I have tried a number of different things to fix my chart, from zorder on the plots to plt.rcParams.
I feel that this is such a simple problem but I just dont know where I have gone wrong. As you can see the bottom annotation in cyan blue is unreadable and mashed with the y label.
Ideally, the annotation sits over the y label to a point where text inside annotation is readable.
If possible just for the annotation to sit on top and still overlay the y label..something like this
Any help on this would be greatly appreciated.
ax = df.plot(x=df.columns[0], y=df.columns[1], legend=False, zorder=0, linewidth=1)
y1 =df.loc[:, df.columns[2]].tail(1)
y2= df.loc[:, df.columns[1]].tail(1)
colors = plt.rcParams["axes.prop_cycle"].by_key()["color"]
print(colors)
for var in (y1, y2):
plt.annotate('%0.2f' % var.max(), xy=(1, var.max()), zorder=1, xytext=(8, 0),
xycoords=('axes fraction', 'data'),
textcoords='offset points',
bbox=dict(boxstyle="round", fc=colors[0], ec=colors[0],))
ax2 = ax.twinx()
df.plot(x=df.columns[0], y=df.columns[2], ax=ax2, legend=False, color='#fa8174', zorder=0,linewidth=1)
ax.figure.legend(prop=subtitle_font)
ax.grid(True, color="white",alpha=0.2)
pack = [df.columns[1], df.columns[2], freq[0]]
plt.text(0.01, 0.95,'{0} v {1} - ({2})'.format(df.columns[1], df.columns[2], freq[0]),
horizontalalignment='left',
verticalalignment='center',
transform = ax.transAxes,
zorder=10,
fontproperties=subtitle_font)
ax.text(0.01,0.02,"Sources: FRED, Quandl, #Paul92s",
color="white",fontsize=10,
horizontalalignment='left',
transform = ax.transAxes,
verticalalignment='center',
zorder=20,
fontproperties=subtitle_font)
ax.xaxis.set_major_locator(matplotlib.dates.YearLocator())
ax.xaxis.set_minor_locator(matplotlib.dates.MonthLocator((4,7,10)))
ax.xaxis.set_major_formatter(matplotlib.dates.DateFormatter("%Y"))
ax.xaxis.set_minor_formatter(ticker.NullFormatter()) # matplotlib.dates.DateFormatter("%m")
plt.setp(ax.get_xticklabels(), rotation=0, ha="center", zorder=-1)
plt.setp(ax2.get_yticklabels(), rotation=0, zorder=-1)
plt.setp(ax.get_yticklabels(), rotation=0, zorder=-1)
plt.gcf().set_size_inches(14,7)
ax.set_xlabel('Data as of; {0}'.format(df['Date'].max().strftime("%B %d, %Y")), fontproperties=subtitle_font)
y1 =df.loc[:, df.columns[2]].tail(1)
y2= df.loc[:, df.columns[1]].tail(1)
for var in (y1, y2):
plt.annotate('%0.2f' % var.max(), xy=(1, var.max()), zorder=1,xytext=(8, 0),
xycoords=('axes fraction', 'data'),
textcoords='offset points',
bbox=dict(boxstyle="round", fc="#fa8174", ec="#fa8174"))
plt.title('{0}'.format("FRED Velocity of M2 Money Stock v Trade Weighted U.S. Dollar Index: Broad"),fontproperties=heading_font)
ax.texts.append(ax.texts.pop())
ax.set_facecolor('#181818')
ax.figure.set_facecolor('#181818')
plt.rcParams['axes.axisbelow'] = True
I don't figure out why zorder doesn't work, but you can directly set the label style of tick labels:
import matplotlib.pyplot as plt
import numpy as np
from numpy.random import rand
import matplotlib.patches as mpatches
fig, ax = plt.subplots(1, 1)
ax.plot(rand(100), '^', color='r')
for label in ax.get_xticklabels():
label.set_bbox(dict(facecolor='orange'))
ax1 = ax.twinx()
ax1.plot(rand(100), 'o', color='b')
index_to_add_bbox = [2, 4]
ax1_labels = ax1.get_yticklabels()
for i in index_to_add_bbox:
ax1_labels[i].set_bbox(dict(boxstyle='Circle', facecolor='orange'))
plt.show()
Related
My goal is to create plot with four subplots, where the bottom two are really just empty boxes where I will display some text. Unfortunately, all of my efforts to remove the y and x axis tick marks and labels have failed. I'm still new to matplotlib so I'm sure there's something simple that I'm missing. Here's what I'm trying and what I get:
import matplotlib.pyplot as plt
fig, axes = plt.subplots(2, 2, sharex=False, sharey=True, figsize=(6,6))
fig.add_subplot(111, frameon=False)
plt.tick_params(labelcolor='none', top=False, bottom=False, left=False, right=False)
plt.title('Neuron Length')
plt.xlabel('Strain')
plt.ylabel('Neuron Length (um)')
aIP = fig.add_subplot(223, frameon=False)
aIP.annotate('Big Axes \nGridSpec[1:, -1]', (0.1, 0.5),
xycoords='axes fraction', va='center')
# First approach
aIP.axes.xaxis.set_ticks([])
aIP.axes.yaxis.set_ticks([])
# Second approach
ax = plt.gca()
ax.axes.yaxis.set_visible(False)
plt.show()
This is achieved by using plt.subplots() to draw four of them and remove the bottom left frame.
import matplotlib.pyplot as plt
import numpy as np
t = np.linspace(-np.pi, np.pi, 1000)
x1 = np.sin(2*t)
x2 = np.cos(2*t)
x3 = x1 + x2
fig,axes = plt.subplots(nrows=2,ncols=2,figsize=(6,6), sharex=True, sharey=True)
axes[0,0].plot(t, x1, linewidth=2)
axes[0,1].plot(t, x2, linewidth=2)
axes[1,1].plot(t, x3, linewidth=2)
axes[1,0].axis('off') # off
axes[1,0].annotate('Big Axes \nGridSpec[1:, -1]', (0.1, 0.5), xycoords='axes fraction', va='center')
fig.suptitle('Neuron Length')
for ax in axes.flat:
ax.set(xlabel='Strain', ylabel='Neuron Length (um)')
plt.show()
How can I create distplot from countplot
plt.rcdefaults()
%config InlineBackend.figure_format='retina'
sns.set_style('darkgrid')
ax = sns.countplot(x='Age',hue='Gender',data=df,edgecolor="None")
ax.tick_params(bottom=False, left=False)
ax.set_axisbelow(True)
for rect in ax.patches:
x = rect.get_x() + rect.get_width()/2.
y = rect.get_height()
try:
ax.annotate("{}".format(int(y)), (x,y), ha='center', va='bottom', clip_on=True)
except:
pass
ax.set_xlabel('Age', color='green')
ax.set_ylabel('Count', color='green')
ax.set_title('Countplot for Age(Gender)', color='tomato',weight='bold')
plt.legend(title='Gender', fontsize='large', loc='upper right').get_frame().set_facecolor('white')
plt.tight_layout()
plt.savefig('files\\Countplot_for_Age(Gender).jpg')
I want distplot for 2 Genders either in same plot or separately
Any suggestions or help will be highly appreciable
The x-axis of a countplot is categorical: it puts one bar for each encountered age, skipping bars when there are no rows for a certain age (21 and 23 in the example). Internally the bars are numbered as 0, 1, 2, ...
The y-axis is the count, which is proportional to the number of rows.
For a distplot, the x-axis are the ages themselves, and the y-axis is a probability distribution, which usually are quite small numbers (the area under the curve is normalized to be 1).
So, as both the x-axis and the y-axis are different, it is better to use separate subplots.
A distplot can be generated directly from the given data. Passing the same ax results in two distplots in the same subplot. A distplot is a combination of a histogram and a kdeplot. If the histogram isn't needed, hist=False leaves
it out, or the kdeplot can be called directly. The shade=True option adds shading to the plot.
from matplotlib import pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
NF = 50
NM = 10
df = pd.DataFrame({'Age': np.concatenate([np.random.randint(13, 20, NF) + np.random.randint(2, 7, NF),
np.random.randint(15, 23, NM)]),
'Gender': np.repeat(['female', 'male'], (NF, NM))})
df['Age'] = df['Age'].where((df['Age'] != 21) & (df['Age'] != 23), 20)
sns.set_style('darkgrid')
fig, axs = plt.subplots(ncols=2, figsize=(12, 4))
ax = sns.countplot(x='Age', hue='Gender', data=df, edgecolor="None", ax=axs[0])
ax.tick_params(bottom=False, left=False)
ax.set_axisbelow(True)
for rect in ax.patches:
x = rect.get_x() + rect.get_width() / 2.
y = rect.get_height()
ax.annotate(f"{y:.0f}", (x, y), ha='center', va='bottom', clip_on=True)
ax.set_xlabel('Age', color='green')
ax.set_ylabel('Count', color='green')
ax.set_title('Countplot for Age(Gender)', color='tomato', weight='bold')
ax.legend(title='Gender', fontsize='large', loc='upper right').get_frame().set_facecolor('white')
for gender in ('female', 'male'):
# ax2 = sns.kdeplot(df[df['Gender'] == gender]['Age'], shade=True, ax=axs[1], label=gender)
ax2 = sns.distplot(df[df['Gender'] == gender]['Age'], hist=False, kde_kws={'shade': True}, ax=axs[1], label=gender)
ax2.set_axisbelow(True)
ax2.set_xlabel('Age', color='green')
ax2.set_ylabel('probability distribution', color='green')
ax2.set_title('Distplot for Age(Gender)', color='tomato', weight='bold')
ax2.legend(title='Gender', fontsize='large', loc='upper right').get_frame().set_facecolor('white')
plt.tight_layout()
plt.show()
I create two scatterplots with matplotlib in python with this code, the data for the code is here:
import matplotlib.pyplot as plt
from matplotlib.colors import Normalize
fig = plt.figure(figsize=(20,12))
ax1 = fig.add_subplot(111)
ax3 = ax1.twinx()
norm = Normalize(vmin=0.95*min(arr), vmax=1.05*max(arr))
ax1.scatter(x, y1, s=20, c=arr, cmap='Blues_r', norm=norm, marker='x', label='bla1')
ax3.scatter(x, y2, s=(20*(1.1-arr))**3.5, c=arr, cmap='Reds_r', norm=norm, marker='^', label='bla1')
The created fig. looks like this:
So, the dot size (in ax3) and the dot colour (in ax1 and ax3) are taken from arrays containing floats with all kinds of values in the range [0,1]. My question: How do I create a legend that displays the corresponding y-values for, let's say 5 different dot sizes and 5 different colour nuances?
I would like the legend to look like in the figure below (source here), but with the colour bar and size bar put into a single legend, if possible. Thanks for suggestions and code!
# using your data in dataframe df
# create s2
df['s2'] = (20*(1.1-df.arr))**3.5
fig = plt.figure(figsize=(20,12))
ax1 = fig.add_subplot(111)
ax3 = ax1.twinx()
norm = Normalize(vmin=0.95*min(df.arr), vmax=1.05*max(df.arr))
p1 = ax1.scatter(df.x, df.y1, s=20, c=df.arr, cmap='Blues_r', norm=norm, marker='x')
fig.colorbar(p1, label='arr')
p2 = ax3.scatter(df.x, df.y2, s=df.s2, c=df.arr, cmap='Reds_r', norm=norm, marker='^')
fig.colorbar(p2, label='arr')
# create the size legend for red
for x in [15, 80, 150]:
plt.scatter([], [], c='r', alpha=1, s=x, label=str(x), marker='^')
plt.legend(loc='upper center', bbox_to_anchor=(1.23, 1), ncol=1, fancybox=True, shadow=True, title='s2')
plt.show()
There's no legend for p1 because the size is static.
I think this would be better as two separate plots
I used Customizing Plot Legends: Legend for Size of Points
Separate
fig, (ax1, ax2) = plt.subplots(nrows=2, figsize=(20, 10))
norm = Normalize(vmin=0.95*min(df.arr), vmax=1.05*max(df.arr))
p1 = ax1.scatter(df.x, df.y1, s=20, c=df.arr, cmap='Blues_r', norm=norm, marker='x')
fig.colorbar(p1, ax=ax1, label='arr')
p2 = ax2.scatter(df.x, df.y2, s=df.s2, c=df.arr, cmap='Reds_r', norm=norm, marker='^')
fig.colorbar(p2, ax=ax2, label='arr')
# create the size legend for red
for x in [15, 80, 150]:
plt.scatter([], [], c='r', alpha=1, s=x, label=str(x), marker='^')
plt.legend(loc='upper center', bbox_to_anchor=(1.2, 1), ncol=1, fancybox=True, shadow=True, title='s2')
plt.show()
How do we draw an average line (horizontal) for a histogram in using matplotlib?
Right now, I'm able to draw the histogram without any issues.
Here is the code I'm using:
## necessary variables
ind = np.arange(N) # the x locations for the groups
width = 0.2 # the width of the bars
plt.tick_params(axis='both', which='major', labelsize=30)
plt.tick_params(axis='both', which='minor', labelsize=30)
ax2 = ax.twinx()
## the bars
rects1 = ax.bar(ind, PAAE1, width,
color='0.2',
error_kw=dict(elinewidth=2,ecolor='red'),
label='PAAE1')
rects2 = ax.bar(ind+width, PAAE2, width,
color='0.3',
error_kw=dict(elinewidth=2,ecolor='black'),
label='PAAE2')
rects3 = ax2.bar(ind+width+width, AAE1, width,
color='0.4',
error_kw=dict(elinewidth=2,ecolor='red'),
label='AAE1')
rects4 = ax2.bar(ind+3*width, AAE2, width,
color='0.5',
error_kw=dict(elinewidth=2,ecolor='black'),
label='AAE3')
maxi = max(dataset[2])
maxi1 = max(dataset[4])
f_max = max(maxi, maxi1)
lns = [rects1,rects2,rects3,rects4]
labs = [l.get_label() for l in lns]
ax.legend(lns, labs, loc='upper center', ncol=4)
# axes and labels
ax.set_xlim(-width,len(ind)+width)
ax.set_ylim(0, 100)
ax.set_ylabel('PAAE', fontsize=25)
ax2.set_ylim(0, f_max+500)
ax2.set_ylabel('AAE (mW)', fontsize=25)
xTickMarks = dataset[0]
ax.set_xticks(ind+width)
xtickNames = ax.set_xticklabels(xTickMarks)
plt.setp(xtickNames, rotation=90, fontsize=25)
I want to plot the average line for PAAE 1, 2 and AAE 1, 2.
What should I be using to plot the average line?
If you'd like a vertical line to denote the mean use axvline(x_value). This will place a vertical line that always spans the full (or specified fraction of) y-axis. There's also axhline for horizontal lines.
In other works, you might have something like this:
ax.axvline(data1.mean(), color='blue', linewidth=2)
ax.axvline(data2.mean(), color='green', linewidth=2)
As a more complete, but unnecessarily complex example (most of this is nicely annotating the means with curved arrows):
import numpy as np
import matplotlib.pyplot as plt
data1 = np.random.normal(0, 1, 1000)
data2 = np.random.normal(-2, 1.5, 1000)
fig, ax = plt.subplots()
bins = np.linspace(-10, 5, 50)
ax.hist(data1, bins=bins, color='blue', label='Dataset 1',
alpha=0.5, histtype='stepfilled')
ax.hist(data2, bins=bins, color='green', label='Dataset 2',
alpha=0.5, histtype='stepfilled')
ax.axvline(data1.mean(), color='blue', linewidth=2)
ax.axvline(data2.mean(), color='green', linewidth=2)
# Add arrows annotating the means:
for dat, xoff in zip([data1, data2], [15, -15]):
x0 = dat.mean()
align = 'left' if xoff > 0 else 'right'
ax.annotate('Mean: {:0.2f}'.format(x0), xy=(x0, 1), xytext=(xoff, 15),
xycoords=('data', 'axes fraction'), textcoords='offset points',
horizontalalignment=align, verticalalignment='center',
arrowprops=dict(arrowstyle='-|>', fc='black', shrinkA=0, shrinkB=0,
connectionstyle='angle,angleA=0,angleB=90,rad=10'),
)
ax.legend(loc='upper left')
ax.margins(0.05)
plt.show()
I would like to put text in the right bottom corner of equal aspect figure.
I set the position relative to the figure by ax.transAxes,
but I have to define the relative coordinate value manually depending on height scales of each figures.
What would be a good way to know axes height scale and the correct text position within the script?
ax = plt.subplot(2,1,1)
ax.plot([1,2,3],[1,2,3])
ax.set_aspect('equal')
ax.text(1,-0.15, 'text', transform=ax.transAxes, ha='right', fontsize=16)
print ax.get_position().height
ax = plt.subplot(2,1,2)
ax.plot([10,20,30],[1,2,3])
ax.set_aspect('equal')
ax.text(1,-0.15, 'text', transform=ax.transAxes, ha='right', fontsize=16)
print ax.get_position().height
Use annotate.
In fact, I hardly ever use text. Even when I want to place things in data coordinates, I usually want to offset it by some fixed distance in points, which is much easier with annotate.
As a quick example:
import matplotlib.pyplot as plt
fig, axes = plt.subplots(nrows=2, subplot_kw=dict(aspect=1))
axes[0].plot(range(1, 4))
axes[1].plot(range(10, 40, 10), range(1, 4))
for ax in axes:
ax.annotate('Test', xy=(1, 0), xycoords='axes fraction', fontsize=16,
horizontalalignment='right', verticalalignment='bottom')
plt.show()
If you'd like it slightly offset from the corner, you can specify an offset through the xytext kwarg (and textcoords to control how the values of xytext are interpreted). I'm also using the ha and va abbreviations for horizontalalignment and verticalalignment here:
import matplotlib.pyplot as plt
fig, axes = plt.subplots(nrows=2, subplot_kw=dict(aspect=1))
axes[0].plot(range(1, 4))
axes[1].plot(range(10, 40, 10), range(1, 4))
for ax in axes:
ax.annotate('Test', xy=(1, 0), xycoords='axes fraction', fontsize=16,
xytext=(-5, 5), textcoords='offset points',
ha='right', va='bottom')
plt.show()
If you're trying to place it below the axes, you can use the offset to place it a set distance below in points:
import matplotlib.pyplot as plt
fig, axes = plt.subplots(nrows=2, subplot_kw=dict(aspect=1))
axes[0].plot(range(1, 4))
axes[1].plot(range(10, 40, 10), range(1, 4))
for ax in axes:
ax.annotate('Test', xy=(1, 0), xycoords='axes fraction', fontsize=16,
xytext=(0, -15), textcoords='offset points',
ha='right', va='top')
plt.show()
Also have a look at the Matplotlib annotation guide for more information.