def test(zpoints, data, cdf, rvs, ddof = 1):
obs_freq = fp.calculate_data_freq(zpoints, data)
exp_prob = fp.calculate_exp_prob(zpoints, cdf)
exp_freq = fp.convert_prob_2_freq(exp_prob, len(data))
print "Observations freq", obs_freq
print "Expected freq", exp_freq
print "Run Pearson test"
chisq, p = stats.chisquare(obs_freq, exp_freq, ddof)
print "p", p
print "chisq", chisq
chi2val = stats.chi2.ppf(0.95, len(obs_freq) - 1 - ddof)
print "chi2 border value", chi2val
print "H0 is accepted" if chisq < chi2val else "H0 is rejected "
obs_data = data
obs_data.sort()
rand_data = rvs(len(obs_data))
rand_data = [x if x > 1 else 1 for x in rand_data]
rand_data.sort()
x_values = xrange(len(obs_data))
plt.ylabel("age")
plt.plot(obs_data, 'b-')
plt.plot(rand_data, 'ro')
plt.show()
print "Autumn" low_filter = 180 zpoints = [216, 238, 261] workdays, holidays = fp.load_data() print "Workdays loaded:", len(workdays) print "Holidays loaded:", len(holidays) print s1, s2, s3, s4 = fp.get_season_data(workdays) #fp.plot_seasons_data(s1, s2, s3, s4) alldata = s4 data = [x for x in alldata if x > low_filter] obs_freq = fp.calculate_data_freq(zpoints, data) print "Observations freq", obs_freq nobs, (min, max), mean, variance, s, k = stats.describe(data) std = math.sqrt(variance) print "Nobs", nobs print "Mean", mean print "Variance", variance print exp_prob = fp.calculate_exp_prob(zpoints, lambda x: stats.norm.cdf(x, mean, std)) print "Expected prob", exp_prob exp_freq = fp.convert_prob_2_freq(exp_prob, nobs) print "Expected freq", exp_freq print
