Plotting from Pandas and with Seaborn

Original Source: https://www.coursera.org/specializations/data-science-python

Pandas Visualization

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

%matplotlib inline

# set default figure size to (14, 8)
plt.rcParams['figure.figsize'] = (14.0, 8.0)

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

['bmh',
 'classic',
 'dark_background',
 'fast',
 'fivethirtyeight',
 'ggplot',
 'grayscale',
 'seaborn-bright',
 'seaborn-colorblind',
 'seaborn-dark-palette',
 'seaborn-dark',
 'seaborn-darkgrid',
 'seaborn-deep',
 'seaborn-muted',
 'seaborn-notebook',
 'seaborn-paper',
 'seaborn-pastel',
 'seaborn-poster',
 'seaborn-talk',
 'seaborn-ticks',
 'seaborn-white',
 'seaborn-whitegrid',
 'seaborn',
 'Solarize_Light2',
 'tableau-colorblind10',
 '_classic_test']

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

DataFrame.plot

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()

	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

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

We can select which plot we want to use by passing it into the ‘kind’ parameter.

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

# 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')

<matplotlib.axes._subplots.AxesSubplot at 0x20d94e15630>

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

df.plot.box();

df.plot.hist(alpha=0.5);

Kernel density estimation plots are useful for deriving a smooth continuous function from a given sample.

df.plot.kde();

pandas.plotting

Iris flower data set

import numpy as np
import pandas as pd
from sklearn.datasets import load_iris

iris = load_iris()

# np.c_ is the numpy concatenate function
# which is used to concat iris['data'] and iris['target'] arrays
# for pandas column argument: concat iris['feature_names'] list
# and string list (in this case one string); you can make this anything you'd like..  
# the original dataset would probably call this ['Species']
iris = pd.DataFrame(data= np.c_[iris['data'], iris['target']],
                     columns= iris['feature_names'] + ['target'])
iris.head()

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)	target
0	5.1	3.5	1.4	0.2	0.0
1	4.9	3.0	1.4	0.2	0.0
2	4.7	3.2	1.3	0.2	0.0
3	4.6	3.1	1.5	0.2	0.0
4	5.0	3.6	1.4	0.2	0.0

pd.plotting.scatter_matrix(iris);

plt.figure()
pd.plotting.parallel_coordinates(iris, 'target');

Seaborn

import seaborn as sns

# set seaborn design
sns.set()

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')

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();

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

plt.figure()
# sns.displot does this in one line
sns.distplot(v3);

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

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

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

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

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

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

plt.figure(figsize=(8,6))
plt.subplot(121)
sns.swarmplot('target', 'petal length (cm)', data=iris);
plt.subplot(122)
sns.violinplot('target', 'petal length (cm)', data=iris);