Develop Reference

How can you make a python histogram percentage sum to 100%?

I am struggling to make a histogram plot where the total percentage of events sums to 100%. Instead, for this particular example, it sums to approximately 3%. Will anyone be able to show me how I make the percentages of my events sum to 100% for any array used?
import matplotlib.pyplot as plt
from matplotlib.ticker import PercentFormatter
import numpy as np
plt.gca().yaxis.set_major_formatter(PercentFormatter(1))
data = np.array([0,9,78,6,44,23,88,77,12,29])
length_of_data = len(data) # Length of data
bins = int(np.sqrt(length_of_data)) # Choose number of bins
y = data
plt.title('Histogram')
plt.ylabel('Percentage Of Events')
plt.xlabel('bins')
plt.hist(y,bins=bins, density = True)
plt.show()
print(bins)

One way of doing it is to get the bin heights that plt.hist returns, then re-set the patch heights to the normalized height you want. It's not that involved if you know what to do, but not that ideal. Here's your case:
import matplotlib.pyplot as plt
from matplotlib.ticker import PercentFormatter
import numpy as np
plt.gca().yaxis.set_major_formatter(PercentFormatter(100)) # <-- changed here
data = np.array([0,9,78,6,44,23,88,77,12,29])
length_of_data = len(data) # Length of data
bins = int(np.sqrt(length_of_data)) # Choose number of bins
y = data
plt.title('Histogram')
plt.ylabel('Percentage Of Events')
plt.xlabel('bins')
#### Setting new heights
n, bins, patches = plt.hist(y, bins=bins, density = True, edgecolor='k')
scaled_n = n / n.sum() * 100
for new_height, patch in zip(scaled_n, patches):
patch.set_height(new_height)
####
# Setting cumulative sum as verification
plt.plot((bins[1:] + bins[:-1])/2, scaled_n.cumsum())
# If you want the cumsum to start from 0, uncomment the line below
#plt.plot(np.concatenate([[0], (bins[1:] + bins[:-1])/2]), np.concatenate([[0], scaled_n.cumsum()]))
plt.ylim(top=110)
plt.show()
This is the resulting picture:
As others said, you can use seaborn. Here's how to reproduce my code above. You'd still need to add all the labels and styling you want.
import seaborn as sns
sns.histplot(data, bins=int(np.sqrt(length_of_data)), stat='percent')
sns.histplot(data, bins=int(np.sqrt(length_of_data)), stat='percent', cumulative=True, element='poly', fill=False, color='C1')
This is the resulting picture:

How to plot a list of figures in a single subplot?

I have 2 lists of figures and their axes.
I need to plot each figure in a single subplot so that the figures become in one big subplot. How can I do that?
I tried for loop but it didn't work.
Here's what I have tried:
import ruptures as rpt
import matplotlib.pyplot as plt
# make random data with 100 samples and 9 columns
n_samples, n_dims, sigma = 100, 9, 2
n_bkps = 4
signal, bkps = rpt.pw_constant(n_samples, n_dims, n_bkps, noise_std=sigma)
figs, axs = [], []
for i in range(signal.shape[1]):
points = signal[:,i]
# detection of change points
algo = rpt.Dynp(model='l2').fit(points)
result = algo.predict(n_bkps=2)
fig, ax = rpt.display(points, bkps, result, figsize=(15,3))
figs.append(fig)
axs.append(ax)
plt.show()

I had a look at the source code of ruptures.display(), and it accepts **kwargs that are passed on to matplotlib. This allows us to redirect the output to a single figure, and with gridspec, we can position individual subplots within this figure:
import ruptures as rpt
import matplotlib.pyplot as plt
n_samples, n_dims, sigma = 100, 9, 2
n_bkps = 4
signal, bkps = rpt.pw_constant(n_samples, n_dims, n_bkps, noise_std=sigma)
#number of subplots
n_subpl = signal.shape[1]
#give figure a name to refer to it later
fig = plt.figure(num = "ruptures_figure", figsize=(8, 15))
#define grid of nrows x ncols
gs = fig.add_gridspec(n_subpl, 1)
for i in range(n_subpl):
points = signal[:,i]
algo = rpt.Dynp(model='l2').fit(points)
result = algo.predict(n_bkps=2)
#rpt.display(points, bkps, result)
#plot into predefined figure
_, curr_ax = rpt.display(points, bkps, result, num="ruptures_figure")
#position current subplot within grid
curr_ax[0].set_position(gs[i].get_position(fig))
curr_ax[0].set_subplotspec(gs[i])
plt.show()
Sample output:

Heatmap with circles indicating size of population

I would like to produce a heatmap in Python, similar to the one shown, where the size of the circle indicates the size of the sample in that cell. I looked in seaborn's gallery and couldn't find anything, and I don't think I can do this with matplotlib.

It's the inverse. While matplotlib can do pretty much everything, seaborn only provides a small subset of options.
So using matplotlib, you can plot a PatchCollection of circles as shown below.
Note: You could equally use a scatter plot, but since scatter dot sizes are in absolute units it would be rather hard to scale them into the grid.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.collections import PatchCollection
N = 10
M = 11
ylabels = ["".join(np.random.choice(list("PQRSTUVXYZ"), size=7)) for _ in range(N)]
xlabels = ["".join(np.random.choice(list("ABCDE"), size=3)) for _ in range(M)]
x, y = np.meshgrid(np.arange(M), np.arange(N))
s = np.random.randint(0, 180, size=(N,M))
c = np.random.rand(N, M)-0.5
fig, ax = plt.subplots()
R = s/s.max()/2
circles = [plt.Circle((j,i), radius=r) for r, j, i in zip(R.flat, x.flat, y.flat)]
col = PatchCollection(circles, array=c.flatten(), cmap="RdYlGn")
ax.add_collection(col)
ax.set(xticks=np.arange(M), yticks=np.arange(N),
xticklabels=xlabels, yticklabels=ylabels)
ax.set_xticks(np.arange(M+1)-0.5, minor=True)
ax.set_yticks(np.arange(N+1)-0.5, minor=True)
ax.grid(which='minor')
fig.colorbar(col)
plt.show()

Here's a possible solution using Bokeh Plots:
import pandas as pd
from bokeh.palettes import RdBu
from bokeh.models import LinearColorMapper, ColumnDataSource, ColorBar
from bokeh.models.ranges import FactorRange
from bokeh.plotting import figure, show
from bokeh.io import output_notebook
import numpy as np
output_notebook()
d = dict(x = ['A','A','A', 'B','B','B','C','C','C','D','D','D'],
y = ['B','C','D', 'A','C','D','B','D','A','A','B','C'],
corr = np.random.uniform(low=-1, high=1, size=(12,)).tolist())
df = pd.DataFrame(d)
df['size'] = np.where(df['corr']<0, np.abs(df['corr']), df['corr'])*50
#added a new column to make the plot size
colors = list(reversed(RdBu[9]))
exp_cmap = LinearColorMapper(palette=colors,
low = -1,
high = 1)
p = figure(x_range = FactorRange(), y_range = FactorRange(), plot_width=700,
plot_height=450, title="Correlation",
toolbar_location=None, tools="hover")
p.scatter("x","y",source=df, fill_alpha=1, line_width=0, size="size",
fill_color={"field":"corr", "transform":exp_cmap})
p.x_range.factors = sorted(df['x'].unique().tolist())
p.y_range.factors = sorted(df['y'].unique().tolist(), reverse = True)
p.xaxis.axis_label = 'Values'
p.yaxis.axis_label = 'Values'
bar = ColorBar(color_mapper=exp_cmap, location=(0,0))
p.add_layout(bar, "right")
show(p)

One option is to use matplotlib's scatter plots with legends and grid. You can specify size of those circles with specifying the scales. You can also change the color of each circle. You should somehow specify X,Y values so that the circles sit straight on lines. This is an example I got from here:
volume = np.random.rayleigh(27, size=40)
amount = np.random.poisson(10, size=40)
ranking = np.random.normal(size=40)
price = np.random.uniform(1, 10, size=40)
fig, ax = plt.subplots()
# Because the price is much too small when being provided as size for ``s``,
# we normalize it to some useful point sizes, s=0.3*(price*3)**2
scatter = ax.scatter(volume, amount, c=ranking, s=0.3*(price*3)**2,
vmin=-3, vmax=3, cmap="Spectral")
# Produce a legend for the ranking (colors). Even though there are 40 different
# rankings, we only want to show 5 of them in the legend.
legend1 = ax.legend(*scatter.legend_elements(num=5),
loc="upper left", title="Ranking")
ax.add_artist(legend1)
# Produce a legend for the price (sizes). Because we want to show the prices
# in dollars, we use the *func* argument to supply the inverse of the function
# used to calculate the sizes from above. The *fmt* ensures to show the price
# in dollars. Note how we target at 5 elements here, but obtain only 4 in the
# created legend due to the automatic round prices that are chosen for us.
kw = dict(prop="sizes", num=5, color=scatter.cmap(0.7), fmt="$ {x:.2f}",
func=lambda s: np.sqrt(s/.3)/3)
legend2 = ax.legend(*scatter.legend_elements(**kw),
loc="lower right", title="Price")
plt.show()
Output:

I don't have enough reputation to comment on Delenges' excellent answer, so I'll leave my comment as an answer instead:
R.flat doesn't order the way we need it to, so the circles assignment should be:
circles = [plt.Circle((j,i), radius=R[j][i]) for j, i in zip(x.flat, y.flat)]

Here is an easy example to plot circle_heatmap.
from matplotlib import pyplot as plt
import pandas as pd
from sklearn.datasets import load_wine as load_data
from psynlig import plot_correlation_heatmap
plt.style.use('seaborn-talk')
data_set = load_data()
data = pd.DataFrame(data_set['data'], columns=data_set['feature_names'])
#data = df_corr_selected
kwargs = {
'heatmap': {
'vmin': -1,
'vmax': 1,
'cmap': 'viridis',
},
'figure': {
'figsize': (14, 10),
},
}
plot_correlation_heatmap(data, bubble=True, annotate=False, **kwargs)
plt.show()

Proper Matplotlib axes construction / reuse

I currently am building a set of scatter plot charts using pandas plot.scatter. In this construction off of two base axes.
My current construction looks akin to
ax1 = pandas.scatter.plot()
ax2 = pandas.scatter.plot(ax=ax1)
for dataframe in list:
output_ax = pandas.scatter.plot(ax2)
output_ax.get_figure().save("outputfile.png")
total_output_ax = total_list.scatter.plot(ax2)
total_output_ax.get_figure().save("total_output.png")
This seems inefficient. For 1...N permutations I want to reuse a base axes that has 50% of the data already plotted. What I am trying to do is:
Add base data to scatter plot
For item x in y: (save data to base scatter and save image)
Add all data to scatter plot and save image

here's one way to do it with plt.scatter.
I plot column 0 on x-axis, and all other columns on y axis, one at a time.
Notice that there is only 1 ax object, and I don't replot all points, I just add points using the same axes with a for loop.
Each time I get a corresponding png image.
import numpy as np
import pandas as pd
np.random.seed(2)
testdf = pd.DataFrame(np.random.rand(20,4))
testdf.head(5) looks like this
0 1 2 3
0 0.435995 0.025926 0.549662 0.435322
1 0.420368 0.330335 0.204649 0.619271
2 0.299655 0.266827 0.621134 0.529142
3 0.134580 0.513578 0.184440 0.785335
4 0.853975 0.494237 0.846561 0.079645
#I put the first axis out of a loop, that can be in the loop as well
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(testdf[0],testdf[1], color='red')
fig.legend()
fig.savefig('fig_1.png')
colors = ['pink', 'green', 'black', 'blue']
for i in range(2,4):
ax.scatter(testdf[0], testdf[i], color=colors[i])
fig.legend()
fig.savefig('full_' + str(i) + '.png')
Then you get these 3 images (fig_1, fig_2, fig_3)

Axes objects cannot be simply copied or transferred. However, it is possible to set artists to visible/invisible in a plot. Given your ambiguous question, it is not fully clear how your data are stored but it seems to be a list of dataframes. In any case, the concept can easily be adapted to different input data.
import matplotlib.pyplot as plt
#test data generation
import pandas as pd
import numpy as np
rng = np.random.default_rng(123456)
df_list = [pd.DataFrame(rng.integers(0, 100, (7, 2))) for _ in range(3)]
#plot all dataframes into an axis object to ensure
#that all plots have the same scaling
fig, ax = plt.subplots()
patch_collections = []
for i, df in enumerate(df_list):
pc = ax.scatter(x=df[0], y=df[1], label=str(i))
pc.set_visible(False)
patch_collections.append(pc)
#store individual plots
for i, pc in enumerate(patch_collections):
pc.set_visible(True)
ax.set_title(f"Dataframe {i}")
fig.savefig(f"outputfile{i}.png")
pc.set_visible(False)
#store summary plot
[pc.set_visible(True) for pc in patch_collections]
ax.set_title("All dataframes")
ax.legend()
fig.savefig(f"outputfile_0_{i}.png")
plt.show()

How to make standard deviation and percentile bands in a python scatter plot

I have data for a scatter plot (for reference, x values are labelled sm, y values are labelled bhm) and my three goals are to find the medians of binned data, create standard deviation bands, and create bands at the 90th and 10th percentiles. I've managed to do the first, and while I've been able to make vertical bars indicating the standard deviation, I can't figure out how to make filled-in bands since every time I try to set parameters with the fill_between function, it says operators with sm/bhm are incompatible since they're datasets and I'm comparing them to singular values (the mean line). I copied all of my code down below and there's a comment pointing out the relevant stuff - I just kept all of it since the variable names are a bit important and also because some parts of the plot don't show up properly without the seemingly extraneous code
To create the bands at 90/10 percent, I tried this bit of code by trying to bin the mean as I did for the median, and then filling the top and bottom of the line +-90% of the data but I keep getting
patsy.PatsyError: model is missing required outcome variables
#stuff that really doesn't work
model = smf.quantreg(bhm, sm)
quantiles = [0.1, 0.9]
fits = [model.fit(q=q) for q in quantiles]
figure, axes = plt.subplots()
_sm = np.linspace(min(sm), max(sm))
for index, quantile in enumerate(quantiles):
_bhm = fits[index].params['world'] * _sm +
fits[index].params['Intercept']
axes.plot(_sm, _bhm, label = quantile)
axes.plot(_sm, _sm, 'g--', label = 'i guess this line is the mean')
#stuff that also doesn't really work
import matplotlib.pyplot as plt
import numpy as np
import matplotlib.patches as mpatches
import h5py
import statistics as stat
import pandas as pd
import statsmodels.formula.api as smf
#my files and labels for things
f=h5py.File(r'C:\Users\hanna\Downloads\CatalogueGalsz0p0.hdf5', 'r')
sm = f['StellarMass']
bhm = f['BHMass']
bt = f['BtoT']
dt = f['DtoT']
nbins = 125
#titles and scaling for the plot
plt.title('Relationships Between Stellar Mass, Black Hole Mass, and Bulge
to Total Ratios')
plt.xlabel('Stellar Mass')
plt.ylabel('Black Hole Mass')
plt.xscale('log')
plt.yscale('log')
axes = plt.gca()
axes.set_ylim([500000,max(bhm)])
axes.set_xlim([min(sm),max(sm)])
#labels for the legend and how I colored the points in the plot
DtoT = np.copy(f['DtoT'].value)
colour = np.zeros(len(DtoT),dtype=str)
for i in np.arange(0, len(bt)):
if bt[i]>=0.5:
colour[i]='green'
else:
colour[i]='red'
redbt = mpatches.Patch(color = 'red', label = 'Bulge to Total Ratios Below 0.5')
greenbt = mpatches.Patch(color = 'green', label = 'Bulge to Total Ratios Above 0.5')
plt.legend(handles = [(redbt), (greenbt)])
#the important part - this is how I binned my data to make the median line, and this part works but not the standard deviation bands
bins = np.linspace(0, max(sm), nbins)
delta = bins[1]-bins[0]
idx = np.digitize(sm, bins)
runningmedian = [np.median(bhm[idx==k]) for k in range(nbins)]
runningstd = [bhm[idx==k].std() for k in range(nbins)]
plt.plot(bins-delta/2, runningmedian, c = 'b', lw=1)
plt.scatter(sm, bhm, c=colour, s=.2)
plt.show()