utils.py 文件源码

def corr_fea(df,cols,de=None,bar=0.9):
    from scipy.stats import pearsonr
    xcols = []
    for c,i in enumerate(cols[:-1]):
        for j in cols[c+1:]:
            if i==j:
                continue
            #score = pearsonr(df[i],df[j])[0]
            score = df[i].corr(df[j])
            #print(i,j,score)
            if score>bar:
                df["%s-%s"%(i,j)] = df[i]-df[j]
                if de is not None:
                    de["%s-%s"%(i,j)] = de[i]-de[j]
                xcols.append(j)
            if score<-bar:
                df["%s+%s"%(i,j)] = df[i]+df[j]
                if de is not None:
                    de["%s+%s"%(i,j)] = de[i]+de[j]
                xcols.append(j)
    return xcols