I'm drawing my axes title with the method ax.set_title("Horizontal Bars", ha="left", x=0, fontsize=16) and it draw as below:
How do I draw it in the left-most position, as the "title here" in red above? I know I can use a negative value for x, but I'd like to find this value automatically.
To dynamically generate the bounds you would do:
import matplotlib.pyplot as plt
import numpy as np
# Fixing random state for reproducibility
np.random.seed(19680801)
plt.rcdefaults()
fig, ax = plt.subplots()
# Example data
people = ('Tom', 'Dick', 'Harry', 'Slim', 'Jim')
y_pos = np.arange(len(people))
performance = 3 + 10 * np.random.rand(len(people))
error = np.random.rand(len(people))
ax.barh(y_pos, performance, xerr=error, align='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.invert_yaxis() # labels read top-to-bottom
ax.set_xlabel('Performance')
# Get min x and max y
# get the inverse of the transformation from data coordinates to pixels
transf = ax.transData.inverted()
bb = plt.figure().get_window_extent(renderer = plt.figure().canvas.get_renderer())
bb_datacoords = bb.transformed(transf)
points = bb_datacoords.get_points()
x_lim = points[0][0]
y_lim = points[1][1]
ax.text(x=x_lim, y=y_lim, s="Horizontal Bars", weight="bold", fontsize=16) # <- Use text instead of title
which gives you an output of:
Related
I'd like to invert the bars in this diagram when they are below 1, not when they are negative. Additionally I'd like to have even spacing between the ticks/steps on the y-axis
Here is my current code
import matplotlib.pyplot as plt
import numpy as np
labels = ['A','B','C']
Vals1 = [28.3232, 12.232, 9.6132]
Vals2 = [0.00456, 17.868, 13.453]
Vals3 = [0.0032, 1.234, 0.08214]
x = np.arange(len(labels))
width = 0.2
fig, ax = plt.subplots()
rects1 = ax.bar(x - width, Vals1, width, label='V1')
rects2 = ax.bar(x, Vals2, width, label='V2')
rects3 = ax.bar(x + width, Vals3, width, label='V3')
ax.set_xticks(x)
ax.set_xticklabels(labels)
plt.xticks(rotation=90)
ax.legend()
yScale = [0.0019531,0.0039063,0.0078125,0.015625,0.03125,0.0625,0.125,0.25,0.5,1,2,4,8,16,32]
ax.set_yticks(yScale)
plt.show()
I believe I've stumbled upon the answer, here it is for anyone else looking for the solution. Add the argument bottom='1' to ax.bar instantiation, and then flip the values in the array.
for i in range(len(Vals1)):
Vals1[i] = (1 - Vals1[i]) * -1
As you mentioned, the key is the bottom param of Axes.bar:
bottom (default: 0): The y coordinate(s) of the bars bases.
But beyond that, you can simplify your plotting code using pandas:
Put your data into a DataFrame:
import pandas as pd
df = pd.DataFrame({'V1': Vals1, 'V2': Vals2, 'V3': Vals3}, index=labels)
# V1 V2 V3
# A 28.3232 0.00456 0.00320
# B 12.2320 17.86800 1.23400
# C 9.6132 13.45300 0.08214
Then use DataFrame.sub to subtract the offset and DataFrame.plot.bar with the bottom param:
bottom = 1
ax = df.sub(bottom).plot.bar(bottom=bottom)
I want to make a line graph where essentially (Dog,1), (Cat,2), (Bird,3) and so on are plotted and connected by line. In additional, I would like to be able to determine the order of the label in the X axis. Matplotlib auto-plotted with the order 'Dog', 'Cat', and 'Bird' label. Despite my attempt at re-arranging the order to 'Dog','Bird','Giraffe','Cat', the graph doesn't change (see image). What should I do to be able to arrange the graph accordingly?
x = ['Dog','Cat','Bird','Dog','Cat','Bird','Dog','Cat','Cat','Cat']
y = [1,2,3,4,5,6,7,8,9,10]
x_ticks_labels = ['Dog','Bird','Giraffe','Cat']
fig, ax = plt.subplots(1,1)
ax.plot(x,y)
# Set number of ticks for x-axis
ax.set_xticks(range(len(x_ticks_labels)))
# Set ticks labels for x-axis
ax.set_xticklabels(x_ticks_labels)
Use matplotlib's categorical feature
You may predetermine the order of categories on the axes by first plotting something in the correct order then removing it again.
import numpy as np
import matplotlib.pyplot as plt
x = ['Dog','Cat','Bird','Dog','Cat','Bird','Dog','Cat','Cat','Cat']
y = [1,2,3,4,5,6,7,8,9,10]
x_ticks_labels = ['Dog','Bird','Giraffe','Cat']
fig, ax = plt.subplots(1,1)
sentinel, = ax.plot(x_ticks_labels, np.linspace(min(y), max(y), len(x_ticks_labels)))
sentinel.remove()
ax.plot(x,y, color="C0", marker="o")
plt.show()
Determine indices of values
The other option is to determine the indices that the values from x would take inside of x_tick_labels. There is unfortunately no canonical way to do so; here I take the
solution from this answer using np.where. Then one can simply plot the y values against those indices and set the ticks and ticklabels accordingly.
import numpy as np
import matplotlib.pyplot as plt
x = ['Dog','Cat','Bird','Dog','Cat','Bird','Dog','Cat','Cat','Cat']
y = [1,2,3,4,5,6,7,8,9,10]
x_ticks_labels = ['Dog','Bird','Giraffe','Cat']
xarr = np.array(x)
ind = np.where(xarr.reshape(xarr.size, 1) == np.array(x_ticks_labels))[1]
fig, ax = plt.subplots(1,1)
ax.plot(ind,y, color="C0", marker="o")
ax.set_xticks(range(len(x_ticks_labels)))
ax.set_xticklabels(x_ticks_labels)
plt.show()
Result in both cases
I am saving two separate figures, that each should contain 2 plots together.
The problem is that the first figure is ok, but the second one, does not gets overwritten on the new plot but on the previous one, but in the saved figure, I only find one of the plots :
This is the first figure , and I get the first figure correctly :
import scipy.stats as s
import numpy as np
import os
import pandas as pd
import openpyxl as pyx
import matplotlib
matplotlib.rcParams["backend"] = "TkAgg"
#matplotlib.rcParams['backend'] = "Qt4Agg"
#matplotlib.rcParams['backend'] = "nbAgg"
import matplotlib.pyplot as plt
import math
data = [336256, 620316, 958846, 1007830, 1080401]
pdf = array([ 0.00449982, 0.0045293 , 0.00455894, 0.02397463,
0.02395788, 0.02394114])
fig, ax = plt.subplots();
fig = plt.figure(figsize=(40,30))
x = np.linspace(np.min(data), np.max(data), 100);
plt.plot(x, s.exponweib.pdf(x, *s.exponweib.fit(data, 1, 1, loc=0, scale=2)))
plt.hist(data, bins = np.linspace(data[0], data[-1], 100), normed=True, alpha= 1)
text1= ' Weibull'
plt.savefig(text1+ '.png' )
datar =np.asarray(data)
mu, sigma = datar.mean() , datar.std() # mean and standard deviation
normal_std = np.sqrt(np.log(1 + (sigma/mu)**2))
normal_mean = np.log(mu) - normal_std**2 / 2
hs = np.random.lognormal(normal_mean, normal_std, 1000)
print(hs.max()) # some finite number
print(hs.mean()) # about 136519
print(hs.std()) # about 50405
count, bins, ignored = plt.hist(hs, 100, normed=True)
x = np.linspace(min(bins), max(bins), 10000)
pdfT = [];
for el in range (len(x)):
pdfTmp = (math.exp(-(np.log(x[el]) - normal_mean)**2 / (2 * normal_std**2)))
pdfT += [pdfTmp]
pdf = np.asarray(pdfT)
This is the second set :
fig, ax = plt.subplots();
fig = plt.figure(figsize=(40,40))
plt.plot(x, pdf, linewidth=2, color='r')
plt.hist(data, bins = np.linspace(data[0], data[-1], 100), normed=True, alpha= 1)
text= ' Lognormal '
plt.savefig(text+ '.png' )
The first plot saves the histogram together with curve. instead the second one only saves the curve
update 1 : looking at This Question , I found out that clearing the plot history will help the figures don't mixed up , but still my second set of plots, I mean the lognormal do not save together, I only get the curve and not the histogram.
This is happening, because you have set normed = True, which means that area under the histogram is normalized to 1. And since your bins are very wide, this means that the actual height of the histogram bars are very small (in this case so small that they are not visible)
If you use
n, bins, _ = plt.hist(data, bins = np.linspace(data[0], data[-1], 100), normed=True, alpha= 1)
n will contain the y-value of your bins and you can confirm this yourself.
Also have a look at the documentation for plt.hist.
So if you set normed to False, the histogram will be visible.
Edit: number of bins
import numpy as np
import matplotlib.pyplot as plt
rand_data = np.random.uniform(0, 1.0, 100)
fig = plt.figure()
ax_1 = fig.add_subplot(211)
ax_1.hist(rand_data, bins=10)
ax_2 = fig.add_subplot(212)
ax_2.hist(rand_data, bins=100)
plt.show()
will give you two plots similar (since its random) to:
which shows how the number of bins changes the histogram.
A histogram visualises the distribution of your data along one dimension, so not sure what you mean by number of inputs and bins.
I'm writing a function that modifies the axes size and position on a figure, but when comes twin axes it makes a problem:
import matplotlib.pyplot as plt
def fig_layout(fig, vspace = 0.3): # function to make space at the bottom for legend box and
#+ other text input
for ax in ~~~fig.axes~~~: # Here 'fig.axes' is not right, I need to find the exact syntax
#+ I need to put
box = ax.get_position()
ax.set_position([box.x0, box.y0 + box.height * vspace,
box.width, box.height * (1 - vspace)])
x = np.arange(10)
fig = plt.figure()
ax1 = fig.add_subplot(1, 1, 1)
n = 3
line = {}
for i in range(3):
line['lines'].append(ax1.plot(x, i*x**2))
line['labels'].append(r'$y = %i \cdot x^2$'%i)
ax1.set_title('example plot')
ax2 = ax1.twinx()
line['lines'].append(ax2.plot(x, x^-1, label = r'$y = x^-1$'))
line['labels'].append(r'$y = x^-1$')
leg = ax1.legend(line['lines'], line['labels'])
fig_layout(fig)
# I will put the legend box at the bottom of the axes with another function.
plt.show()
I think you can use fig.get_axes().
For example, to modify the title of the first sub-plot, you can do:
plt.gcf().get_axes()[0].set_title("example plot")
I am plotting a histogram for some data points with bar heights being the percentage of that bin from the whole data:
x = normal(size=1000)
hist, bins = np.histogram(x, bins=20)
plt.bar(bins[:-1], hist.astype(np.float32) / hist.sum(), width=(bins[1]-bins[0]), alpha=0.6)
The result is:
I would like all bars that sum up to be 50% of the data to be in a different color, for example:
(I selected the colored bars without actually checking whether their sum adds to 50%)
Any suggestions how to accomplish this?
Here is how you can plot the first half of the bins with a different color, this looks like your mock, but I am not sure it complies to %50 of the data (it is not clear to me what do you mean by that).
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.mlab as mlab
mu, sigma = 100, 15
x = mu + sigma * np.random.randn(10000)
fig = plt.figure()
ax = fig.add_subplot(111)
# the histogram of the data
n, bins, patches = ax.hist(x, 50, normed=1, facecolor='green', alpha=0.75)
# now that we found the index we color all the beans smaller than middle index
for p in patches[:len(bins)/2]:
p.set_facecolor('red')
# hist uses np.histogram under the hood to create 'n' and 'bins'.
# np.histogram returns the bin edges, so there will be 50 probability
# density values in n, 51 bin edges in bins and 50 patches. To get
# everything lined up, we'll compute the bin centers
bincenters = 0.5*(bins[1:]+bins[:-1])
# add a 'best fit' line for the normal PDF
y = mlab.normpdf( bincenters, mu, sigma)
l = ax.plot(bincenters, y, 'r--', linewidth=1)
ax.set_xlabel('Smarts')
ax.set_ylabel('Probability')
ax.set_xlim(40, 160)
ax.set_ylim(0, 0.03)
ax.grid(True)
plt.show()
And the output is:
update
The key method you want to look at is patch.set_set_facecolor. You have to understand that almost everything you plot inside the axes object is a Patch, and as such it has this method, here is another example, I arbitrary choose the first 3 bars to have another color, you can choose based on what ever you decide:
import numpy as np
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
## the data
N = 5
menMeans = [18, 35, 30, 35, 27]
## necessary variables
ind = np.arange(N) # the x locations for the groups
width = 0.35 # the width of the bars
## the bars
rects1 = ax.bar(ind, menMeans, width,
color='black',
error_kw=dict(elinewidth=2,ecolor='red'))
for patch in rects1.patches[:3]:
patch.set_facecolor('red')
ax.set_xlim(-width,len(ind)+width)
ax.set_ylim(0,45)
ax.set_ylabel('Scores')
xTickMarks = ['Group'+str(i) for i in range(1,6)]
ax.set_xticks(ind)
xtickNames = ax.set_xticklabels(xTickMarks)
plt.setp(xtickNames, rotation=45, fontsize=10)
plt.show()