Python pylab.median函数代码示例

def add_to_results(model, name):
    df = getattr(model, name)
    model.results['param'].append(name)
    model.results['bias'].append(df['abs_err'].mean())
    model.results['mae'].append((pl.median(pl.absolute(df['abs_err'].dropna()))))
    model.results['mare'].append(pl.median(pl.absolute(df['rel_err'].dropna())))
    model.results['pc'].append(df['covered?'].mean())

def trace_fibers(flatim, params):

    trace_im1 = pf.getdata(flatim)*0

    imdat, imhead = pf.getdata(flatim), pf.getheader(flatim)

    ###  separating fibers in first column and assigning fibers ids
    print '\n\tSEARCHING FOR FIBERS BETWEEN x=0 & y=[' +str(params.LO_BUFFER) +':'+str(len(imdat[:,0])-params.HI_BUFFER)+']'
    fiber_peaks_pix = pl.find( imdat[:,0] > pl.median(imdat[:,0]) )
    fiber_peaks_pix,fiber_peaks_flx = sep_peaks( fiber_peaks_pix, imdat[:,0] )
    if pl.median(fiber_peaks_pix[0])<=params.LO_BUFFER:
        fiber_peaks_pix = fiber_peaks_pix[1:]
        fiber_peaks_flx = fiber_peaks_flx[1:]
    if (len(imdat[:,0])-pl.median(fiber_peaks_pix[-1]))<=params.HI_BUFFER:
        fiber_peaks_pix = fiber_peaks_pix[:-1]
        fiber_peaks_flx = fiber_peaks_flx[:-1]
    print '\t  --> FOUND ', len(fiber_peaks_pix), ' FIBER PEAKS'

    ###  creating array for fibers
    fibers0 = []
    id_cnt = 1
    for f in range(len(fiber_peaks_pix)):
        while params.FIBERS_EXCLUDE.tolist().count(id_cnt)==1: id_cnt+=1

        fibx,fiby = fiber_peaks_pix[f],fiber_peaks_flx[f]
        peakx = fibx[ fiby.tolist().index(max(fiby)) ]
        yrange = pl.arange(  peakx-params.FIBER_WIDTH/2  ,  peakx+params.FIBER_WIDTH/2+1  )

        fibers0.append( fiber(id_cnt, 0,     yrange     ))
        id_cnt+=1

##  TRACING FIBERS ALONG X-AXIS INDIVIDUALLY
    for fib in fibers0:
        for x in range(1,len(imdat)):
##  FIRST, TAKE THE FLUXES IN THE PIXELS AT x
##  THAT ENCOMPASSED THE PEAK AT x-1
            fluxes = imdat[ fib.xy[-1][1] , x ]
##  NEXT, FIND THE VERTICAL SHIFT TO CENTER ON
##  THE PEAK FLUX AT x. MAXIMUM SHIFT IS DETERMINED
##  FROM THE FIBER_WIDTH PARAMETER.
            deltay = range( -len(fluxes)/2+1 , len(fluxes)/2+1 )[ fluxes.tolist().index(max(fluxes)) ]

##  RECORD THE NEW Y-PIXELS THAT ARE CENTERD ON
##  THE FIBER AT x.
            fib.xy.append( [ x, fib.xy[-1][1]+deltay ] )

##  FLAG PIXELS FOR FIBER IN FIRST-PASS TRACE IMAGE
            trace_im1[fib.xy[-1][1],x] = fib.id



    trc0 = 'trace_pass1.fits'
    print '\n\tWRITING INITIAL TRACING TO ', trc0
    try: pf.writeto(trc0, trace_im1, header=imhead)
    except:
        os.remove(trc0)
        pf.writeto(trc0, trace_im1, header=imhead)
        
    return fibers0

def combine_output(J, T, model, dir, reps, save=False):
    """
    Combine output on absolute error, relative error, csmf_accuracy, and coverage from from
    multiple runs of validate_once. Either saves the output to the disk, or returns arays
    for each. 
    """

    cause = pl.zeros(J*T, dtype='f').view(pl.recarray)
    time = pl.zeros(J*T, dtype='f').view(pl.recarray)
    abs_err = pl.zeros(J*T, dtype='f').view(pl.recarray) 
    rel_err = pl.zeros(J*T, dtype='f').view(pl.recarray)
    coverage = pl.zeros(J*T, dtype='f').view(pl.recarray)
    csmf_accuracy = pl.zeros(J*T, dtype='f').view(pl.recarray)

    for i in range(reps): 
        metrics = pl.csv2rec('%s/metrics_%s_%i.csv' % (dir, model, i))
        cause = pl.vstack((cause, metrics.cause))
        time = pl.vstack((time, metrics.time))
        abs_err = pl.vstack((abs_err, metrics.abs_err))
        rel_err = pl.vstack((rel_err, metrics.rel_err))
        coverage = pl.vstack((coverage, metrics.coverage))
        csmf_accuracy = pl.vstack((csmf_accuracy, metrics.csmf_accuracy))

    cause = cause[1:,]
    time = time[1:,]    
    abs_err = abs_err[1:,]
    rel_err = rel_err[1:,]
    coverage = coverage[1:,]
    csmf_accuracy = csmf_accuracy[1:,]

    mean_abs_err = abs_err.mean(0)
    median_abs_err =  pl.median(abs_err, 0)
    mean_rel_err = rel_err.mean(0)
    median_rel_err = pl.median(rel_err, 0)
    mean_csmf_accuracy = csmf_accuracy.mean(0)
    median_csmf_accuracy = pl.median(csmf_accuracy, 0)
    mean_coverage_bycause = coverage.mean(0)
    mean_coverage = coverage.reshape(reps, T, J).mean(0).mean(1)
    percent_total_coverage = (coverage.reshape(reps, T, J).sum(2)==3).mean(0)
    mean_coverage = pl.array([[i for j in range(J)] for i in mean_coverage]).ravel()
    percent_total_coverage = pl.array([[i for j in range(J)] for i in percent_total_coverage]).ravel()

    models = pl.array([[model for j in range(J)] for i in range(T)]).ravel()
    true_cf = metrics.true_cf
    true_std = metrics.true_std
    std_bias = metrics.std_bias

    all = pl.np.core.records.fromarrays([models, cause[0], time[0], true_cf, true_std, std_bias, mean_abs_err, median_abs_err, mean_rel_err, median_rel_err, 
                                         mean_csmf_accuracy, median_csmf_accuracy, mean_coverage_bycause, mean_coverage, percent_total_coverage], 
                                        names=['model', 'cause', 'time', 'true_cf', 'true_std', 'std_bias', 'mean_abs_err', 'median_abs_err', 
                                         'mean_rel_err', 'median_rel_err', 'mean_csmf_accuracy', 'median_csmf_accuracy', 
                                         'mean_covearge_bycause', 'mean_coverage', 'percent_total_coverage'])   
    
    if save: 
        pl.rec2csv(all, '%s/%s_summary.csv' % (dir, model)) 
    else: 
        return all

def loadFile(objectFileName):
    oimg = pyfits.open(objectFileName)

    # Load the IFU data -- Row-stacked spectra
    odata = oimg[1].data
    oError = oimg[2].data
    odata_dim = odata.shape
    wcs = astWCS.WCS(objectFileName, extensionName=1)
    owavelengthStartEnd = wcs.getImageMinMaxWCSCoords()[0:2]
    fiberNumber = wcs.getImageMinMaxWCSCoords()[2:4]
    owavelengthStep = oimg[1].header['CDELT1']

    owavelengthRange = [owavelengthStartEnd[0] + i * owavelengthStep
                        for i in range(odata_dim[1])]

    # Check to make sure we got it right
    if not owavelengthRange[-1] == owavelengthStartEnd[-1]:
        print 'The ending wavelenghts do not match... Exiting'
        sys.exit(1)
    else:
        # make median sky
        specs = pyl.array([flux for flux in odata])
        skySpec = pyl.median(specs, axis=0)

    RSS = []
    for i in range(int(fiberNumber[1])):
        #oflux = odata[i] - oskyflux
        oflux = odata[i] - skySpec
        oflux[pyl.isnan(oflux)] = 0.0
        oErrorFlux = oError[i]
        #oflux = odata[i]

        # Mask out extreme values in spectrum
        # Just because edges dodgy in efosc
        med = pyl.median(oflux)
        oflux[pyl.greater(abs(oflux), 10.0 * med)] = 0.0001

        objSED = astSED.SED(wavelength=owavelengthRange, flux=oflux)
        #skySED = astSED.SED(wavelength=owavelengthRange, flux=oskyflux)
        skySED = astSED.SED(wavelength=owavelengthRange, flux=skySpec)
        errSED = astSED.SED(wavelength=owavelengthRange, flux=oErrorFlux)

        #  make it > 0 everywhere
        objSED.flux = objSED.flux - objSED.flux.min()
        objSED.flux = objSED.flux / objSED.flux.max()
        errSED.flux = errSED.flux - errSED.flux.min()
        errSED.flux = errSED.flux / errSED.flux.max()
        skySED.flux = skySED.flux - skySED.flux.min()
        skySED.flux = skySED.flux / skySED.flux.max()

        RSS.append({'object': objSED, 'sky': skySED, 'error': errSED})

    return RSS

  def one_ci(v, ci, bootstraps):
    v = pylab.array(v)
    v = pylab.ma.masked_array(v,pylab.isnan(v)).compressed()
    if v.size == 0:
      return pylab.nan, 0, 0 #Nothing to compute

    r = pylab.randint(v.size, size=(v.size, bootstraps))
    booted_samp = pylab.array([pylab.median(v[r[:,n]]) for n in xrange(bootstraps)])
    booted_samp.sort()

    med = pylab.median(booted_samp)
    idx_lo = int(bootstraps * ci/2.0)
    idx_hi = int(bootstraps * (1.0-ci/2))

    return med, med-booted_samp[idx_lo], booted_samp[idx_hi]-med

def remove_discontinuity(value, xgap=10, ygap=200):
    """
    Remove discontinuity (sudden jump) in a series of values.
    Written by Denis, developed for LLC Fringe Counts data.
    value : list or numpy.array
    xgap  : "width" of index of the list/array to adjust steps
    ygap  : threshold value to detect discontinuity
    """
    difflist = pl.diff(value)
    discont_index = pl.find(abs(difflist) > ygap)

    if len(discont_index) == 0:
        return value
    else:
        discont_index = pl.append(discont_index, len(difflist))

    # find indice at discontinuities
    discont = {"start": [], "end": []}
    qstart = discont_index[0]
    for i in range(len(discont_index) - 1):
        if discont_index[i + 1] - discont_index[i] > xgap:
            qend = discont_index[i]
            discont["start"].append(qstart - xgap)
            discont["end"].append(qend + xgap)
            qstart = discont_index[i + 1]

    # add offsets at discontinuities
    result = pl.array(value)
    for i in range(len(discont["end"])):
        result[0 : discont["start"][i]] += result[discont["end"][i]] - result[discont["start"][i]]

    # remove the median
    result = result - pl.median(result)
    return result

 def makePlots(self, ax, x, fNum, fColor, fMarker, feedstock):
     
     x.getQuery()
     
     if x.queryString.startswith('No'):
         pass    
     
     elif x.queryString.startswith('FR'):
         data = [1,1]
         ax.plot([fNum]*2,[1,1],fColor,marker=fMarker,markersize=2)
         
     else:
         cur = self.conn.cursor()
         print x.queryString
         cur.execute(x.queryString)
         #[all data]
         data = cur.fetchall()
         cur.close()
         medVal = median(data)
         maxVal = max(data)
         minVal = min(data)
         
         ax.plot([fNum],medVal,fColor,marker='_', markersize=7)
 
         #Plot the max/min values
         ax.plot([fNum]*2,[maxVal, minVal],fColor,marker=fMarker, markersize=2)    
         
         self.writeResults(feedstock, str(maxVal[0]), str(medVal), str(minVal[0]))

def flow_rate_hist(sheets):
    ant_rates = []
    weights = []
    for sheet in sheets:
        ants, seconds, weight = flow_rate(sheet)
        ant_rate = seconds / ants
        #ant_rate = ants / seconds
        ant_rates.append(ant_rate)
        weights.append(float(weight))
        #weights.append(seconds)

    weights = pylab.array(weights)
    weights /= sum(weights)

    #print "ants per second"
    print "seconds per ant"
    mu = pylab.mean(ant_rates)
    print "mean", pylab.mean(ant_rates)
    wmean = pylab.average(ant_rates, weights=weights)
    print "weighted mean", wmean
    print "median", pylab.median(ant_rates)
    print "std", pylab.std(ant_rates, ddof=1)
    ant_rates = pylab.array(ant_rates)
    werror = (ant_rates - mu) * weights
    print "weighted std", ((sum(werror ** 2))) ** 0.5
    print "weighted std 2", (pylab.average((ant_rates - mu)**2, weights=weights)) ** 0.5
    pylab.figure()
    pylab.hist(ant_rates)
    pylab.savefig('ant_flow_rates.pdf', format='pdf')
    pylab.close()

def scatter_times(name, sheets):
    means = []
    medians = []
    delays = []
    mean_points = []
    med_points = []
    for sheet, delay in sheets:
        delays.append(delay)
        times = get_times(sheet)
        mean = pylab.mean(times)
        median = pylab.median(times)
        means.append(mean)
        medians.append(median)
        mean_points.append((mean, sheet))
        med_points.append((median, sheet)) 
    
    print "----------mean points-----------"    
    for mean, sheet in sorted(mean_points):
        print mean, sheet
    print "----------median points-----------"
    for median, sheet in sorted(med_points):
        print median, sheet
          
    pylab.scatter(delays, means, color='r')
    pylab.scatter(delays, medians, color='b')
    print "show"
    pylab.show()

def pitch_estimate(dw):
    step = 8
    wsize = 2048
    wfun = pl.ones
    wa = 3
    lo, hi = 50, 700
    hist_params = dict(bins=800, lw=0, range=[lo,hi], rwidth=1.0,
        normed=True, log=True)

    subplots = wplot.Subplots(6, 1,
        yticks=[0,.1,.25,.5,1],
        xlim=(120,240),
        autoscalex_on=False)

    for wfun in [pl.hanning, pl.hamming, pl.blackman, pl.bartlett, pl.ones]:
        cc = chunker.Chunker(dw, window=wfun(wsize), step=step)
        acs = [cc.ac for c in cc.chunks()]
        pp = [chunker.find_peak(a, lo, hi, wa=wa) for a in acs]
        mm = pl.median(pp)
        subplots(
            title='window: %s(%d) step=%s range=%s wa=%d' % (wfun.func_name, wsize, step, [lo,hi], wa),
            xticks=[mm]+range(lo,hi+50,50))
        subplots.next()
        freq, bins, patches = pl.hist(pp, **hist_params)

    print 'Ok!'

def mare(model, data_type):
    try:
        pred = model.vars[data_type]['p_pred'].trace().mean(0)
    except:
        pred = 0    
    obs = model.get_data(data_type)['value']
    mare = pl.median((abs(pred - obs)/obs)*100)
    return mare

def plot_histogram(histogram, html_writer, title='', max_pathway_length=8, xmin=None, xlim=20, error_bars=True, min_to_show=20, legend_loc='upper left'):
    fig = pylab.figure()

    pylab.hold(True)

    reps = 1000
    
    y_offset = 0
    offset_step = 0.007
    colors = {1:'r', 2:'orange', 3:'green', 4:'cyan', 5:'blue', 'Rest':'violet', 'Not first':'k--', 'No known regulation':'grey', 'Activated':'green', 'Inhibited':'r', 'Mixed regulation':'blue'}
    for key, value in histogram.iteritems():
        if len(value) >= min_to_show:
            m = stats.cmedian(value)
            
            sample_std = None
            
            if error_bars:
                sample_vals = []
                i = 0
                while i < reps:
                    samples = []
                    while len(samples) < len(value):
                        samples.append(random.choice(value))
                    sample_vals.append(pylab.median(samples))
                    i += 1
                
                sample_std = pylab.std(sample_vals)
                        
            plotting.cdf(value, label='%s (med=%.1f, N=%d)' % \
                (key, m, len(value)),
                style=colors.get(key, 'grey'), std=sample_std, y_offset=y_offset)
            y_offset += offset_step
            

    xmin = -1 * xlim if xmin == None else xmin
    pylab.xlim(xmin, xlim)
    pylab.xlabel('Irreversability')
    #pylab.xlabel('deltaG')
    pylab.ylabel('Cumulative distribution')
    legendfont = matplotlib.font_manager.FontProperties(size=11)
    pylab.legend(loc=legend_loc, prop=legendfont)
    pylab.title(title)
    pylab.hold(False)
    
    if 'Not first' in histogram:
        print '%s, first vs. non-first ranksum test: ' % title + '(%f, %f)' % stats.ranksums(histogram[1], histogram['Not first'])
    
    if 'Inhibited' in histogram:
        print '%s, inhibited vs. non-regulated ranksum test: ' % title + '(%f, %f)' % stats.ranksums(histogram['Inhibited'], histogram['No known regulation'])
         
    
    #for k1, h1 in histogram.iteritems():
    #    for k2, h2 in histogram.iteritems():
    #        print k1, k2, stats.ranksums(h1, h2)
    
    return fig

def get_stats(typeid,date):
    global db
    cur = db.cursor()
    cur.execute("SELECT AVG(price),SUM(volremain),SUM(volenter) - SUM(volremain),bid FROM archive_market WHERE typeid = %s AND (reportedtime) :: date = %s GROUP BY orderid,bid", [typeid, date])
    a = cur.fetchall()
    avg_b = array(zeros(len(a)),dtype=float)
    vol_b = array(zeros(len(a)),dtype=float)
    move_b = array(zeros(len(a)),dtype=float)
    avg_s = array(zeros(len(a)),dtype=float)
    vol_s = array(zeros(len(a)),dtype=float)
    move_s = array(zeros(len(a)),dtype=float)

    x_s = 0
    x_b = 0
    for r in a:
	if r[3]:
	    avg_b[x_b] = r[0]

	    vol_b[x_b] = r[1]
	    move_b[x_b] = r[2]
	    x_b += 1
	else:
	    avg_s[x_s] = r[0]
	    vol_s[x_s] = r[1]
	    move_s[x_s] = r[2]
	    x_s += 1
    avg_b.resize(x_b)
    avg_s.resize(x_s)
    vol_b.resize(x_b)
    vol_s.resize(x_s)
    move_b.resize(x_b)
    move_s.resize(x_s)
    b = (None,None,None)
    s = (None,None,None)
    try:
	b = (pylab.median(avg_b), pylab.mean(vol_b), pylab.mean(move_b))
	s = (pylab.median(avg_s), pylab.mean(vol_s), pylab.mean(move_s))
    except:
	return (b,b,b)

    ret = ( ((b[0]+s[0])/2, (b[1]+s[1])/2, (b[2]+s[2])/2), b, s)
    print ret
    return ret

def simulateGame(numGames, tilePairs, gameType):
    runTimeList = []
    for i in range(numGames):
        gameTime = gameType(tilePairs)
        runTimeList.append(gameTime)
    medTime = pylab.median(runTimeList)
    meanTime = pylab.mean(runTimeList)
    pylab.hist(runTimeList,[x*2 for x in range(400)])
    print 'meanTime: ' + str(meanTime)
    print 'medianTime: ' + str(medTime)
    return meanTime, medTime

def DFA(data, npoints=None, degree=1, use_median=False):
    """
    computes the detrended fluctuation analysis
    returns the fluctuation F and the corresponding window length L

    :args:
        data (n-by-1 array): the data from which to compute the DFA
        npoints (int): the number of points to evaluate; if omitted the log(n)
            will be used
        degree (int): degree of the polynomial to use for detrending
        use_median (bool): use median instead of mean fluctuation

    :returns:
        F, L: the fluctuation F as function of the window length L

    """
    # max window length: n/4

    #0th: compute integral
    integral = cumsum(data - mean(data))

    #1st: compute different window lengths
    n_samples = npoints if npoints is not None else int(log(len(data)))
    lengths = sort(array(list(set(
            logspace(2,log(len(data)/4.),n_samples,base=exp(1)).astype(int)
             ))))

    #print lengths
    all_flucs = []
    used_lengths = []
    for wlen in lengths:
        # compute the fluctuation of residuals from a linear fit
        # according to Kantz&Schreiber, ddof must be the degree of polynomial,
        # i.e. 1 (or 2, if mean also counts? -> see in book)
        curr_fluc = []
#        rrt = 0
        for startIdx in arange(0,len(integral),wlen):
            pt = integral[startIdx:startIdx+wlen]
            if len(pt) > 3*(degree+1):
                resids = pt - polyval(polyfit(arange(len(pt)),pt,degree),
                                  arange(len(pt)))
#                if abs(wlen - lengths[0]) < -1:
#                    print resids[:20]
#                elif rrt == 0:
#                    print "wlen", wlen, "l0", lengths[0]
#                    rrt += 1
                curr_fluc.append(std(resids, ddof=degree+1))
        if len(curr_fluc) > 0:
            if use_median:
                all_flucs.append(median(curr_fluc))
            else:
                all_flucs.append(mean(curr_fluc))
            used_lengths.append(wlen)
    return array(all_flucs), array(used_lengths)