Python numpy.fromiter函数代码示例

def decode4js(obj):
    """
    return decoded Python object from encoded object.
    """
    out = obj
    if isinstance(obj, dict):
        classname = obj.pop('__class__', None)
        if classname is None:
            return obj
        elif classname == 'Complex':
            out = obj['value'][0] + 1j*obj['value'][1]
        elif classname in ('List', 'Tuple'):
            out = []
            for item in obj['value']:
                out.append(decode4js(item))
            if classname == 'Tuple':
                out = tuple(out)
        elif classname == 'Array':
            if obj['__dtype__'].startswith('complex'):
                re = np.fromiter(obj['value'][0], dtype='double')
                im = np.fromiter(obj['value'][1], dtype='double')
                out = re + 1j*im
            else:
                out = np.fromiter(obj['value'], dtype=obj['__dtype__'])
            out.shape = obj['__shape__']
        elif classname in ('Dict', 'Parameter', 'Group'):
            out = {}
            for key, val in obj.items():
                out[key] = decode4js(val)
            if classname == 'Parameter':
                out = Parameter(**out)
            elif classname == 'Group':
                out = Group(**out)
    return out

def calculate_switch_stats(mappable, linkage_map_file, linkage_map_format, MST_grouping_threshold):
    genotypes_of_locus = mappable
    if linkage_map_format.lower() == 'mst':
        ini_map, loci_on_lg = parse_map_file_MST(linkage_map_file)
    elif linkage_map_format.lower() == 'rqtl':   
        ini_map, loci_on_lg = parse_map_file_rqtl(linkage_map_file)
    else:
        raise ValueError("unknown linkage_map_format")
    
    int_arr = convert_genotypes_to_int_array(genotypes_of_locus, ini_map)
    num_loci = int_arr.shape[0]
    num_pairs =  int((num_loci * (num_loci-1))/2)
    pairs = itertools.combinations(int_arr, 2)
    R = numpy.fromiter(getR(pairs), dtype = numpy.float64, count = num_pairs)
    pairs = itertools.combinations(int_arr, 2)
    NR = numpy.fromiter(getNR(pairs), dtype = numpy.float64, count = num_pairs)
    ml_R_frac = get_ml_R_frac(R = R, NR = NR)
    Z = get_LOD(R = R, NR = NR, R_frac = ml_R_frac)
    NR_matrix = get_NR_matrix(NR)
    #rf = get_rf_matrix(ml_R_frac)
    lod = get_lod_matrix(Z)
    index_of_lg = get_index_of_LG(loci_on_lg)
    lgs_longer_than_1 = find_LGs_with_multiple_loci(index_of_lg, loci_on_lg)
    #mean_rf = get_LG_pairwise_mean_rf(lgs_longer_than_1, rf, index_of_lg)
    #mean_lod = get_LG_pairwise_mean_lod(lgs_longer_than_1,lod, index_of_lg)
    sum_lod = get_LG_pairwise_sum_lod(lgs_longer_than_1,lod, index_of_lg)
    sq_sum_lod = get_square_form(sum_lod, lgs_longer_than_1)
    n = len(mappable.items()[0][1]) #number of individuals
    NR_threshold = get_threshold_recombinants_for_same_LGs(n, MST_grouping_threshold)
    NR_under_threshold = get_LG_pairwise_count_NR_threshold(lgs_longer_than_1, NR_matrix, index_of_lg, threshold = NR_threshold)
    sq_NR_matrix = get_square_form(NR_under_threshold, lgs_longer_than_1)
    return(ini_map, sq_sum_lod, sq_NR_matrix, R, NR, lgs_longer_than_1)

def _stats_to_movie_results(bam_stats, movie_names):
    """
    Separate out per-movie results from process stats.
    """
    results = []
    movies = sorted(list(movie_names))
    for movie_name in movies:
        def _base_calls():
            for r in bam_stats:
                if r.movieName == movie_name:
                    yield r.qLen

        def _num_passes():
            for r in bam_stats:
                if r.movieName == movie_name:
                    yield r.numPasses

        def _accuracy():
            for r in bam_stats:
                if r.movieName == movie_name:
                    yield r.readScore

        read_lengths = np.fromiter(_base_calls(), dtype=np.int64, count=-1)
        num_passes = np.fromiter(_num_passes(), dtype=np.int64, count=-1)
        accuracy = np.fromiter(_accuracy(), dtype=np.float, count=-1)

        results.append(MovieResult(
            movie_name, read_lengths, accuracy, num_passes))
    return results

def _bam_file_to_movie_results(file_name):
    """
    Read what is assumed to be a single BAM file (as a ConsensusReadSet).
    """
    from pbcore.io import IndexedBamReader
    results = []
    with IndexedBamReader(file_name) as bam:
        for rg in bam.readGroupTable:
            assert rg["ReadType"] == "CCS"

        movies = list(set([rg["MovieName"] for rg in bam.readGroupTable]))
        for movie_name in movies:
            def _base_calls():
                for r in bam:
                    if r.movieName == movie_name:
                        yield r.peer.query_length

            def _num_passes():
                for r in bam:
                    if r.movieName == movie_name:
                        yield r.numPasses

            def _accuracy():
                for r in bam:
                    if r.movieName == movie_name:
                        yield r.readScore

            read_lengths = np.fromiter(_base_calls(), dtype=np.int64, count=-1)
            num_passes = np.fromiter(_num_passes(), dtype=np.int64, count=-1)
            accuracy = np.fromiter(_accuracy(), dtype=np.float, count=-1)

            results.append(MovieResult(
                file_name, movie_name, read_lengths, accuracy, num_passes))
        return results

def _listparser(dlist, freq=None):
    "Constructs a DateArray from a list."
    dlist = np.array(dlist, copy=False, ndmin=1)
    # Case #1: dates as strings .................
    if dlist.dtype.kind in 'SU':
        #...construct a list of dates
        dlist = np.fromiter((Date(freq, string=s).value for s in dlist),
                            dtype=int)
    # Case #2: dates as numbers .................
    elif dlist.dtype.kind in 'if':
        #...hopefully, they are values
        pass
    # Case #3: dates as objects .................
    elif dlist.dtype.kind == 'O':
        template = dlist[0]
        #...as Date objects
        if isinstance(template, Date):
            dlist = np.fromiter((d.value for d in dlist), dtype=int)
            if freq in (_c.FR_UND, None):
                freq = template.freq
        #...as mx.DateTime objects
        elif hasattr(template, 'absdays'):
            dlist = np.fromiter((Date(freq, datetime=m) for m in dlist),
                                dtype=int)
        #...as datetime objects
        elif hasattr(template, 'toordinal'):
            dlist = np.fromiter((Date(freq, datetime=d) for d in dlist),
                                dtype=int)
    #
    result = dlist.view(DateArray)
    result.freq = freq
    return result

    def _fit_once(self, X, initial_order):
        adj_matrix = self.adj_matrix_strategy(X)
        N = adj_matrix.shape[0]
        degrees = adj_matrix.sum(axis=1)
        boundary = np.zeros(N)

        ordering = prc.createOrder(initial_order)
        policy = prc.tiloPolicyStruct()
        if self.refine_order:
            prc.RefineTILO(adj_matrix, ordering, policy)
        else:
            prc.TILO(adj_matrix, ordering, policy)
            
        boundary = np.fromiter(ordering.b.b, dtype=float)[:-1]
        ordering = np.fromiter(ordering.vdata, dtype=int)

        #print 'BDR', boundary
        #print 'PRS', pinch_ratios(boundary)
        #print 'ORD', ordering
        pinch_ratios, clusters = self._find_clusters(ordering, boundary)
        labels = np.zeros(N, dtype=int)
        for i, cluster in enumerate(clusters):
            labels[cluster] = i

        return ordering, boundary, labels, pinch_ratios

    def system_values(self, when: Union[Real, Sequence[Real]], which: Union[str, Sequence[str]]=None):
        which = self._observable_names if which is None else which
        max_when = when if isinstance(when, Real) else max(when)

        self.integrate_to(max_when)

        if len(self.solution_times) == 1:
            # Handle scipy bug when there is only one time point
            # TODO (drhagen): super hacky solution here
            state_interpolator = lambda t: self.solution_states[0]
        else:
            state_interpolator = interp1d(self.solution_times, self.solution_states, axis=0, assume_sorted=True,
                                          copy=False)

        # Extract values from solution
        output_fun = self.ode_system.outputs
        if isinstance(which, str) and isinstance(when, Real):
            states = state_interpolator(when)
            return output_fun(which, when, states)
        elif isinstance(which, str):
            return np.fromiter((output_fun(which, when_i, state_interpolator(when_i)) for when_i in when),
                               'float', count=len(when))
        elif isinstance(when, Real):
            states = state_interpolator(when)
            return np.fromiter((output_fun(which_i, when, states) for which_i in which),
                               'float', count=len(which))
        else:
            def values():
                for when_i in when:
                    states = state_interpolator(when_i)
                    for which_i in which:
                        yield output_fun(which_i, when_i, states)

            values = np.fromiter(values(), 'float', count=len(which)*len(when))
            return np.reshape(values, [len(when), len(which)])

  def _computeNormalizations(self):
    
    #Use a generator instead of a list to gain speed
    generator1               = (x.value for x in self.parameters.values()[1::2])
    self.alphas              = numpy.fromiter(generator1,float)
    #alphasDiff               = self.alphas[:-1]-self.alphas[1:]
    
    generator2               = (x.value for x in self.parameters.values()[2::2])
    self.betas               = numpy.fromiter(generator2,float)
    #betasDiff                = self.betas[:-1]-self.betas[1:]
    
    #bLogEpivot               = self.betas*self.logPivotEnergies
    #bLogEpivotDiff           = bLogEpivot[1:]-bLogEpivot[:-1]

        
    self.normalizations[0]   = self.parameters['K'].value
    self.normalizations[1:-1]  = (self._logP(self.energyBreaks,self.alphas[:-1],self.betas[:-1],self.pivotEnergies[:-1])/
                                  self._logP(self.energyBreaks,self.alphas[1:],self.betas[1:],self.pivotEnergies[1:])
                                  )
    self.normalizations[-1]  = 1.0
    
    #This compute the cumulative product of the array
    #(i.e., the first elements is a0, the second a0*a1,
    #the third a0*a1*a2, and so on...)
    self.products            = numpy.cumprod(self.normalizations)

    def get_world_endpoints(edges, pos, scale):
        """Returns the edge endpoints in homogeneous world coordinates

        Parameters
        ----------
        edges : iterable of Edge
        pos : numpy array
        scale : float

        Returns
        -------
        tuple of iterable of points
            a value in the form `(start_points, end_points)`, where
            `start_points` and `end_points` are in the form of a numpy matrix
        """
        edge_starts = (coord
                       for edge in edges
                       for coord in chain(scale * edge.start + pos, (1.0, )))
        edge_ends = (coord
                     for edge in edges
                     for coord in chain(scale * edge.end + pos, (1.0, )))

        homo_starts = np.fromiter(edge_starts, np.float, count=4 * len(edges))
        homo_ends = np.fromiter(edge_ends, np.float, count=4 * len(edges))

        homo_starts = homo_starts.reshape((len(edges), 4))
        homo_ends = homo_ends.reshape((len(edges), 4))

        return homo_starts, homo_ends

 def test_vector(self):
     v1 = Vector(self.list1)
     v2 = Vector(2*x for x in self.list1)
     self.assertEqual(2*v1, v2)
     n1 = np.fromiter(v1, int)
     n2 = np.fromiter(v2, int)
     self.assertEqual(v1.dot(v2), np.dot(n1,n2))

    def get_charge_resolution(self):
        """
        Calculate and obtain the charge resolution graph arrays.

        Returns
        -------
        true_charge : ndarray
            The X axis true charges.
        chargeres : ndarray
            The Y axis charge resolution values.
        chargeres_error : ndarray
            The error on the charge resolution.
        scaled_chargeres : ndarray
            The Y axis charge resolution divided by the Goal.
        scaled_chargeres_error : ndarray
            The error on the charge resolution divided by the Goal.
        """
        log.debug('[chargeres] Calculating charge resolution')
        true_charge = np.fromiter(iter(self.sum_dict.keys()), dtype=int)
        summed_charge = np.fromiter(iter(self.sum_dict.values()), dtype=float)
        num = np.fromiter(iter(self.n_dict.values()), dtype=int)

        chargeres = np.sqrt((summed_charge / num) + true_charge) / true_charge
        chargeres_error = chargeres * (1 / np.sqrt(2 * num))

        scale = self.goal(true_charge)
        scaled_chargeres = chargeres/scale
        scaled_chargeres_error = chargeres_error/scale

        return true_charge, chargeres, chargeres_error, \
            scaled_chargeres, scaled_chargeres_error

    def __init__(self, image):
        # number of points
        self.nx = int(image.shape[0])
        self.ny = int(image.shape[1])

        # spacing
        self.dx = 1.0
        self.dy = 1.0

        # limits
        self.xmin = 0
        self.ymin = 0

        self.xmax = float(self.nx)
        self.ymax = float(self.ny)

        # lengths
        self.lx = abs(self.xmax - self.xmin)
        self.ly = abs(self.ymax - self.ymin)

        # mesh
        self.y, self.x = np.meshgrid(
            np.fromiter(((0.5 + i) * self.dx for i in range(self.nx)),
                dtype=np.float64, count=self.nx),
            np.fromiter(((0.5 + i) * self.dy for i in range(self.ny)),
                dtype=np.float64, count=self.ny))

def extract_surf(jpgfile):
  start = time.time()
  out = os.path.join(os.path.dirname(jpgfile), os.path.basename(jpgfile)[:-4] + 'surf.npy')
  if os.path.exists(out):
    INFO('%s already exists' % out)
    return

  im = cv.LoadImageM(jpgfile, cv.CV_LOAD_IMAGE_GRAYSCALE)
  INFO('cv loaded %dx%d image' % (im.rows, im.cols))

  g, features = cv.ExtractSURF(im, None, cv.CreateMemStorage(), (0, 500, 3, 4))
  data = np.ndarray(len(features), SURFReader.surf_dtype)

  for i in range(len(features)):
    data[i]['vec'] = np.fromiter(features[i], np.float32)
    data[i]['geom'] = np.fromiter([g[i][0][0], g[i][0][1], g[i][2]], np.uint16)
    data[i]['index'] = 0

## Simple Quantization into bytes
#  for i in range(len(features)):
#    surfvalues = np.fromiter(features[i], np.float)
#
#    assert max(surfvalues) <= 1.0
#    assert min(surfvalues) >= -1.0
#
#    data[i]['vec'] = np.int8(127*surfvalues)
#    data[i]['geom'] = np.fromiter([g[i][0][0], g[i][0][1], g[i][2]], np.uint16)
#    data[i]['index'] = 0

  save_atomic(lambda d: np.save(d, data), out)
  INFO('cv wrote %d features' % len(features))
  INFO_TIMING('took %f seconds' % (time.time() - start))

def decodePacket(bin_data,  data_size = None, packet_mode = 'i64u', track_t0 = False):
    # Works only for i64bit unpacked mode
    global compressed_t0
    #assert (packet_mode == 'i64u')
    if packet_mode == 'i64u':
        data_size = len(bin_data)//ctypes.sizeof(Timetag_I64)

        t = ctypes.cast(bin_data, timetag_I64_p)

        time = np.fromiter((i.time for i in t), np.int64, data_size)
        channel = np.fromiter((i.channel for i in t), np.int8, data_size)

    if packet_mode == 'i64c':
        data_size = len(bin_data)//ctypes.sizeof(Timetag_I64c)

        t = ctypes.cast(bin_data, timetag_I64c_p)
        #if t[0].highlow == 0:
        #    ctypes.cast(bin_data, timetag_I64c_p)  
        highlow = np.fromiter((i.highlow for i in t ), np.uint64, data_size)
        time =   np.fromiter((i.timehigh for i in t ), np.uint64, data_size)+(cumsum(highlow))*2**27
        channel = np.fromiter((i.channel for i in t ), np.uint8, data_size)
        time    = time[highlow == 0]
        channel = channel[highlow == 0]

        if track_t0:
            time = time + compressed_t0
            compressed_t0 += sum(highlow)*2**27
        else:
            track_t0 = 0
    return(time, channel)

def token_type(disc_clsdict, wrd_corpus, fragments_within, fragments_cross,
               dest, verbose, n_jobs):
    if verbose:
        print banner('TOKEN/TYPE')
    ptoc, rtoc, ptyc, rtyc = _token_type_sub(disc_clsdict, wrd_corpus,
                                             fragments_cross, 'cross',
                                             verbose, n_jobs)
    ftoc = np.fromiter((fscore(ptoc[i], rtoc[i]) for i in xrange(ptoc.shape[0])),
                       dtype=np.double)
    ftyc = np.fromiter((fscore(ptyc[i], rtyc[i]) for i in xrange(ptyc.shape[0])),
                       dtype=np.double)

    ptow, rtow, ptyw, rtyw = _token_type_sub(disc_clsdict, wrd_corpus,
                                             fragments_within, 'within',
                                             verbose, n_jobs)
    ftow = np.fromiter((fscore(ptow[i], rtow[i]) for i in xrange(ptow.shape[0])),
                       dtype=np.double)
    ftyw = np.fromiter((fscore(ptyw[i], rtyw[i]) for i in xrange(rtyw.shape[0])),
                       dtype=np.double)
    with open(path.join(dest, 'token_type'), 'w') as fid:
        fid.write(pretty_score_f(ptoc, rtoc, ftoc, 'token total',
                                 len(fragments_cross),
                                 sum(map(len, fragments_cross))))
        fid.write('\n')
        fid.write(pretty_score_f(ptyc, rtyc, ftyc, 'type total',
                                 len(fragments_cross),
                                 sum(map(len, fragments_cross))))
        fid.write('\n')
        fid.write(pretty_score_f(ptow, rtow, ftow, 'token within-speaker only',
                                 len(fragments_within),
                                 sum(map(len, fragments_within))))
        fid.write('\n')
        fid.write(pretty_score_f(ptyw, rtyw, ftyw, 'type within-speaker only',
                                 len(fragments_within),
                                 sum(map(len, fragments_within))))