<p>分享一些我参与的代码。这允许您在excel电子表格的每一列上运行统计信息。</p>
<pre><code>import xlrd
import sys
import csv
import numpy as np
import itertools
from itertools import chain
book = xlrd.open_workbook('/filepath/workbook.xlsx')
sh = book.sheet_by_name("Sheet1")
ofile = '/outputfilepath/workbook.csv'
masses = sh.col_values(0, start_rowx=1) # first column has mass
age = sh.row_values(0, start_colx=1) # first row has age ranges
count = 1
mass = []
for a in ages:
age.append(sh.col_values(count, start_rowx=1))
count += 1
stats = []
count = 0
for a in ages:
expanded = []
# create a tuple with the mass vector
age_mass = zip(masses, age[count])
count += 1
# replicate element[0] for element[1] times
expanded = list(list(itertools.repeat(am[0], int(am[1]))) for am in age_mass)
# separate into one big list
medianlist = [x for t in expanded for x in t]
# convert to array and mask out zeroes
npa = np.array(medianlist)
npa = np.ma.masked_equal(npa,0)
median = np.median(npa)
meanMass = np.average(npa)
maxMass = np.max(npa)
minMass = np.min(npa)
stdev = np.std(npa)
stats1 = [median, meanMass, maxMass, minMass, stdev]
print stats1
stats.append(stats1)
np.savetxt(ofile, (stats), fmt="%d")
</code></pre>