Python plotting.plot_connectome函数代码示例

def plot_connectivity_glassbrain(subject_id, group, pc, roi_coords,
                                 suffix, session='func1',
                                 preprocessing_folder='pipeline_1',
                                 save=True, msdl=False):
    """Plots connectome of pc
    """
    title = '-'.join([suffix, group, subject_id, session])
    
    output_folder = os.path.join(set_figure_base_dir('connectivity'), suffix)
    if not os.path.isdir(output_folder):
        os.makedirs(output_folder)
    
    output_file = os.path.join(output_folder,
                               '_'.join([suffix, 'connectome', group,
                                         session,
                                         preprocessing_folder, subject_id]))
                                         
    if msdl:
        title += '_msdl'
        output_file += '_msdl'
                                         
    plt.figure(figsize=(10, 20), dpi=90)
    if save:    
        plot_connectome(pc, roi_coords, edge_threshold='90%', title=title,
                        output_file=output_file)
    else:
        plot_connectome(pc, roi_coords, edge_threshold='90%', title=title)

    def plot_cluster_freqs_on_brain(self, cluster_name, xyz, colormap='viridis', vmin=None, vmax=None, do_3d=False):
        """
        Plot the frequencies of single electrode cluster on either a 2d or interactive 2d brain.

        Parameters
        ----------
        cluster_name: str
            Name of column in self.res['clusters']
        xyz: np.ndarray
            3 x n array of electrode locations. Should be in MNI space.
        colormap: str
            matplotlib colormap name
        vmin: float
            lower limit of colormap values. If not given, lowest value in frequency column will be used
        vmax: float
            upper limit of colormap values. If not given, highest value in frequency column will be used
        do_3d:
            Whether to plot an interactive 3d brain, or a 2d brain

        Returns
        -------
        If 2d, returns the matplotlib figure. If 3d, returns the html used to render the brain.
        """

        # get frequecies for this cluster
        freqs = self.res['clusters'][cluster_name].values

        # get color for each frequency. Start with all black
        colors = np.stack([[0., 0., 0., 0.]] * len(freqs))

        # fill in colors of electrodes with defined frequencies
        cm = plt.get_cmap(colormap)
        cNorm = clrs.Normalize(vmin=np.nanmin(freqs) if vmin is None else vmin,
                               vmax=np.nanmax(freqs) if vmax is None else vmax)
        colors[~np.isnan(freqs)] = cmx.ScalarMappable(norm=cNorm, cmap=cm).to_rgba(freqs[~np.isnan(freqs)])

        # if plotting 2d, use the nilearn glass brain
        if not do_3d:
            fig, ax = plt.subplots()
            ni_plot.plot_connectome(np.eye(xyz.shape[0]), xyz,
                                    node_kwargs={'alpha': 0.7, 'edgecolors': None},
                                    node_size=60, node_color=colors, display_mode='lzr',
                                    axes=ax)
            divider = make_axes_locatable(ax)
            cax = divider.append_axes('bottom', size='4%', pad=0)
            cb1 = mpl.colorbar.ColorbarBase(cax, cmap=colormap,
                                            norm=cNorm,
                                            orientation='horizontal')
            cb1.set_label('Frequency', fontsize=20)
            cb1.ax.tick_params(labelsize=14)
            fig.set_size_inches(15, 10)
            return fig

        # if plotting 3d use the nilearn 3d brain. Unfortunately this doesn't add a colorbar.
        else:
            # you need to return the html. If in jupyter, it will automatically render
            return ni_plot.view_markers(xyz, colors=colors, marker_size=6)

def run_mini_pipeline():
    atlas = datasets.fetch_atlas_msdl()
    atlas_img = atlas['maps']
    labels = pd.read_csv(atlas['labels'])['name']

    masker = NiftiMapsMasker(maps_img=atlas_img, standardize=True,
                               memory='/tmp/nilearn', verbose=0)

    data = datasets.fetch_adhd(number_subjects)

    figures_folder = '../figures/'
    count=0
    for func_file, confound_file in zip(data.func, data.confounds):
        
        # fit the data to the atlas mask, regress out confounds
        time_series = masker.fit_transform(func_file, confounds=confound_file)

        correlation = np.corrcoef(time_series.T)

        #plotting starts here
        plt.figure(figsize=(10, 10))
        plt.imshow(correlation, interpolation="nearest")
        x_ticks = plt.xticks(range(len(labels)), labels, rotation=90)
        y_ticks = plt.yticks(range(len(labels)), labels)
        corr_file = figures_folder+'subject_number_' + str(count) + '_correlation.pdf'
        plt.savefig(corr_file)

        atlas_region_coords = [plotting.find_xyz_cut_coords(img) for img in image.iter_img(atlas_img)]
        threshold = 0.6
        plotting.plot_connectome(correlation, atlas_region_coords, edge_threshold=threshold)
        connectome_file = figures_folder+'subject_number_' + str(count) + '_connectome.pdf'
        plt.savefig(connectome_file)


        #graph setup

        #binarize correlation matrix
        correlation[correlation<threshold] = 0
        correlation[correlation != 0] = 1

        graph = nx.from_numpy_matrix(correlation)

        partition=louvain.best_partition(graph)

        values = [partition.get(node) for node in graph.nodes()]

        plt.figure()
        nx.draw_spring(graph, cmap = plt.get_cmap('jet'), node_color = values, node_size=30, with_labels=True)
        graph_file = figures_folder+'subject_number_' + str(count) + '_community.pdf'
        plt.savefig(graph_file)

        count += 1

        plt.close('all')

###############################################################################
# Plot matrix and graph
# ---------------------
#
# We use `matplotlib` plotting functions to visualize our correlation matrix
# and display the graph of connections with `nilearn.plotting.plot_connectome`.
import matplotlib.pyplot as plt
from nilearn import plotting

plt.imshow(matrix, vmin=-1.0, vmax=1.0, cmap="RdBu_r", interpolation="nearest")
plt.colorbar()
plt.title("Power correlation matrix")

# Tweak edge_threshold to keep only the strongest connections.
plotting.plot_connectome(
    matrix, coords, title="Power correlation graph", edge_threshold="99.8%", node_size=20, colorbar=True
)

###############################################################################
# Note the 1. on the matrix diagonal: These are the signals variances, set to
# 1. by the `spheres_masker`. Hence the covariance of the signal is a
# correlation matrix

###############################################################################
# Connectome extracted from Dosenbach's atlas
# -------------------------------------------
#
# We repeat the same steps for Dosenbach's atlas.
dosenbach = datasets.fetch_coords_dosenbach_2010()

coords = np.vstack((dosenbach.rois["x"], dosenbach.rois["y"], dosenbach.rois["z"])).T

# All individual coefficients are stacked in a unique 2D matrix.
print('Correlations of ADHD patients are stacked in an array of shape {0}'
      .format(correlation_matrices.shape))

###############################################################################
# as well as the average correlation across all fitted subjects.
mean_correlation_matrix = correlation_measure.mean_
print('Mean correlation has shape {0}.'.format(mean_correlation_matrix.shape))

###############################################################################
# We display the connectomes of the first 3 ADHD subjects and the mean
# correlation matrix over all ADHD patients.
from nilearn import plotting

plot_matrices(correlation_matrices[:4], 'correlation')
plotting.plot_connectome(mean_correlation_matrix, msdl_coords,
                         title='mean correlation over 13 ADHD subjects')

###############################################################################
# Look at blocks structure, reflecting functional networks.

###############################################################################
# Examine partial correlations
# ----------------------------
# We can also study **direct connections**, revealed by partial correlation
# coefficients. We just change the `ConnectivityMeasure` kind
partial_correlation_measure = ConnectivityMeasure(kind='partial correlation')

###############################################################################
# and repeat the previous operation.
partial_correlation_matrices = partial_correlation_measure.fit_transform(
    adhd_subjects)

# The covariance can be found at estimator.covariance_
plt.imshow(estimator.covariance_, interpolation="nearest",
           vmax=1, vmin=-1, cmap=plt.cm.RdBu_r)
# And display the labels
x_ticks = plt.xticks(range(len(labels)), labels, rotation=90)
y_ticks = plt.yticks(range(len(labels)), labels)
plt.title('Covariance')

##############################################################################
# And now display the corresponding graph
# ----------------------------------------
from nilearn import plotting
coords = atlas.region_coords

plotting.plot_connectome(estimator.covariance_, coords,
                         title='Covariance')


##############################################################################
# Display the sparse inverse covariance
# --------------------------------------
# we negate it to get partial correlations
plt.figure(figsize=(10, 10))
plt.imshow(-estimator.precision_, interpolation="nearest",
           vmax=1, vmin=-1, cmap=plt.cm.RdBu_r)
# And display the labels
x_ticks = plt.xticks(range(len(labels)), labels, rotation=90)
y_ticks = plt.yticks(range(len(labels)), labels)
plt.title('Sparse inverse covariance')

##############################################################################

masker = NiftiMapsMasker(maps_img=atlas_filename, standardize=True,
                           memory='nilearn_cache', verbose=5)

data = datasets.fetch_adhd(n_subjects=1)

time_series = masker.fit_transform(data.func[0],
                                   confounds=data.confounds)

correlation_matrix = np.corrcoef(time_series.T)

# Display the correlation matrix
from matplotlib import pyplot as plt
plt.figure(figsize=(10, 10))
plt.imshow(correlation_matrix, interpolation="nearest")
# And display the labels
x_ticks = plt.xticks(range(len(names)), names, rotation=90)
y_ticks = plt.yticks(range(len(names)), names)

# And now display the corresponding graph
from nilearn import plotting
coords = np.vstack((labels['x'], labels['y'], labels['z']))

# We threshold to keep only the 20% of edges with the highest value
# because the graph is very dense
plotting.plot_connectome(correlation_matrix, coords.T,
                         edge_threshold="80%")

plt.show()

__author__ = '2d Lt Kyle Palko'

import numpy as np
from nilearn import plotting as plt

# import Pitt 0050013, a young autistic subject
ts = np.genfromtxt('/media/kap/8e22f6f8-c4df-4d97-a388-0adcae3ec1fb/Python/Thesis/C200/ABIDE_pcp/cpac/filt_noglobal/'
                   'Pitt_0050013_rois_cc200.1D', skip_header=1)
cor = np.corrcoef(ts.T)

# create matrix
x = np.zeros((200, 200))
for i in range(0, np.size(x, axis=0)):
    x[i][i] = 1

a = np.genfromtxt('cc200_roi.csv', delimiter=',')
row = np.array([c[0] for c in a])
col = np.array([c[1] for c in a])
del a

for i in range(0, 10):
    r = row[i]
    c = col[i]
    x[r, c] = cor[r, c]
    x[c, r] = cor[c, r]

node_coords = np.genfromtxt('cc200_lab_coord.csv', delimiter=',')
plt.plot_connectome(x, node_coords, output_file='corrtest_1.png', node_size=1)

    if kind == 'tangent':
        mean_connectivity_matrix[kind] = conn_measure.mean_
    else:
        mean_connectivity_matrix[kind] = \
            individual_connectivity_matrices[kind].mean(axis=0)


######################################################################
# Plot the mean connectome with hemispheric saggital cuts
import numpy as np
from nilearn import plotting
labels = atlas.labels
region_coords = atlas.region_coords
for kind in kinds:
    plotting.plot_connectome(mean_connectivity_matrix[kind],
                             region_coords, edge_threshold='98%',
                             title=kind, display_mode='lzry')


######################################################################
# Use the connectivity coefficients to classify ADHD vs controls
from sklearn.svm import LinearSVC
from sklearn.cross_validation import StratifiedKFold, cross_val_score
classes = ['{0}{1}'.format(site, adhd) for site, adhd in zip(sites, adhds)]
print('Classification accuracy:')
mean_scores = []
cv = StratifiedKFold(classes, n_folds=3)
for kind in kinds:
    svc = LinearSVC()
    # Transform the connectivity matrices to 1D arrays
    coonectivity_coefs = connectome.sym_to_vec(

plt.tight_layout()


##########################################################################
# Compute partial correlation matrix
# -----------------------------------
# Using object :class:`nilearn.connectome.ConnectivityMeasure`: Its
# default covariance estimator is Ledoit-Wolf, allowing to obtain accurate
# partial correlations.
from nilearn.connectome import ConnectivityMeasure
connectivity_measure = ConnectivityMeasure(kind='partial correlation')
partial_correlation_matrix = connectivity_measure.fit_transform(
    [time_series])[0]

##########################################################################
# Display connectome
# -------------------
from nilearn import plotting

plotting.plot_connectome(partial_correlation_matrix, dmn_coords,
                         title="Default Mode Network Connectivity")

##########################################################################
# Display connectome with hemispheric projections.
# Notice (0, -52, 18) is included in both hemispheres since x == 0.
plotting.plot_connectome(partial_correlation_matrix, dmn_coords,
                         title="Connectivity projected on hemispheres",
                         display_mode='lyrz')

plotting.show()

for time_serie, label in zip(time_series.T, labels):
    plt.plot(time_serie, label=label)

plt.title("Default Mode Network Time Series")
plt.xlabel("Scan number")
plt.ylabel("Normalized signal")
plt.legend()
plt.tight_layout()


##########################################################################
# Compute precision matrices
from sklearn.covariance import LedoitWolf

cve = LedoitWolf()
cve.fit(time_series)


##########################################################################
# Display connectome
from nilearn import plotting

plotting.plot_connectome(cve.precision_, dmn_coords, title="Default Mode Network Connectivity")

# Display connectome with hemispheric projections.
# Notice (0, -52, 18) is included in both hemispheres since x == 0.
title = "Connectivity projected on hemispheres"
plotting.plot_connectome(cve.precision_, dmn_coords, title=title, display_mode="lyrz")

plotting.show()

from nilearn.connectome import ConnectivityMeasure
connectivity_measure = ConnectivityMeasure(kind='partial correlation')
partial_correlation_matrix = connectivity_measure.fit_transform(
    [time_series])[0]


##########################################################################
# Display connectome
# -------------------
#
# We display the graph of connections with `:func: nilearn.plotting.plot_connectome`.

from nilearn import plotting

plotting.plot_connectome(partial_correlation_matrix, dmn_coords,
                         title="Default Mode Network Connectivity")


##########################################################################
# Display connectome with hemispheric projections.
# Notice (0, -52, 18) is included in both hemispheres since x == 0.
plotting.plot_connectome(partial_correlation_matrix, dmn_coords,
                         title="Connectivity projected on hemispheres",
                         display_mode='lyrz')

plotting.show()


##############################################################################
# 3D visualization in a web browser
# ---------------------------------

roi_names, roi_coords = load_msdl_names_and_coords()
stat_av = read_test('pc', 'av', 'avg')
stat_v = read_test('pc', 'v', 'avg')
stat2 = read_test2('pc', ['av', 'v'], 'avg')


i, j = np.unravel_index(stat2.argmax(), stat2.shape)
print 'av 1sample pval :', stat_av[i, j]
print 'v 1sample pval :', stat_v[i, j]
print roi_names[i], roi_names[j]
print i, j

m = np.eye(2)
m[1,0] = stat2[i, j]
m[0,1] = m[1,0] 
plot_connectome(m, [roi_coords[i], roi_coords[j]])


conn = []
behav = []
for i in range(len(dataset.subjects)):
    c = load_dynacomp_fc(dataset.subjects[i], session='func1', metric='pc', msdl=True)
    conn.append(c[i, j])
    b = behav_data[i]['postRT'] - behav_data[i]['preRT']
    behav.append(b)

sns.jointplot(np.array(conn), np.array(behav), kind='kde')
sns.axlabel('Connectivity', 'Behavior')

###############################################################################
# Extract and plot correlation matrix

# calculate connectivity and plot Power-264 correlation matrix
connectivity = connectome.ConnectivityMeasure(kind='correlation')
corr_matrix = connectivity.fit_transform([timeseries])[0]
np.fill_diagonal(corr_matrix, 0)
plt.imshow(corr_matrix, vmin=-1., vmax=1., cmap='RdBu_r')
plt.colorbar()
plt.title('Power 264 Connectivity')

# Plot the connectome

plotting.plot_connectome(corr_matrix,
                         power_coords,
                         edge_threshold='99.8%',
                         node_size=20)


###############################################################################
# Extract and plot covariance and sparse covariance

# Compute the sparse inverse covariance
from sklearn.covariance import GraphLassoCV

estimator = GraphLassoCV()
estimator.fit(timeseries)

# Display the covariance
plt.figure(figsize=(5, 5))
plt.imshow(estimator.covariance_, interpolation="nearest",

###############################################################################
# as well as the average correlation across all fitted subjects.
mean_correlation_matrix = correlation_measure.mean_
print('Mean correlation has shape {0}.'.format(mean_correlation_matrix.shape))

###############################################################################
# We display the connectome matrices of the first 4 children
from nilearn import plotting

plot_matrices(correlation_matrices[:4], 'correlation')
###############################################################################
# The blocks structure that reflect functional networks are visible.

###############################################################################
# Now we display as a connectome the mean correlation matrix over all children.
plotting.plot_connectome(mean_correlation_matrix, msdl_coords,
                         title='mean correlation over all children')

###############################################################################
# Studying partial correlations
# -----------------------------
# We can also study **direct connections**, revealed by partial correlation
# coefficients. We just change the `ConnectivityMeasure` kind
partial_correlation_measure = ConnectivityMeasure(kind='partial correlation')

###############################################################################
# and repeat the previous operation.
partial_correlation_matrices = partial_correlation_measure.fit_transform(
    children)

###############################################################################
# Most of direct connections are weaker than full connections,