Python numpy.invert函数代码示例

 def ScoreSimilarity(ideal, pattern):
   inverted_ideal = np.invert(ideal)
   inverted_pattern = np.invert(pattern)
   # I DON'T THINK THIS IS RIGHT.
   white = np.sum(np.bitwise_and(ideal, pattern))
   black = np.sum(np.bitwise_and(inverted_ideal, inverted_pattern))
   return white + black                           

def three_dim_pos_bundle(table, key1, key2, key3, 
    return_complement=False, **kwargs):
    """ 
    Method returns 3d positions of particles in 
    the standard form of the inputs used by many of the 
    functions in the `~halotools.mock_observables`. 

    Parameters 
    ----------
    table : data table 
        `~astropy.table.Table` object 

    key1, key2, key3: strings 
        Keys used to access the relevant columns of the data table. 

    mask : array, optional 
        array used to apply a mask over the input ``table``. Default is None. 

    return_complement : bool, optional 
        If set to True, method will also return the table subset given by the inverse mask. 
        Default is False. 

    """
    if 'mask' in kwargs.keys():
        mask = kwargs['mask']
        x, y, z = table[key1][mask], table[key2][mask], table[key3][mask]
        if return_complement is True:
            x2, y2, z2 = table[key1][np.invert(mask)], table[key2][np.invert(mask)], table[key3][np.invert(mask)]
            return np.vstack((x, y, z)).T, np.vstack((x2, y2, z2)).T
        else:
            return np.vstack((x, y, z)).T 
    else:
        x, y, z = table[key1], table[key2], table[key3]
        return np.vstack((x, y, z)).T

def _make_image_mask(outlines, pos, res):
    """Aux function
    """

    mask_ = np.c_[outlines['mask_pos']]
    xmin, xmax = (np.min(np.r_[np.inf, mask_[:, 0]]),
                  np.max(np.r_[-np.inf, mask_[:, 0]]))
    ymin, ymax = (np.min(np.r_[np.inf, mask_[:, 1]]),
                  np.max(np.r_[-np.inf, mask_[:, 1]]))

    inside = _inside_contour(pos, mask_)
    outside = np.invert(inside)
    outlier_points = pos[outside]
    while np.any(outlier_points):  # auto shrink
        pos *= 0.99
        inside = _inside_contour(pos, mask_)
        outside = np.invert(inside)
        outlier_points = pos[outside]
    image_mask = np.zeros((res, res), dtype=bool)
    xi_mask = np.linspace(xmin, xmax, res)
    yi_mask = np.linspace(ymin, ymax, res)
    Xi_mask, Yi_mask = np.meshgrid(xi_mask, yi_mask)

    pos_ = np.c_[Xi_mask.flatten(), Yi_mask.flatten()]
    inds = _inside_contour(pos_, mask_)
    image_mask[inds.reshape(image_mask.shape)] = True

    return image_mask, pos

	def get_combined_calibration(self, nbc_disc, nbc_bulge, split_half=2, names=["m", "c1", "c2"]):
		print "Will combine bulge and disc calibration fits."
		if split_half==0:
			for bias in names:
				self.res = arr.add_col(self.res, bias, np.zeros_like(self.res['e1']))
				bulge = self.res["is_bulge"].astype(bool)
				print "column : %s, bulge : %d/%d, disc : %d/%d"%(bias, self.res[bulge].size, self.res.size, self.res[np.invert(bulge)].size, self.res.size)
				try:
					self.res[bias][bulge] = nbc_bulge.res[bias][bulge]
				except:
					import pdb ; pdb.set_trace()
				self.res[bias][np.invert(bulge)] = nbc_disc.res[bias][np.invert(bulge)]

		else:
			
			com ="""
for i, bias in enumerate(names):
	bulge = self.res['is_bulge'].astype(bool)
	if i==0: print 'bulge :', self.res[bulge].size, 'disc : ', self.res[np.invert(bulge)].size, 'total : ', self.res.size
	self.res = arr.add_col(self.res, bias, np.zeros_like(self.res['e1']))

	print 'column : ', bias
				
	self.res[bias][bulge] = nbc_bulge.res[bias][bulge]
	self.res[bias][np.invert(bulge)] = nbc_disc.res[bias][np.invert(bulge)]""".replace("res", "res%d"%split_half)
			exec(com)
		print "done"

def archive_human_masks(human_directory, new_directory, work_directory):
	'''
	For a directory of hand-drawn masks, mask out everything in the accompanying bright-field file except for the worm itself and a 100-pixel surrounding area to save disk space. Also, re-compress all images to maximize compression and space efficiency.
	'''
	for a_subdir in os.listdir(human_directory):
		if os.path.isdir(human_directory + os.path.sep + a_subdir):
			folderStuff.ensure_folder(new_directory + os.path.sep + a_subdir)
			for a_file in os.listdir(human_directory + os.path.sep + a_subdir):
				if a_file.split(' ')[-1] == 'hmask.png':
					if not os.path.isfile(new_directory + os.path.sep + a_subdir + os.path.sep + a_file):
						print('Up to ' + a_subdir + ' ' + a_file + '.')
						my_stem = a_file.split(' ')[0]
						my_mask = freeimage.read(human_directory + os.path.sep + a_subdir + os.path.sep + my_stem + ' ' + 'hmask.png')
						bf_path = human_directory + os.path.sep + a_subdir + os.path.sep + my_stem + ' ' + 'bf.png'
						if os.path.isfile(bf_path):
							my_image = freeimage.read(bf_path)
						else:
							my_image = freeimage.read(bf_path.replace(human_directory, work_directory))
						area_mask = my_mask.copy().astype('bool')
						distance_from_mask = scipy.ndimage.morphology.distance_transform_edt(np.invert(area_mask)).astype('uint16')
						area_mask[distance_from_mask > 0] = True
						area_mask[distance_from_mask > 100] = False
						my_image[np.invert(area_mask)] = False
						freeimage.write(my_image, new_directory + os.path.sep + a_subdir + os.path.sep + my_stem + ' ' + 'bf.png', flags = freeimage.IO_FLAGS.PNG_Z_BEST_COMPRESSION)					
						freeimage.write(my_mask, new_directory + os.path.sep + a_subdir + os.path.sep + my_stem + ' ' + 'hmask.png', flags = freeimage.IO_FLAGS.PNG_Z_BEST_COMPRESSION)					
				elif a_file.split('.')[-1] == 'json':					
					shutil.copyfile(human_directory + os.path.sep + a_subdir + os.path.sep + a_file, new_directory + os.path.sep + a_subdir + os.path.sep + a_file)
	return

    def baseline_recovery_test(self, model):

        baseline_method = getattr(model, 'baseline_'+model._method_name_to_decorate)
        baseline_result = baseline_method(halo_table = self.toy_halo_table2)

        method = getattr(model, model._method_name_to_decorate)
        result = method(halo_table = self.toy_halo_table2)

        mask = self.toy_halo_table2['halo_zform_percentile'] >= model._split_ordinates[0]
        oldmean = result[mask].mean()
        youngmean = result[np.invert(mask)].mean()
        baseline_mean = baseline_result.mean()
        assert oldmean != youngmean
        assert oldmean != baseline_mean
        assert youngmean != baseline_mean 

        param_key = model._method_name_to_decorate + '_assembias_param1'
        param = model.param_dict[param_key]
        if param > 0:
            assert oldmean > youngmean 
        elif param < 0: 
            assert oldmean < youngmean
        else:
            assert oldmean == youngmean 

        split = model.percentile_splitting_function(halo_table = self.toy_halo_table2)
        split = np.where(mask, split, 1-split)
        derived_result = split*oldmean
        derived_result[np.invert(mask)] = split[np.invert(mask)]*youngmean
        derived_mean = derived_result[mask].mean() + derived_result[np.invert(mask)].mean()
        baseline_mean = baseline_result.mean()
        np.testing.assert_allclose(baseline_mean, derived_mean, rtol=1e-3)

def data_checker_mask(loader):
	X, Y = next(loader.get())
	X, Y = X[:100].squeeze(), Y[:100]

	X, Y = X.transpose([1, 2, 0]), Y.transpose([1, 2, 0])


	stride = 60
	pos_x = np.arange(0, 600, stride)
	pos_y = np.arange(0, 600, stride)
	vx, vy = np.meshgrid(pos_x, pos_y)
	pos = np.stack([vx, vy]).reshape((2, -1)).transpose([1,0])+stride//2

	real, binary = np.zeros((600, 600)), np.zeros((600, 600))

	real[patch_interface(pos[:,0], pos[:,1], stride//2)] = X
	binary[patch_interface(pos[:,0], pos[:,1], stride//2)] = Y

	binary = binary.astype('bool')

	# print(real.max(), binary.max(), binary.sum(), binary.size)

	img = np.stack([real]*3, axis=2)+500
	img[:,:, 0] = img[:,:, 0]*binary 
	img[:,:, 1] = img[:,:, 1]*np.invert(binary)
	img[:,:, 2] = img[:,:, 2]*np.invert(binary)
	imwrite(rescale_intensity(img.astype('uint8')), "./save/data_check.png")

 def uniform():
     bits_to_get = fast_random_bool((self.psize, self.numbit))
     pop_part = self.pop_part_rec  # if fitness function is too hard, then it could be faster to take best children only for some part of population
     # When pop_part = 1.0 it is slower, but based on few tests it's better to leave the children with max fit. Maybe with some probability?
     bound = int(self.psize * pop_part)
     buff1 = np.empty((1, self.numbit), dtype=int)
     buff2 = np.empty((1, self.numbit), dtype=int)
     for p_index in range(bound):
         buff1[0] = (self.data[self.parents[2 * p_index]] & bits_to_get[p_index]) + (
             self.data[self.parents[2 * p_index + 1]] & (np.invert(bits_to_get[p_index]) + 2))
         buff2[0] = (self.data[self.parents[2 * p_index + 1]] & bits_to_get[p_index]) + (
             self.data[self.parents[2 * p_index]] & (np.invert(bits_to_get[p_index]) + 2))
         if self.fitness_function(buff1[0]) > self.fitness_function(buff2[0]):
             self.children[p_index] = buff1[0]
         else:
             self.children[p_index] = buff2[0]
     if bound != self.psize:
         # choose just first child, not necessarily the best
         self.children[bound:self.psize] = (self.data[self.parents[2 * bound::2]] & bits_to_get[
                                                                                    bound:self.psize]) + (
                                               self.data[self.parents[2 * bound + 1::2]] & (
                                                   np.invert(bits_to_get[bound:self.psize]) + 2))
     del buff1
     del buff2
     return

def distance_combinatorics(Dorig,FDR,resolution,n,th,tl,as_str=True,mode=0,res_diff=1.):
	D = np.copy(Dorig)
	D[((D > tl) & (D < th))] = 1
	D[(FDR == 0)] = 1
	Dmerged = defaultdict(list)
	Dmax = np.zeros(D.shape[1])
	for low,high in itertools.combinations(range(D.shape[0]),2):
		if resolution[low]/resolution[high] < res_diff:
			Dcurrent = np.zeros(D.shape[1])
		elif mode == 1:
			# positive low, negative high
			# zeros where one or both signs incorrect
			Dcurrent = (1./(high - low))/(1./4 + 1./(high - low))*((D[high] - 1)*(1 - D[low]))**.5
			Dcurrent[np.invert((1 - D[high] < 0)*(1 - D[low] > 0))] = 0
		elif mode == 2:
			# positive low, positive high
			Dcurrent = (1./4 + 1./(high - low))/(1./(high - low))*((1 - D[high])*(1 - D[low]))**.5
			Dcurrent[np.invert((1 - D[high] > 0)*(1 - D[low] > 0))] = 0
		Dmax = np.array([Dmax,Dcurrent]).max(0)
		#Dmax[np.isnan(Dmax)] = 0
		del Dcurrent
	for i,idx in enumerate(itertools.combinations(xrange(n),2)):
		d = Dmax[i]
		if d > .0:
			if as_str:
				Dmerged[idx[0]].append('%d:%f' % (idx[1],d))
				Dmerged[idx[1]].append('%d:%f' % (idx[0],d))
			else:
				Dmerged[idx[0]].append((idx[1],d))
				Dmerged[idx[1]].append((idx[0],d))
	return Dmerged

def derivative_G(propensities,V,X,w,deter_vector,stoc_positions, positions, valid):
	
	# just the deterministics
	X_d = X[deter_vector,:].copy()
	temp_eta = np.zeros((np.sum(deter_vector),X.shape[1]))
	j = 0
	for i in range(len(stoc_positions)):
		##pdb.set_trace()
		# If x-\nu_i is non zero
		if stoc_positions[i] == True:
			
			if np.sum(valid[:,j]) != 0:
				#print(" X shape: " + str(X.shape))
				#print(" w shape: " + str(w.shape))
				#print("test :" + str(map(propensities[i],*X[:,positions[valid[:,j]][:,j]])))
				
				
				temp_eta[:,valid[:,j]] += (X_d[:,positions[valid[:,j]][:,j]] 
							    - X_d[:,valid[:,j]] +
								V[i][deter_vector][:,np.newaxis]
							  )*map(propensities[i],* X[:,positions[valid[:,j]][:,j]])*w[positions[valid[:,j]][:,j]]
			j += 1
		else:
			temp_eta[:,:] += (V[i][deter_vector][:,np.newaxis])*map(propensities[i],* X)*w
			
	return_X = np.zeros(X.shape)
	return_X[deter_vector,:] = temp_eta
	return_X[np.invert(deter_vector),:] = X[np.invert(deter_vector),:].copy()
	return return_X

 def pcols(self, pheno):
     '''
     Requires a list.
     '''
     expt_cols = []
     pheno_cols = []
     if pheno is None:
         self._experimentcolumns = self.columns
         self._phenocolumns = None
         return
     if not isinstance(pheno, list):
         raise TypeError("A list is required for setting pheno columns")
     # Create a column name dict for quick lookups
     col_dict = dict(zip(self.columns, range(0, len(self.columns))))
     is_pheno = array([c in pheno for c in col_dict])
     is_expt = invert(is_pheno)
     num_pheno = sum(is_pheno)
     num_expt = sum(is_expt)
     # Sanity check!
     if num_pheno + num_expt != len(self.columns):
         raise ValueError("Not all phenotype columns could be found in \
         the GenomeFrame.")
     # Assign values
     if num_pheno > 0:
         pheno_cols = self.columns[is_pheno].tolist()
     if num_expt > 0:
         expt_cols = self.columns[invert(is_pheno)].tolist()
     self._phenocolumns = pheno_cols
     self._experimentcolumns = expt_cols

def query_by_bagging(X, y, current_model, batch_size, rng, base_model=SVC(C=1, kernel='linear'), n_bags=5, method="KL", D=None):
    """
    :param base_model: Model that will be  **fitted every iteration**
    :param n_bags: Number of bags on which train n_bags models
    :param method: 'entropy' or 'KL'
    :return:
    """
    assert method == 'entropy' or method == 'KL'
    eps = 0.0000001
    if method == 'KL':
        assert hasattr(base_model, 'predict_proba'), "Model with probability prediction needs to be passed to this strategy!"
    clfs = BaggingClassifier(base_model, n_estimators=n_bags, random_state=rng)
    clfs.fit(X[y.known], y[y.known])
    pc = clfs.predict_proba(X[np.invert(y.known)])
    # Settles page 17
    if method == 'entropy':
        pc += eps
        fitness = np.sum(pc * np.log(pc), axis=1)
        ids =  np.argsort(fitness)[:batch_size]
    elif method == 'KL':
        p = np.array([clf.predict_proba(X[np.invert(y.known)]) for clf in clfs.estimators_])
        fitness = np.mean(np.sum(p * np.log(p / pc), axis=2), axis=0)
        ids = np.argsort(fitness)[-batch_size:]

    return y.unknown_ids[ids], fitness/np.max(fitness)

    def predict(self, data, modes):
        """predict whether a list of position follows atrain route by detecting
        the nearest train stops. Input is the pandas data frame of
        measurements and an array of current mode predictions.  Returns
        an array of predicted modes of the same size as the input data
        frame has rows.

        """
        # extract lat/lon from data frame
        lat = data['WLATITUDE'].values
        lon = data['WLONGITUDE'].values

        # chunk is a tuple (start_idx, end_idx, mode)
        for start_idx, end_idx, _ in ifilter(lambda chunk: chunk[2] in [MODE_CAR, MODE_BUS, MODE_TRAIN],
                                             chunks(modes, include_values=True)):
            # test for distance first
            lat_seg = lat[start_idx:end_idx]
            lon_seg = lon[start_idx:end_idx]
            valid_lat_seg = lat_seg[np.where(np.invert(np.isnan(lat_seg)))[0]]
            valid_lon_seg = lon_seg[np.where(np.invert(np.isnan(lon_seg)))[0]]

            if len(valid_lon_seg) == 0:
                continue
            # TODO: parameters have to be tuned carefully
            is_train = predict_mode_by_location(valid_lat_seg,
                                                valid_lon_seg,
                                                self.train_location_tree,
                                                self.train_location_dict,
                                                self.train_route_dict,
                                                dist_thre = 400,
                                                dist_pass_thres = 7, 
                                                num_stops_thre = 3,
                                                dist_pass_thres_perc = 0.7)

            #check entry point distance
            entry_pt_near = -1
            exit_pt_near = -1

            if start_idx-1>=0:
                if not np.isnan(lat[start_idx-1]):
                    nearest_station = find_nearest_station(lat[start_idx-1], lon[start_idx-1], self.train_location_tree, self.dist_thres_entry_exit)
                    if len(nearest_station)!=0:
                        entry_pt_near = 1
                    else:
                        entry_pt_near = 0

            if end_idx < len(modes):
                if not np.isnan(lat[end_idx]):
                    nearest_station = find_nearest_station(lat[end_idx],lon[end_idx],
                                                           self.train_location_tree,
                                                           self.dist_thres_entry_exit)
                    if len(nearest_station)!=0:
                        exit_pt_near = 1
                    else:
                        exit_pt_near = 0
            if is_train or entry_pt_near + exit_pt_near == 2:
                modes[start_idx:end_idx] = MODE_TRAIN
            else:
                modes[start_idx:end_idx] = MODE_CAR
        return modes

def extract_coordinates():

	data = np.loadtxt(config_variables.name_of_time_series_promoter_file_for_TSS_start, dtype = str,  delimiter = '\t')	
	plus_strand = data[:, 4] == '+'
	minus_strand = np.invert(plus_strand)

	promoter_data = np.zeros_like(data).astype(int)[:,:4]
	promoter_data[plus_strand, 1] = data[plus_strand, 1].astype(int) - upstream_validation
	promoter_data[plus_strand, 2] = data[plus_strand, 1].astype(int) + downstream_validation
	
	promoter_data[minus_strand, 2] = data[minus_strand, 2].astype(int) + upstream_validation
	promoter_data[minus_strand, 1] = data[minus_strand, 2].astype(int) - downstream_validation

	promoter_data = promoter_data.astype(str)
	promoter_data[:, 0] = data[:, 0]

	#--------------------
	ER_promoters = np.loadtxt("{0}ER_controled_promoters_pindexed.txt".format(temp_output), dtype = str, delimiter = '\t')
	Non_ER_promoters = np.loadtxt("{0}Non_ER_controled_promoters_pindexed.txt".format(temp_output), dtype = str, delimiter = '\t')
	def un_string(array_to_clean):  return np.array(map(lambda x: int(re.findall('\d+', x)[0]), array_to_clean))
	ER_promoters_indexes = un_string(ER_promoters[:, 3])

	ER_promoters_indexes_mask = np.zeros(len(data), bool)
	ER_promoters_indexes_mask[ER_promoters_indexes] = True 

	promoter_data[np.invert(ER_promoters_indexes_mask), 3] = Non_ER_promoters[:,-1]
	promoter_data[ER_promoters_indexes_mask, 3] = ER_promoters[:,-1]
	
	np.savetxt("{0}ER_controled_promoters_pindexed_2.txt".format(temp_output), promoter_data[ER_promoters_indexes_mask], fmt = "%s", delimiter = "\t")
	np.savetxt("{0}Non_ER_controled_promoters_pindexed_2.txt".format(temp_output), promoter_data[np.invert(ER_promoters_indexes_mask)], fmt = "%s", delimiter = "\t")

def enrichment_apply_fn(row, timepoints):
    """
    :py:meth:`pandas.DataFrame.apply` apply function for calculating 
    enrichment scores and r-squared values.
    """
    if math.isnan(row[0]):
        # not present in input library
        score = float("NaN")
        r_sq = float("NaN")
    else:
        row = row.values
        ratios = row[np.invert(np.isnan(row))]
        times = timepoints[np.invert(np.isnan(row))]
        if len(ratios) == 1:
            # only present in input library
            score = float("NaN")
            r_sq = float("NaN")
        elif len(ratios) == 2:
            # rise over run
            score = (ratios[1] - ratios[0]) / (times[1] - times[0])
            r_sq = float("NaN")
        else:
            score, _, r, _, _ = stats.linregress(times, ratios)
            r_sq = r ** 2

    return pd.Series({'score' : score, 'r_sq' : r_sq})