To contain large numbers of subplots as multipage output inside a single pdf, you will need to create a new page immediately after detecting that the most recent subplot addition in your iteration of plots has maxed out the available space in the current page's 𝑚-rows × 𝑛-cols subplot-array layout [i.e., an 𝑚 × 𝑛 matrix of subplots].
Here's a way to do it where the dimensions (𝑚 × 𝑛) controlling the number of subplots per page can easily be changed:
import sys
import timeit
import matplotlib
from matplotlib.backends.backend_pdf import PdfPages
import matplotlib.pyplot as plt
import numpy as np
matplotlib.rcParams.update({"font.size": 6})
# Dimensions for any m-rows × n-cols array of subplots / pg.
m, n = 4, 5
# Don't forget to indent after the with statement
with PdfPages("auto_subplotting.pdf") as pdf:
# Let's time the execution required to create and save
# each full page of subplots to the pdf
start_time = timeit.default_timer()
# Before beginning the iteration through all the data,
# initialize the layout for the plots and create a
# representation of the subplots that can be easily
# iterated over for knowing when to create the next page
# (and also for custom settings like partial axes labels)
f, axarr = plt.subplots(m, n, sharex="col", sharey="row")
arr_ij = [(x, y) for x, y in np.ndindex(axarr.shape)]
subplots = [axarr[index] for index in arr_ij]
# To conserve needed plotting real estate,
# only label the bottom row and leftmost subplots
# as determined automatically using m and n
splot_index = 0
for s, splot in enumerate(subplots):
splot.set_ylim(0, 0.15)
splot.set_xlim(0, 50)
last_row = m * n - s < n + 1
first_in_row = s % n == 0
if last_row:
splot.set_xlabel("X-axis label")
if first_in_row:
splot.set_ylabel("Y-axis label")
# Iterate through each sample in the data
for sample in range(33):
# As a stand-in for real data, let's just make numpy take 100 random draws
# from a poisson distribution centered around say ~25 and then display
# the outcome as a histogram
scaled_y = np.random.randint(20, 30)
random_data = np.random.poisson(scaled_y, 100)
subplots[splot_index].hist(
random_data,
bins=12,
normed=True,
fc=(0, 0, 0, 0),
lw=0.75,
ec="b",
)
# Keep subplotting through the samples in the data and increment
# a counter each time. The page will be full once the count is equal
# to the product of the user-set dimensions (i.e. n * m)
splot_index += 1
# We can basically repeat the same exact code block used for the
# first layout initialization, but with the addition of 4 new lines:
# 2 for saving the just-finished page to the pdf, 1 for the
# page's execution time, & 1 more to reset the subplot index
if splot_index == m * n:
pdf.savefig()
plt.close(f)
print(timeit.default_timer() - start_time)
start_time = timeit.default_timer()
f, axarr = plt.subplots(m, n, sharex="col", sharey="row")
arr_ij = [(x, y) for x, y in np.ndindex(axarr.shape)]
subplots = [axarr[index] for index in arr_ij]
splot_index = 0
for s, splot in enumerate(subplots):
splot.set_ylim(0, 0.15)
splot.set_xlim(0, 50)
last_row = (m * n) - s < n + 1
first_in_row = s % n == 0
if last_row:
splot.set_xlabel("X-axis label")
if first_in_row:
splot.set_ylabel("Y-axis label")
# Done!
# But don't forget to save to pdf after the last page
pdf.savefig()
plt.close(f)
For any m×n layout, just change the declarations for the values of m and n, respectively. Have a list of your plots ready, declared with the name subplots (for above code to work as is). From the code above (where "m, n = 4, 5"), a 4x5 matrix of subplots with a total 33 samples is produced as a two-page pdf output file:
Note:
There will be, on the final page of the multipage PDF, a number of blank subplots equal to the remainder from the the product of your chosen subplots 𝑚 × 𝑛 layout dimension numbers and your total number of samples/data to plot. E.g., say m=3, and n=4, thus you get 3 rows of 4 subplots each (ala 4 columns of 3 subplots each) and if you had 20 samples then there would be two pages auto-created with a total of 24 subplots in the PDF doc as a whole (both pages) with the last 4, so bottom-most row, of subplots on page 2 empty.
For a more advanced ( / more 'pythonic'*) extension, keep reading:
The multipage handling should probably be simplified by creating a new_page function; it's better to not repeat code verbatim*, especially if you start customizing the plots in which case you won't want to have to mirror every change and type the same thing twice. A more customized aesthetic based off of seaborn and utilizing the available matplotlib parameters like shown below might be preferable too.
Add a new_page function & some customizations for the subplot style:
import matplotlib.pyplot as plt
import numpy as np
import random
import seaborn as sns
import timeit
from matplotlib.backends.backend_pdf import PdfPages
# this erases labels for any blank plots on the last page
sns.set(font_scale=0.0)
m, n = 4, 6
datasize = 39 # 39 % (m*n) = 15, 24 (m*n) - 15 thus should result in 9 blank subplots on final page
ctheme = [
"k", "gray", "magenta", "fuchsia", "#be03fd", "#1e488f",
(0.44313725490196076, 0.44313725490196076, 0.88627450980392153), "#75bbfd",
"teal", "lime", "g", (0.6666674, 0.6666663, 0.29078014184397138), "y",
"#f1da7a", "tan", "orange", "maroon", "r", ] # pick whatever colors you wish
colors = sns.blend_palette(ctheme, datasize)
fz = 7 # labels fontsize
def new_page(m, n):
global splot_index
splot_index = 0
fig, axarr = plt.subplots(m, n, sharey="row")
plt.subplots_adjust(hspace=0.5, wspace=0.15)
arr_ij = [(x, y) for x, y in np.ndindex(axarr.shape)]
subplots = [axarr[index] for index in arr_ij]
for s, splot in enumerate(subplots):
splot.grid(
b=True,
which="major",
color="gray",
linestyle="-",
alpha=0.25,
zorder=1,
lw=0.5,
)
splot.set_ylim(0, 0.15)
splot.set_xlim(0, 50)
last_row = m * n - s < n + 1
first_in_row = s % n == 0
if last_row:
splot.set_xlabel("X-axis label", labelpad=8, fontsize=fz)
if first_in_row:
splot.set_ylabel("Y-axis label", labelpad=8, fontsize=fz)
return (fig, subplots)
with PdfPages("auto_subplotting_colors.pdf") as pdf:
start_time = timeit.default_timer()
fig, subplots = new_page(m, n)
for sample in xrange(datasize):
splot = subplots[splot_index]
splot_index += 1
scaled_y = np.random.randint(20, 30)
random_data = np.random.poisson(scaled_y, 100)
splot.hist(
random_data,
bins=12,
normed=True,
zorder=2,
alpha=0.99,
fc="white",
lw=0.75,
ec=colors.pop(),
)
splot.set_title("Sample {}".format(sample + 1), fontsize=fz)
# tick fontsize & spacing
splot.xaxis.set_tick_params(pad=4, labelsize=6)
splot.yaxis.set_tick_params(pad=4, labelsize=6)
# make new page:
if splot_index == m * n:
pdf.savefig()
plt.close(fig)
print(timeit.default_timer() - start_time)
start_time = timeit.default_timer()
fig, subplots = new_page(m, n)
if splot_index > 0:
pdf.savefig()
plt.close(f)
