matplotlib.pyplot plot the wrong order of y-label - python

I tried to plot a bar figure and I want x-label to remain the specific order, so I use set_xticklabels. However, the result turns out the y-value didn't match the x-label.
import matplotlib.pyplot as plt
A=['Dog','Cat','Fish','Bird']
B=[26,39,10,20]
fig=plt.figure()
ax1 = fig.add_subplot(1,1,1)
ax1.bar(A, B)
ax1.set_xticklabels(A)
plt.title("Animals")
plt.show()
The expected result is Dog=26 Cat=39 Fish=10 Bird=20, but the result I got is Dog=20 Cat=39 Fish=26 Bird=20.
Here is one answer I found. However, if I use this method I cannot keep the original order I want.
import itertools
import matplotlib.pyplot as plt
A=['Dog','Cat','Fish','Bird']
B=[26,39,10,20]
lists = sorted(itertools.izip(*[A, B]))
new_x, new_y = list(itertools.izip(*lists))
fig=plt.figure()
ax1 = fig.add_subplot(1,1,1)
ax1.bar(new_x, new_y )
ax1.set_xticklabels(new_x)
plt.title("Animals")
plt.show()
Is there any way I can keep the original order of x-label and make y value match with x?


This code will serve the purpose,
import numpy as np
import matplotlib.pyplot as plt
A=['Dog','Cat','Fish','Bird']
B=[26,39,10,20]
y_pos = np.arange(len(A))
plt.bar(y_pos, B)
plt.xticks(y_pos, A)
plt.title("Animals")
plt.show()


Why don't you use pandas for storing your data:
import pandas as pd
import matplotlib
A= ['Dog','Cat','Fish','Bird']
B= [26,39,10,20]
ser = pd.Series(index=A, values=B)
ax = ser.loc[A].plot(kind='bar', legend=False)
ax.set_ylabel("Value")
ax.set_xlabel("Animals")
plt.show()


In matplotlib 2.2 you can just plot those lists as they are and get the correct result.
import matplotlib.pyplot as plt
A=['Dog','Cat','Fish','Bird']
B=[26,39,10,20]
plt.bar(A, B)
plt.title("Animals")
plt.show()

Related

Moving Graph Titles in the Y axis of Subplots

This question is adapted from this answer, however the solution provided does not work and following is my result. I am interested in adding individual title on the right side for individual subgraphs.
(p.s no matter how much offset for y-axis i provide the title seems to stay at the same y-value)
from matplotlib import pyplot as plt
import numpy as np
fig, axes = plt.subplots(nrows=2)
ax0label = axes[0].set_ylabel('Axes 0')
ax1label = axes[1].set_ylabel('Axes 1')
title = axes[0].set_title('Title')
offset = np.array([-0.15, 0.0])
title.set_position(ax0label.get_position() + offset)
title.set_rotation(90)
fig.tight_layout()
plt.show()

Something like this? This is the only other way i can think of.
from matplotlib import pyplot as plt
import numpy as np
fig, axes = plt.subplots(nrows=2)
ax0label = axes[0].set_ylabel('Axes 0')
ax1label = axes[1].set_ylabel('Axes 1')
ax01 = axes[0].twinx()
ax02 = axes[1].twinx()
ax01.set_ylabel('title')
ax02.set_ylabel('title')
fig.tight_layout()
plt.show()

seaborn jointplot with same size plots

I'm doing a jointplot with a basemap, the problem is that when I add the basemap the main plot doesn't have the same size of the marginal plots. I've tried with different parameters without luck. Does anyone have an idea?
import seaborn as sns
import matplotlib.pyplot as plt
import contextily as ctx
import pandas as pd
##exaplme of the data
coords={'longitud':[-62.2037376443, -62.1263309099, -62.1111660957, -62.2094232682, -62.2373117384, -62.4837603464,
-62.4030570833, -62.3975699059, -62.7017114116, -62.7830883096, -62.7786038141, -62.7683234105, -62.7490101452,
-62.7709656745, -63.1002199219, -63.1890252191, -63.1183018549, -63.069960016, -62.7957745659, -63.1715687622,
-63.2156105034, -63.0634381954, -63.2243260588, -63.1153871895, -63.1068292891, -63.103945266, -63.046202785,
-63.1002257551, -63.2076065143, -62.9766391316, -62.9639256604, -62.9911452446, -62.9819984159, -62.9693649898,
-63.066770885, -62.9867441519, -62.9566360192, -62.962616287, -62.835080907, -63.0704805194, -62.8796906301,
-63.0725050601, -63.2224345145, -63.1609069526, -63.0614466072, -62.8847887504, -63.1093652381, -62.822694115,
-63.211982035, -63.1689040153],
'latitud':[8.54644405234, 8.54344899107, 8.54223724187, 8.54290207992, 8.49122679072, 8.48386575122, 8.46450360179,
8.46404720757, 8.35310083084, 8.31701565261, 8.30258604829, 8.29974870902, 8.29281679496, 8.28939264064, 8.28785272804,
8.28221439317, 8.27978694565, 8.27864159366, 8.27634987807, 8.27619269053, 8.27236343925, 8.27258932351, 8.26833993531,
8.267530064, 8.26446669791, 8.26266392333, 8.2641092051, 8.26208837315, 8.26034269744, 8.26123972942, 8.25789799656,
8.25825378832, 8.25833002805, 8.25914612933, 8.2540499893, 8.25347956867, 8.2540932736, 8.25405171513, 8.2478564527,
8.24561857662, 8.2440865055, 8.24256528837, 8.24089278, 8.23877286416, 8.23782626443, 8.23865421655, 8.23733824299,
8.23477115627, 8.23552604027, 8.24327920905]}
df = pd.DataFrame(coords)
OSM_C = 'http://c.tile.openstreetmap.org/{z}/{x}/{y}.png'
joint_axes = sns.jointplot(
x='longitud', y='latitud', data=df, ec="r", s=5)
ctx.add_basemap(joint_axes.ax_joint,crs=4326,attribution=False,url=OSM_C)
adjust(hspace=0, wspace=0)
#plt.tight_layout()
plt.show()

Here is an approach that:
removes the axes sharing in the y-direction to be able to change the aspect to 'datalim'
sets the aspect to 'equal', 'datalim'
sets the y data limits of the marginal plot to be the same as the joint plot; this seems to need a redraw
The following code shows the idea (using imshow, as I don't have contextily installed):
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
coords = {'longitud' : [-62.2037376443, -62.1263309099, -62.1111660957, -62.2094232682, -62.2373117384, -62.4837603464, -62.4030570833, -62.3975699059, -62.7017114116, -62.7830883096, -62.7786038141, -62.7683234105, -62.7490101452, -62.7709656745, -63.1002199219, -63.1890252191, -63.1183018549, -63.069960016, -62.7957745659, -63.1715687622, -63.2156105034, -63.0634381954, -63.2243260588, -63.1153871895, -63.1068292891, -63.103945266, -63.046202785, -63.1002257551, -63.2076065143, -62.9766391316, -62.9639256604, -62.9911452446, -62.9819984159, -62.9693649898, -63.066770885, -62.9867441519, -62.9566360192, -62.962616287, -62.835080907, -63.0704805194, -62.8796906301, -63.0725050601, -63.2224345145, -63.1609069526, -63.0614466072, -62.8847887504, -63.1093652381, -62.822694115, -63.211982035, -63.1689040153],
'latitud' : [8.54644405234, 8.54344899107, 8.54223724187, 8.54290207992, 8.49122679072, 8.48386575122, 8.46450360179, 8.46404720757, 8.35310083084, 8.31701565261, 8.30258604829, 8.29974870902, 8.29281679496, 8.28939264064, 8.28785272804, 8.28221439317, 8.27978694565, 8.27864159366, 8.27634987807, 8.27619269053, 8.27236343925, 8.27258932351, 8.26833993531, 8.267530064, 8.26446669791, 8.26266392333, 8.2641092051, 8.26208837315, 8.26034269744, 8.26123972942, 8.25789799656, 8.25825378832, 8.25833002805, 8.25914612933, 8.2540499893, 8.25347956867, 8.2540932736, 8.25405171513, 8.2478564527, 8.24561857662, 8.2440865055, 8.24256528837, 8.24089278, 8.23877286416, 8.23782626443, 8.23865421655, 8.23733824299, 8.23477115627, 8.23552604027, 8.24327920905]}
df = pd.DataFrame(coords)
g = sns.jointplot(data=df, x='longitud', y='latitud')
ctx.add_basemap(g.ax_joint,crs=4326,attribution=False,url=OSM_C)
# g.ax_joint.imshow(np.random.rand(20, 10), cmap='spring', interpolation='bicubic',
# extent=[df['longitud'].min(), df['longitud'].max(), df['latitud'].min(), df['latitud'].max()])
for axes in g.ax_joint.get_shared_y_axes():
for ax in axes:
g.ax_joint.get_shared_y_axes().remove(ax)
g.ax_joint.set_aspect('equal', 'datalim')
g.fig.canvas.draw()
g.ax_marg_y.set_ylim(g.ax_joint.get_ylim())
plt.show()
You can still combine this approach with changing the figure's width or height, or adding more whitespace on top or below.

plt.show() does not print plt.plot only plt.scatter

So, for the following code no graph is printed in jupyter notebook. If I use plt.scatter then it does produce graph. Any suggestions what could be wrong? Can it be caused by the data?
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
def calc_gauss(df, index):
x=df.iloc[[index]]
mean = df.apply(lambda x: x.mean(), axis=1)
mu=mean.iloc[[index]]
std = df.std(axis=1)
sig=std.iloc[[index]]
dens = norm.pdf(x,mu,sig)
# build the plot
fig, ax = plt.subplots(figsize=(9,6))
plt.style.use('fivethirtyeight')
ax.plot(x, dens)
return plt.show()
calc_gauss(df_distance, 339)

Instead of
return plt.show()
use
fig.show()
If you want the picture to show in the notebook, use %matplotlib inline in a cell evaluated before the show command
Note the problem was that the arrays were shape (1,24). plot likes only 1D arrays. Replacing ax.plot(x, dens) with ax.plot(x.reshape(-1), dens.reshape(-1)) solved the issue.

How to show label names in pandas groupby histogram plot

I can plot multiple histograms in a single plot using pandas but there are few things missing:
How to give the label.
I can only plot one figure, how to change it to layout=(3,1) or something else.
Also, in figure 1, all the bins are filled with solid colors, and its kind of difficult to know which is which, how to fill then with different markers (eg. crosses,slashes,etc)?
Here is the MWE:
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
df = sns.load_dataset('iris')
df.groupby('species')['sepal_length'].hist(alpha=0.7,label='species')
plt.legend()
Output:
To change layout I can use by keyword, but can't give them colors
HOW TO GIVE DIFFERENT COLORS?
df.hist('sepal_length',by='species',layout=(3,1))
plt.tight_layout()
Gives:

You can resolve to groupby:
fig,ax = plt.subplots()
hatches = ('\\', '//', '..') # fill pattern
for (i, d),hatch in zip(df.groupby('species'), hatches):
d['sepal_length'].hist(alpha=0.7, ax=ax, label=i, hatch=hatch)
ax.legend()
Output:

In pandas version 1.1.0 you can simply set the legend keyword to true.
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
df = sns.load_dataset('iris')
df.groupby('species')['sepal_length'].hist(alpha=0.7, legend = True)
output image

It's more code, but using pure matplotlib will always give you more control over the plots. For your second case:
import matplotlib.pyplot as plt
import numpy as np
from itertools import zip_longest
# Dictionary of color for each species
color_d = dict(zip_longest(df.species.unique(),
plt.rcParams['axes.prop_cycle'].by_key()['color']))
# Use the same bins for each
xmin = df.sepal_length.min()
xmax = df.sepal_length.max()
bins = np.linspace(xmin, xmax, 20)
# Set up correct number of subplots, space them out.
fig, ax = plt.subplots(nrows=df.species.nunique(), figsize=(4,8))
plt.subplots_adjust(hspace=0.4)
for i, (lab, gp) in enumerate(df.groupby('species')):
ax[i].hist(gp.sepal_length, ec='k', bins=bins, color=color_d[lab])
ax[i].set_title(lab)
# same xlim for each so we can see differences
ax[i].set_xlim(xmin, xmax)

plotting multiple histograms in grid

I am running following code to draw histograms in 3 by 3 grid for 9 varaibles.However, it plots only one variable.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
def draw_histograms(df, variables, n_rows, n_cols):
fig=plt.figure()
for i, var_name in enumerate(variables):
ax=fig.add_subplot(n_rows,n_cols,i+1)
df[var_name].hist(bins=10,ax=ax)
plt.title(var_name+"Distribution")
plt.show()

You're adding subplots correctly but you call plt.show for each added subplot which causes what has been drawn so far to be shown, i.e. one plot. If you're for instance plotting inline in IPython you will only see the last plot drawn.
Matplotlib provides some nice examples of how to use subplots.
Your problem is fixed like:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
def draw_histograms(df, variables, n_rows, n_cols):
fig=plt.figure()
for i, var_name in enumerate(variables):
ax=fig.add_subplot(n_rows,n_cols,i+1)
df[var_name].hist(bins=10,ax=ax)
ax.set_title(var_name+" Distribution")
fig.tight_layout() # Improves appearance a bit.
plt.show()
test = pd.DataFrame(np.random.randn(30, 9), columns=map(str, range(9)))
draw_histograms(test, test.columns, 3, 3)
Which gives a plot like:

In case you don't really worry about titles, here's a one-liner
df = pd.DataFrame(np.random.randint(10, size=(100, 9)))
df.hist(color='k', alpha=0.5, bins=10)

Categories

Resources