问使用矢量化通过Pandas转换R函数插入符号：：findCorrelation与Python 3的关系

EN

function (x, cutoff = 0.9, verbose = FALSE, names = FALSE, exact = ncol(x) < 
100) 
 {
  if (names & is.null(colnames(x))) 
    stop("'x' must have column names when `names = TRUE`")
  out <- if (exact) 
    findCorrelation_exact(x = x, cutoff = cutoff, verbose = verbose)
  else findCorrelation_fast(x = x, cutoff = cutoff, verbose = verbose)
  out
  if (names) 
    out <- colnames(x)[out]
  out
}

findCorrelation_fast <- function(x, cutoff = .90)
{
 if(any(!complete.cases(x)))
 stop("The correlation matrix has some missing values.")
 averageCorr <- colMeans(abs(x))
 averageCorr <- as.numeric(as.factor(averageCorr))
 x[lower.tri(x, diag = TRUE)] <- NA
 combsAboveCutoff <- which(abs(x) > cutoff)

 colsToCheck <- ceiling(combsAboveCutoff / nrow(x))
 rowsToCheck <- combsAboveCutoff %% nrow(x)

 colsToDiscard <- averageCorr[colsToCheck] > averageCorr[rowsToCheck]
 rowsToDiscard <- !colsToDiscard

 deletecol <- c(colsToCheck[colsToDiscard], rowsToCheck[rowsToDiscard])
 deletecol <- unique(deletecol)
 deletecol
}

import numpy as np
import pandas as pd

# calculate pair-wise correlations

def findCorrelated(corrmat, cutoff = 0.8):    

### search correlation matrix and identify pairs that if removed would reduce pair-wise correlations
# args:
    # corrmat: a correlation matrix
    # cutoff: pairwise absolute correlation cutoff
# returns:
    # variables to removed

    if(len(corrmat) != len(corrmat.columns)) : return 'Correlation matrix is not square'
    averageCorr = corrmat.abs().mean(axis = 1)

    # set lower triangle and diagonal of correlation matrix to NA
    corrmat = corrmat.where(np.triu(np.ones(corrmat.shape)).astype(np.bool))
    corrmat.values[[np.arange(len(corrmat))]*2] = None 

    # where a pairwise correlation is greater than the cutoff value, check whether mean abs.corr of a or b is greater and cut it
    to_delete = list()
    for col in range(0, len(corrmat.columns)):
        for row in range(0, len(corrmat)):
            if(corrmat.iloc[row, col] > cutoff):
                if(averageCorr.iloc[row] > averageCorr.iloc[col]): to_delete.append(row)
                else: to_delete.append(col)

    to_delete = list(set(to_delete))

    return to_delete

# generate some data
df = pd.DataFrame(np.random.randn(50,25))

# demonstrate usage of function    
removeCols = findCorrelated(df.corr(), cutoff = 0.01) #set v.low cutoff as data is uncorrelated
print('Columns to be removed:')
print(removeCols)
uncorrelated = df.drop(df.index[removeCols], axis =1, inplace = False)
print('Uncorrelated variables:')
print(uncorrelated)