Linear Regression Visualisation using Seaborn

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from mpl_toolkits.basemap import Basemap
%matplotlib inline
import warnings
warnings.filterwarnings('ignore')
%config InlineBackend.figure_format = 'retina'

In [2]:

cars = pd.read_csv("http://web.pdx.edu/~gerbing/data/cars.csv")

In [3]:

cars.head()

Out[3]:

	Model	MPG	Cylinders	Engine Disp	Horsepower	Weight	Accelerate	Year	Origin
0	amc ambassador dpl	15.0	8	390.0	190	3850	8.5	70	American
1	amc gremlin	21.0	6	199.0	90	2648	15.0	70	American
2	amc hornet	18.0	6	199.0	97	2774	15.5	70	American
3	amc rebel sst	16.0	8	304.0	150	3433	12.0	70	American
4	buick estate wagon (sw)	14.0	8	455.0	225	3086	10.0	70	American

In [8]:

cars.columns = ["model","mpg","cylinder","engine","hp","weight","accelerate","year","origin"]

In [18]:

cars.head()

Out[18]:

	model	mpg	cylinder	engine	hp	weight	accelerate	year	origin
0	amc ambassador dpl	15.0	8	390.0	190	3850	8.5	70	American
1	amc gremlin	21.0	6	199.0	90	2648	15.0	70	American
2	amc hornet	18.0	6	199.0	97	2774	15.5	70	American
3	amc rebel sst	16.0	8	304.0	150	3433	12.0	70	American
4	buick estate wagon (sw)	14.0	8	455.0	225	3086	10.0	70	American

Regression Plot¶

In [17]:

sns.lmplot(x='weight', y='hp', data=cars, size=5, aspect=2)
plt.title("Weight vs HP")
plt.show()

Generating residual plot of the regression line¶

In [25]:

fig = plt.figure(figsize=(10,8))
sns.residplot(x = 'weight',y = 'hp', data = cars, color = "green")

Out[25]:

<matplotlib.axes._subplots.AxesSubplot at 0x11f1618d0>

In [24]:

fig = plt.figure(figsize=(10,8))
sns.residplot(x='hp', y='mpg', data=cars, color='green')

Out[24]:

<matplotlib.axes._subplots.AxesSubplot at 0x11ef3f4e0>

Higher order regressions¶

In [27]:

# Generate a scatter plot of 'weight' and 'mpg' using red circles
plt.scatter(cars['weight'], cars['mpg'], label='data', color='red', marker='o')

Out[27]:

<matplotlib.collections.PathCollection at 0x11fe96588>

In [35]:

# Plot in blue a linear regression of order 1 between 'weight' and 'mpg'
# Generate a scatter plot of 'weight' and 'mpg' using red circles
plt.figure(figsize=(10,8))
plt.scatter(cars['weight'], cars['mpg'], label='data', color='red', marker='o')
sns.regplot(x='weight', y='mpg', data=cars, scatter=None, color='blue', label='order 1')
# Plot in green a linear regression of order 2 between 'weight' and 'mpg'
sns.regplot(x='weight', y='mpg', data=cars, scatter=None, order=2, color='green', label='order 2')

plt.legend(loc='upper right')

Out[35]:

<matplotlib.legend.Legend at 0x1212b50f0>

In [37]:

sns.lmplot(x='weight', y='hp', data=cars, hue='origin', palette='Set1')

Out[37]:

<seaborn.axisgrid.FacetGrid at 0x121515ef0>

<matplotlib.figure.Figure at 0x121bcdac8>

Grouping linear regressions by row or column¶

In [40]:

sns.lmplot(x='weight', y='hp', data=cars, col='origin')

Out[40]:

<seaborn.axisgrid.FacetGrid at 0x117ccacc0>