with the following function we can select highly correlated features

Solutions on MaxInterview for with the following function we can select highly correlated features by the best coders in the world

showing results for - "with the following function we can select highly correlated features"
Celestine
08 Jan 2020
1# with the following function we can select highly correlated features
2# it will remove the first feature that is correlated with anything other feature
3
4def correlation(dataset, threshold):
5    col_corr = set()  # Set of all the names of correlated columns
6    corr_matrix = dataset.corr()
7    for i in range(len(corr_matrix.columns)):
8        for j in range(i):
9            if abs(corr_matrix.iloc[i, j]) > threshold: # we are interested in absolute coeff value
10                colname = corr_matrix.columns[i]  # getting the name of column
11                col_corr.add(colname)
12    return col_corr
13
14
15
16corr_features = correlation(X_train, 0.7)
17len(set(corr_features))