Fixed bugs related to plot_utils, SVD, and kMeans changes

jupyter_notebooks/Image_Cleaning_Atom_Finding.ipynb

@@ -170,14 +170,11 @@
 
 %% Cell type:code id: tags:
 
 ``` python
 fig, axis = plt.subplots(figsize=(10,10))
-img = axis.imshow(raw_image_mat,cmap=px.plot_utils.cmap_jet_white_center(), origin='lower');
-divider = make_axes_locatable(axis)
-cax = divider.append_axes("right", size="5%", pad=0.2)
-plt.colorbar(img, cax=cax)
+px.plot_utils.plot_map(axis, raw_image_mat, cmap=px.plot_utils.cmap_jet_white_center())
 axis.set_title('Raw Image', fontsize=16);
 ```
 
 %% Cell type:markdown id: tags:
 
@@ -199,19 +196,17 @@
 # win_size = 8
 
 # plot a single window
 row_offset = int(0.5*(num_x-win_size))
 col_offset = int(0.5*(num_y-win_size))
-plt.figure()
-plt.imshow(raw_image_mat[row_offset:row_offset+win_size,
-                         col_offset:col_offset+win_size], 
-           cmap=px.plot_utils.cmap_jet_white_center(),
-           origin='lower');
-
+fig, axis = plt.subplots(figsize=(5, 5))
+px.plot_utils.plot_map(axis, raw_image_mat[row_offset:row_offset+win_size,
+                                           col_offset:col_offset+win_size], 
+                       cmap=px.plot_utils.cmap_jet_white_center())
 # the result should be about the size of a unit cell
 # if it is the wrong size, just choose on manually by setting the win_size
-plt.show()
+axis.set_title('Example window', fontsize=18);
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Now break the image into a sequence of small windows
@@ -261,11 +256,11 @@
 
 for rand_ind, rand_pos in enumerate(rand_positions):
     example_wins[:, :, rand_ind] = np.reshape(h5_wins[rand_pos], (windowing_parms['win_x'], windowing_parms['win_y']))
     
 px.plot_utils.plot_map_stack(example_wins, heading='Example Windows', cmap=px.plot_utils.cmap_jet_white_center(),
-                             title=['Window # ' + str(win_pos) for win_pos in rand_positions]);
+                             title=['Window # ' + str(win_pos) for win_pos in rand_positions], fig_title_yoffset=0.93);
 ```
 
 %% Cell type:markdown id: tags:
 
 ## Performing Singular Value Decompostion (SVD) on the windowed data
@@ -279,19 +274,18 @@
 # check to make sure number of components is correct:
 num_comp = 1024
 num_comp = min(num_comp, 
                 min(h5_wins.shape)*len(h5_wins.dtype))
 
-proc = px.SVD(h5_main, num_comps=num_comp)
+proc = px.processing.SVD(h5_wins, num_components=num_comp)
 
-# First check if SVD was already computed on this dataset:
 if proc.duplicate_h5_groups is None:
-    print('SVD was either not performed or was performed with different parameters')
+    print('SVD not performed with these parameters')
     h5_svd = proc.compute()
 else:
-    print('Taking previous SVD results already present in file')
-    h5_svd = proc.duplicate_h5_groups[-1]
+    print('Taking existing results!')
+    h5_svd = proc.duplicate_h5_groups  
     
 h5_U = h5_svd['U']
 h5_S = h5_svd['S']
 h5_V = h5_svd['V']
 
@@ -322,11 +316,11 @@
 Note also that the plot below is a log-log plot. The importance of each subsequent component drops exponentially.
 
 %% Cell type:code id: tags:
 
 ``` python
-fig_S, ax_S = px.plot_utils.plotScree(h5_S[()]);
+fig_S, ax_S = px.plot_utils.plot_scree(h5_S[()]);
 ```
 
 %% Cell type:markdown id: tags:
 
 #### V (Eigenvectors or end-members)
@@ -494,20 +488,15 @@
 ## Check the cleaned image now:
 
 %% Cell type:code id: tags:
 
 ``` python
-num_comps = 12
+num_comps = 24
 
 fig, axis = plt.subplots(figsize=(7, 7))
 clean_image_mat = image_components[:, :, num_comps]
-img_clean = axis.imshow(clean_image_mat, cmap=px.plot_utils.cmap_jet_white_center(), origin='lower')
-mean_val = np.mean(clean_image_mat)
-std_val = np.std(clean_image_mat)
-img_clean.set_clim(vmin=mean_val-img_stdevs*std_val, vmax=mean_val+img_stdevs*std_val)
-axis.get_yaxis().set_visible(False)
-axis.get_xaxis().set_visible(False)
+_ = px.plot_utils.plot_map(axis, clean_image_mat, cmap=px.plot_utils.cmap_jet_white_center())
 axis.set_title('Cleaned Image', fontsize=16);
 ```
 
 %% Cell type:markdown id: tags:
 
@@ -520,25 +509,21 @@
 We want a large enough number of clusters so that K-means identifies fine nuances in the data. At the same time, we want to minimize computational time by reducing the number of clusters. We recommend 32 - 64 clusters.
 
 %% Cell type:code id: tags:
 
 ``` python
-clean_components = 32
-num_clusters = 32
+num_clusters = 4
+estimator = px.Cluster(h5_U, KMeans(n_clusters=num_clusters), num_comps=num_comps)
 
-proc = px.Cluster(h5_U, KMeans(n_clusters=num_clusters), num_comps=clean_components)
-
-# Check for existing Clustering results
-if proc.duplicate_h5_groups is None:
-    print('No k-Means computation found. Doing K-Means now')
+if estimator.duplicate_h5_groups is None:
     t0 = time()
-    h5_kmeans = proc.compute()
+    h5_kmeans = estimator.compute()
     print('kMeans took {} seconds.'.format(round(time()-t0, 2)))
 else:
-    print('Taking existing results of previous K-Means computation')
-    h5_kmeans = proc.duplicate_h5_groups[-1]
-
+    h5_kmeans = estimator.duplicate_h5_groups[-1]
+    print( 'Using existing results.') 
+    
 print( 'Clustering results in {}.'.format(h5_kmeans.name))
 
 half_wind = int(win_size*0.5)
 # generate a cropped image that was effectively the area that was used for pattern searching
 # Need to get the math righ on the counting
@@ -564,24 +549,24 @@
 
 %% Cell type:code id: tags:
 
 ``` python
 # Plot dendrogram here
-# Get the distrance between cluster means 
+#Get the distrance between cluster means 
 distance_mat = pdist(h5_kmeans['Mean_Response'][()]) 
  
-# get hierachical pairings of clusters 
+#get hierachical pairings of clusters 
 linkage_pairing = linkage(distance_mat,'weighted') 
 
 # Normalize the pairwise distance with the maximum distance
 linkage_pairing[:,2] = linkage_pairing[:,2]/max(linkage_pairing[:,2]) 
 
 # Visualize dendrogram
 fig = plt.figure(figsize=(10,3)) 
 retval = dendrogram(linkage_pairing, count_sort=True, 
            distance_sort=True, leaf_rotation=90) 
-# fig.axes[0].set_title('Dendrogram') 
+#fig.axes[0].set_title('Dendrogram') 
 fig.axes[0].set_xlabel('Cluster number', fontsize=20) 
 fig.axes[0].set_ylabel('Cluster separation', fontsize=20)
 px.plot_utils.set_tick_font_size(fig.axes[0], 12)
 ```