In [2]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib notebook
In [2]:
# see the pre-defined styles provided.
plt.style.available
Out[2]:
In [3]:
# use the 'seaborn-colorblind' style
plt.style.use('seaborn-colorblind')
In [4]:
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[4]:
In [5]:
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.
In [6]:
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 [7]:
# 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[7]:
In [8]:
ax = df.plot.scatter('A', 'C', c='B', s=df['B'], colormap='viridis')
ax.set_aspect('equal')
In [9]:
df.plot.box();
In [10]:
df.plot.hist(alpha=0.7);
Kernel density estimation plots are useful for deriving a smooth continuous function from a given sample.
In [11]:
df.plot.kde();
In [4]:
iris = pd.read_csv('iris.csv')
iris.head()
Out[4]:
In [6]:
pd.plotting.scatter_matrix(iris);
In [7]:
plt.figure()
pd.plotting.parallel_coordinates(iris, 'Name');
In [8]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib notebook
In [9]:
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 [10]:
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 [11]:
# 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 [12]:
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 [13]:
sns.jointplot(v1, v2, alpha=0.4);
In [14]:
grid = sns.jointplot(v1, v2, alpha=0.4);
grid.ax_joint.set_aspect('equal')
In [15]:
sns.jointplot(v1, v2, kind='hex');
In [16]:
# set the seaborn style for all the following plots
sns.set_style('white')
sns.jointplot(v1, v2, kind='kde', space=0);
In [17]:
iris = pd.read_csv('iris.csv')
iris.head()
Out[17]:
In [18]:
sns.pairplot(iris, hue='Name', diag_kind='kde', size=2);
In [20]:
plt.figure(figsize=(8,6))
plt.subplot(121)
sns.swarmplot('Name', 'PetalLength', data=iris);
plt.subplot(122)
sns.violinplot('Name', 'PetalLength', data=iris);