Correlation and Correlation Matrices

source: https://datascience.stackexchange.com/questions/10459/calculation-and-visualization-of-correlation-matrix-with-pandas



In [2]:

    
import matplotlib
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

# Read file into a Pandas dataframe
from pandas import DataFrame, read_csv
f = 'https://archive.ics.uci.edu/ml/machine-learning-databases/abalone/abalone.data'
df = read_csv(f)
df=df[0:10]
df



In [ ]:

    
Correlation matrix plotting function:



In [9]:

    
# Correlation matric plotting function
def correlation_matrix(df):
    from matplotlib import pyplot as plt
    from matplotlib import cm as cm

    fig = plt.figure()
    ax1 = fig.add_subplot(111)
    cmap = cm.get_cmap('jet', 30)
    cax = ax1.imshow(df.corr(), interpolation="nearest", cmap=cmap)
    ax1.grid(True)
    plt.title('Abalone Feature Correlation')
    labels=['Sex','Length','Diam','Height','Whole','Shucked','Viscera','Shell','Rings',]
    ax1.set_xticklabels(labels,fontsize=6)
    ax1.set_yticklabels(labels,fontsize=6)
    # Add colorbar, make sure to specify tick locations to match desired ticklabels
    fig.colorbar(cax, ticks=[.75,.8,.85,.90,.95,1])
    plt.show()

correlation_matrix(df)

	M	0.455	0.365	0.095	0.514	0.2245	0.101	0.15	15
0	M	0.350	0.265	0.090	0.2255	0.0995	0.0485	0.070	7
1	F	0.530	0.420	0.135	0.6770	0.2565	0.1415	0.210	9
2	M	0.440	0.365	0.125	0.5160	0.2155	0.1140	0.155	10
3	I	0.330	0.255	0.080	0.2050	0.0895	0.0395	0.055	7
4	I	0.425	0.300	0.095	0.3515	0.1410	0.0775	0.120	8
5	F	0.530	0.415	0.150	0.7775	0.2370	0.1415	0.330	20
6	F	0.545	0.425	0.125	0.7680	0.2940	0.1495	0.260	16
7	M	0.475	0.370	0.125	0.5095	0.2165	0.1125	0.165	9
8	F	0.550	0.440	0.150	0.8945	0.3145	0.1510	0.320	19
9	F	0.525	0.380	0.140	0.6065	0.1940	0.1475	0.210	14