Using the new formulation of the Cluster and SVD classes

jupyter_notebooks/Ptychography.ipynb

@@ -25,10 +25,12 @@
 import numpy as np
 import matplotlib.pyplot as plt
 import matplotlib.patches as patches
 from IPython.display import display, HTML
 import ipywidgets as widgets
+from sklearn.cluster import KMeans
+    
 import pycroscopy as px
 
 # set up notebook to show plots within the notebook
 % matplotlib notebook
 
@@ -167,18 +169,19 @@
 Here, SVD essentially compares every single ronchigram with every other ronchigram to find statistically significant trends in the dataset. Such correlation would be infeasible if the ronchigrams were averaged to bright-field and dark-field scalar values. 
 
 %% Cell type:code id: tags:
 
 ``` python
+proc = px.SVD(h5_main, num_comps=256)
+
 # First check if SVD was already computed on this dataset:
-h5_svd_group = px.hdf_utils.findH5group(h5_main, 'SVD')
-if len(h5_svd_group) == 0:
+if proc.duplicate_h5_groups is None:
     print('No prior SVD results found - doing SVD now')
-    h5_svd_group = px.doSVD(h5_main, num_comps=256)
+    h5_svd_group = proc.compute()
 else:
     print('Taking previous SVD results already present in file')
-    h5_svd_group = h5_svd_group[-1]
+    h5_svd_group = proc.duplicate_h5_groups[-1]
     
 h5_u = h5_svd_group['U']
 h5_v = h5_svd_group['V']
 h5_s = h5_svd_group['S']
 num_comps = 16
@@ -241,20 +244,22 @@
 
 %% Cell type:code id: tags:
 
 ``` python
 # Attempt to find any previous computation
-h5_kmeans_group = px.hdf_utils.findH5group(h5_u, 'Cluster')
-if len(h5_kmeans_group) == 0:
+num_clusters = 32
+spectral_components = 128
+estimator = KMeans(n_clusters=num_clusters)
+
+proc = px.Cluster(h5_u, estimator, num_comps=spectral_components)
+
+if proc.duplicate_h5_groups is None:
     print('No k-Means computation found. Doing K-Means now')
-    num_clusters = 32
-    num_comps_for_clustering = 128
-    estimator = px.Cluster(h5_u, 'KMeans', num_comps=num_comps_for_clustering, n_clusters=num_clusters)
-    h5_kmeans_group = estimator.do_cluster()
+    h5_kmeans_group = proc.compute()
 else:
     print('Taking existing results of previous K-Means computation')
-    h5_kmeans_group = h5_kmeans_group[-1]
+    h5_kmeans_group = proc.duplicate_h5_groups[-1]
     
 h5_labels = h5_kmeans_group['Labels']
 h5_centroids = h5_kmeans_group['Mean_Response']
 
 # In case we take existing results, we need to get these parameters
@@ -281,11 +286,11 @@
 The vertical length of the branches indicates the relative separation between neighboring clusters.
 
 %% Cell type:code id: tags:
 
 ``` python
-e_vals = np.reshape(h5_u[:, :num_comps_for_clustering], 
+e_vals = np.reshape(h5_u[:, :spectral_components], 
                     (num_rows, num_cols, -1))
 fig = px.plot_utils.plot_cluster_dendrogram(label_mat, e_vals, 
                                             num_comps_for_clustering, 
                                             num_clusters, 
                                             last=num_clusters);