def fit_transform(self, X, y=None, init=None):
mapper = km.KeplerMapper()
dist_matrix, lens, bp = mapper.fit_transform(
X, projection=self.filter_function, BP=self.BP)
graph = mapper.map(lens,
X,
clusterer=self.clusterer,
nr_cubes=self.nr_cubes,
overlap_perc=self.overlap_perc,
auto_tuning=self.auto_tuning)
landmarks = self._get_landmarks(graph)
Landmark, links = self._compute_skeleton(landmarks, X)
self.landmarks = Landmark
self.skeleton = links
self.basePoint = bp
self.lens = lens
X = X.tolist()
Index_of_landmarks = []
for i in range(0, len(Landmark)):
Index_of_landmarks.append((X.index(Landmark.tolist()[i])))
self.landmarks_indexes = Index_of_landmarks
Y, proj_landmark = self.Landmark_Isomap(X, 2, Index_of_landmarks,
dist_matrix)
return Y
import StringIO
from scipy.misc import imsave, toimage
import base64
tooltip_s = []
for image_data in data:
output = StringIO.StringIO()
img = toimage(image_data.reshape((8,8))) # Data was a flat row of 64 "pixels".
img.save(output, format="PNG")
contents = output.getvalue()
tooltip_s.append( """ <img src="data:image/png;base64,%s"> """%base64.b64encode(contents).replace("\n","") )
output.close()
tooltip_s = km.np.array(tooltip_s) # need to make sure to feed it as a NumPy array, not a list
# Initialize to use t-SNE with 2 components (reduces data to 2 dimensions). Also note high overlap_percentage.
mapper = km.KeplerMapper(cluster_algorithm=km.cluster.DBSCAN(eps=0.3, min_samples=15),
reducer = km.manifold.TSNE(), nr_cubes=35, overlap_perc=0.9,
link_local=False, verbose=2)
# Fit and transform data
data = mapper.fit_transform(data)
# Create the graph
complex = mapper.map(data, dimension_index=[0,1], dimension_name="t-SNE(2) 2D")
# Create the visualizations (increased the graph_gravity for a tighter graph-look.)
# Tooltips with image data for every cluster member
mapper.visualize(complex, "keplermapper_digits_custom_tooltips.html", "Digits", graph_gravity=0.25, custom_tooltips=tooltip_s)
# Tooltips with the target y-labels for every cluster member
mapper.visualize(complex, "keplermapper_digits_ylabel_tooltips.html", "Digits", graph_gravity=0.25, custom_tooltips=labels)
__copyright__ = "Copyright (C) 2017 Inria"
__license__ = "GPL v3"
parser = argparse.ArgumentParser(description='Creates an html Keppler Mapper '
'file to visualize a SC.txt file.',
epilog='Example: '
'./KeplerMapperVisuFromTxtFile.py '
'-f ../../data/points/human.off_sc.txt'
'- Constructs an human.off_sc.html file.')
parser.add_argument("-f", "--file", type=str, required=True)
args = parser.parse_args()
with open(args.file, 'r') as f:
network = {}
mapper = km.KeplerMapper(verbose=0)
data = np.zeros((3, 3))
projected_data = mapper.fit_transform(data, projection="sum", scaler=None)
nodes = defaultdict(list)
links = defaultdict(list)
custom = defaultdict(list)
dat = f.readline()
lens = f.readline()
color = f.readline()
param = [float(i) for i in f.readline().split(" ")]
nums = [int(i) for i in f.readline().split(" ")]
num_nodes = nums[0]
num_edges = nums[1]
import km
data = km.np.genfromtxt('horse-reference.csv',delimiter=',')
mapper = km.KeplerMapper(cluster_algorithm=km.cluster.DBSCAN(eps=0.3, min_samples=3), nr_cubes=25, link_local=False, overlap_perc=0.7, verbose=1)
mapper.fit(data)
complex = mapper.map(data, dimension_index=1, dimension_name="Y-axis")
mapper.visualize(complex, "horse_keplermapper_output.html", "horse-reference.csv")
# You may want to visualize the original point cloud data in 3D scatter too
"""
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(data[:,0],data[:,1],data[:,2])
plt.savefig("horse-reference.csv.png")
plt.show()
"""
import km
data = km.np.genfromtxt('cat-reference.csv',delimiter=',')
mapper = km.KeplerMapper()
lens = mapper.fit_transform(data)
graph = mapper.map(lens,
data,
clusterer=km.cluster.DBSCAN(eps=0.1, min_samples=5),
nr_cubes=15,
overlap_perc=0.2)
mapper.visualize(graph,
path_html="cat_keplermapper_output.html")
# You may want to visualize the original point cloud data in 3D scatter too
"""
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(data[:,0],data[:,1],data[:,2])
plt.savefig("cat-reference.csv.png")
plt.show()
"""
import km
data = km.np.genfromtxt('cat-reference.csv', delimiter=',')
mapper = km.KeplerMapper(cluster_algorithm=km.cluster.DBSCAN(eps=0.1,
min_samples=5),
nr_cubes=10,
overlap_perc=0.8,
verbose=1)
mapper.fit(data)
complex = mapper.map(data, dimension_index=1, dimension_name="Y-axis")
mapper.visualize(complex, "cat_keplermapper_output.html", "cat-reference.csv")
# You may want to visualize the original point cloud data in 3D scatter too
"""
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(data[:,0],data[:,1],data[:,2])
plt.savefig("cat-reference.csv.png")
plt.show()
"""
