We Keep Coding

Seaborn boxplot : set median color and set tick label colors to boxes color

I'm using this nice boxplot graph, answer from #Parfait.
I got an out of bound error on j and had to use range(i*5,i*5+5). Why?
I'd like to set the median to a particular color, let's say red. medianprops=dict(color="red") won't work. How to do it?
How to set the y-axis tick labels to the same color as the boxes?
Disclaimer: I don't know what I'm doing.
Here's the code using random data :
# import the required library
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import string
import matplotlib.colors as mc
import colorsys
# data
df = pd.DataFrame(np.random.normal(np.random.randint(5,15),np.random.randint(1,5),size=(100, 16)), columns=list(string.ascii_uppercase)[:16])
# Boxplot
fig, ax = plt.subplots(figsize=(9, 10))
medianprops=dict(color="red")
ax = sns.boxplot(data=df, orient="h", showfliers=False, palette = "husl")
ax = sns.stripplot(data=df, orient="h", jitter=True, size=7, alpha=0.5, palette = "husl") # show data points
ax.set_title("Title")
plt.xlabel("X label")
def lighten_color(color, amount=0.5):
# --------------------- SOURCE: #IanHincks ---------------------
try:
c = mc.cnames[color]
except:
c = color
c = colorsys.rgb_to_hls(*mc.to_rgb(c))
return colorsys.hls_to_rgb(c[0], 1 - amount * (1 - c[1]), c[2])
for i,artist in enumerate(ax.artists):
# Set the linecolor on the artist to the facecolor, and set the facecolor to None
col = lighten_color(artist.get_facecolor(), 1.2)
artist.set_edgecolor(col)
# Each box has 6 associated Line2D objects (to make the whiskers, fliers, etc.)
# Loop over them here, and use the same colour as above
for j in range(i*5,i*5+5):
line = ax.lines[j]
line.set_color(col)
line.set_mfc(col)
line.set_mec(col)
#line.set_linewidth(0.5)

To change the color of the median, you can use the medianprops in sns.boxplot(..., medianprops=...). If you also set a unique label, that label can be tested again when iterating through the lines.
To know how many lines belong to each boxplot, you can divide the number of lines by the number of artists (just after the boxplot has been created, before other elements have been added to the plot). Note that a line potentially has 3 colors: the line color, the marker face color and the marker edge color. Matplotlib creates the fliers as an invisible line with markers. The code below thus also changes these colors to make it more robust to different options and possible future changes.
Looping simultaneously through the boxes and the y tick labels allows copying the color. Making them a bit larger and darker helps for readability.
import matplotlib.pyplot as plt
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb, to_rgb
import seaborn as sns
import pandas as pd
import numpy as np
def enlighten(color, factor=0.5):
h, s, v = rgb_to_hsv(to_rgb(color))
return hsv_to_rgb((h, s, 1 - factor * (1 - v)))
def endarken(color, factor=0.5):
h, s, v = rgb_to_hsv(to_rgb(color))
return hsv_to_rgb((h, s, factor * v))
df = pd.DataFrame(np.random.normal(1, 5, size=(100, 16)).cumsum(axis=0),
columns=['Hydrogen', 'Helium', 'Lithium', 'Beryllium', 'Boron', 'Carbon', 'Nitrogen', 'Oxygen',
'Fluorine', 'Neon', 'Sodium', 'Magnesium', 'Aluminum', 'Silicon', 'Phosphorus', 'Sulfur'])
sns.set_style('white')
fig, ax = plt.subplots(figsize=(9, 10))
colors = sns.color_palette("husl", len(df.columns))
sns.boxplot(data=df, orient="h", showfliers=False, palette='husl',
medianprops=dict(color="yellow", label='median'), ax=ax)
lines_per_boxplot = len(ax.lines) // len(ax.artists)
for i, (box, ytick) in enumerate(zip(ax.artists, ax.get_yticklabels())):
ytick.set_color(endarken(box.get_facecolor()))
ytick.set_fontsize(20)
color = enlighten(box.get_facecolor())
box.set_color(color)
for lin in ax.lines[i * lines_per_boxplot: (i + 1) * lines_per_boxplot]:
if lin.get_label() != 'median':
lin.set_color(color)
lin.set_markerfacecolor(color)
lin.set_markeredgecolor(color)
sns.stripplot(data=df, orient="h", jitter=True, size=7, alpha=0.5, palette='husl', ax=ax)
sns.despine(ax=ax)
ax.set_title("Title")
ax.set_xlabel("X label")
plt.tight_layout()
plt.show()

I just answer point 2. of my question.
After tinkering, I found this to work :
# Each box has 5 associated Line2D objects (the whiskers and median)
# Loop over them here, and use the same colour as above
n=5 # this was for tinkering
for j in range(i*n,i*n+n):
if j != i*n+4 : line = ax.lines[j] # not the median
line.set_color(col)
Again, I don't know what I'm doing. So someone more knowledgeable may provide a more valuable answer.
I removed the stripplot for better clarity.

How to add (or annotate) value labels (or frequencies) on a matplotlib "histogram" chart

I want to add frequency labels to the histogram generated using plt.hist.
Here is the data :
np.random.seed(30)
d = np.random.randint(1, 101, size = 25)
print(sorted(d))
I looked up other questions on stackoverflow like :
Adding value labels on a matplotlib bar chart
and their answers, but apparantly, the objects returnded by plt.plot(kind='bar') are different than than those returned by plt.hist, and I got errors while using the 'get_height' or 'get width' functions, as suggested in some of the answers for bar plot.
Similarly, couldn't find the solution by going through the matplotlib documentation on histograms.
got this error

Here is how I managed it. If anyone has some suggestions to improve my answer, (specifically the for loop and using n=0, n=n+1, I think there must be a better way to write the for loop without having to use n in this manner), I'd welcome it.
# import base packages
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# generate data
np.random.seed(30)
d = np.random.randint(1, 101, size = 25)
print(sorted(d))
# generate histogram
# a histogram returns 3 objects : n (i.e. frequncies), bins, patches
freq, bins, patches = plt.hist(d, edgecolor='white', label='d', bins=range(1,101,10))
# x coordinate for labels
bin_centers = np.diff(bins)*0.5 + bins[:-1]
n = 0
for fr, x, patch in zip(freq, bin_centers, patches):
height = int(freq[n])
plt.annotate("{}".format(height),
xy = (x, height), # top left corner of the histogram bar
xytext = (0,0.2), # offsetting label position above its bar
textcoords = "offset points", # Offset (in points) from the *xy* value
ha = 'center', va = 'bottom'
)
n = n+1
plt.legend()
plt.show;

Fitting subplots, suptitle, legend into one figure WITHOUT tight_layout

I am creating a figure with a title, 16 subplots, and a legend. I cannot for the life of me get it to save nicely. I am going to try my best to explain my predicament but my vocabulary may not be correct, so I apologize in advanced.
If I run my code (end) I receive the following output:
That is not pretty, everything is overlapping or cut off. If I were to add plt.savefig() that is what I get.
I can drag the corners of the pop-up window and that gives me a very nicely spaced figure, and is precisely what I want:
However, the save function at the bottom of that pop up window does not always work, and I would much rather be able to create a nice figure in my code that i send to the plt.savefig() function.
In all my searches I keep seeing tight_layout being recommended as a fix to this. The issue with that is it adjusts my plot sizes rather than the spacing between plots, so my titles overlap and my data isn't as visible:
I have also tried constrained_layout() with zero success
I am really hoping there is an obvious solution I am missing, as taking screen shots of the plot isn't really working for me.
eq_csv = r'/here/is/the/file.csv'
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
eq_df = pd.read_csv(eq_csv)
eq_data = eq_df[['LON', 'LAT', 'DEPTH', 'MAG']] # retrieve only the columns I need
eq_data = eq_data.sort_values(['MAG'], ascending=False)
# Get the NSEW boundaries and the Magnitude min and max
nbound = max(eq_data.LAT) + 0.05
sbound = min(eq_data.LAT) - 0.05
ebound = max(eq_data.LON) + 0.01
wbound = min(eq_data.LON)
xlimit = (wbound, ebound)
ylimit = (sbound, nbound)
magmin = min(eq_data.MAG)
magmax = max(eq_data.MAG)
# Loop through depth slices and create a 4 x 4 figure of subplots
fig, axes = plt.subplots(4,4)
for ax in axes.flat:
for n in list(range(1, 17)):
km = eq_data[(eq_data.DEPTH > n - 1) & (eq_data.DEPTH <= n)]
km = km.sort_values(['MAG'], ascending=True)
plt.subplot(4, 4, n) # plot a 4x4 sub plot at the nth location
scatter = plt.scatter(km["LON"], km['LAT'], s=10, c=km['MAG'], vmin=magmin, vmax=magmax, alpha = 0.5)
plt.ylim(sbound, nbound)
plt.xlim(wbound, ebound)
plt.tick_params(axis='both', which='major', labelsize=4)
plt.yticks(rotation = 90)
plt.ylabel('Latitude', rotation = 90, size = 6)
plt.xlabel('Longitude', size = 6)
plt.subplots_adjust(hspace=0.65, wspace=0.25)
plt.gca().set_title('Depth = ' + str(n - 1) + 'km to ' + str(n) + 'km', size=8, fontweight = 'bold') # set title of subplots
plt.suptitle('Magnitude of Events at Different Depth Slices, 1950 to Today', size = 20, fontweight = 'bold')
plt.tight_layout()
fig.subplots_adjust(right=0.8) #adust location of plot
cbar_ax = fig.add_axes([0.85, 0.15, 0.01, 0.7]) #location of color bar
cbar = fig.colorbar(scatter, cax=cbar_ax)
cbar.set_alpha(1)
cbar.set_label('Magnitude', rotation = 270, labelpad = 10)
cbar.draw_all()
plt.show()
plt.savefig('save/location')

Bokeh: How to add a legend and custom color boundaries to an image plot?

I have a two-dimensional array that I want to plot using bokeh's bokeh.plotting.figure.Figure.image. It works wonderful.
Now, I want to add a legend using the colors used for the image. I don't find any example for my case. The legend that I'd like to achieve is similar to the picture.
from bokeh.models import LinearColorMapper, ColorBar
from bokeh.plotting import figure, show
plot = figure(x_range=(0,1), y_range=(0,1), toolbar_location="right")
color_mapper = LinearColorMapper(palette="YlGn9", low=-1, high=1, nan_color="white")
plot.image(image=[ndvi], color_mapper=color_mapper,dh=[1.0], dw=[1.0], x=[0], y=[0])
color_bar = ColorBar(color_mapper=color_mapper,label_standoff=12, border_line_color=None, location=(0,0))
plot.add_layout(color_bar, 'right')
Additionally, I'd like to have some custom color boundaries, with non-fixed intervals. Here is an example how it would be done with matplotlib:
cmap = colors.ListedColormap(['#27821f', '#3fa336', '#6ce362','#ffffff','#e063a8' ,'#cc3b8b','#9e008c','#59044f'])
bounds = [-1000, -500, -100, 0, 50, 100, 300, 500, 10000000]
norm = colors.BoundaryNorm(bounds, cmap.N)
fig, ax = plt.subplots()
ax.imshow(data, cmap=cmap, norm=norm)

You can choose the red-yellow-green palette. In bokeh the name is 'RdYlGn5', where the digit at the end tells how many colors are needed. To use it in a legend, you'ld need to import RdYlGn5 from bokeh.palettes.
For creating the legend, I only know of employing some dummy glyphs as in the code below.
I updated my example with the new requirements of setting custom bounds with non-fixed intervals. This post offers some guidance. Basically, the idea is to use a larger colormap with repeated colors. Such a format doesn't fit for general types of boundaries, but it fits yours, at least when the lowest and highest bound are interpreted to be infinite.
I also tried to layout the legend with some custom spaces to get all labels aligned. A background color is chosen to contrast with the legend entries.
There is a colorbar to verify how the colormap bounds work internally. After verification, you may leave it out. The example image has values from -1000 to 1000 to show how the values outside the strict colormap limits are handled.
Here is an example with dummy data:
from bokeh.models import LinearColorMapper, Legend, LegendItem, ColorBar, SingleIntervalTicker
from bokeh.plotting import figure, show
import numpy as np
x, y = np.meshgrid(np.linspace(0, 10, 1000), np.linspace(0, 10, 1000))
z = 1000*np.sin(x + np.cos(y))
plot = figure(x_range=(0, 1), y_range=(0, 1), toolbar_location="right")
base_colors = ['#27821f', '#3fa336', '#6ce362','#ffffff','#e063a8' ,'#cc3b8b','#9e008c','#59044f']
bounds = [-1000, -500, -100, 0, 50, 100, 300, 500, 10000000]
low = -600
high = 600
bound_colors = []
j = 0
for i in range(low, high, 50):
if i >= bounds[j+1]:
j += 1
bound_colors.append(base_colors[j])
color_mapper = LinearColorMapper(palette=bound_colors, low=low, high=high, nan_color="white")
plot.image(image=[z], color_mapper=color_mapper, dh=[1.0], dw=[1.0], x=[0], y=[0])
# these are a dummy glyphs to help draw the legend
dummy_for_legend = [plot.line(x=[1, 1], y=[1, 1], line_width=15, color=c, name='dummy_for_legend')
for c in base_colors]
legend_labels = [f' < {bounds[1]}'] + \
[('' if l < 0 else ' ' if l < 10 else ' ' if l < 100 else ' ')
+ f'{l} ‒ {h}' for l, h in zip(bounds[1:], bounds[2:-1])] + \
[f' > {bounds[-2]}']
legend1 = Legend(title="NDVI", background_fill_color='gold',
items=[LegendItem(label=lab, renderers=[gly]) for lab, gly in zip(legend_labels, dummy_for_legend) ])
plot.add_layout(legend1)
color_bar = ColorBar(color_mapper=color_mapper, label_standoff=12, border_line_color=None, location=(0, 0),
ticker=SingleIntervalTicker(interval=50))
plot.add_layout(color_bar)
show(plot)

python scatter plot with errorbars and colors mapping a physical quantity

I'm trying to do a quite simple scatter plot with error bars and semilogy scale. What is a little bit different from tutorials I have found is that the color of the scatterplot should trace a different quantity. On one hand, I was able to do a scatterplot with the errorbars with my data, but just with one color. On the other hand, I realized a scatterplot with the right colors, but without the errorbars.
I'm not able to combine the two different things.
Here an example using fake data:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import division
import numpy as np
import matplotlib.pyplot as plt
n=100
Lx_gas = 1e40*np.random.random(n) + 1e37
Tx_gas = np.random.random(n) + 0.5
Lx_plus_error = Lx_gas
Tx_plus_error = Tx_gas/2.
Tx_minus_error = Tx_gas/4.
#actually positive numbers, this is the quantity that should be traced by the
#color, in this example I use random numbers
Lambda = np.random.random(n)
#this is actually different from zero, but I want to be sure that this simple
#code works with the log axis
Lx_minus_error = np.zeros_like(Lx_gas)
#normalize the color, to be between 0 and 1
colors = np.asarray(Lambda)
colors -= colors.min()
colors *= (1./colors.max())
#build the error arrays
Lx_error = [Lx_minus_error, Lx_plus_error]
Tx_error = [Tx_minus_error, Tx_plus_error]
##--------------
##important part of the script
##this works, but all the dots are of the same color
#plt.errorbar(Tx_gas, Lx_gas, xerr = Tx_error,yerr = Lx_error,fmt='o')
##this is what is should be in terms of colors, but it is without the error bars
#plt.scatter(Tx_gas, Lx_gas, marker='s', c=colors)
##what I tried (and failed)
plt.errorbar(Tx_gas, Lx_gas, xerr = Tx_error,yerr = Lx_error,\
color=colors, fmt='o')
ax = plt.gca()
ax.set_yscale('log')
plt.show()
I even tried to plot the scatterplot after the errorbar, but for some reason everything plotted on the same window is put in background with respect to the errorplot.
Any ideas?
Thanks!

You can set the color to the LineCollection object returned by the errorbar as described here.
from __future__ import division
import numpy as np
import matplotlib.pyplot as plt
n=100
Lx_gas = 1e40*np.random.random(n) + 1e37
Tx_gas = np.random.random(n) + 0.5
Lx_plus_error = Lx_gas
Tx_plus_error = Tx_gas/2.
Tx_minus_error = Tx_gas/4.
#actually positive numbers, this is the quantity that should be traced by the
#color, in this example I use random numbers
Lambda = np.random.random(n)
#this is actually different from zero, but I want to be sure that this simple
#code works with the log axis
Lx_minus_error = np.zeros_like(Lx_gas)
#normalize the color, to be between 0 and 1
colors = np.asarray(Lambda)
colors -= colors.min()
colors *= (1./colors.max())
#build the error arrays
Lx_error = [Lx_minus_error, Lx_plus_error]
Tx_error = [Tx_minus_error, Tx_plus_error]
sct = plt.scatter(Tx_gas, Lx_gas, marker='s', c=colors)
cb = plt.colorbar(sct)
_, __ , errorlinecollection = plt.errorbar(Tx_gas, Lx_gas, xerr = Tx_error,yerr = Lx_error, marker = '', ls = '', zorder = 0)
error_color = sct.to_rgba(colors)
errorlinecollection[0].set_color(error_color)
errorlinecollection[1].set_color(error_color)
ax = plt.gca()
ax.set_yscale('log')
plt.show()