How to plot a superimposed bar chart using matplotlib in python? - python

I want to plot a bar chart or a histogram using matplotlib. I don't want a stacked bar plot, but a superimposed barplot of two lists of data, for instance I have the following two lists of data with me:
Some code to begin with :
import matplotlib.pyplot as plt
from numpy.random import normal, uniform
highPower = [1184.53,1523.48,1521.05,1517.88,1519.88,1414.98,1419.34,
1415.13,1182.70,1165.17]
lowPower = [1000.95,1233.37, 1198.97,1198.01,1214.29,1130.86,1138.70,
1104.12,1012.95,1000.36]
plt.hist(highPower, bins=10, histtype='stepfilled', normed=True,
color='b', label='Max Power in mW')
plt.hist(lowPower, bins=10, histtype='stepfilled', normed=True,
color='r', alpha=0.5, label='Min Power in mW')
I want to plot these two lists against the number of values in the two lists such that I am able to see the variation per reading.

You can produce a superimposed bar chart using plt.bar() with the alpha keyword as shown below.
The alpha controls the transparency of the bar.
N.B. when you have two overlapping bars, one with an alpha < 1, you will get a mixture of colours. As such the bar will appear purple even though the legend shows it as a light red. To alleviate this I have modified the width of one of the bars, this way even if your powers should change you will still be able to see both bars.
plt.xticks can be used to set the location and format of the x-ticks in your graph.
import matplotlib.pyplot as plt
import numpy as np
width = 0.8
highPower = [1184.53,1523.48,1521.05,1517.88,1519.88,1414.98,
1419.34,1415.13,1182.70,1165.17]
lowPower = [1000.95,1233.37, 1198.97,1198.01,1214.29,1130.86,
1138.70,1104.12,1012.95,1000.36]
indices = np.arange(len(highPower))
plt.bar(indices, highPower, width=width,
color='b', label='Max Power in mW')
plt.bar([i+0.25*width for i in indices], lowPower,
width=0.5*width, color='r', alpha=0.5, label='Min Power in mW')
plt.xticks(indices+width/2.,
['T{}'.format(i) for i in range(len(highPower))] )
plt.legend()
plt.show()

Building on #Ffisegydd's answer, if your data is in a Pandas DataFrame, this should work nicely:
def overlapped_bar(df, show=False, width=0.9, alpha=.5,
title='', xlabel='', ylabel='', **plot_kwargs):
"""Like a stacked bar chart except bars on top of each other with transparency"""
xlabel = xlabel or df.index.name
N = len(df)
M = len(df.columns)
indices = np.arange(N)
colors = ['steelblue', 'firebrick', 'darksage', 'goldenrod', 'gray'] * int(M / 5. + 1)
for i, label, color in zip(range(M), df.columns, colors):
kwargs = plot_kwargs
kwargs.update({'color': color, 'label': label})
plt.bar(indices, df[label], width=width, alpha=alpha if i else 1, **kwargs)
plt.xticks(indices + .5 * width,
['{}'.format(idx) for idx in df.index.values])
plt.legend()
plt.title(title)
plt.xlabel(xlabel)
plt.ylabel(ylabel)
if show:
plt.show()
return plt.gcf()
And then in a python command line:
low = [1000.95, 1233.37, 1198.97, 1198.01, 1214.29, 1130.86, 1138.70, 1104.12, 1012.95, 1000.36]
high = [1184.53, 1523.48, 1521.05, 1517.88, 1519.88, 1414.98, 1419.34, 1415.13, 1182.70, 1165.17]
df = pd.DataFrame(np.matrix([high, low]).T, columns=['High', 'Low'],
index=pd.Index(['T%s' %i for i in range(len(high))],
name='Index'))
overlapped_bar(df, show=False)

It is actually simpler than the answers all over the internet make it appear.
a = range(1,10)
b = range(4,13)
ind = np.arange(len(a))
fig = plt.figure()
ax = fig.add_subplot(111)
ax.bar(x=ind, height=a, width=0.35,align='center')
ax.bar(x=ind, height=b, width=0.35/3, align='center')
plt.xticks(ind, a)
plt.tight_layout()
plt.show()

Related

How to customize seaborn boxplot with specific color sequence when boxplots have hue

I want to make boxplots with hues but I want to color code it so that each specific X string is a certain color with the hue just being a lighter color. I am able to do a boxplot without a hue. When I incorporate the hue, I get the second boxplot which loses the colors. Can someone help me customize the colors for the figure that contains the hue?
Essentially, its what the answer for this question is but with boxplots.
This is my code:
first boxplot
order=['Ash1','E1A','FUS','p53']
colors=['gold','teal','darkorange','royalblue']
color_dict=dict(zip(order,colors))
fig,ax=plt.subplots(figsize=(25,15))
bp=sns.boxplot(data=df_idrs, x=df_idrs["construct"], y=df_idrs['Norm_Ef_IDR/Ef_GS'],ax=ax,palette=color_dict)
sns.stripplot(ax=ax,y='Norm_Ef_IDR/Ef_GS', x='construct', data=df_idrs,palette=color_dict,
jitter=1, marker='o', alpha=0.4,edgecolor='black',linewidth=1, dodge=True)
ax.axhline(y=1,linestyle="--",color='black',linewidth=2)
plt.legend(loc='upper left', bbox_to_anchor=(1.03, 1))
second boxplot
order=['Ash1','E1A','FUS','p53']
colors=['gold','teal','darkorange','royalblue']
color_dict=dict(zip(order,colors))
fig,ax=plt.subplots(figsize=(25,15))
bp=sns.boxplot(data=df_idrs, x=df_idrs["construct"], y=df_idrs['Norm_Ef_IDR/Ef_GS'],ax=ax, hue=df_idrs["location"])
sns.stripplot(y='Norm_Ef_IDR/Ef_GS', x='construct', data=df_idrs, hue=df_idrs["location"],
jitter=1, marker='o', alpha=0.4,edgecolor='black',linewidth=1, dodge=True)
ax.axhline(y=1,linestyle="--",color='black',linewidth=2)
plt.legend(loc='upper left', bbox_to_anchor=(1.03, 1))
The only thing that changed was the palette to hue. I have seen many examples on here but I am unable to get them to work. Using the second code, I have tried the following:
Nothing happens for this one.
for ind, bp in enumerate(ax.findobj(PolyCollection)):
rgb = to_rgb(colors[ind // 2])
if ind % 2 != 0:
rgb = 0.5 + 0.5 * np.array(rgb) # make whiter
bp.set_facecolor(rgb)
I get index out of range for the following one.
for i in range(0,4):
mybox = bp.artists[i]
mybox.set_facecolor(color_dict[order[i]])
Matplotlib stores the boxes in ax.patches, but there are also 2 dummy patches (used to construct the legend) that need to be filtered away. The dots of the stripplot are stored in ax.collections. There are also 2 dummy collections for the legend, but as those come at the end, they don't form a problem.
Some remarks:
sns.boxplot returns the subplot on which it was drawn; as it is called with ax=ax it will return that same ax
Setting jitter=1in the stripplot will smear the dots over a width of 1. 1 is the distance between the x positions, and the boxes are only 0.4 wide. To avoid clutter, the code below uses jitter=0.4.
Here is some example code starting from dummy test data:
from matplotlib import pyplot as plt
from matplotlib.legend_handler import HandlerTuple
from matplotlib.patches import PathPatch
from matplotlib.colors import to_rgb
import seaborn as sns
import pandas as pd
import numpy as np
np.random.seed(20230215)
order = ['Ash1', 'E1A', 'FUS', 'p53']
colors = ['gold', 'teal', 'darkorange', 'royalblue']
hue_order = ['A', 'B']
df_idrs = pd.DataFrame({'construct': np.repeat(order, 200),
'Norm_Ef_IDR/Ef_GS': (np.random.normal(0.03, 1, 800).cumsum() + 10) / 15,
'location': np.tile(np.repeat(hue_order, 100), 4)})
fig, ax = plt.subplots(figsize=(12, 5))
sns.boxplot(data=df_idrs, x=df_idrs['construct'], y=df_idrs['Norm_Ef_IDR/Ef_GS'], hue='location',
order=order, hue_order=hue_order, ax=ax)
box_colors = [f + (1 - f) * np.array(to_rgb(c)) # whiten colors depending on hue
for c in colors for f in np.linspace(0, 0.5, len(hue_order))]
box_patches = [p for p in ax.patches if isinstance(p, PathPatch)]
for patch, color in zip(box_patches, box_colors):
patch.set_facecolor(color)
sns.stripplot(y='Norm_Ef_IDR/Ef_GS', x='construct', data=df_idrs, hue=df_idrs['location'],
jitter=0.4, marker='o', alpha=0.4, edgecolor='black', linewidth=1, dodge=True, ax=ax)
for collection, color in zip(ax.collections, box_colors):
collection.set_facecolor(color)
ax.axhline(y=1, linestyle='--', color='black', linewidth=2)
handles = [tuple(box_patches[i::len(hue_order)]) for i in range(len(hue_order))]
ax.legend(handles=handles, labels=hue_order, title='hue category',
handlelength=4, handler_map={tuple: HandlerTuple(ndivide=None, pad=0)},
loc='upper left', bbox_to_anchor=(1.01, 1))
plt.tight_layout()
plt.show()

How do I plot percentage labels for a horizontal bar graph in Python?

Can someone please help me plot x axis labels in percentages given the following code of my horizontal bar chart?
Finding it difficult to find as I want a more simplistic chart without x axis labels and ticks.
[Horizontal Bar Chart][1]
# Plot the figure size
plt.figure(figsize= (8,6))
# New variable and plot the question of the data frame in a normalized in a horizontal bar chat.
ax1 = df[q1].value_counts(normalize=True).sort_values().plot(kind="barh", color='#fd6a02', width=0.75, zorder=2)
# Draw vague vertical axis lines and set lines to the back of the order
vals = ax1.get_xticks()
for tick in vals:
ax1.axvline(x=tick, linestyle='dashed', alpha=0.4, color = '#d3d3d3', zorder=1)
# Tot3als to produce a composition ratio
total_percent = df[q1].value_counts(normalize=True) *100
# Remove borders
ax1.spines['right'].set_visible(False)
ax1.spines['top'].set_visible(False)
ax1.spines['left'].set_visible(False)
ax1.spines['bottom'].set_visible(False)
# Set the title of the graph inline with the Y axis labels.
ax1.set_title(q1, weight='bold', size=14, loc = 'left', pad=20, x = -0.16)
# ax.text(x,y,text,color)
for i,val in enumerate(total):
ax1.text(val - 1.5, i, str("{:.2%}".format(total_percent), color="w", fontsize=10, zorder=3)
# Create axis labels
plt.xlabel("Ratio of Responses", labelpad=20, weight='bold', size=12)
Each time I get a EOF error. Can someone help?
It's not based on your code, but I'll customize the answer from the official reference.
The point is achieved with ax.text(), which is a looping process.
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))
ax.barh(y_pos, performance, align='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.invert_yaxis() # labels read top-to-bottom
ax.set_xlabel('Performance')
ax.set_title('How fast do you want to go today?')
# Totals to produce a composition ratio
total = sum(performance)
# ax.text(x,y,text,color)
for i,val in enumerate(performance):
ax.text(val - 1.5, i, str("{:.2%}".format(val/total)), color="w", fontsize=10)
plt.show()

How to plot a paired histogram using seaborn

I would like to make a paired histogram like the one shown here using the seaborn distplot.
This kind of plot can also be referred to as the back-to-back histogram shown here, or a bihistogram inverted/mirrored along the x-axis as discussed here.
Here is my code:
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
green = np.random.normal(20,10,1000)
blue = np.random.poisson(60,1000)
fig, ax = plt.subplots(figsize=(8,6))
sns.distplot(blue, hist=True, kde=True, hist_kws={'edgecolor':'black'}, kde_kws={'linewidth':2}, bins=10, color='blue')
sns.distplot(green, hist=True, kde=True, hist_kws={'edgecolor':'black'}, kde_kws={'linewidth':2}, bins=10, color='green')
ax.set_xticks(np.arange(-20,121,20))
ax.set_yticks(np.arange(0.0,0.07,0.01))
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
plt.show()
Here is the output:
When I use the method discussed here (plt.barh), I get the bar plot shown just below, which is not what I am looking for.
Or maybe I haven't understood the workaround well enough...
A simple/short implementation of python-seaborn-distplot similar to these kinds of plots would be perfect. I edited the figure of my first plot above to show the kind of plot I hope to achieve (though y-axis not upside down):
Any leads would be greatly appreciated.
You could use two subplots and invert the y-axis of the lower one and plot with the same bins.
df = pd.DataFrame({'a': np.random.normal(0,5,1000), 'b': np.random.normal(20,5,1000)})
fig =plt.figure(figsize=(5,5))
ax = fig.add_subplot(211)
ax2 = fig.add_subplot(212)
bins = np.arange(-20,40)
ax.hist(df['a'], bins=bins)
ax2.hist(df['b'],color='orange', bins=bins)
ax2.invert_yaxis()
edit:
improvements suggested by #mwaskom
fig, axes = plt.subplots(nrows=2, ncols=1, sharex=True, figsize=(5,5))
bins = np.arange(-20,40)
for ax, column, color, invert in zip(axes.ravel(), df.columns, ['teal', 'orange'], [False,True]):
ax.hist(df[column], bins=bins, color=color)
if invert:
ax.invert_yaxis()
plt.subplots_adjust(hspace=0)
Here is a possible approach using seaborn's displots.
Seaborn doesn't return the created graphical elements, but the ax can be interrogated. To make sure the ax only contains the elements you want upside down, those elements can be drawn first. Then, all the patches (the rectangular bars) and the lines (the curve for the kde) can be given their height in negative. Optionally the x-axis can be set at y == 0 using ax.spines['bottom'].set_position('zero').
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
green = np.random.normal(20, 10, 1000)
blue = np.random.poisson(60, 1000)
fig, ax = plt.subplots(figsize=(8, 6))
sns.distplot(green, hist=True, kde=True, hist_kws={'edgecolor': 'black'}, kde_kws={'linewidth': 2}, bins=10,
color='green')
for p in ax.patches: # turn the histogram upside down
p.set_height(-p.get_height())
for l in ax.lines: # turn the kde curve upside down
l.set_ydata(-l.get_ydata())
sns.distplot(blue, hist=True, kde=True, hist_kws={'edgecolor': 'black'}, kde_kws={'linewidth': 2}, bins=10,
color='blue')
ax.set_xticks(np.arange(-20, 121, 20))
ax.set_yticks(np.arange(0.0, 0.07, 0.01))
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
pos_ticks = np.array([t for t in ax.get_yticks() if t > 0])
ticks = np.concatenate([-pos_ticks[::-1], [0], pos_ticks])
ax.set_yticks(ticks)
ax.set_yticklabels([f'{abs(t):.2f}' for t in ticks])
ax.spines['bottom'].set_position('zero')
plt.show()

How to make a bar chart with only a height indicator not showing the full bar?

This chart almost looks good but is probably not the way to model this in matplotlib. How to have two horizontal bars that extend to the left and right of vertical line at an x-point to show the change of the two datasets eg SDR from 0.7 to 0.25.
Currently i patch things together with '$-$' markers which make misaligned legends and i am not able to place properly. If i change the figsize the markers start misaligning from the vertical bar at their x-point, eg SDR.
How to model this kind of chart proberly?
layer0 = np.random.random(10)
fig, ax = plt.subplots(1,1, figsize=(15/2,1.5*2.5),)
ind = np.arange(10, dtype=np.float64)*1#cordx
ax.plot(ind[0::2]+0.05, layer0[0::2]-0.04, ls='None', marker='$-$', markersize=40)
ax.plot(ind[1::2]-0.15, layer0[1::2]-0.04, ls='None', marker='$-$', markersize=40)
ax.set_ylim(0,1.05)
ax.set_yticks(np.arange(0, 1.1, step=0.1))
ax.set_xticks(ind[0::2]+0.5)
ax.set_xticklabels( ('SDR', 'SSR', 'SCR', 'RCR', 'GUR') )
plt.grid(b=True)
plt.grid(color='black', which='major', axis='y', linestyle='--', lw=0.2)
plt.show()
Alternatively, you can use a horizontal bar chart barh which is more intuitive in this case. Here the key parameter is left which will shift your horizontal bar charts to left/right.
Following is a complete answer:
import numpy as np
import matplotlib.pyplot as plt
np.random.seed(2)
layer0 = np.random.random(10)
fig, ax = plt.subplots(1,1, figsize=(15/2,1.5*2.5),)
n = 10
width = 0.5
ind = np.arange(n, dtype=np.float64)*1#cordx
ax.barh(layer0[0::2], [width]*int(n/2), height=0.01, left = ind[0::2])
ax.barh(layer0[1::2], [width]*int(n/2), height=0.01, left = ind[0::2]+width)
ax.set_ylim(0,1.05)
ax.set_yticks(np.arange(0, 1.1, step=0.1))
ax.set_xticks(ind[0::2]+0.5)
ax.set_xticklabels( ('SDR', 'SSR', 'SCR', 'RCR', 'GUR') )
plt.grid(b=True)
plt.grid(color='black', which='major', axis='y', linestyle='--', lw=0.2)
plt.show()
up until now i havent thought of bar charts with bottom offset, which seems to be ok:
layer0 = np.random.random(10)
fig, ax = plt.subplots(1,1, figsize=(15/1.3,1.5*2.5),)# sharey=True)
ind = np.arange(10, dtype=np.float64)*1#cordx
height=0.03
width=0.8
ax.bar(ind[0::2]-width/2, height, width=width, bottom=layer0[0::2]-height)
ax.bar(ind[0::2]+width/2, height, width=width, bottom=layer0[1::2]-height)
ax.set_ylim(-0.,1.05)
plt.grid(color='black', which='major', axis='x', linestyle='-', lw=0.8)

Python - dual y axis chart, align zero

I'm trying to create a horizontal bar chart, with dual x axes. The 2 axes are very different in scale, 1 set goes from something like -5 to 15 (positive and negative value), the other set is more like 100 to 500 (all positive values).
When I plot this, I'd like to align the 2 axes so zero shows at the same position, and only the negative values are to the left of this. Currently the set with all positive values starts at the far left, and the set with positive and negative starts in the middle of the overall plot.
I found the align_yaxis example, but I'm struggling to align the x axes.
Matplotlib bar charts: Aligning two different y axes to zero
Here is an example of what I'm working on with simple test data. Any ideas/suggestions? thanks
import pandas as pd
import matplotlib.pyplot as plt
d = {'col1':['Test 1','Test 2','Test 3','Test 4'],'col 2':[1.4,-3,1.3,5],'Col3':[900,750,878,920]}
df = pd.DataFrame(data=d)
fig = plt.figure() # Create matplotlib figure
ax = fig.add_subplot(111) # Create matplotlib axes
ax2 = ax.twiny() # Create another axes that shares the same y-axis as ax.
width = 0.4
df['col 2'].plot(kind='barh', color='darkblue', ax=ax, width=width, position=1,fontsize =4, figsize=(3.0, 5.0))
df['Col3'].plot(kind='barh', color='orange', ax=ax2, width=width, position=0, fontsize =4, figsize=(3.0, 5.0))
ax.set_yticklabels(df.col1)
ax.set_xlabel('Positive and Neg',color='darkblue')
ax2.set_xlabel('Positive Only',color='orange')
ax.invert_yaxis()
plt.show()
I followed the link from a question and eventually ended up at this answer : https://stackoverflow.com/a/10482477/5907969
The answer has a function to align the y-axes and I have modified the same to align x-axes as follows:
def align_xaxis(ax1, v1, ax2, v2):
"""adjust ax2 xlimit so that v2 in ax2 is aligned to v1 in ax1"""
x1, _ = ax1.transData.transform((v1, 0))
x2, _ = ax2.transData.transform((v2, 0))
inv = ax2.transData.inverted()
dx, _ = inv.transform((0, 0)) - inv.transform((x1-x2, 0))
minx, maxx = ax2.get_xlim()
ax2.set_xlim(minx+dx, maxx+dx)
And then use it within the code as follows:
import pandas as pd
import matplotlib.pyplot as plt
d = {'col1':['Test 1','Test 2','Test 3','Test 4'],'col 2' [1.4,-3,1.3,5],'Col3':[900,750,878,920]}
df = pd.DataFrame(data=d)
fig = plt.figure() # Create matplotlib figure
ax = fig.add_subplot(111) # Create matplotlib axes
ax2 = ax.twiny() # Create another axes that shares the same y-axis as ax.
width = 0.4
df['col 2'].plot(kind='barh', color='darkblue', ax=ax, width=width, position=1,fontsize =4, figsize=(3.0, 5.0))
df['Col3'].plot(kind='barh', color='orange', ax=ax2, width=width, position=0, fontsize =4, figsize=(3.0, 5.0))
ax.set_yticklabels(df.col1)
ax.set_xlabel('Positive and Neg',color='darkblue')
ax2.set_xlabel('Positive Only',color='orange')
align_xaxis(ax,0,ax2,0)
ax.invert_yaxis()
plt.show()
This will give you what you're looking for

Categories