In [2]:
import seaborn as sns
%matplotlib inline
In [3]:
tips = sns.load_dataset('tips')
In [4]:
tips.head()
Out[4]:
In [16]:
sns.distplot(tips['total_bill'])
# Safe to ignore warnings
Out[16]:
To remove the kde layer and just have the histogram use:
In [9]:
sns.distplot(tips['total_bill'],kde=False,bins=30)
Out[9]:
In [12]:
sns.jointplot(x='total_bill',y='tip',data=tips,kind='scatter')
Out[12]:
In [15]:
sns.jointplot(x='total_bill',y='tip',data=tips,kind='hex')
Out[15]:
In [17]:
sns.jointplot(x='total_bill',y='tip',data=tips,kind='reg')
Out[17]:
In [18]:
sns.pairplot(tips)
Out[18]:
In [21]:
sns.pairplot(tips,hue='sex',palette='coolwarm')
Out[21]:
In [22]:
sns.rugplot(tips['total_bill'])
Out[22]:
kdeplots are Kernel Density Estimation plots. These KDE plots replace every single observation with a Gaussian (Normal) distribution centered around that value. For example:
In [35]:
# Don't worry about understanding this code!
# It's just for the diagram below
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
#Create dataset
dataset = np.random.randn(25)
# Create another rugplot
sns.rugplot(dataset);
# Set up the x-axis for the plot
x_min = dataset.min() - 2
x_max = dataset.max() + 2
# 100 equally spaced points from x_min to x_max
x_axis = np.linspace(x_min,x_max,100)
# Set up the bandwidth, for info on this:
url = 'http://en.wikipedia.org/wiki/Kernel_density_estimation#Practical_estimation_of_the_bandwidth'
bandwidth = ((4*dataset.std()**5)/(3*len(dataset)))**.2
# Create an empty kernel list
kernel_list = []
# Plot each basis function
for data_point in dataset:
# Create a kernel for each point and append to list
kernel = stats.norm(data_point,bandwidth).pdf(x_axis)
kernel_list.append(kernel)
#Scale for plotting
kernel = kernel / kernel.max()
kernel = kernel * .4
plt.plot(x_axis,kernel,color = 'grey',alpha=0.5)
plt.ylim(0,1)
Out[35]:
In [37]:
# To get the kde plot we can sum these basis functions.
# Plot the sum of the basis function
sum_of_kde = np.sum(kernel_list,axis=0)
# Plot figure
fig = plt.plot(x_axis,sum_of_kde,color='indianred')
# Add the initial rugplot
sns.rugplot(dataset,c = 'indianred')
# Get rid of y-tick marks
plt.yticks([])
# Set title
plt.suptitle("Sum of the Basis Functions")
Out[37]:
So with our tips dataset:
In [41]:
sns.kdeplot(tips['total_bill'])
sns.rugplot(tips['total_bill'])
Out[41]:
In [42]:
sns.kdeplot(tips['tip'])
sns.rugplot(tips['tip'])
Out[42]: