sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..'))
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
#----------------------------Example Simple--------------------------------------
#import needed packages
import numpy as np
from teaspoon.SP.network import knn_graph
from teaspoon.TDA.PHN import PH_network
#generate a siple sinusoidal time series
t = np.linspace(0, 30, 300)
ts = np.sin(t) + np.sin(2 * t)
#create adjacency matrix, this
A = knn_graph(ts)
#create distance matrix and calculate persistence diagram
D, diagram = PH_network(A, method='unweighted', distance='shortest_path')
print('1-D Persistent Homology (loops): ', diagram[1])
stats = point_summaries(diagram, A)
print('Persistent homology of network statistics: ', stats)
#---------------------------Complex Example---------------------------------------
#import needed packages
import numpy as np
from teaspoon.SP.network import ordinal_partition_graph
from teaspoon.TDA.PHN import PH_network
plt.plot(embedded_ts.T[0][NN], embedded_ts.T[1][NN], 'rs') #plot NN
plt.plot(embedded_ts.T[0][i], embedded_ts.T[1][i],
'bd') #plot point of interest
plt.show()
# In[ ]: make graph from time series
#import needed packages
import numpy as np
from teaspoon.SP.network import knn_graph
from teaspoon.SP.network import ordinal_partition_graph
t = np.linspace(0, 30, 200)
ts = np.sin(t) + np.sin(2 * t) #generate a simple time series
A_knn = knn_graph(ts) #ordinal partition network from time series
A_op = ordinal_partition_graph(ts) #knn network from time series
#ANOTHER EXAMPLE
t = np.linspace(0, 30, 200)
ts = np.sin(t) + np.sin(2 * t) #generate a simple time series
from teaspoon.SP.network import knn_graph
A = knn_graph(ts)
from teaspoon.SP.network_tools import make_network
G, pos = make_network(A)
import matplotlib.pyplot as plt