How to show a confidence interval in python using matplotlib? - python

I need to show a confidence interval, like in this image:
but I don't know how to do it. I've tried doing lb.fill_between(x, (y1-ci), (y1+ci), color = 'b', alpha = 0.1) but it returns the error: AttributeError: 'list' object has no attribute 'fill_between'.
This is my code:
import matplotlib.pyplot as plt
x = [10, 100, 1000]
y1 = [215103, 22824279.7, 22063128311]
y2 = [211298.5, 21315505.2, 20563930722]
plt.subplot(2, 2, 1)
ci = 1300
#la = plt.plot(x,y,'b*', label = 'normal')
lb = plt.plot(x,y1, '#FA8072', label = 'LI')
lc = plt.plot(x,y2, '#7FFFD4', label = 'LU')
plt.legend(loc = 'upper left')
plt.title("L1-dcache-loads")
plt.xscale("log")
Thanks in advance!

Use fill_between like this:
plt.figure()
plt.fill_between(x, y1, y2, edgecolor='g', facecolor='g', alpha=0.3)
y1 is your lower bound curve, and y2 is your upper bound curve. Output:
In your example:
plt.figure()
plt.plot(x,y1, '#FA8072', label = 'LI')
plt.fill_between(x, np.array(y1)-ci, np.array(y1)+ci, edgecolor='r', facecolor='r', alpha=0.3)
plt.plot(x,y2, '#7FFFD4', label = 'LU')
plt.fill_between(x, np.array(y2)-ci, np.array(y2)+ci, edgecolor='g', facecolor='g', alpha=0.3)
plt.legend(loc = 'upper left')
plt.title("L1-dcache-loads")
plt.xscale("log")
But the intervals are too small to see.

Related

Calculate distance between the center of a point on a scatter plot to the edge of it's marker, for dynamically changing marker sizes in Matplotlib

I have a scatter plot which I'd like to place by another scatter plot, however they have a dynamic marker size.
The green triangles (x, y) are calculated from the original scatter and they're close but not perfect (just from trial and error).
import pandas as pd
from mplsoccer import Pitch, VerticalPitch
data = [['JA', 35, 60, 2000], ['RN', 20, 47, 1500], ['GG', 10, 32, 1000]]
df = pd.DataFrame(data, columns=['Name', 'x', 'y', 'marker_size'])
#This is calculated from x or y length divided by marker size of biggest marker,
# divide by 2 for the radius, but the marker sizes seem to be non-linear.
df['xDiff'] = df['marker_size'] * ((7.3/2000) / 2)
df['yDiff'] = df['marker_size'] * ((11.3/2000) / 2)
df['leftArrowX'] = df['x'] - df['xDiff']
df['leftArrowY'] = df['y']
df['rightArrowX'] = df['x'] + df['xDiff']
df['rightArrowY'] = df['y']
df['downArrowY'] = df['y'] - df['yDiff']
df['downArrowX'] = df['x']
df['upArrowY'] = df['y'] + df['yDiff']
df['upArrowX'] = df['x']
pitch = Pitch(pitch_type='opta', pitch_color='#202428', line_color='#F2F2F2', linewidth=2)
fig, ax = pitch.draw(figsize=(16, 10))
players = pitch.scatter(df.x, df.y, s=df.marker_size, marker='8', color='orange', edgecolors='black', linewidth=1, alpha=1, ax=ax)
leftArrows = pitch.scatter(df.leftArrowX, df.leftArrowY, s=100, marker='<', color='lightgreen', alpha=1, ax=ax)
rightArrows = pitch.scatter(df.rightArrowX, df.rightArrowY, s=100, marker='>', color='lightgreen', alpha=1, ax=ax)
downArrows = pitch.scatter(df.downArrowX, df.downArrowY, s=100, marker='v', color='lightgreen', alpha=1, ax=ax)
upArrows = pitch.scatter(df.upArrowX, df.upArrowY, s=100, marker='^', color='lightgreen', alpha=1, ax=ax)
Result
How can I calculate the co-ordinates for the triangles more accurately given the original marker co-ordinates & marker size, so that they are placed evenly away at each point.
Or possibly any other solution to my problem.
Note: The pitch has co-ordinates 100x100, done in Jupyter Notebook. Thanks.

Matplotlib/Pandas - Plot not reflective of data

Trying to work out what is going wrong. I am using pandas to generate dataframes and matplotlib to plot a figure with 5 subplots.
Datasets are large xlsx sheets, all data is relative to depth below ground surface, duplicate depths have been removed, all number as text errors have been removed, although depth is shown between 0 - 60 ft data is not continuous over entire interval.
What I am going for
Current issue, x-axis not reflecting trends of data, line plotted straight through data
#Import libraries
import matplotlib.pyplot as plt
import pandas as pd
#Import Excel Data
df1 = pd.read_excel (r'017_FLD_and_FLS.xlsx')
df2 = pd.read_excel (r'017_SUMD_SUMS.xlsx')
#Sort data for plotting
gam = list(df2['Natural Gamma'])
cal_Pre = list(df2['Caliper (pre-pumping)'])
cal_post = list(df2['Caliper (post-pumping)'])
fc = list(df2['Formation Conductivity'])
fr = list(df2['Formation Resistivity'])
neu = list(df2['Neutron'])
den = list(df2['Spherical Density (long-S)'])
htp = list(df1['Heat Pulse Flow'])
tp = list(df1['Static Fluid Temperature'])
t1 = list(df1['Pumping Temperature Run 1'])
t2 = list(df1['Pumping Temperature Run 2'])
t3 = list(df1['Pumping Temperature Run 3'])
depth = list(df2['Depth'])
depth_t = list(df1['Depth'])
#Test to verify subset
#print(gam)
#print (tp)
#Plot space
fig = plt.figure(figsize=(15,20))
# Caliper
ax01 = plt.subplot(151)
plt.plot(cal_Pre, depth, color="black")
ax01 = plt.gca()
ax01.invert_yaxis()
ax01.set_xlabel('Caliper (Inches)', color="black")
ax01.set_ylabel('Depth (Feet)', color="black")
plt.grid(True)
ax11 = ax01.twiny()
ax11.plot(cal_post, depth, color = 'green')
ax11.set_xlabel('Gamma (counts)', color="green")
ax11.tick_params(axis='x', labelcolor="green")
plt.grid(True, linestyle='--')
# Gamma
ax02 = plt.subplot(152)
plt.plot(cal_Pre, depth, color="black")
ax02 = plt.gca()
ax02.invert_yaxis()
ax02.set_xlabel('Caliper (Inches)', color="black")
plt.grid(True)
# Neutron Density
ax03 = plt.subplot(153, sharey=ax01)
plt.plot(den, depth, color = 'red')
ax03 = plt.gca()
ax03.invert_yaxis()
ax03.set_xlabel('Density (counts)', color = 'red')
ax03.tick_params(axis='x', labelcolor="red")
plt.grid(True)
ax13 = ax03.twiny()
ax13.plot(neu, depth, color = 'blue')
ax13.invert_xaxis()
ax13.set_xlabel('Neutron (counts)', color="blue")
ax13.tick_params(axis='x', labelcolor="blue")
plt.grid(True, linestyle='--')
# Conductivity and Resistivity
ax04 = plt.subplot(154, sharey=ax01)
plt.plot(fc, depth, color="black")
ax04 = plt.gca()
ax04.invert_yaxis()
ax04.set_xlabel('Formation Conductivity(mS/cm)', color="black")
ax04.tick_params(axis='x', labelcolor="black")
plt.grid(True)
ax14 = ax04.twiny()
ax14.plot(fr, depth, color = 'blue')
ax14.invert_xaxis()
ax14.set_xlabel('Formation Resistivity (ohm-m)', color="blue")
ax14.tick_params(axis='x', labelcolor="blue")
plt.grid(True, linestyle='--')
# Temperature and heat pulse
ax05 = plt.subplot(155)
plt.plot(htp, depth_t, color="black")
ax05 = plt.gca()
ax05.invert_yaxis()
ax05.set_xlabel('Heat Pulse Flow (gpm)', color="black")
ax05.set_ylabel('Depth (Feet)', color="black")
plt.grid(True)
ax15 = ax05.twiny()
ax15.plot(tp, depth_t, color = 'blue')
ax15.invert_xaxis()
ax15.set_xlabel('Formation Resistivity (ohm-m)', color="blue")
ax15.tick_params(axis='x', labelcolor="blue")
ax15 = ax05.twiny()
ax15.plot(t3, depth_t, color = 'blue')
ax15.invert_xaxis()
ax15.set_xlabel('Formation Resistivity (ohm-m)', color="blue")
ax15.tick_params(axis='x', labelcolor="blue")
plt.grid(True, linestyle='--')
fig.suptitle('GB017', fontsize=30, x=0.5, y=1.01)
fig.tight_layout()
plt.show()
Open to suggestions on making code more elegant but maintaining ease of figure modification.

Gradient fill from zero till a curve

I have been using Is it possible to get color gradients under curve in matplotlib? as a reference (you can see the similarities, however i cant for the life of me figure out how to push the shading all the way down to 0 on the Y AXIS, for some reason which i cant find out, it has an upward sloping straight line cutting off the shading, i cant find anything in my data to suggest why its doing this.
for context the y axis can show positive and negative and i want to fill the scale the whole way so using gradient colour to fill from 0 to the line (positive) then fill from 0 to the negative line (see my blue example from a previous chart -same data-)
Here is my code
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors as mcolors
from matplotlib.patches import Polygon
# Variables
AUM = df['#AHD_AUM'].head(104)
MM = df['#AHD_Managed_Money_Net'].head(104)
PRICE = df['#AHD_Price'].head(104)
DATES = df['DATES'].head(104)
# Date Friendly Variables for Plot
List_AUM = df['#AHD_AUM'].head(104).to_list()
List_MM = df['#AHD_Managed_Money_Net'].head(104).to_list()
List_DATES = df['DATES'].head(104).to_list()
X = 0 * df['#AHD_AUM'].head(104)
# Make a date list changing dates with numbers to avoid the issue with the plot
interpreting dates
for i in range(len(df['DATES'].head(104))):
count = i
df['count'][i] = 120 - i
# X and Y data variables changed to arrays as when i had these set as dates
matplotlib hates it
x = df['count'].head(104).to_numpy()
y = df['#AHD_Managed_Money_Net'].head(104).to_numpy()
#DD = AUM.to_numpy()
#MMM = MM.to_numpy()
def main():
for _ in range(len(DD)):
gradient_fill(x,y)
plt.show()
def gradient_fill(x,y, fill_color=None, ax=None, **kwargs):
"""
"""
if ax is None:
ax = plt.gca()
line, = ax.plot(x, y, **kwargs)
if fill_color is None:
fill_color = line.get_color()
zorder = line.get_zorder()
alpha = line.get_alpha()
alpha = 1.0 if alpha is None else alpha
z = np.empty((100, 1, 4), dtype=float)
rgb = mcolors.colorConverter.to_rgb(fill_color)
z[:,:,:3] = rgb
z[:,:,-1] = np.linspace(0, alpha, 100)[:,None]
xmin, xmax, ymin, ymax = x.min(), x.max(), y.min(), y.max()
im = ax.imshow(z, aspect='auto', extent=[xmin, xmax, ymin, ymax],
origin='lower', zorder=zorder)
xy = np.column_stack([x, y])
# xy = np.vstack([[xmin, ymin], xy, [xmax, ymin], [xmin, ymin]]) ### i dont
need this so i have just commented it out
clip_path = Polygon(xy, facecolor='none', edgecolor='none', closed=True)
ax.add_patch(clip_path)
im.set_clip_path(clip_path)
ax.autoscale(True)
return line, im
main()
this is my current output
An easier way to clip the gradient by the curve, is to use a polygon obtained from fill_between.
Here is some example code to get you started.
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(123)
x = np.linspace(0, 10, 200)
y = np.random.normal(0.01, 1, 200).cumsum()
fig, ax = plt.subplots(figsize=(12, 5))
ax.plot(x, y)
ylim = ax.get_ylim()
grad1 = ax.imshow(np.linspace(0, 1, 256).reshape(-1, 1), cmap='Blues', vmin=-0.5, aspect='auto',
extent=[x.min(), x.max(), 0, y.max()], origin='lower')
poly_pos = ax.fill_between(x, y.min(), y, alpha=0.1)
grad1.set_clip_path(poly_pos.get_paths()[0], transform=ax.transData)
poly_pos.remove()
grad2 = ax.imshow(np.linspace(0, 1, 256).reshape(-1, 1), cmap='Reds', vmin=-0.5, aspect='auto',
extent=[x.min(), x.max(), y.min(), 0], origin='upper')
poly_neg = ax.fill_between(x, y, y.max(), alpha=0.1)
grad2.set_clip_path(poly_neg.get_paths()[0], transform=ax.transData)
poly_neg.remove()
ax.set_ylim(ylim)
ax.axhline(0, color='black') # show a line at x=0
plt.show()
PS: vmin in imshow can be used to remove the color range where it's very light:
grad1 = ax.imshow(np.linspace(0, 1, 256).reshape(-1, 1), cmap='Blues', vmin=-0.5, aspect='auto',
extent=[x.min(), x.max(), 0, y.max()], origin='lower')
grad2 = ax.imshow(np.linspace(0, 1, 256).reshape(-1, 1), cmap='Reds', vmin=-0.5, aspect='auto',
extent=[x.min(), x.max(), y.min(), 0], origin='upper')
import pandas as pd # For data handling
import seaborn as sns # For plotting
import numpy as np
import matplotlib.pyplot as plt # For plotting
import matplotlib
#some preferred user settings
plt.rcParams['figure.figsize'] = (18.0, 12.0)
pd.set_option('display.max_columns', None)
%matplotlib inline
import warnings
warnings.filterwarnings(action='ignore')
from mpl_toolkits.axisartist.parasite_axes import HostAxes, ParasiteAxes
import matplotlib.pyplot as plt
from matplotlib.ticker import MultipleLocator
import datetime as dt
import matplotlib.dates as mdates
import pandas
Metal = CAD
# Variables
AUM = Metal.iloc[:,[7]].head(104)
MM = Metal.iloc[:,[0]].head(104)
PRICE = Metal.iloc[:,[8]].head(104)
#Last_Report = Metal.iloc[:,[9]].head(1).dt.strftime('%d %b %Y').to_list()
DATES = Metal.iloc[:,[10]].head(104)
# Dataframe for Net Position High
Net_High = Metal[Metal.iloc[:,[0]] == Metal.iloc[:,[0]].max()]
# Variables for Chart Annotation for Net Position High
Pos_High_Date = Net_High.iloc[:, [0]]
Pos_High_AUM = Net_High.iloc[:, [7]][0]/[1000000000]
Pos_High_Price = Net_High.iloc[:, [8]].to_numpy()[0].round().astype('int')
Pos_High = Net_High.iloc[:, [0]][0].astype('int')
Str_Date = mdates.num2date(Pos_High_Date)
Str_Date = pd.to_datetime(Str_Date[0]).strftime("%d %b %y")[0]
# Dataframe for Net Position Low
Net_Low = df[df['#CAD_Managed_Money_Net'] == df['#CAD_Managed_Money_Net'].head(104).min()]
# Variables for Chart Annotation for Net Position High
Pos_Low_Date = Net_Low.iloc[:, [55]].to_numpy()
Pos_Low_AUM = Net_Low.iloc[:, [26]].to_numpy()[0].round()/[1000000000]
Pos_Low_Price = Net_Low.iloc[:, [27]].to_numpy()[0].round().astype('int')
Pos_Low = Net_Low['#CAD_Managed_Money_Net'][0].astype('int')
Str_Date_Low = mdates.num2date(Pos_Low_Date)
Str_Date_Low = pd.to_datetime(Str_Date_Low[0]).strftime("%d %b %y")[0]
# C Brand Colour Scheme
C = ['deepskyblue', '#003399', 'slategray', '#027608','#cc0000']
def make_patch_spines_invisible(ax):
ax.set_frame_on(True)
ax.patch.set_visible(False)
for sp in ax.spines.values():
sp.set_visible(False)
fig, host = plt.subplots(figsize=(25,15))
fig.subplots_adjust(right=0.8)
#twinx() creates another axes sharing the x axis we do this twice
par1 = host.twinx()
par2 = host.twinx()
# Offset the right spine of par2 the ticks
par2.spines["right"].set_position(("axes",1.08))
#because par2 was created by twinx the frame is off so we need to use the method created above
make_patch_spines_invisible(par2)
# second, show the right spine
par2.spines["right"].set_visible(True)
######### Colouring in Plots
x = DATES
y = MM
ylim = host.get_ylim()
Long = host.imshow(np.linspace(0, 1, 256).reshape(-1, 1), cmap= 'Blues', vmin=-0.5, aspect='auto',
extent=[x.min(), x.max(), 0, y.max()], origin='lower')
poly_pos = host.fill_between(x, y.min(), y, alpha=0.1)
Long.set_clip_path(poly_pos.get_paths()[0], transform=host.transData)
poly_pos.remove()
Short = host.imshow(np.linspace(0, 1, 256).reshape(-1, 1), cmap='OrRd', vmin=-0.5, aspect='auto',
extent=[x.min(), x.max(), y.min(), 0], origin='upper')
poly_neg = host.fill_between(x, y, y.max(), alpha=0.1)
Short.set_clip_path(poly_neg.get_paths()[0], transform=host.transData)
poly_neg.remove()
##########
#plot data
p1, = host.plot(DATES, MM, label="Managed Money Net Position", linewidth=0.0,color = Citi[1], alpha = 0.8)
p2, = par1.plot(DATES, AUM, label="AUM",linewidth=1, marker = '$A$',mew = 1,mfc = 'w', color = Citi[0], alpha = 0.8)
p3, = par2.plot(DATES, PRICE, label="3M Price",linewidth=1, marker = '$p$', color = Citi[2], alpha = 0.8)
#Automatically scale and format
host_labels = ['{:,.0f}'.format(x) + 'K Lots' for x in host.get_yticks()/1000]
host.set_yticklabels(host_labels)
par1_labels = ['{:,.1f}'.format(x) + ' $Billion' for x in par1.get_yticks()/1000000000]
par1.set_yticklabels(par1_labels)
par2_labels = ['{:,.0f}'.format(x) + ' $' for x in par2.get_yticks()]
par2.set_yticklabels(par2_labels)
# x Axis formatting (date)
formatter = matplotlib.dates.DateFormatter('%b- %Y')
host.xaxis.set_major_formatter(formatter)
# Rotates and right-aligns the x labels so they don't crowd each other.
for label in host.get_xticklabels(which='major'):
label.set(rotation=30, horizontalalignment='right')
# Axis Labels
host.set_xlabel("Date")
host.set_ylabel("Managed Money Net Position")
par1.set_ylabel("AUM")
par2.set_ylabel("3M Price")
# Tick Parameters
tkw = dict(size=10, width=2.5)
# Set tick colours
host.tick_params(axis = 'y', colors = Citi[1], **tkw)
par1.tick_params(axis = 'y', colors = Citi[0], **tkw)
par2.tick_params(axis = 'y', colors = Citi[2], **tkw)
#host.tick_params(which='major',axis = 'x',direction='out', colors = Citi[2], **tkw)
#plt.xticks(x, rotation='vertical')
#host.xaxis.set_major_locator(AutoMajorLocator())
host.xaxis.set_major_locator(MultipleLocator(24))
host.tick_params('x',which='major', length=7)
#Label colours taken from plot
host.yaxis.label.set_color(p1.get_color())
par1.yaxis.label.set_color(p2.get_color())
par2.yaxis.label.set_color(p3.get_color())
# Map Title
host.set_title('Aluminium Managed Money Net Positioning as of %s'% Last_Report[0],fontsize='large')
#Colour Spines cant figure out how to do it for the host
par1.spines["right"].set_edgecolor(p2.get_color())
par2.spines["right"].set_edgecolor(p3.get_color())
###### Annotation Tests ##########
## Net Position High Box
host.annotate(f' Net Position High | {Pos_High} \n Date | {Str_Date} \n AUM | ${Pos_High_AUM[0].round(1)} Billion\n 3M Price | ${Pos_High_Price[0]}$',
xy=(Pos_High_Date, Pos_High), xycoords='data',
xytext=(0.02, .85), textcoords='axes fraction',
horizontalalignment='left',
verticalalignment='bottom',
color='white',
bbox=dict(boxstyle="round", fc= Citi[1],edgecolor='white'),
arrowprops=dict(
facecolor='black',
arrowstyle= '->'))
## Net Position Low Box
host.annotate(f' Net Position Low | {Pos_Low} \n Date | {Str_Date_Low} \n AUM | ${Pos_Low_AUM[0].round(1)} Billion\n 3M Price | ${Pos_Low_Price[0]}$',
xy=(Pos_Low_Date, Pos_Low), xycoords='data',
xytext=(0.02, .80), textcoords='axes fraction',
horizontalalignment='left',
verticalalignment='top',
color='white',
bbox=dict(boxstyle="round", fc= Citi[4],edgecolor='white'),
arrowprops=dict(
facecolor='black',
arrowstyle= '->'))
################
# Legend - a little complicated as we have to take from multiple axis
lines = [p1, p2, p3]
########## Plot text and line on chart if you want to
# host.axvline(x = DATES[52] , linestyle='dotted', color='black') ###Dotted Line when Needed
# host.text(2020.3, 10, 'Managed Money \n Aluminium')
# host.text(2020.5, 92, r'Ali',color='black')
# host.text(2020.8,15, r'some event', rotation=90)
host.legend(lines,[l.get_label() for l in lines],loc=2, fontsize=12,frameon=False)
plt.savefig('multiple_axes.png', dpi=300, bbox_inches='tight')

Matplot lib animation not working as expected

I have 4 variables like this:
# generate 4 random variables from the random, gamma, exponential, and uniform distributions
x1 = np.random.normal(-2.5, 1, 10000)
x2 = np.random.gamma(2, 1.5, 10000)
x3 = np.random.exponential(2, 10000)+7
x4 = np.random.uniform(14,20, 10000)
And I need to create one figure with 4 subplots.
so I tried this:
plt.figure(figsize=(9,3))
plt.subplot(1,4,1)
plt.hist(x1, normed=True, bins=20, alpha=0.5)
plt.subplot(1,4,2)
plt.hist(x2, normed=True, bins=20, alpha=0.5)
plt.subplot(1,4,3)
plt.hist(x3, normed=True, bins=20, alpha=0.5)
plt.subplot(1,4,4)
plt.hist(x4, normed=True, bins=20, alpha=0.5)
plt.axis([-7,21,0,0.6])
And I got this result
Now I want to create an animation on the subplots, so I did the following (trying one subplot only)
import matplotlib.animation as animation
def update(curr):
if curr == n:
a.event_source.stop()
plt.cla()
plt.figure(figsize=(9,3))
plt.subplot(1,4,1)
plt.hist(x1, normed=True, bins=20, alpha=0.5)
plt.axis([-7,21,0,0.6])
plt.gca().set_title('Sample')
plt.gca().set_ylabel('Frequency')
plt.gca().set_xlabel('Value')
plt.annotate('n = {}'.format(curr), [3.27])
fig = plt.figure()
a = animation.FuncAnimation(fig, update, interval=100)
However the end result is empty, nothing is shown.
Any idea?
I re-structured your code in order to plot the animation of the 4 subplots.
Without any specific indication on what you want to see changing between one frame and the next, I assume the number of sample drawn from each distribution is inscreasing in each frame by 10.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.animation import FuncAnimation
def update(curr):
N = 10*curr
x1 = np.random.normal(-2.5, 1, N)
x2 = np.random.gamma(2, 1.5, N)
x3 = np.random.exponential(2, N) + 7
x4 = np.random.uniform(14, 20, N)
ax[0].cla()
ax[0].hist(x1, bins = 20, alpha = 0.5, color = 'blue', edgecolor = 'blue')
ax[0].set_title('Normal')
ax[0].set_ylabel('Frequency')
ax[0].set_xlabel('Value')
ax[0].set_xlim(-6, 1)
ax[1].cla()
ax[1].hist(x2, bins = 20, alpha = 0.5, color = 'blue', edgecolor = 'blue')
ax[1].set_title('Gamma')
ax[1].set_ylabel('Frequency')
ax[1].set_xlabel('Value')
ax[1].set_xlim(0, 12)
ax[2].cla()
ax[2].hist(x3, bins = 20, alpha = 0.5, color = 'blue', edgecolor = 'blue')
ax[2].set_title('Exponential')
ax[2].set_ylabel('Frequency')
ax[2].set_xlabel('Value')
ax[2].set_xlim(7, 25)
ax[3].cla()
ax[3].hist(x4, bins = 20, alpha = 0.5, color = 'blue', edgecolor = 'blue')
ax[3].set_title('Uniform')
ax[3].set_ylabel('Frequency')
ax[3].set_xlabel('Value')
ax[3].set_xlim(14, 20)
ax[0].set_ylim(0, 250)
fig.suptitle(f'Number of samples: {N}')
plt.tight_layout()
fig, ax = plt.subplots(1, 4, figsize = (9, 3), sharey = 'all')
a = FuncAnimation(fig, update, interval = 100, frames = 81)
plt.show()

matplotlib uneven group size bar charts side-by-side

I am trying to plot groups of data which have different bar sizes and may have different group sizes. How can I group the bars that belong to the same groups (shown as the same color) so that they are side by side? (Similar to this, except the same colors should be side-by-side)
width = 0.50
groupgap=2
y1=[20,80]
y2=[60,30,10]
x1 = np.arange(len(y1))
x2 = np.arange(len(y2))+groupgap
ind = np.concatenate((x1,x2))
fig, ax = plt.subplots()
rects1 = ax.bar(x1, y1, width, color='r', ecolor= "black",label="Gender")
rects2 = ax.bar(x2, y2, width, color='b', ecolor= "black",label="Type")
ax.set_ylabel('Population',fontsize=14)
ax.set_xticks(ind)
ax.set_xticklabels(('Male', 'Female','Student', 'Faculty','Others'),fontsize=14)
ax.legend()
The idea of using a gap between the categories (groupgap) is indeed a way to go. You would just have to add the length of the first group as well:
x2 = np.arange(len(y2))+groupgap+len(y1)
Here is the complete example where I used groupgap=1:
import matplotlib.pyplot as plt
import numpy as np
width = 1
groupgap=1
y1=[20,80]
y2=[60,30,10]
x1 = np.arange(len(y1))
x2 = np.arange(len(y2))+groupgap+len(y1)
ind = np.concatenate((x1,x2))
fig, ax = plt.subplots()
rects1 = ax.bar(x1, y1, width, color='r', edgecolor= "black",label="Gender")
rects2 = ax.bar(x2, y2, width, color='b', edgecolor= "black",label="Type")
ax.set_ylabel('Population',fontsize=14)
ax.set_xticks(ind)
ax.set_xticklabels(('Male', 'Female','Student', 'Faculty','Others'),fontsize=14)
plt.show()

Categories