Python scipy.product函数代码示例

def tag_images_with_color_value(NUM_CLUSTERS = 4, INPUT_FOLDER = './data/covers/'):

    isbn = list()
    cover_color = list()

    files = os.listdir(INPUT_FOLDER)
    for eachFile in files:
        print eachFile
        im = Image.open(INPUT_FOLDER + eachFile)
        im = im.resize((50, 50))                          # optional, to reduce time
        ar = scipy.misc.fromimage(im)
        shape = ar.shape
        print len(shape)

        if len(shape) == 2:
            ar = ar.reshape(scipy.product(shape[:1]), shape[1])
        else:
            ar = ar.reshape(scipy.product(shape[:2]), shape[2])

        # finding clusters
        codes, dist = scipy.cluster.vq.kmeans(ar, NUM_CLUSTERS)
        # cluster centres:\n', codes

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

        index_max = scipy.argmax(counts)                    # find most frequent
        peak = codes[index_max]
        colour = ''.join(chr(c) for c in peak).encode('hex')

        isbn.append(eachFile[:-4])
        cover_color.append(colour)

    result = zip(isbn, cover_color)
    return result

def prblm_8():
    """Find the largest product of 13 adjacent digits in the following series"""
    from scipy import product
    series = """73167176531330624919225119674426574742355349194934
96983520312774506326239578318016984801869478851843
85861560789112949495459501737958331952853208805511
12540698747158523863050715693290963295227443043557
66896648950445244523161731856403098711121722383113
62229893423380308135336276614282806444486645238749
30358907296290491560440772390713810515859307960866
70172427121883998797908792274921901699720888093776
65727333001053367881220235421809751254540594752243
52584907711670556013604839586446706324415722155397
53697817977846174064955149290862569321978468622482
83972241375657056057490261407972968652414535100474
82166370484403199890008895243450658541227588666881
16427171479924442928230863465674813919123162824586
17866458359124566529476545682848912883142607690042
24219022671055626321111109370544217506941658960408
07198403850962455444362981230987879927244284909188
84580156166097919133875499200524063689912560717606
05886116467109405077541002256983155200055935729725
71636269561882670428252483600823257530420752963450""".replace('\n','')
    serilist = [int(x) for x in series]
    heighestprod = 0
    for ii in range(0, len(serilist) - 13):
        if product(serilist[ii:ii + 13]) > heighestprod:
            heighestprod = product(serilist[ii:ii+13])
            heighestset = serilist[ii:ii+13]
    return heighestprod, heighestset

def test():
    intlist = load_test()
    triads = get_groups(intlist, cachefile=TESTCACHE)

    x = itergroups(triads).next()
    print 'group 1: {}'.format(x)
    print 'QE     : {}'.format(scipy.product(list(x[0])))

    quads = get_groups(intlist, num=4, cachefile=TESTCACHE)
    x = itergroups(quads, num=4).next()
    print 'group 1: {}'.format(x)
    print 'QE     : {}'.format(scipy.product(list(x[0])))

 def stats(self, startdate, enddate, mktbasket, avdate, output=False, mappingoverride=None):
     """
     Calculates statistics for a fund over a period.
     
     Parameters
     ----------
     startdate : datetime
         beginning of statistic period
     enddate : datetime
         end of statistic period
     mktbasket : dict
         dictionary of market streams
     output : bool
         if True, output results to db
     mappingoverride : None or mapping dictionary
     	whether to override the db mapping
     
     Returns
     -------
     stats : dict
         dictionary of statistics
     """
     actualstream, projstream = self.project(mktbasket, mappingoverride)
     if actualstream[startdate:enddate] is None: return None
     if projstream[startdate:enddate] is None: return None 
     actual = actualstream[startdate:enddate].returns
     projected = projstream[startdate:enddate].returns
     diff = actual - projected
     outdata = {
              'TE'     : scipy.std(diff) * 100.0 * 100.0,
              'BETA'   : scipy.cov(projected, actual, bias=1)[1, 0] / scipy.var(projected),
              'ALPHA'  : (scipy.product(diff + 1.0)) ** (1.0 / diff.size) - 1.0,
              'VOL'    : scipy.std(actual) * scipy.sqrt(252.0),
              'PROJ'   : scipy.product(1.0 + projected) - 1.0,
              'ACT'    : scipy.product(1.0 + actual) - 1.0,
              'R2'     : 0.0 if scipy.all(actual == 0.0) else scipy.corrcoef(projected, actual)[1, 0] ** 2.0,
              'AV'     : self.av(avdate),
              'DELTA'  : self.deltaestimate(avdate)
             }
     outdata['DIFF'] = outdata['ACT'] - outdata['PROJ']
     outdata['PL'] = outdata['DELTA'] * outdata['DIFF'] * 100.0 
     if output:
         cnxn = pyodbc.connect(ORACLESTRING)
         cursor = cnxn.cursor()
         sql = 'INSERT INTO FUNDOUTPUT VALUES ({0!s},{1!s},{2!s},{3!s},{4!s},{5!s},{6},{7},{8!s},{9!s},{10!s},{11!s},{12!s},{13!s});'
         sql = sql.format(self.fundcode, outdata['PROJ'], outdata['ACT'], outdata['DIFF'],
                    outdata['DELTA'], outdata['PL'], oracledatebuilder(startdate),
                    oracledatebuilder(enddate), outdata['TE'], outdata['R2'], outdata['BETA'],
                    outdata['ALPHA'], outdata['VOL'], outdata['AV'])
         cursor.execute(sql)
         cnxn.commit()
         cnxn.close()
     return outdata

            self.mapping[indexes[i]] = finalbeta[i]
        return self.mapping

    def stats(self, startdate, enddate, mktbasket, output = False):
        """
        Calculates statistics for a fund over a period.
        
        Parameters
        ----------
        startdate : datetime
            beginning of statistic period
        enddate : datetime
            end of statistic period
        mktbasket : dict
            dictionary of market streams
        output : bool
            if True, output results to db
        
        Returns
        -------
        stats : dict
            dictionary of statistics
        """
        inputmatrix, fundreturns, indexes, daterange = self.align(startdate, enddate, mktbasket)
        if self.mapping and not(inputmatrix is None):
            weights = scipy.array([self.mapping[mykey] if mykey in self.mapping else 0.0 for mykey in mktbasket.keys()])
            projected = scipy.dot(inputmatrix,weights.reshape(len(indexes),1)).flatten()
            actual = fundreturns.flatten()
            diff = actual-projected
            outdata = {
                     'TE'     : scipy.std(diff)*100.0*100.0,
                     'BETA'   : scipy.cov(projected,actual)[1,0]/scipy.var(projected),
                     'ALPHA'  : (scipy.product(diff+1.0))**(1.0/diff.size)-1.0,
                     'VOL'    : scipy.std(actual)*scipy.sqrt(252.0),
                     'PROJ'   : scipy.product(1.0+projected)-1.0,
                     'ACT'    : scipy.product(1.0+actual)-1.0,
                     'R2'     : 0.0 if scipy.all(actual==0.0) else scipy.corrcoef(projected,actual)[1,0]**2.0,
                     'AV'     : self.av(startdate),
                     'DELTA'  : self.deltaestimate(startdate)
                    }
            outdata['DIFF'] = outdata['ACT']-outdata['PROJ']
            outdata['PL'] = outdata['DELTA']*outdata['DIFF']*100.0 
            if output:
                cnxn = pyodbc.connect(ORACLESTRING)
                cursor = cnxn.cursor()
                sql = 'INSERT INTO FUNDOUTPUT VALUES ({0!s},{1!s},{2!s},{3!s},{4!s},{5!s},{6},{7},{8!s},{9!s},{10!s},{11!s},{12!s},{13!s});'
                sql = sql.format(self.fundcode,outdata['PROJ'],outdata['ACT'],outdata['DIFF'],
                           outdata['DELTA'],outdata['PL'],oracledatebuilder(startdate),
                           oracledatebuilder(enddate),outdata['TE'],outdata['R2'],outdata['BETA'],
                           outdata['ALPHA'],outdata['VOL'],outdata['AV'])
                cursor.execute(sql)
                cnxn.commit()            
                cnxn.close()

def getDominantColor(img_url):
    if r.exists(img_url):
        cache_result = r.hmget(img_url, ['r', 'g', 'b'])
        return cache_result
        
    NUM_CLUSTERS = 5
    im = Image.open(StringIO.StringIO(urllib2.urlopen(img_url).read()))
    img_arr = scipy.misc.fromimage(im)
    img_shape = img_arr.shape
    
    if len(img_shape) > 2:
        img_arr = img_arr.reshape(scipy.product(img_shape[:2]), img_shape[2])
    
    codes, _ = scipy.cluster.vq.kmeans(img_arr, NUM_CLUSTERS)
    
    original_codes = codes
    for low, hi in [(60, 200), (35, 230), (10, 250)]:
        codes = scipy.array([code for code in codes if not (all([c < low for c in code]) or all([c > hi for c in code]))])
        if not len(codes):
            codes = original_codes
        else:
            break

    vecs, _ = scipy.cluster.vq.vq(img_arr, codes)
    counts, bins = scipy.histogram(vecs, len(codes))

    index_max = scipy.argmax(counts)
    peak = codes[index_max]
    color = [int(c) for c in peak[:3]]
    r.hmset(img_url, {'r':color[0], 'g':color[1], 'b':color[2]})
    #r.expire(img_url, 86400)
    return color

 def maskLowStddVoxels(self, dds, nMeanDds, nStddDds):
     unique = np.unique(sp.where(nStddDds.subd.asarray() <= 1.0/3, dds.subd.asarray(), dds.mtype.maskValue()))
     unique = unique[sp.where(unique != dds.mtype.maskValue())]
     if (dds.mpi.comm != None):
         unique = dds.mpi.comm.allreduce(unique.tolist(), op=mpi.SUM)
         unique = np.unique(unique)
     rootLogger.info("Unique constant stdd values = %s" % (unique,))
     rootLogger.info("Creating mask from unique constant values...")
     mskDds = mango.zeros_like(dds, mtype="segmented")
     for uVal in unique:
         mskDds.asarray()[...] = sp.where(dds.asarray() == uVal, 1, mskDds.asarray())
     rootLogger.info("Done creating mask from unique constant values.")
 
     rootLogger.info("Labeling connected constant zero-stdd regions...")
     mskDds.updateHaloRegions()
     mskDds.mirrorOuterLayersToBorder(False)
     self.writeIntermediateDds("_000ZeroStddForLabeling", mskDds)
     lblDds = mango.image.label(mskDds, 1)
     rootLogger.info("Done labeling connected constant stdd regions.")
     self.writeIntermediateDds("_000ZeroStdd", lblDds)
     
     countThresh = 0.01 * sp.product(lblDds.shape)
     rootLogger.info("Eliminating large clusters...")
     lblDds = mango.image.eliminate_labels_by_size(lblDds, minsz=int(countThresh), val=lblDds.mtype.maskValue())
     self.writeIntermediateDds("_000ZeroStddLargeEliminated", lblDds)
 
     rootLogger.info("Assigning mask values...")
     mskDds.subd.asarray()[...] = \
         sp.where(lblDds.subd.asarray() == lblDds.mtype.maskValue(), True, False)
     self.writeIntermediateDds("_000ZeroStddMskd", mskDds)
     del lblDds
     for tmpDds in [dds, nMeanDds, nStddDds]:
         tmpDds.subd.asarray()[...] = \
             sp.where(mskDds.subd.asarray(), tmpDds.mtype.maskValue(), tmpDds.subd.asarray())

 def testGaussianPValue(self):
     for typePair in [(None, "float32"), ("tomo", None)]:
         mtype = typePair[0]
         dtype = typePair[1]
         mean = 32000.0
         stdd = 1000.0
         noisDds = mango.data.gaussian_noise(shape=(105,223,240), mean=mean, stdd=stdd, mtype=mtype, dtype=dtype)
         
         pvalDds = \
             mango.fmm.gaussian_pvalue(
                 noisDds,
                 mean=mean,
                 stdd=stdd,
                 sidedness=mango.fmm.PValueSidednessType.RIGHT_SIDEDNESS
             )
         
         alpha = 0.05
         count = sp.sum(sp.where(pvalDds.asarray() <= alpha, 1, 0))
         if (pvalDds.mpi.comm != None):
             count = pvalDds.mpi.comm.allreduce(count)
         
         expCount = sp.product(noisDds.shape)*alpha
         count = float(count)
         relErr = sp.absolute(expCount-float(count))/sp.absolute(max(expCount,count))
         rootLogger.info("relErr = %s" % relErr)
         self.assertTrue(relErr < 0.10)

def get_dominant_color(image_path):
    '''
    Parse image and return dominant color in image.

    @param image_path: Image path to parse.
    @return: Return dominant color, format as hexadecimal number. 
    '''
    # print 'reading image'
    im = Image.open(image_path)
    im = im.resize((150, 150))      # optional, to reduce time
    ar = scipy.misc.fromimage(im)
    shape = ar.shape
    ar = ar.reshape(scipy.product(shape[:2]), shape[2])
    
    # print 'finding clusters'
    NUM_CLUSTERS = 5
    codes, dist = scipy.cluster.vq.kmeans(ar, NUM_CLUSTERS)
    # print 'cluster centres:\n', codes
    
    vecs, dist = scipy.cluster.vq.vq(ar, codes)         # assign codes
    counts, bins = scipy.histogram(vecs, len(codes))    # count occurrences
    
    index_max = scipy.argmax(counts)                    # find most frequent
    peak = codes[index_max]
    colour = ''.join(chr(c) for c in peak).encode('hex')
    # print 'most frequent is %s (#%s)' % (peak, colour)
    
    return "#%s" % (colour[0:6])

    def determine_dominant_color_in_image(self, image):
        NUM_CLUSTERS = 5
            
        ar = scipy.misc.fromimage(image)
        shape = ar.shape
        if len(shape) > 2:
            ar = ar.reshape(scipy.product(shape[:2]), shape[2])

        codes, _ = scipy.cluster.vq.kmeans(ar, NUM_CLUSTERS)
        # print "Before: %s" % codes
        original_codes = codes
        for low, hi in [(60, 200), (35, 230), (10, 250)]:
            codes = scipy.array([code for code in codes 
                                 if not ((code[0] < low and code[1] < low and code[2] < low) or
                                         (code[0] > hi and code[1] > hi and code[2] > hi))])
            if not len(codes): codes = original_codes
            else: break
        # print "After: %s" % codes
    
        vecs, _ = scipy.cluster.vq.vq(ar, codes)         # assign codes
        counts, bins = scipy.histogram(vecs, len(codes))    # count occurrences
        # colors = [''.join(chr(c) for c in code).encode('hex') for code in codes]
        # total = scipy.sum(counts)
        # print dict(zip(colors, [count/float(total) for count in counts]))
        index_max = scipy.argmax(counts)                    # find most frequent
        peak = codes[index_max]
        color = ''.join(chr(c) for c in peak).encode('hex')
        # print 'most frequent is %s (#%s)' % (peak, color)
        
        return color[:6]

def calculate_dominant_colors(image, num_clusters):
    ar = scipy.misc.fromimage(image)
    shape = ar.shape
    ar = ar.reshape(scipy.product(shape[:2]), shape[2])
    codes, _ = scipy.cluster.vq.kmeans(ar.astype(float), num_clusters)
    vecs, _ = scipy.cluster.vq.vq(ar, codes)
    return ar, shape, codes, vecs

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 getPredominantColor(filename):
    im = Image.open(filename).convert('RGB')

    # Convert to numpy array
    ar = scipy.misc.fromimage(im)

    # Get dimensions
    shape = ar.shape

    # Convert to bidimensional array of width x height rows and 3 columns (RGB)
    ar = ar.reshape(scipy.product(shape[:2]), shape[2])

    # Find cluster centers and their distortions
    # codes contains the RGB value of the centers
    codes, dist = scipy.cluster.vq.kmeans(ar.astype(float), NUM_CLUSTERS)

    # Maps all the pixels in the image to their respective centers
    vecs, dist = scipy.cluster.vq.vq(ar, codes)

    # Counts the occurances of each color (NUM_CLUSTER different colors after the mapping)
    counts, bins = scipy.histogram(vecs, len(codes))

    # Find most frequent color
    index_max = scipy.argmax(counts)
    peak = codes[index_max]

    return peak.astype(int)

def getDomIMAGEColor( imName ):
	# Reference:
	# 	http://stackoverflow.com/questions/3241929/
	# 	python-find-dominant-most-common-color-in-an-image

	# number of k-means clusters
	NUM_CLUSTERS = 4

	# Open target image
	im = imName
	im = im.resize((150, 150))      # optional, to reduce time
	ar = scipy.misc.fromimage(im)
	shape = ar.shape
	ar = ar.reshape(scipy.product(shape[:2]), shape[2])
	ar = ar.astype(float)

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

	# Find most frequent
	index_max = scipy.argmax(counts)                    
	peak = codes[index_max]
	color = ''.join(chr(int(c)) for c in peak).encode('hex')

	return (peak, color)

def cluster_colors(image_url, num_clusters=5):
    """
    Return the most clustered colors of an image.
    Use scipy's k-means clustering algorithm.
    """

    print 'Reading image...'
    response = requests.get(image_url)
    im = Image.open(StringIO(response.content))
    im = im.resize((150, 150))      # optional, to reduce time
    ar = scipy.misc.fromimage(im)
    shape = ar.shape
    ar = ar.reshape(scipy.product(shape[:2]), shape[2])
    ar = ar.astype(float)

    print 'Finding clusters...'
    # k-means clustering
    codes, dist = scipy.cluster.vq.kmeans(ar, num_clusters)
    vecs, dist = scipy.cluster.vq.vq(ar, codes)         # assign codes
    counts, bins = scipy.histogram(vecs, len(codes))    # count occurrences
    sorted_index = sorted(range(len(counts)), key=lambda index: counts[index], reverse=True)

    most_common_colors = []
    for index in sorted_index:
        peak = codes[index]
        peak = peak.astype(int)
        colour = ''.join(format(c, '02x') for c in peak)
        most_common_colors.append('#' + colour)
    return most_common_colors