def stats(self,SigmaR,B_Col):
#Chi Squared test
print('Our Null Hypothesis states that the variance of our population = sample variance')
#Variance of our radius from measured points
observed = SigmaR
#Expected variance (3mm per x,y,z observation)
expected = .003**2+.003**2+.003**2
#Calculation of degrees of freedom
dof = B_Col-1
#Calculation of test statistics
teststatx = B_Col*((observed - expected)**2/expected)
teststatx1 = dof*(observed/expected)
#User is prompted to input desired significance level
significance = np.float(input('Please specify the significance level: '))
print(teststatx),
print(teststatx1)
#Using built in scipy.stats.chi2 function instead of looking up values on a table
mean, var, skew, kurt = chi2.stats(dof, moments='mvsk')
Chi = chi2.ppf((1-significance),dof)
#If our sampled variance is greater than the population variance at the chosen significance level then we reject the null hypothesis at that significance level
if teststatx > Chi:
print 'We reject the null hypothesis at the ',significance,'significance level'
else:
print 'We fail to reject the null hypothesis at the ',significance,'significance level'
print(teststatx, dof)
def main():
fig, ax = plt.subplots(1, 1)
df = 5
loc = 20
scale = 8
mean, var, skew, kurt = chi2.stats(df, moments='mvsk')
#x = np.linspace(chi2.ppf(0.01, df, loc, scale),chi2.ppf(0.99, df, loc, scale), 20)
valmax = int(chi2.ppf(0.99, df, loc, scale)) + 1
if (valmax % 2 != 0): valmax = valmax + 1
#valmax= 46
x = np.linspace(0, valmax, valmax + 1)
#print (x)
proba = chi2.pdf(x, df, loc, scale)
vs = map(repr, proba.tolist())
repartition = list(zip(x.tolist(), proba.tolist()))
nbTranche = 5
valmin = loc
space = (valmax - valmin) / nbTranche
remain = 100
tranche0 = int(100 *
sum([pro for val, pro in repartition if (val < valmin)]))
remain -= tranche0
print("P(v < %d) = %d" % (valmin, tranche0))
for traidx in range(nbTranche):
deb = valmin + traidx * space
fin = valmin + (traidx + 1) * space
tranche = int(100 * sum(
[pro for val, pro in repartition if (val >= deb) and (val < fin)]))
remain -= tranche
print("P(%d <= v < %d) = %d" % (deb, fin, tranche))
trancheF = 100 * sum([
pro for val, pro in repartition if (val >= valmin + nbTranche * space)
])
print("P(v >= %d) = %d" % (valmin + nbTranche * space, remain))
for certitude in [0.6, 0.7, 0.75, 0.8, 0.85, 0.90, 0.95]:
print("certi = %d , val = %d" %
(certitude, int(chi2.ppf(certitude, df, loc, scale))))
#print (" ".join(list(vs)).replace (".",","))
#print (" ".join(proba.tolist()))
#print (" ".join().replace(".",","))
ax.plot(x, proba, 'r-', lw=5, alpha=0.6, label='chi2 pdf')
#rv = chi2(df, loc, scale)
#ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf')
#vals = chi2.ppf([0.001, 0.5, 0.999], df, loc, scale)
#np.allclose([0.001, 0.5, 0.999], chi2.cdf(vals, df, loc, scale))
#r = chi2.rvs(df, loc = loc, scale = scale , size=1000)
#ax.hist(r, density=True, histtype='stepfilled', alpha=0.2)
#ax.legend(loc='best', frameon=False)
plt.show()
def chi_squared(df):
fig, ax = plt.subplots(1, 1)
# Calculate a few first moments:
mean, var, skew, kurt = chi2.stats(df, moments='mvsk')
# Display the probability density function (pdf):
x = np.linspace(chi2.ppf(0.01, df), chi2.ppf(0.99, df), 100)
ax.plot(x, chi2.pdf(x, df), 'r-', lw=5, alpha=0.6, label='chi2 pdf')
plt.show()
def plot_chi2():
from scipy.stats import chi2
chi2s = np.loadtxt("txt_files/chi2.txt")
good = np.where(chi2s < 200)[0]
chi2s = chi2s[good]
dofs = np.loadtxt("txt_files/dofs.txt")
df = np.mean(dofs)
fchi2s = chi2s.flatten()
mean, var = chi2.stats(df, moments="mv")
x = np.linspace(chi2.ppf(0.01, df), chi2.ppf(0.99, df), 100)
plt.plot(x, chi2.pdf(x, df))
plt.hist(fchi2s, 40, normed=True)
plt.xlabel(r"$\chi_2$", fontsize=24)
plt.subplots_adjust(bottom=0.15)
plt.show()
def kafang():
#卡方分布仅有一个参数还是比较好理解的
fig, ax = plt.subplots(1, 1)
df = 5
mean, var, skew, kurt = chi2.stats(df, moments='mvsk')
x = np.linspace(chi2.ppf(0.01, df), chi2.ppf(0.99, df), 100)
ax.plot(x, chi2.pdf(x, df), 'r-', lw=5, alpha=0.6, label='chi2 pdf')
rv = chi2(df)
# ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf')
# plt.show()
#自由度为15,卡方值小于10的概率
chi2.cdf(10, df=15)
#卡方分布右尾概率为0.05时的反函数
chi2.ppf(0.95, df=10)
def test_chi2(self):
from scipy.stats import chi2
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1)
df = 55
mean, var, skew, kurt = chi2.stats(df, moments='mvsk')
x = np.linspace(chi2.ppf(0.01, df), chi2.ppf(0.99, df), 100)
ax.plot(x, chi2.pdf(x, df), 'r-', lw=5, alpha=0.6, label='chi2 pdf')
rv = chi2(df)
ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf')
vals = chi2.ppf([0.001, 0.5, 0.999], df)
np.allclose([0.001, 0.5, 0.999], chi2.cdf(vals, df))
r = chi2.rvs(df, size=1000)
ax.hist(r, density=True, histtype='stepfilled', alpha=0.2)
ax.legend(loc='best', frameon=False)
self.assertEqual(str(ax), "AxesSubplot(0.125,0.11;0.775x0.77)")
#lM = np.log10(np.mean(10**lM_bins,1))
#visualize.NM_plot(lM,N_data,N_err,lM,N_emu)
if add_uncertainty:
np.savetxt("chi2s_p%dpc.txt" % percent, chi2s)
else:
np.savetxt("chi2s.txt", chi2s)
np.savetxt("Nfp.txt", Nfp)
import matplotlib.pyplot as plt
from scipy.stats import chi2
plt.rc('text', usetex=True, fontsize=20)
if add_uncertainty:
chi2s = np.loadtxt("chi2s_p%dpc.txt" % percent).flatten()
else:
chi2s = np.loadtxt("chi2s.txt").flatten()
Nfp = np.loadtxt("Nfp.txt")
plt.hist(chi2s, 20, normed=True) #Make the histogram
df = np.mean(Nfp)
mean, var, skew, kurt = chi2.stats(df, moments='mvsk')
x = np.linspace(chi2.ppf(0.01, df), chi2.ppf(0.99, df), 100)
plt.plot(x, chi2.pdf(x, df))
plt.xlabel(r"$\chi^2$", fontsize=24)
plt.xlim(0, 80)
plt.ylim(0, 0.1)
plt.subplots_adjust(bottom=0.15)
plt.show()
import matplotlib.pyplot as plt import numpy import pandas as pd import numpy as np from scipy.stats import chi2_contingency, chi2 from scipy.stats import ttest_ind # from bioinfokit.analys import stat, get_data, chisq from itertools import combinations df = pd.read_csv(r'C:\Users\ether\OneDrive\Desktop\info.csv') deg_of_frdm = 15 data = np.random.randint(0, 5, (199, 15)) p_value_matrix = np.zeros((15, 15)) mean, var, skew, kurt = chi2.stats(deg_of_frdm, moments='mvsk') sigma = np.sqrt(var) # x = np.linspace(chi2.ppf(0.01, deg_of_frdm), chi2.ppf(0.99, deg_of_frdm), 199) chi2.cdf(np.array((data[:, 0][:, None], data[:, 1][:, None])), mean, sigma) p_val = chi2.cdf(np.array((data[:, 0], data[:, 1])), mean, sigma) p_val = chi2.cdf(np.array((data[:, 0][:, None], data[:, 1][:, None])).mean(), mean, sigma) i_mean = np.mean(data[:, 0]) j_mean = np.mean(data[:, 1]) i_std = np.std(data[:, 0]) j_std = np.std(data[:, 1]) ttest, pval = ttest_ind(data[:, 0], data[:, 1])
def test_fast_mcd(data):
"""
"""
n = data.shape[0]
p = data.shape[1]
### Naive location and scatter estimates
location = data.mean(0)
covariance = np.cov(data.T)
# invert the covariance matrix
try:
inv_sigma = linalg.inv(robust_covariance)
except:
u, s, vh = linalg.svd(covariance)
inv_s = (1. / s) * \
((np.cumsum(s) < np.sum(s) * .95) | ([True]+[False]*(len(s)-1)))
inv_sigma = np.dot(np.dot(vh.T, np.diag(inv_s)), u.T)
# get distribution of data's Mahalanobis distances
Y = data - location
R = np.sqrt((np.dot(Y, inv_sigma) * Y).sum(1))
# estimate the density with a gaussian kernel
nonnan_subjects_arg = np.where(~np.isnan(R))[0]
R = R[nonnan_subjects_arg]
x1 = np.arange(0., 1.2*np.amax(R), 0.0012*np.amax(R))
n = R.size
sigma = 1.05 * np.std(R) * n**(-0.2)
kernel_arg = (np.tile(x1, (n,1)).T - R) / sigma
fh = ((1/np.sqrt(2*np.pi)) * np.exp(-0.5*kernel_arg**2)).sum(1) / (n*sigma)
# plot the distribution
if PLOT:
plt.figure()
plt.plot(x1, fh, color='blue')
# Khi-2 distribution
diff_scale = np.sqrt(R.var() / float(chi2.stats(p, moments='v')))
diff_loc = R.mean() - float(chi2.stats(p, scale=diff_scale, moments='m'))
template = chi2(p, loc=diff_loc, scale=diff_scale)
if PLOT:
plt.plot(x1, template.pdf(x1), linestyle='--', color='blue')
mse_naive = ((fh - template.pdf(x1))**2).mean()
imse_naive = 0.5 * ((fh - template.pdf(x1))**2).sum() * (x1[1] - x1[0])
if PLOT:
print "MSE (naive case) =", mse_naive
print "IMSE (naive case) =", imse_naive
### Robust location and scatter estimates
robust_location, robust_covariance = fast_mcd(data)
try:
inv_sigma = linalg.inv(robust_covariance)
except:
u, s, vh = linalg.svd(robust_covariance)
inv_s = (1. / s) * \
((np.cumsum(s) < np.sum(s) * .95) | ([True]+[False]*(len(s)-1)))
inv_sigma = np.dot(np.dot(vh.T, np.diag(inv_s)), u.T)
# get distribution of data's Mahalanobis distances
Y = data - robust_location
R = np.sqrt((np.dot(Y, inv_sigma) * Y).sum(1))
# estimate the density with a gaussian kernel
nonnan_subjects_arg = np.where(~np.isnan(R))[0]
R = R[nonnan_subjects_arg]
x2 = np.arange(0., 1.2*np.amax(R), 0.0012*np.amax(R))
n = R.size
sigma = 1.05 * np.std(R) * n**(-0.2)
kernel_arg = (np.tile(x2, (n,1)).T - R) / sigma
fh = ((1/np.sqrt(2*np.pi)) * np.exp(-0.5*kernel_arg**2)).sum(1) / (n*sigma)
# plot the distribution
if PLOT:
plt.plot(x2, fh, color='green')
# Khi-2 distribution
diff_scale = np.sqrt(R.var() / float(chi2.stats(p, moments='v')))
diff_loc = R.mean() - float(chi2.stats(p, scale=diff_scale, moments='m'))
template = chi2(p, loc=diff_loc, scale=diff_scale)
if PLOT:
plt.plot(x2, template.pdf(x2), linestyle='--', color='green')
mse_robust = ((fh - template.pdf(x2))**2).mean()
imse_robust = 0.5 * ((fh - template.pdf(x2))**2).sum() * (x2[1] - x2[0])
if PLOT:
print "MSE (robust case) =", mse_robust
print "IMSE (robust case) =", imse_robust
plt.legend(('empirical distribution (naive)', 'chi-2 (naive)',
'empirical distribution (robust)', 'chi-2 (robust)'),
loc='upper center', bbox_to_anchor=(0.5, 0.))
plt.show()
return mse_naive, mse_robust, imse_naive, imse_robust
imgh = np.reshape(img, nx*ny)
imgh1 = np.reshape(img_mask1, nx1*ny1)
df=36*38
dof=chi2_distance(imgh,imgh1)
chi2_distance(imgh, imght[0,:])
chi2_distance(imgh, imght[1,:])
chi2_distance(imgh, imght[2,:])
chi2_distance(imgh, imght[3,:])
chi2_distance(imgh, imght[4,:])
chi2_distance(imgh, imght[5,:])
chi2_distance(imgh, imght[6,:])
chi_sfh=np.array([502.5312995308081,580.45729191839803,204.19667370317001,518.27719309677684,1534.8645907539676,1555.9265125639893])
weights = np.ones_like(chi_sfh)/float(len(chi_sfh))
fig, ax = plt.subplots(1, 1)
mean, var, skew, kurt = chi2.stats(df, moments='mvsk')
x = np.linspace(chi2.ppf(0.01, df), chi2.ppf(0.99, df), 100)
xu = np.linspace(chi2.ppf(0.01, dof), chi2.ppf(0.99, dof), 100)
ax.axvline(x=dof/df,color='k', linestyle='dashed',lw=4, label='UGC11680NED01 $\chi^2$')
ax.hist(chi_sfh/df,bins=10, normed=False,weights=weights, histtype='step', lw=3,label='Mass $10<\log (M/M_{\odot})<11$ , color $2<g-r<3$')
ax.legend(loc='best', frameon=False)
ax.set_ylabel('Probability density $\chi ^2$')
ax.set_xlabel('$x$')
plt.show()
popt_pdf2, pcov_pdf2 = curve_fit(
modified_sch,
bins_final[index],
pdf_spinpar[index],
sigma=yerr[index],
p0=[(1e-3, 4., 0.6, 1e-3)]) #,maxfev=100000)#,p0=[(1e-3,4.,0.6,1e-3)])
print('popt_pdf2 = ', popt_pdf2)
model_pdf2 = modified_sch(bins_final, *popt_pdf2)
chi2 = np.sum(
(pdf_spinpar[index] - model_pdf2[index])**2 / (yerr[index])**2)
dof = len(pdf_spinpar[index]) - 5
print('chi2 = ', chi2)
print('dof = ', dof)
chi2r = chi2 / dof
print('chi2r = ', chi2r)
chi2_expected = chi2scipy.stats(dof)[0]
print('expexted chi2 = ', chi2_expected)
t[i].add_column(Column(name='pars', data=popt_pdf2, unit=''))
t[i].add_column(Column(name='errors', data=np.diag(pcov_pdf2), unit=''))
outsch = os.path.join(this_dir, 'tables',
'schechter_HMD_lambda_z_%.3g.fit' % (z_snap))
t[i].write(outsch, overwrite=True)
ax.scatter(bins_final,
pdf_spinpar,
label=r'$z=%.3g$' % (z_snap),
ls='None',
marker='o',
s=15)
# ax.fill_between(bins_final[index],pdf_spinpar[index] - yerr[index],pdf_spinpar[index] + yerr[index], alpha=0.4 )
import numpy as np
from scipy.stats import chi2, norm
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
# k degrees of freedom
k = 5
th_mean, th_var, _, _ = chi2.stats(k, moments='mvsk')
print("THEORY MEAN=", th_mean, "THEORY VARIANCE=", th_var)
# prob dens function
# what X is in 0.01 and 0.99 quantiles
start = chi2.ppf(0.01, k)
stop = chi2.ppf(0.99, k)
# theoretical dist
x = np.linspace(start, stop, 100)
plt.plot(x, chi2.pdf(x, k), 'r-', lw=5, alpha=0.6, label='chi2 pdf')
# histogram
# random nums from dist
r = chi2.rvs(k, size=1000)
plt.hist(r, normed=True, histtype='stepfilled', alpha=0.2)
plt.legend(loc='best', frameon=False)
plt.title('Theoretical Dist')
plt.ylabel('Prob Dens')
plt.xlabel('X')
plt.show()
# calculate means for 1000 expirements with n samples in each
def sample_mean(n):
smeans = []
for x in range(1000):
def testChisquare(N, size):
values = [lhw.rnchsq(N) for i in range(size)]
mean, var = chi2.stats(N, moments='mv')
startWork(values, mean, var, "chiSquare")
pass
sortedR = R[~np.isnan(R)].copy()
sortedR.sort()
qi, qe, qa = np.outer(len(sortedR), [0.25, 0.5, 0.75])[0]
bnd = (sortedR[qa] - sortedR[qi])*3 + sortedR[qe]
### Estimate the density with a gaussian kernel
nonnan_subjects_arg = np.where(~np.isnan(R))[0]
R = R[nonnan_subjects_arg]
x = np.arange(0., 1.2*np.amax(R), 0.0012*np.amax(R))
n = R.size
sigma = 1.05 * np.std(R) * n**(-0.2)
kernel_arg = (np.tile(x, (n,1)).T - R) / sigma
fh = ((1/np.sqrt(2*np.pi)) * np.exp(-0.5*kernel_arg**2)).sum(1) / (n*sigma)
# print it
plt.figure()
plt.plot(x, fh)
plt.vlines(sortedR[qe], 0, np.amax(fh))
plt.vlines(bnd, 0, np.amax(fh))
# Khi-2 distribution
p = labels.size
diff_scale = np.sqrt(R.var() / float(chi2.stats(p, moments='v')))
diff_loc = R.mean() - float(chi2.stats(p, scale=diff_scale, moments='m'))
template = chi2(p, loc=diff_loc, scale=diff_scale)
plt.plot(x, template.pdf(x), linestyle='--', color='green')
plt.show()
for i in np.where(R > bnd)[0]:
print actual_files[nonnan_subjects_arg[i]][26:38]
out_table = os.path.join(this_dir,'results','zevo','hsigma_params_Rvir.fit')
os.makedirs(os.path.dirname(out_table), exist_ok=True)
t.write(out_table, overwrite=True)
#fit_ = fit[np.where(counts_tot>c3)]
fit_ = h_func([s_grid_all, xoff_grid_all,spin_grid_all,redshift_all], *popt)
print('min log10(hsigma_) =', min(np.log10(hsigma_all)))
print('min fit_ = ',min(fit_))
print('max log10(hsigma_) =', max(np.log10(hsigma_all)))
print('max fit_ = ',max(fit_))
chi_2 = np.sum((np.log10(hsigma_all)-fit_)**2/herr_all**2)
dof = len(hsigma_all) - len(names)
chi_2r = chi_2/dof
rv = chi2.stats(dof)
print('chi2 = ', chi_2)
print('dof = ', dof)
print('chi2r = ',chi_2r)
print('expected chi2 = ', rv)
#PDF OF THE RESIDUALS
res = ((np.log10(hsigma_all)-fit_)/herr_all)
pdf, b = np.histogram(res,bins=100,density=True)
bins = (b[:-1]+b[1:])/2
def ga(x, x0, sigma):
a=1/sigma/np.sqrt(2*np.pi)
return a*np.exp(-(x-x0)**2/(2*sigma**2))
par,cov = curve_fit(ga,bins,pdf)
gauss = ga(bins,*par)
