# loading libraries
import os
import pandas as pd
import numpy as np
import seaborn as sb
import matplotlib.pyplot as plt

os.chdir("D:\\SURA\\Combined")

# load data
Data = pd.read_csv('AttacksBinarized.csv')

X = Data.drop('Label', axis=1)
y = Data['Label']

df = pd.DataFrame(X)

# Creating correlation matrix
cor_matrix = df.corr(method='spearman').abs()

# Selecting upper triangle of correlation matrix
upper_tri = cor_matrix.where(np.triu(np.ones(cor_matrix.shape),
                                     k=1).astype(bool))

# Finding index of feature columns with correlation greater than 0.80
to_drop = [column for column in upper_tri.columns if any(upper_tri[column] > 0.80)]

# Dropping Marked Features
df1 = Data.drop(to_drop, axis=1)

df1.to_csv("SpearmanRankCorrelatedData.csv", index=False)

sb.heatmap(cor_matrix,
           xticklabels=cor_matrix.columns,
           yticklabels=cor_matrix.columns,
           cmap='RdBu_r',
           annot=True,
           linewidths=0.5
           )
plt.show()