This question already has answers here:
How to add value labels on a bar chart
(7 answers)
Closed 4 months ago.
I would like to add data labels to factor plots generated by Seaborn. Here is an example:
import pandas as pd
from pandas import Series, DataFrame
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
titanic_df = pd.read_csv('train.csv')
sns.factorplot('Sex',data=titanic_df,kind='count')
How can I add the 'count' values to the top of each bar on the graph?
You could do it this way:
import math
# Set plotting style
sns.set_style('whitegrid')
# Rounding the integer to the next hundredth value plus an offset of 100
def roundup(x):
return 100 + int(math.ceil(x / 100.0)) * 100
df = pd.read_csv('train.csv')
sns.factorplot('Sex', data=df, kind='count', alpha=0.7, size=4, aspect=1)
# Get current axis on current figure
ax = plt.gca()
# ylim max value to be set
y_max = df['Sex'].value_counts().max()
ax.set_ylim([0, roundup(y_max)])
# Iterate through the list of axes' patches
for p in ax.patches:
ax.text(p.get_x() + p.get_width()/2., p.get_height(), '%d' % int(p.get_height()),
fontsize=12, color='red', ha='center', va='bottom')
plt.show()
You could do something even simpler
plt.figure(figsize=(4, 3))
plot = sns.catplot(x='Sex', y='count', kind='bar', data=titanic_df)
# plot.ax gives the axis object
# plot.ax.patches gives list of bars that can be access using index starting at 0
for i, bar in enumerate(plot.ax.patches):
h = bar.get_height()
plot.ax.text(
i, # bar index (x coordinate of text)
h+10, # y coordinate of text
'{}'.format(int(h)), # y label
ha='center',
va='center',
fontweight='bold',
size=14)
The above answer from #nickil-maveli is simply great.
This is just to add some clarity about the parameters when you are adding the data labels to the barplot (as requested in the comments by #user27074)
# loop through all bars of the barplot
for nr, p in enumerate(ax.patches):
# height of bar, which is basically the data value
height = p.get_height()
# add text to specified position
ax.text(
# bar to which data label will be added
# so this is the x-coordinate of the data label
nr,
# height of data label: height / 2. is in the middle of the bar
# so this is the y-coordinate of the data label
height / 2.,
# formatting of data label
u'{:0.1f}%'.format(height),
# color of data label
color='black',
# size of data label
fontsize=18,
# horizontal alignment: possible values are center, right, left
ha='center',
# vertical alignment: possible values are top, bottom, center, baseline
va='center'
)
Related
I'm drawing my axes title with the method ax.set_title("Horizontal Bars", ha="left", x=0, fontsize=16) and it draw as below:
How do I draw it in the left-most position, as the "title here" in red above? I know I can use a negative value for x, but I'd like to find this value automatically.
To dynamically generate the bounds you would do:
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))
error = np.random.rand(len(people))
ax.barh(y_pos, performance, xerr=error, align='center')
ax.set_yticks(y_pos)
ax.set_yticklabels(people)
ax.invert_yaxis() # labels read top-to-bottom
ax.set_xlabel('Performance')
# Get min x and max y
# get the inverse of the transformation from data coordinates to pixels
transf = ax.transData.inverted()
bb = plt.figure().get_window_extent(renderer = plt.figure().canvas.get_renderer())
bb_datacoords = bb.transformed(transf)
points = bb_datacoords.get_points()
x_lim = points[0][0]
y_lim = points[1][1]
ax.text(x=x_lim, y=y_lim, s="Horizontal Bars", weight="bold", fontsize=16) # <- Use text instead of title
which gives you an output of:
I have the following heatmap:
I've broken up the category names by each capital letter and then capitalised them. This achieves a centering effect across the labels on my x-axis by default which I'd like to replicate across my y-axis.
yticks = [re.sub("(?<=.{1})(.?)(?=[A-Z]+)", "\\1\n", label, 0, re.DOTALL).upper() for label in corr.index]
xticks = [re.sub("(?<=.{1})(.?)(?=[A-Z]+)", "\\1\n", label, 0, re.DOTALL).upper() for label in corr.columns]
fig, ax = plt.subplots(figsize=(20,15))
sns.heatmap(corr, ax=ax, annot=True, fmt="d",
cmap="Blues", annot_kws=annot_kws,
mask=mask, vmin=0, vmax=5000,
cbar_kws={"shrink": .8}, square=True,
linewidths=5)
for p in ax.texts:
myTrans = p.get_transform()
offset = mpl.transforms.ScaledTranslation(-12, 5, mpl.transforms.IdentityTransform())
p.set_transform(myTrans + offset)
plt.yticks(plt.yticks()[0], labels=yticks, rotation=0, linespacing=0.4)
plt.xticks(plt.xticks()[0], labels=xticks, rotation=0, linespacing=0.4)
where corr represents a pre-defined pandas dataframe.
I couldn't seem to find an align parameter for setting the ticks and was wondering if and how this centering could be achieved in seaborn/matplotlib?
I've adapted the seaborn correlation plot example below.
from string import ascii_letters
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set_theme(style="white")
# Generate a large random dataset
rs = np.random.RandomState(33)
d = pd.DataFrame(data=rs.normal(size=(100, 7)),
columns=['Donald\nDuck','Mickey\nMouse','Han\nSolo',
'Luke\nSkywalker','Yoda','Santa\nClause','Ronald\nMcDonald'])
# Compute the correlation matrix
corr = d.corr()
# Generate a mask for the upper triangle
mask = np.triu(np.ones_like(corr, dtype=bool))
# Set up the matplotlib figure
f, ax = plt.subplots(figsize=(11, 9))
# Generate a custom diverging colormap
cmap = sns.diverging_palette(230, 20, as_cmap=True)
# Draw the heatmap with the mask and correct aspect ratio
sns.heatmap(corr, mask=mask, cmap=cmap, vmax=.3, center=0,
square=True, linewidths=.5, cbar_kws={"shrink": .5})
for i in ax.get_yticklabels():
i.set_ha('right')
i.set_rotation(0)
for i in ax.get_xticklabels():
i.set_ha('center')
Note the two for sequences above. These get the label and then set the horizontal alignment (You can also change the vertical alignment (set_va()).
The code above produces this:
I have a DF like that:
Day Destiny Flight Year
0 10 AJU 1504 2019
1 10 AJU 1502 2020
2 10 FOR 1524 2019
3 10 FOR 1522 2020
4 10 FOR 1528 2019
I am using this code to plot the chart to compare the year side by side for each destination.It's working well.
df.groupby(["Destiny","Year"])["Flight"].count().unstack().plot.bar(figsize=(12, 3))
I have this other one to plot values on top of the bars. But it is plotting in the wrong place.
a = df.groupby(["Destiny","Year"])["Flight"].count().unstack().plot.bar(figsize=(12, 3))
for i, v in enumerate(df.groupby(["Destiny","Year"])["Flight"].count()):
a.text(v, i, str(v))
How to display the value of the bar on each bar correctly?
I've been looking for something like that, but I haven't found it.
Update:
Version 3.4 of matplotlib added function bar_label, which could be incorporated as follows in the code below:
for bar_group in ax.containers:
ax.bar_label(bar_group, fmt='%.0f', size=18)
Old answer:
You can loop through the generated bars, and use their x, height and width to position the text. Adding an empty line into the string helps position the text independent of the scale. ax.margins() can add some space above the bars to make the text fit.
from matplotlib import pyplot as plt
import pandas as pd
df = pd.DataFrame({'Destiny': ['AJU','AJU','FOR','FOR','FOR' ],
'Flight':range(1501,1506),
'Year':[2019,2020,2019,2020,2019]})
ax = df.groupby(["Destiny","Year"])["Flight"].count().unstack().plot.bar(figsize=(12, 3))
for p in ax.patches:
x = p.get_x()
h = p.get_height()
w = p.get_width()
ax.annotate(f'{h:.0f}\n', (x + w/2, h), ha='center', va='center', size=18)
plt.margins(y=0.2)
plt.tight_layout()
plt.show()
The below add_value_labels function is from justfortherec, it's very easy to use, just pass matplotlib.axes.Axes object to it:
import pandas as pd
import matplotlib.pyplot as plt
def add_value_labels(ax, spacing=5):
"""Add labels to the end of each bar in a bar chart.
Arguments:
ax (matplotlib.axes.Axes): The matplotlib object containing the axes
of the plot to annotate.
spacing (int): The distance between the labels and the bars.
"""
# For each bar: Place a label
for rect in ax.patches:
# Get X and Y placement of label from rect.
y_value = rect.get_height()
x_value = rect.get_x() + rect.get_width() / 2
# Number of points between bar and label. Change to your liking.
space = spacing
# Vertical alignment for positive values
va = 'bottom'
# If value of bar is negative: Place label below bar
if y_value < 0:
# Invert space to place label below
space *= -1
# Vertically align label at top
va = 'top'
# Use Y value as label and format number with one decimal place
label = "{:.1f}".format(y_value)
# Create annotation
ax.annotate(
label, # Use `label` as label
(x_value, y_value), # Place label at end of the bar
xytext=(0, space), # Vertically shift label by `space`
textcoords="offset points", # Interpret `xytext` as offset in points
ha='center', # Horizontally center label
va=va) # Vertically align label differently for
# positive and negative values.
df = pd.read_csv("1.csv")
ax = df.groupby(["Destiny","Year"])["Flight"].count().unstack().plot.bar(figsize=(12, 3))
# Call the function above. All the magic happens there.
add_value_labels(ax)
plt.show()
I think we can adapt this answer referenced by #JohanC to fit your problem.
import pandas as pd
import seaborn as sn
import matplotlib.pyplot as plt
from decimal import Decimal
df = pd.DataFrame({'Day':[10]*5, 'Destiny':['AJU']*2+['FOR']*3, 'Flight':[1504,1502,1524,1522,1528],'Year':[2019,2020,2019,2020,2019]})
df.groupby(["Destiny","Year"])["Flight"].count().unstack().plot.bar(figsize=(12, 3))
a = df.groupby(["Destiny","Year"])["Flight"].count().unstack().plot.bar(figsize=(12, 3))
for p in a.patches:
a.annotate('{}'.format(Decimal(str(p.get_height()))), (p.get_x(), p.get_height()))
plt.show()
I'd like a function in Matplotlib similar to the Matlab 'scatterhist' function which takes continuous values for 'x' and 'y' axes, plus a categorical variable as input; and produces a scatter plot with marginal KDE plots and two or more categorical variables in different colours as output:
I've found examples of scatter plots with marginal histograms in Matplotlib, marginal histograms in Seaborn jointplot, overlapping histograms in Matplotlib and marginal KDE plots in Matplotib ; but I haven't found any examples which combine scatter plots with marginal KDE plots and are colour coded to indicate different categories.
If possible, I'd like a solution which uses 'vanilla' Matplotlib without Seaborn, as this will avoid dependencies and allow complete control and customisation of the plot appearance using standard Matplotlib commands.
I was going to try to write something based on the above examples; but before doing so wanted to check whether a similar function was already available, and if not then would be grateful for any guidance on the best approach to use.
#ImportanceOfBeingEarnest: Many thanks for your help.
Here's my first attempt at a solution.
It's a bit hacky but achieves my objectives, and is fully customisable using standard matplotlib commands. I'm posting the code here with annotations in case anyone else wishes to use it or develop it further. If there are any improvements or neater ways of writing the code I'm always keen to learn and would be grateful for guidance.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import gridspec
from scipy import stats
label = ['Setosa','Versicolor','Virginica'] # List of labels for categories
cl = ['b','r','y'] # List of colours for categories
categories = len(label)
sample_size = 20 # Number of samples in each category
# Create numpy arrays for dummy x and y data:
x = np.zeros(shape=(categories, sample_size))
y = np.zeros(shape=(categories, sample_size))
# Generate random data for each categorical variable:
for n in range (0, categories):
x[n,:] = np.array(np.random.randn(sample_size)) + 4 + n
y[n,:] = np.array(np.random.randn(sample_size)) + 6 - n
# Set up 4 subplots as axis objects using GridSpec:
gs = gridspec.GridSpec(2, 2, width_ratios=[1,3], height_ratios=[3,1])
# Add space between scatter plot and KDE plots to accommodate axis labels:
gs.update(hspace=0.3, wspace=0.3)
# Set background canvas colour to White instead of grey default
fig = plt.figure()
fig.patch.set_facecolor('white')
ax = plt.subplot(gs[0,1]) # Instantiate scatter plot area and axis range
ax.set_xlim(x.min(), x.max())
ax.set_ylim(y.min(), y.max())
ax.set_xlabel('x')
ax.set_ylabel('y')
axl = plt.subplot(gs[0,0], sharey=ax) # Instantiate left KDE plot area
axl.get_xaxis().set_visible(False) # Hide tick marks and spines
axl.get_yaxis().set_visible(False)
axl.spines["right"].set_visible(False)
axl.spines["top"].set_visible(False)
axl.spines["bottom"].set_visible(False)
axb = plt.subplot(gs[1,1], sharex=ax) # Instantiate bottom KDE plot area
axb.get_xaxis().set_visible(False) # Hide tick marks and spines
axb.get_yaxis().set_visible(False)
axb.spines["right"].set_visible(False)
axb.spines["top"].set_visible(False)
axb.spines["left"].set_visible(False)
axc = plt.subplot(gs[1,0]) # Instantiate legend plot area
axc.axis('off') # Hide tick marks and spines
# Plot data for each categorical variable as scatter and marginal KDE plots:
for n in range (0, categories):
ax.scatter(x[n],y[n], color='none', label=label[n], s=100, edgecolor= cl[n])
kde = stats.gaussian_kde(x[n,:])
xx = np.linspace(x.min(), x.max(), 1000)
axb.plot(xx, kde(xx), color=cl[n])
kde = stats.gaussian_kde(y[n,:])
yy = np.linspace(y.min(), y.max(), 1000)
axl.plot(kde(yy), yy, color=cl[n])
# Copy legend object from scatter plot to lower left subplot and display:
# NB 'scatterpoints = 1' customises legend box to show only 1 handle (icon) per label
handles, labels = ax.get_legend_handles_labels()
axc.legend(handles, labels, scatterpoints = 1, loc = 'center', fontsize = 12)
plt.show()`
`
Version 2, using Pandas to import 'real' data from a csv file, with a different number of entries in each category. (csv file format: row 0 = headers; col 0 = x values, col 1 = y values, col 2 = category labels). Scatterplot axis and legend labels are generated from column headers.
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import gridspec
from scipy import stats
import pandas as pd
"""
Create scatter plot with marginal KDE plots
from csv file with 3 cols of data
formatted as following example (first row of
data are headers):
'x_label', 'y_label', 'category_label'
4,5,'virginica'
3,6,'sentosa'
4,6, 'virginica' etc...
"""
df = pd.read_csv('iris_2.csv') # enter filename for csv file to be imported (within current working directory)
cl = ['b','r','y', 'g', 'm', 'k'] # Custom list of colours for each categories - increase as needed...
headers = list(df.columns) # Extract list of column headers
# Find min and max values for all x (= col [0]) and y (= col [1]) in dataframe:
xmin, xmax = df.min(axis=0)[0], df.max(axis=0)[0]
ymin, ymax = df.min(axis=0)[1], df.max(axis=0)[1]
# Create a list of all unique categories which occur in the right hand column (ie index '2'):
category_list = df.ix[:,2].unique()
# Set up 4 subplots and aspect ratios as axis objects using GridSpec:
gs = gridspec.GridSpec(2, 2, width_ratios=[1,3], height_ratios=[3,1])
# Add space between scatter plot and KDE plots to accommodate axis labels:
gs.update(hspace=0.3, wspace=0.3)
fig = plt.figure() # Set background canvas colour to White instead of grey default
fig.patch.set_facecolor('white')
ax = plt.subplot(gs[0,1]) # Instantiate scatter plot area and axis range
ax.set_xlim(xmin, xmax)
ax.set_ylim(ymin, ymax)
ax.set_xlabel(headers[0], fontsize = 14)
ax.set_ylabel(headers[1], fontsize = 14)
ax.yaxis.labelpad = 10 # adjust space between x and y axes and their labels if needed
axl = plt.subplot(gs[0,0], sharey=ax) # Instantiate left KDE plot area
axl.get_xaxis().set_visible(False) # Hide tick marks and spines
axl.get_yaxis().set_visible(False)
axl.spines["right"].set_visible(False)
axl.spines["top"].set_visible(False)
axl.spines["bottom"].set_visible(False)
axb = plt.subplot(gs[1,1], sharex=ax) # Instantiate bottom KDE plot area
axb.get_xaxis().set_visible(False) # Hide tick marks and spines
axb.get_yaxis().set_visible(False)
axb.spines["right"].set_visible(False)
axb.spines["top"].set_visible(False)
axb.spines["left"].set_visible(False)
axc = plt.subplot(gs[1,0]) # Instantiate legend plot area
axc.axis('off') # Hide tick marks and spines
# For each category in the list...
for n in range(0, len(category_list)):
# Create a sub-table containing only entries matching current category:
st = df.loc[df[headers[2]] == category_list[n]]
# Select first two columns of sub-table as x and y values to be plotted:
x = st[headers[0]]
y = st[headers[1]]
# Plot data for each categorical variable as scatter and marginal KDE plots:
ax.scatter(x,y, color='none', s=100, edgecolor= cl[n], label = category_list[n])
kde = stats.gaussian_kde(x)
xx = np.linspace(xmin, xmax, 1000)
axb.plot(xx, kde(xx), color=cl[n])
kde = stats.gaussian_kde(y)
yy = np.linspace(ymin, ymax, 1000)
axl.plot(kde(yy), yy, color=cl[n])
# Copy legend object from scatter plot to lower left subplot and display:
# NB 'scatterpoints = 1' customises legend box to show only 1 handle (icon) per label
handles, labels = ax.get_legend_handles_labels()
axc.legend(handles, labels, title = headers[2], scatterpoints = 1, loc = 'center', fontsize = 12)
plt.show()
I am trying to plot some data with a discrete color bar. I was following the example given (https://gist.github.com/jakevdp/91077b0cae40f8f8244a) but the issue is this example does not work 1-1 with different spacing. For example, the spacing in the example in the link is for only increasing by 1 but my data is increasing by 0.5. You can see the output from the code I have.. Any help with this would be appreciated. I know I am missing something key here but cant figure it out.
import matplotlib.pylab as plt
import numpy as np
def discrete_cmap(N, base_cmap=None):
"""Create an N-bin discrete colormap from the specified input map"""
# Note that if base_cmap is a string or None, you can simply do
# return plt.cm.get_cmap(base_cmap, N)
# The following works for string, None, or a colormap instance:
base = plt.cm.get_cmap(base_cmap)
color_list = base(np.linspace(0, 1, N))
cmap_name = base.name + str(N)
return base.from_list(cmap_name, color_list, N)
num=11
x = np.random.randn(40)
y = np.random.randn(40)
c = np.random.randint(num, size=40)
plt.figure(figsize=(10,7.5))
plt.scatter(x, y, c=c, s=50, cmap=discrete_cmap(num, 'jet'))
plt.colorbar(ticks=np.arange(0,5.5,0.5))
plt.clim(-0.5, num - 0.5)
plt.show()
Not sure what version of matplotlib/pyplot introduced this, but plt.get_cmap now supports an int argument specifying the number of colors you want to get, for discrete colormaps.
This automatically results in the colorbar being discrete.
By the way, pandas has an even better handling of the colorbar.
import numpy as np
from matplotlib import pyplot as plt
plt.style.use('ggplot')
# remove if not using Jupyter/IPython
%matplotlib inline
# choose number of clusters and number of points in each cluster
n_clusters = 5
n_samples = 20
# there are fancier ways to do this
clusters = np.array([k for k in range(n_clusters) for i in range(n_samples)])
# generate the coordinates of the center
# of each cluster by shuffling a range of values
clusters_x = np.arange(n_clusters)
clusters_y = np.arange(n_clusters)
np.random.shuffle(clusters_x)
np.random.shuffle(clusters_y)
# get dicts like cluster -> center coordinate
x_dict = dict(enumerate(clusters_x))
y_dict = dict(enumerate(clusters_y))
# get coordinates of cluster center for each point
x = np.array(list(x_dict[k] for k in clusters)).astype(float)
y = np.array(list(y_dict[k] for k in clusters)).astype(float)
# add noise
x += np.random.normal(scale=0.5, size=n_clusters*n_samples)
y += np.random.normal(scale=0.5, size=n_clusters*n_samples)
### Finally, plot
fig, ax = plt.subplots(figsize=(12,8))
# get discrete colormap
cmap = plt.get_cmap('viridis', n_clusters)
# scatter points
scatter = ax.scatter(x, y, c=clusters, cmap=cmap)
# scatter cluster centers
ax.scatter(clusters_x, clusters_y, c='red')
# add colorbar
cbar = plt.colorbar(scatter)
# set ticks locations (not very elegant, but it works):
# - shift by 0.5
# - scale so that the last value is at the center of the last color
tick_locs = (np.arange(n_clusters) + 0.5)*(n_clusters-1)/n_clusters
cbar.set_ticks(tick_locs)
# set tick labels (as before)
cbar.set_ticklabels(np.arange(n_clusters))
Ok so this is the hack I found for my own question. I am sure there is a better way to do this but this works for what I am doing. Feel free to suggest a better way to do this.
import numpy as np
import matplotlib.pylab as plt
def discrete_cmap(N, base_cmap=None):
"""Create an N-bin discrete colormap from the specified input map"""
# Note that if base_cmap is a string or None, you can simply do
# return plt.cm.get_cmap(base_cmap, N)
# The following works for string, None, or a colormap instance:
base = plt.cm.get_cmap(base_cmap)
color_list = base(np.linspace(0, 1, N))
cmap_name = base.name + str(N)
return base.from_list(cmap_name, color_list, N)
num=11
plt.figure(figsize=(10,7.5))
x = np.random.randn(40)
y = np.random.randn(40)
c = np.random.randint(num, size=40)
plt.scatter(x, y, c=c, s=50, cmap=discrete_cmap(num, 'jet'))
cbar=plt.colorbar(ticks=range(num))
plt.clim(-0.5, num - 0.5)
cbar.ax.set_yticklabels(np.arange(0.0,5.5,0.5))
plt.show()
For some reason I cannot upload the image associated with the code above. I get an error when uploading so not sure how to show the final example. But simply I set the color bar axes for tick labels for a vertical color bar and passed in the labels I want and it produced the correct output.