Python Examples of scipy.histogram

Source File: idlplot.py From astrolibpy with GNU General Public License v3.0

6 votes

def __findKnuth(x, minv, maxv):
    """
	Implement Knuth method for histogram bin selection
		
	"""
    N = ((x >= minv) & (x <= maxv)).sum()

    def funcer(M):
        hh, loc = scipy.histogram(x, bins=M, range=[minv, maxv])
        return np.log(M) + 1. / N * (scipy.special.gammaln(M / 2.) -
                                     M * scipy.special.gammaln(0.5) -
                                     scipy.special.gammaln(N + M / 2.) +
                                     scipy.special.gammaln(hh + 0.5).sum())

    maxN = 1000
    ns = np.arange(1, maxN + 1)
    vals = ns * 0.
    for i in range(len(ns)):
        vals[i] = funcer(ns[i])
    bestn = ns[np.argmax(vals)]
    if bestn == maxN:
        print('WARNING the best number of bins is > maxbin(%d)' % (maxn))
    return bestn

Source File: leveler.py From Maybe-Useful-Cogs with MIT License

5 votes

def _auto_color(self, url:str, ranks):
        phrases = ["Calculating colors..."] # in case I want more
        #try:
        await self.bot.say("**{}**".format(random.choice(phrases)))
        clusters = 10

        async with aiohttp.get(url) as r:
            image = await r.content.read()
        with open('data/leveler/temp_auto.png','wb') as f:
            f.write(image)

        im = Image.open('data/leveler/temp_auto.png').convert('RGBA')
        im = im.resize((290, 290)) # resized to reduce time
        ar = scipy.misc.fromimage(im)
        shape = ar.shape
        ar = ar.reshape(scipy.product(shape[:2]), shape[2])

        codes, dist = scipy.cluster.vq.kmeans(ar.astype(float), clusters)
        vecs, dist = scipy.cluster.vq.vq(ar, codes)         # assign codes
        counts, bins = scipy.histogram(vecs, len(codes))    # count occurrences

        # sort counts
        freq_index = []
        index = 0
        for count in counts:
            freq_index.append((index, count))
            index += 1
        sorted_list = sorted(freq_index, key=operator.itemgetter(1), reverse=True)

        colors = []
        for rank in ranks:
            color_index = min(rank, len(codes))
            peak = codes[sorted_list[color_index][0]] # gets the original index
            peak = peak.astype(int)

            colors.append(''.join(format(c, '02x') for c in peak))
        return colors # returns array
        #except:
            #await self.bot.say("```Error or no scipy. Install scipy doing 'pip3 install numpy' and 'pip3 install scipy' or read here: https://github.com/AznStevy/Maybe-Useful-Cogs/blob/master/README.md```")

    # converts hex to rgb

Source File: window_func.py From astrolibpy with GNU General Public License v3.0

5 votes

def window_func(x, y, func, xmin=None, xmax=None, nbin=100, empty=False,
			xlog=False):
	"""This function does compute a user-supplied function 
	on the subsets of y grouped by values of x
	E.g. imagine that you have x from 0 to 100 and you want
	to know the mean values of y for 0<x<10, 10<x<2- etc..
	In that case you need to do
	xbin,funcy,nperbin=window_func(x,y,lambda x: x.mean(),0,100,nbin=10)
	where xbin is the array with the centers of bins, 
	funcy is the func -- evaluated for y where x is within the appropriate bin
	and nperbin is the number of points in the appropriate bin
	empty keyword is needed if you want to retrieve the function evaluation 
	in empty bins too, otherwise they aren't returned at all
	"""
	
	if xmin is None:
		xmin = x.min()
	if xmax is None:
		xmax = x.max()
	if xlog:
		xmin,xmax,x=[numpy.log10(tmp) for tmp in [xmin,xmax,x]]
	if (len(x)!=len(y) and x.ndim==1) or (x.shape!=y.shape and x.ndim>1):
		raise ValueError('Input arrays must have the same size')
	#hh,loc=scipy.histogram(x,range=(xmin,xmax),bins=nbin)
	inds = ((x-xmin)/float(xmax-xmin)*nbin).astype(int)
	mask = numpy.zeros(nbin, bool)
	retv = numpy.zeros(nbin)
	hh = numpy.zeros(nbin,int)

	for i in range(nbin):
		cury=y[inds==i]
		hh[i]=len(cury)
		mask[i]=len(cury)>0
		if len(cury)>0 or empty:
			retv[i]=func(cury)
	retx = xmin+(xmax-xmin)*1./nbin*(0.5+numpy.arange(nbin))
	if xlog:
		retx = 10**retx
	if empty:
		mask |= True
	return retx[mask], retv[mask],hh[mask]

Source File: chemistry.py From guacamol with MIT License

5 votes

def discrete_kldiv(X_baseline: np.array, X_sampled: np.array) -> float:
    P, bins = histogram(X_baseline, bins=10, density=True)
    P += 1e-10
    Q, _ = histogram(X_sampled, bins=bins, density=True)
    Q += 1e-10

    return entropy(P, Q)