I have two lists, when I plot with the following code, the x axis only shows up to 12 (max is 15). May I know how can I show all of the values in x list to the x axis? Thanks in advance.
x = [4,5,6,7,8,9,10,11,12,13,14,15,0,1,2,3]
y = [10,20,30,40,50,60,70,80,90,100,110,120,130,140,150,160]
fig = plt.figure()
ax1 = fig.add_subplot(111)
ax1.plot(np.arange(len(x)), y, 'o')
ax1.set_xticklabels(x)
plt.show()
If I set minor=True in the set_xticklabels function, it shows me all x=2,4,6,8,..,16... but I want ALL values.
P.S. My x axis is not sorted, should display as it shows.
The issue here is that the number of ticks -set automatically - isn’t the same as the number of points in your plot.
To resolve this, set the number of ticks:
ax1.set_xticks(np.arange(len(x)))
Before the ax1.set_xticklabels(x) call.
or better
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
from other answers in SO
from matplotlib import ticker
import numpy as np
labels = [
"tench",
"English springer",
"cassette player",
"chain saw",
"church",
"French horn",
"garbage truck",
"gas pump",
"golf ball",
"parachute",
]
fig = plt.figure()
ax = fig.add_subplot(111)
plt.title('Confusion Matrix', fontsize=18)
data = np.random.random((10,10))
ax.matshow(data, cmap=plt.cm.Blues, alpha=0.7)
ax.set_xticklabels([''] + labels,rotation=90)
ax.set_yticklabels([''] + labels)
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
for i in range(data.shape[0]):
for j in range(data.shape[1]):
ax.text(x=j, y=i,s=int(data[i, j]), va='center', ha='center', size='xx-small')
plt.xlabel('Predicted')
plt.ylabel('True')
plt.show()
Related
I have a long bar chart with lots of bars and I wanna improve its reability from axis to the bars.
Suppose I have the following graph:
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt
y = np.linspace(1,-1,20)
x = np.arange(0,20)
labels = [f'Test {i}' for i in x]
fig, ax = plt.subplots(figsize=(12,8))
sns.barplot(y = y, x = x, ax=ax )
ax.set_xticklabels(labels, rotation=90)
which provides me the following:
All I know is how to change the label position globally across the chart. How can I change the axis layout to be cantered in the middle and change its label position based on a condition (in this case, being higher or lower than 0)? What I want to achieve is:
Thanks in advance =)
You could remove the existing x-ticks and place texts manually:
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np
y = np.linspace(1,-1,20)
x = np.arange(0,20)
labels = [f'Test {i}' for i in x]
fig, ax = plt.subplots(figsize=(12,8))
sns.barplot(y = y, x = x, ax=ax )
ax.set_xticks([]) # remove existing ticks
for i, (label, height) in enumerate(zip(labels, y)):
ax.text(i, 0, ' '+ label+' ', rotation=90, ha='center', va='top' if height>0 else 'bottom' )
ax.axhline(0, color='black') # draw a new x-axis
for spine in ['top', 'right', 'bottom']:
ax.spines[spine].set_visible(False) # optionally hide spines
plt.show()
Here is another approach, I'm not sure whether it is "more pythonic".
move the existing xaxis to y=0
set the tick marks in both directions
put the ticks behind the bars
prepend some spaces to the labels to move them away from the axis
realign the tick labels depending on the bar value
fig, ax = plt.subplots(figsize=(12, 8))
sns.barplot(y=y, x=x, ax=ax)
ax.spines['bottom'].set_position('zero')
for spine in ['top', 'right']:
ax.spines[spine].set_visible(False)
ax.set_xticklabels([' ' + label for label in labels], rotation=90)
for tick, height in zip(ax.get_xticklabels(), y):
tick.set_va('top' if height > 0 else 'bottom')
ax.tick_params(axis='x', direction='inout')
ax.set_axisbelow(True) # ticks behind the bars
plt.show()
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()
I am trying to generate a plot with x-axis being a geometric sequence while the y axis is a number between 0.0 and 1.0. My code looks like this:
form matplotlib import pyplot as plt
plt.xticks(X)
plt.plot(X,Y)
plt.show()
which generates a plot like this:
As you can see, I am explicitly setting the x-axis ticks to the ones belonging to the geometric sequence.
My question:Is it possible to make x-ticks evenly spaced despite their value, as the initial terms of the sequence are small, and crowded together. Kind of like logarithmic scale, which would be ideal if dealing with powers of a base, but not for a geometric sequence, I think, as is the case here.
You can do it by plotting your variable as a function of the "natural" variable that parametrizes your curve. For example:
n = 12
a = np.arange(n)
x = 2**a
y = np.random.rand(n)
fig = plt.figure(1, figsize=(7,7))
ax1 = fig.add_subplot(211)
ax2 = fig.add_subplot(212)
ax1.plot(x,y)
ax1.xaxis.set_ticks(x)
ax2.plot(a, y) #we plot y as a function of a, which parametrizes x
ax2.xaxis.set_ticks(a) #set the ticks to be a
ax2.xaxis.set_ticklabels(x) # change the ticks' names to x
which produces:
I had the same problem and spent several hours trying to find something appropriate. But it appears to be really easy and you do not need to make any parameterization or play with some x-ticks positions, etc.
The only thing you need to do is just to plot your x-values as str, not int: plot(x.astype('str'), y)
By modifying the code from the previous answer you will get:
n = 12
a = np.arange(n)
x = 2**a
y = np.random.rand(n)
fig = plt.figure(1, figsize=(7,7))
ax1 = fig.add_subplot(211)
ax2 = fig.add_subplot(212)
ax1.plot(x,y)
ax1.xaxis.set_ticks(x)
ax2.plot(x.astype('str'), y)
Seaborn has a bunch of categorical plot handling natively this kind of task.
Such as pointplot:
sns.pointplot(x="x", y="y", data=df, ax=ax)
Exemple
fig, [ax1, ax2] = plt.subplots(2, figsize=(7,7))
sns.lineplot(data=df, x="x", y="y", ax=ax1) #relational plot
sns.pointplot(data=df, x="x", y="y", ax=ax2) #categorical plot
In case of using Pandas Dataframe:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
n = 12
df = pd.DataFrame(dict(
X=2**np.arange(n),
Y=np.random.randint(1, 9, size=n),
)).set_index('X')
# index is reset in order to use as xticks
df.reset_index(inplace=True)
fig = plt.figure()
ax1 = plt.subplot(111)
df['Y'].plot(kind='bar', ax=ax1, figsize=(7, 7), use_index=True)
# set_ticklabels used to place original indexes
ax1.xaxis.set_ticklabels(df['X'])
convert int to str:
X = list(map(str, X))
plt.xticks(X)
plt.plot(X,Y)
plt.show()
Here's some code that does scatter plot of a number of different series using matplotlib and then adds the line y=x:
import numpy as np, matplotlib.pyplot as plt, matplotlib.cm as cm, pylab
nseries = 10
colors = cm.rainbow(np.linspace(0, 1, nseries))
all_x = []
all_y = []
for i in range(nseries):
x = np.random.random(12)+i/10.0
y = np.random.random(12)+i/5.0
plt.scatter(x, y, color=colors[i])
all_x.extend(x)
all_y.extend(y)
# Could I somehow do the next part (add identity_line) if I haven't been keeping track of all the x and y values I've seen?
identity_line = np.linspace(max(min(all_x), min(all_y)),
min(max(all_x), max(all_y)))
plt.plot(identity_line, identity_line, color="black", linestyle="dashed", linewidth=3.0)
plt.show()
In order to achieve this I've had to keep track of all the x and y values that went into the scatter plot so that I know where identity_line should start and end. Is there a way I can get y=x to show up even if I don't have a list of all the points that I plotted? I would think that something in matplotlib can give me a list of all the points after the fact, but I haven't been able to figure out how to get that list.
You don't need to know anything about your data per se. You can get away with what your matplotlib Axes object will tell you about the data.
See below:
import numpy as np
import matplotlib.pyplot as plt
# random data
N = 37
x = np.random.normal(loc=3.5, scale=1.25, size=N)
y = np.random.normal(loc=3.4, scale=1.5, size=N)
c = x**2 + y**2
# now sort it just to make it look like it's related
x.sort()
y.sort()
fig, ax = plt.subplots()
ax.scatter(x, y, s=25, c=c, cmap=plt.cm.coolwarm, zorder=10)
Here's the good part:
lims = [
np.min([ax.get_xlim(), ax.get_ylim()]), # min of both axes
np.max([ax.get_xlim(), ax.get_ylim()]), # max of both axes
]
# now plot both limits against eachother
ax.plot(lims, lims, 'k-', alpha=0.75, zorder=0)
ax.set_aspect('equal')
ax.set_xlim(lims)
ax.set_ylim(lims)
fig.savefig('/Users/paul/Desktop/so.png', dpi=300)
Et voilà
In one line:
ax.plot([0,1],[0,1], transform=ax.transAxes)
No need to modify the xlim or ylim.
Starting with matplotlib 3.3 this has been made very simple with the axline method which only needs a point and a slope. To plot x=y:
ax.axline((0, 0), slope=1)
You don't need to look at your data to use this because the point you specify (i.e. here (0,0)) doesn't actually need to be in your data or plotting range.
If you set scalex and scaley to False, it saves a bit of bookkeeping. This is what I have been using lately to overlay y=x:
xpoints = ypoints = plt.xlim()
plt.plot(xpoints, ypoints, linestyle='--', color='k', lw=3, scalex=False, scaley=False)
or if you've got an axis:
xpoints = ypoints = ax.get_xlim()
ax.plot(xpoints, ypoints, linestyle='--', color='k', lw=3, scalex=False, scaley=False)
Of course, this won't give you a square aspect ratio. If you care about that, go with Paul H's solution.
In my plot, a secondary x axis is used to display the value of another variable for some data. Now, the original axis is log scaled. Unfortunaltely, the twinned axis puts the ticks (and the labels) referring to the linear scale of the original axis and not as intended to the log scale. How can this be overcome?
Here the code example that should put the ticks of the twinned axis in the same (absolute axes) position as the ones for the original axis:
def conv(x):
"""some conversion function"""
# ...
return x2
ax = plt.subplot(1,1,1)
ax.set_xscale('log')
# get the location of the ticks of ax
axlocs,axlabels = plt.xticks()
# twin axis and set limits as in ax
ax2 = ax.twiny()
ax2.set_xlim(ax.get_xlim())
#Set the ticks, should be set referring to the log scale of ax, but are set referring to the linear scale
ax2.set_xticks(axlocs)
# put the converted labels
ax2.set_xticklabels(map(conv,axlocs))
An alternative way would be (the ticks are then not set in the same position, but that doesn't matter):
from matplotlib.ticker import FuncFormatter
ax = plt.subplot(1,1,1)
ax.set_xscale('log')
ax2 = ax.twiny()
ax2.set_xlim(ax.get_xlim())
ax2.xaxis.set_major_formatter(FuncFormatter(lambda x,pos:conv(x)))
Both approaches work well as long as no log scale is used.
Perhaps there exists an easy fix. Is there something I missed in the documentation?
As a workaround, I tried to obtain the ax.transAxes coordinates of the ticks of ax and put the ticks at the very same position in ax2. But there does not exist something like
ax2.set_xticks(axlocs,transform=ax2.transAxes)
TypeError: set_xticks() got an unexpected keyword argument 'transform'
This has been asked a while ago, but I stumbled over it with the same question.
I eventually managed to solve the problem by introducing a logscaled (semilogx) transparent (alpha=0) dummy plot.
Example:
import numpy as np
import matplotlib.pyplot as plt
def conversion_func(x): # some arbitrary transformation function
return 2 * x**0.5 # from x to z
x = np.logspace(0, 5, 100)
y = np.sin(np.log(x))
fig = plt.figure()
ax = plt.gca()
ax.semilogx(x, y, 'k')
ax.set_xlim(x[0], x[-1]) # this is important in order that limits of both axes match
ax.set_ylabel("$y$")
ax.set_xlabel("$x$", color='C0')
ax.tick_params(axis='x', which='both', colors='C0')
ax.axvline(100, c='C0', lw=3)
ticks_x = np.logspace(0, 5, 5 + 1) # must span limits of first axis with clever spacing
ticks_z = conversion_func(ticks_x)
ax2 = ax.twiny() # get the twin axis
ax2.semilogx(ticks_z, np.ones_like(ticks_z), alpha=0) # transparent dummy plot
ax2.set_xlim(ticks_z[0], ticks_z[-1])
ax2.set_xlabel("$z \equiv f(x)$", color='C1')
ax2.xaxis.label.set_color('C1')
ax2.tick_params(axis='x', which='both', colors='C1')
ax2.axvline(20, ls='--', c='C1', lw=3) # z=20 indeed matches x=100 as desired
fig.show()
In the above example the vertical lines demonstrate that first and second axis are indeed shifted to one another as wanted. x = 100 gets shifted to z = 2*x**0.5 = 20. The colours are just to clarify which vertical line goes with which axis.
Don't need to cover them, just Eliminate the ticks!
d= [7,9,14,17,35,70];
j= [100,80,50,40,20,10];
plt.figure()
plt.xscale('log')
plt.plot(freq, freq*spec) #plot some spectrum
ax1 = plt.gca() #define my first axis
ax1.yaxis.set_ticks_position('both')
ax1.tick_params(axis='y',which='both',direction='in');
ax1.tick_params(axis='x',which='both',direction='in');
ax2 = ax1.twiny() #generates second axis (top)
ax2.set_xlim(ax1.get_xlim()); #same limits
plt.xscale('log') #make it log
ax2.set_xticks(freq[d]); #my own 'major' ticks OVERLAPS!!!
ax2.set_xticklabels(j); #change labels
ax2.tick_params(axis='x',which='major',direction='in');
ax2.tick_params(axis='x',which='minor',top=False); #REMOVE 'MINOR' TICKS
ax2.grid()
I think you can fix your issue by calling ax2.set_xscale('log').
import matplotlib.pyplot as plt
import numpy as np
fig, ax = plt.subplots()
ax.semilogx(np.logspace(1.0, 5.0, 20), np.random.random([20]))
new_tick_locations = np.array([10., 100., 1000., 1.0e4])
def tick_function(X):
V = X / 1000.
return ["%.3f" % z for z in V]
ax2 = ax.twiny()
ax2.set_xscale('log')
ax2.set_xlim(ax.get_xlim())
ax2.set_xticks(new_tick_locations)
ax2.set_xticklabels(tick_function(new_tick_locations))
ax2.set_xlabel(r"Modified x-axis: $X/1000$")