Python scipy 模块，histogram() 实例源码

def find_a_dominant_color(image):
    # K-mean clustering to find the k most dominant color, from:
    # http://stackoverflow.com/questions/3241929/python-find-dominant-most-common-color-in-an-image
    n_clusters = 5

    # Get image into a workable form
    im = image.copy()
    im = im.resize((150, 150))      # optional, to reduce time
    ar = scipy.misc.fromimage(im)
    im_shape = ar.shape
    ar = ar.reshape(scipy.product(im_shape[:2]), im_shape[2])
    ar = np.float_(ar)

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

    # Get the indexes of the most frequent, 2nd most frequent, 3rd, ...
    sorted_idxs = np.argsort(counts)

    # Get the color
    peak = codes[sorted_idxs[1]] # get second most frequent color

    return [int(i) for i in peak.tolist()] # list comprehension to quickly cast everything to int

def kde(data, N=None, MIN=None, MAX=None):

    # Parameters to set up the mesh on which to calculate
    N = 2**14 if N is None else int(2**sci.ceil(sci.log2(N)))
    if MIN is None or MAX is None:
        minimum = min(data)
        maximum = max(data)
        Range = maximum - minimum
        MIN = minimum - Range/10 if MIN is None else MIN
        MAX = maximum + Range/10 if MAX is None else MAX

    # Range of the data
    R = MAX-MIN

    # Histogram the data to get a crude first approximation of the density
    M = len(data)
    DataHist, bins = sci.histogram(data, bins=N, range=(MIN,MAX))
    DataHist = DataHist/M
    DCTData = scipy.fftpack.dct(DataHist, norm=None)

    I = [iN*iN for iN in xrange(1, N)]
    SqDCTData = (DCTData[1:]/2)**2

    # The fixed point calculation finds the bandwidth = t_star
    guess = 0.1
    try:
        t_star = scipy.optimize.brentq(fixed_point, 0, guess, 
                                       args=(M, I, SqDCTData))
    except ValueError:
        print 'Oops!'
        return None

    # Smooth the DCTransformed data using t_star
    SmDCTData = DCTData*sci.exp(-sci.arange(N)**2*sci.pi**2*t_star/2)
    # Inverse DCT to get density
    density = scipy.fftpack.idct(SmDCTData, norm=None)*N/R
    mesh = [(bins[i]+bins[i+1])/2 for i in xrange(N)]
    bandwidth = sci.sqrt(t_star)*R

    density = density/sci.trapz(density, mesh)
    return bandwidth, mesh, density

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 self.session.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

def pdf(self):
        if self._pdf is None:
            from scipy import histogram
            self._pdf = histogram(self.speed, range(0, 50, self.bin_width), density=True)
        return self._pdf

def pdf(self):
        if self._pdf is None:
            from scipy import histogram
            self._pdf = histogram(self.speed, range(0, 50, self.bin_width), density=True)
        return self._pdf

def find_dominant_colors(image):
    """Cluster the colors of the image in CLUSTER_NUMBER of clusters. Returns
    an array of dominant colors reverse sorted by cluster size.
    """

    array = img_as_float(fromimage(image))

    # Reshape from MxNx4 to Mx4 array
    array = array.reshape(scipy.product(array.shape[:2]), array.shape[2])

    # Remove transparent pixels if any (channel 4 is alpha)
    if array.shape[-1] > 3:
        array = array[array[:, 3] == 1]

    # Finding centroids (centroids are colors)
    centroids, _ = kmeans(array, CLUSTER_NUMBER)

    # Allocate pixel to a centroid cluster
    observations, _ = vq(array, centroids)

    # Calculate the number of pixels in a cluster
    histogram, _ = scipy.histogram(observations, len(centroids))

    # Sort centroids by number of pixels in their cluster
    sorted_centroids = sorted(zip(centroids, histogram),
                              key=lambda x: x[1],
                              reverse=True)

    sorted_colors = tuple((couple[0] for couple in sorted_centroids))

    return sorted_colors