console_python_corr_analysis

# Unsophisticated corr analysis to deal w variable bias
data_corr = sDf.corr()
size = data_corr.shape[0] - 1 


# Set the threshold to select only highly correlated attributes
threshold = 0.5

# List of pairs along with correlation above threshold
corr_list = []

#Search for the highly correlated pairs
for i in range(0,size): #for 'size' features
    for j in range(i+1,size): #avoid repetition
        if (data_corr.iloc[i,j] >= threshold and data_corr.iloc[i,j] < 1) or (data_corr.iloc[i,j] < 0 and data_corr.iloc[i,j] <= -threshold):
            corr_list.append([data_corr.iloc[i,j],i,j]) #store correlation and columns index

#Sort to show higher ones first 
s_corr_list = sorted(corr_list,key=lambda x: -abs(x[0]))

cols = list(sDf.columns.values)
corrDf = pd.DataFrame(columns=('A','B','corr'))
#Print correlations and column names
for v,i,j in s_corr_list:
    print ("%s and %s = %.2f" % (cols[i],cols[j],v))
    corrDf.loc[i] = [cols[i],cols[j],v ]