticks between 0 - pi
ax.xaxis.set_major_locator(pi_manager.locator())
ax.xaxis.set_major_formatter(pi_manager.formatter())
plt.ylim(top=10) # y axis limit values
plt.ylim(bottom=-10)
y_ticks = np.arange(-10, 10, 1)
plt.yticks(y_ticks)
fig
plt.show()
I want to create a plot for two different datasets similar to the one presented in this answer:
In the above image, the author managed to fix the overlapping problem of the error bars by adding some small random scatter in x to the new dataset.
In my problem, I must plot a similar graphic, but having some categorical data in the x axis:
Any ideas on how to slightly move one the error bars of the second dataset using categorical variables at the x axis? I want to avoid the overlapping between the bars for making the visualization easier.
You can translate each errorbar by adding the default data transform to a prior translation in data space. This is possible when knowing that categories are in general one data unit away from each other.
import numpy as np; np.random.seed(42)
import matplotlib.pyplot as plt
from matplotlib.transforms import Affine2D
x = list("ABCDEF")
y1, y2 = np.random.randn(2, len(x))
yerr1, yerr2 = np.random.rand(2, len(x))*4+0.3
fig, ax = plt.subplots()
trans1 = Affine2D().translate(-0.1, 0.0) + ax.transData
trans2 = Affine2D().translate(+0.1, 0.0) + ax.transData
er1 = ax.errorbar(x, y1, yerr=yerr1, marker="o", linestyle="none", transform=trans1)
er2 = ax.errorbar(x, y2, yerr=yerr2, marker="o", linestyle="none", transform=trans2)
plt.show()
Alternatively, you could translate the errorbars after applying the data transform and hence move them in units of points.
import numpy as np; np.random.seed(42)
import matplotlib.pyplot as plt
from matplotlib.transforms import ScaledTranslation
x = list("ABCDEF")
y1, y2 = np.random.randn(2, len(x))
yerr1, yerr2 = np.random.rand(2, len(x))*4+0.3
fig, ax = plt.subplots()
trans1 = ax.transData + ScaledTranslation(-5/72, 0, fig.dpi_scale_trans)
trans2 = ax.transData + ScaledTranslation(+5/72, 0, fig.dpi_scale_trans)
er1 = ax.errorbar(x, y1, yerr=yerr1, marker="o", linestyle="none", transform=trans1)
er2 = ax.errorbar(x, y2, yerr=yerr2, marker="o", linestyle="none", transform=trans2)
plt.show()
While results look similar in both cases, they are fundamentally different. You will observe this difference when interactively zooming the axes or changing the figure size.
Consider the following approach to highlight plots - combination of errorbar and fill_between with non-zero transparency:
import random
import matplotlib.pyplot as plt
# create sample data
N = 8
data_1 = {
'x': list(range(N)),
'y': [10. + random.random() for dummy in range(N)],
'yerr': [.25 + random.random() for dummy in range(N)]}
data_2 = {
'x': list(range(N)),
'y': [10.25 + .5 * random.random() for dummy in range(N)],
'yerr': [.5 * random.random() for dummy in range(N)]}
# plot
plt.figure()
# only errorbar
plt.subplot(211)
for data in [data_1, data_2]:
plt.errorbar(**data, fmt='o')
# errorbar + fill_between
plt.subplot(212)
for data in [data_1, data_2]:
plt.errorbar(**data, alpha=.75, fmt=':', capsize=3, capthick=1)
data = {
'x': data['x'],
'y1': [y - e for y, e in zip(data['y'], data['yerr'])],
'y2': [y + e for y, e in zip(data['y'], data['yerr'])]}
plt.fill_between(**data, alpha=.25)
Result:
Threre is example on lib site: https://matplotlib.org/stable/gallery/lines_bars_and_markers/errorbar_subsample.html
enter image description here
You need parameter errorevery=(m, n),
n - how often plot error lines, m - shift with range from 0 to n