Drop Highly Correlated Features

Goal

This post aims to introduce how to drop highly correlated features.

Reference

Libraries

In [8]:
import pandas as pd
import numpy as np
from sklearn.datasets import load_boston
import seaborn as sns

Create a data with highly correlated variables

Load boston housing data

In [4]:
boston = load_boston()
df_boston = pd.DataFrame(boston.data, columns=boston.feature_names)
df_boston.head()
Out[4]:
CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT
0 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.0900 1.0 296.0 15.3 396.90 4.98
1 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671 2.0 242.0 17.8 396.90 9.14
2 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671 2.0 242.0 17.8 392.83 4.03
3 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622 3.0 222.0 18.7 394.63 2.94
4 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 3.0 222.0 18.7 396.90 5.33

Add another correlated feature

In [6]:
df_boston['CRIM_correlated'] = df_boston['CRIM'] * 3 + 10 + np.random.random(df_boston.shape[0])
df_boston.head()
Out[6]:
CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT CRIM_correlated
0 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.0900 1.0 296.0 15.3 396.90 4.98 10.284178
1 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671 2.0 242.0 17.8 396.90 9.14 10.102942
2 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671 2.0 242.0 17.8 392.83 4.03 10.387687
3 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622 3.0 222.0 18.7 394.63 2.94 10.607908
4 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 3.0 222.0 18.7 396.90 5.33 10.824663

Calclate Correlation

In [7]:
df_corr = df_boston.corr()
df_corr.head()
Out[7]:
CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT CRIM_correlated
CRIM 1.000000 -0.200469 0.406583 -0.055892 0.420972 -0.219247 0.352734 -0.379670 0.625505 0.582764 0.289946 -0.385064 0.455621 0.999937
ZN -0.200469 1.000000 -0.533828 -0.042697 -0.516604 0.311991 -0.569537 0.664408 -0.311948 -0.314563 -0.391679 0.175520 -0.412995 -0.200756
INDUS 0.406583 -0.533828 1.000000 0.062938 0.763651 -0.391676 0.644779 -0.708027 0.595129 0.720760 0.383248 -0.356977 0.603800 0.406720
CHAS -0.055892 -0.042697 0.062938 1.000000 0.091203 0.091251 0.086518 -0.099176 -0.007368 -0.035587 -0.121515 0.048788 -0.053929 -0.055514
NOX 0.420972 -0.516604 0.763651 0.091203 1.000000 -0.302188 0.731470 -0.769230 0.611441 0.668023 0.188933 -0.380051 0.590879 0.421744
In [10]:
sns.heatmap(df_corr);

Drop highly correlated feature

In [35]:
threshold = 0.9


columns = np.full((df_corr.shape[0],), True, dtype=bool)
for i in range(df_corr.shape[0]):
    for j in range(i+1, df_corr.shape[0]):
        if df_corr.iloc[i,j] >= threshold:
            if columns[j]:
                columns[j] = False
selected_columns = df_boston.columns[columns]
selected_columns
df_boston = df_boston[selected_columns]
In [36]:
df_boston.head()
Out[36]:
CRIM ZN INDUS CHAS NOX RM AGE DIS RAD PTRATIO B LSTAT
0 0.00632 18.0 2.31 0.0 0.538 6.575 65.2 4.0900 1.0 15.3 396.90 4.98
1 0.02731 0.0 7.07 0.0 0.469 6.421 78.9 4.9671 2.0 17.8 396.90 9.14
2 0.02729 0.0 7.07 0.0 0.469 7.185 61.1 4.9671 2.0 17.8 392.83 4.03
3 0.03237 0.0 2.18 0.0 0.458 6.998 45.8 6.0622 3.0 18.7 394.63 2.94
4 0.06905 0.0 2.18 0.0 0.458 7.147 54.2 6.0622 3.0 18.7 396.90 5.33

Comments

Comments powered by Disqus