normality-test.sagews

import scipy.stats
f = open('beauty.csv', 'r')
head = f.readline()
data = f.readlines()
f.close()
wage = []
exper = []
educ = []
for row in data :
    p = row.split(';')
    wage.append(float(p[0]))
    exper.append(float(p[1]))
    educ.append(float(p[8]))
wage, exper, educ = vector(wage), vector(exper), vector(educ)
show(wage[:10], exper[:10], educ[:10])

$\displaystyle \left(5.73,\,4.28,\,7.96,\,11.57,\,11.42,\,3.91,\,8.76,\,7.69,\,5.0,\,3.89\right)$ $\displaystyle \left(30.0,\,28.0,\,35.0,\,38.0,\,27.0,\,20.0,\,12.0,\,5.0,\,5.0,\,12.0\right)$ $\displaystyle \left(14.0,\,12.0,\,10.0,\,16.0,\,16.0,\,12.0,\,16.0,\,16.0,\,16.0,\,12.0\right)$

scipy.stats.normaltest(wage)
scipy.stats.normaltest(exper)
scipy.stats.normaltest(educ)

NormaltestResult(statistic=1320.5280096765098, pvalue=1.7823217192197183e-287) NormaltestResult(statistic=140.58947002276543, pvalue=2.9606323326980526e-31) NormaltestResult(statistic=49.33790613234838, pvalue=1.9337922216783728e-11)

list_plot(wage, axes_labels=['', 'wage'])
list_plot(exper, axes_labels=['', 'exper'])
list_plot(educ, axes_labels=['', 'educ'])

new_wage = list(wage)
new_wage.remove(max(wage))
new_wage = map(lambda x: ln(x), new_wage)
scipy.stats.normaltest(new_wage)

NormaltestResult(statistic=1.9852782645576972, pvalue=0.3705973438644804)

new_exper = map(lambda x: ln(x), list(exper))
scipy.stats.normaltest(new_exper)

NormaltestResult(statistic=nan, pvalue=nan)

new_educ = map(lambda x: ln(x), list(educ))
scipy.stats.normaltest(new_educ)

NormaltestResult(statistic=414.67394638497854, pvalue=9.0094161560384521e-91)