Data Visualisation: Seaborn

In [153]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

%matplotlib inline

In [154]:

# see the pre-defined styles provided.
plt.style.available

Out[154]:

['seaborn-dark',
 'seaborn-ticks',
 'seaborn',
 'bmh',
 'seaborn-pastel',
 'seaborn-whitegrid',
 'seaborn-colorblind',
 'seaborn-muted',
 'seaborn-notebook',
 'dark_background',
 'seaborn-bright',
 'grayscale',
 'seaborn-deep',
 'fivethirtyeight',
 'classic',
 'seaborn-dark-palette',
 'seaborn-darkgrid',
 'ggplot',
 'seaborn-white',
 'seaborn-poster',
 'seaborn-talk',
 'seaborn-paper']

In [155]:

# use the 'seaborn-colorblind' style
plt.style.use('fivethirtyeight')

In [156]:

plt.plot(4,5,"o")

Out[156]:

[<matplotlib.lines.Line2D at 0x121224940>]

In [157]:

np.random.seed(123)

df = pd.DataFrame({'A': np.random.randn(365).cumsum(0), 
                   'B': np.random.randn(365).cumsum(0) + 20,
                   'C': np.random.randn(365).cumsum(0) - 20}, 
                  index=pd.date_range('1/1/2017', periods=365))
df.head()

Out[157]:

	A	B	C
2017-01-01	-1.085631	20.059291	-20.230904
2017-01-02	-0.088285	21.803332	-16.659325
2017-01-03	0.194693	20.835588	-17.055481
2017-01-04	-1.311601	21.255156	-17.093802
2017-01-05	-1.890202	21.462083	-19.518638

In [158]:

df.plot(); # add a semi-colon to the end of the plotting call to suppress unwanted output

In [159]:

df.plot('A','B', kind = 'scatter');

You can also choose the plot kind by using the DataFrame.plot.kind methods instead of providing the kind keyword argument.
kind :

• 'line' : line plot (default)
• 'bar' : vertical bar plot
• 'barh' : horizontal bar plot
• 'hist' : histogram
• 'box' : boxplot
• 'kde' : Kernel Density Estimation plot
• 'density' : same as 'kde'
• 'area' : area plot
• 'pie' : pie plot
• 'scatter' : scatter plot
• 'hexbin' : hexbin plot

In [160]:

# create a scatter plot of columns 'A' and 'C', with changing color (c) and size (s) based on column 'B'
df.plot.scatter('A', 'C', c='B', s=df['B'], colormap='viridis')

Out[160]:

<matplotlib.axes._subplots.AxesSubplot at 0x1213407f0>

In [161]:

ax = df.plot.scatter('A', 'C', c='B', s=df['B'], colormap='viridis')
ax.set_aspect('equal')

In [162]:

df.plot.box();

In [163]:

df.plot.hist(alpha=0.7);

In [164]:

df.plot.kde();

In [165]:

iris = pd.read_csv('iris.csv')
iris.head()

Out[165]:

	Id	SepalLengthCm	SepalWidthCm	PetalLengthCm	PetalWidthCm	Species
0	1	5.1	3.5	1.4	0.2	Iris-setosa
1	2	4.9	3.0	1.4	0.2	Iris-setosa
2	3	4.7	3.2	1.3	0.2	Iris-setosa
3	4	4.6	3.1	1.5	0.2	Iris-setosa
4	5	5.0	3.6	1.4	0.2	Iris-setosa

In [166]:

iris = iris.drop("Id", axis = 1)

In [167]:

plt.figure(figsize=(10,8))
pd.tools.plotting.parallel_coordinates(iris, 'Species');

Seaborn¶

In [168]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

In [169]:

np.random.seed(1234)

v1 = pd.Series(np.random.normal(0,10,1000), name='v1')
v2 = pd.Series(2*v1 + np.random.normal(60,15,1000), name='v2')

In [170]:

plt.figure()
plt.hist(v1, alpha=0.7, bins=np.arange(-50,150,5), label='v1');
plt.hist(v2, alpha=0.7, bins=np.arange(-50,150,5), label='v2');
plt.legend();

In [171]:

# plot a kernel density estimation over a stacked barchart
plt.figure()
plt.hist([v1, v2], histtype='barstacked', normed=True);
v3 = np.concatenate((v1,v2))
sns.kdeplot(v3);

In [172]:

plt.figure()
# we can pass keyword arguments for each individual component of the plot
sns.distplot(v3, hist_kws={'color': 'Teal'}, kde_kws={'color': 'Navy'});

In [173]:

sns.jointplot(v1, v2, alpha=0.4);

In [174]:

grid = sns.jointplot(v1, v2, alpha=0.4);
grid.ax_joint.set_aspect('equal')

In [175]:

sns.jointplot(v1, v2, kind='hex');

In [176]:

# set the seaborn style for all the following plots
sns.set_style('white')

sns.jointplot(v1, v2, kind='kde', space=0);

In [177]:

sns.pairplot(iris, hue='Species', diag_kind='kde', size=2);

In [178]:

plt.figure(figsize=(8,6))
plt.subplot(121)
sns.swarmplot('Species', 'PetalLengthCm', data=iris);
plt.subplot(122)
sns.violinplot('Species', 'PetalLengthCm', data=iris);

In [ ]: