Fixed bugs related to plot_utils, SVD, and kMeans changes

jupyter_notebooks/Image_Cleaning_Atom_Finding.ipynb

@@ -21,7 +21,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "!pip install -U numpy scipy skimage h5py matplotlib Ipython ipywidgets pycroscopy\n",
@@ -75,7 +77,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "image_path = px.io.uiGetFile('*.png *PNG *TIFF * TIF *tif *tiff *BMP *bmp','Images')\n",
@@ -103,7 +107,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "# Check if an HDF5 file with the chosen image already exists.\n",
@@ -151,7 +157,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "print('Datasets and datagroups within the file:')\n",
@@ -181,7 +189,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# Initialize the windowing class\n",
@@ -209,14 +219,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "fig, axis = plt.subplots(figsize=(10,10))\n",
-    "img = axis.imshow(raw_image_mat,cmap=px.plot_utils.cmap_jet_white_center(), origin='lower');\n",
-    "divider = make_axes_locatable(axis)\n",
-    "cax = divider.append_axes(\"right\", size=\"5%\", pad=0.2)\n",
-    "plt.colorbar(img, cax=cax)\n",
+    "px.plot_utils.plot_map(axis, raw_image_mat, cmap=px.plot_utils.cmap_jet_white_center())\n",
     "axis.set_title('Raw Image', fontsize=16);"
    ]
   },
@@ -230,7 +239,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "num_peaks = 2\n",
@@ -242,7 +253,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "# Uncomment this line if you need to manually specify a window size\n",
@@ -251,15 +264,13 @@
     "# plot a single window\n",
     "row_offset = int(0.5*(num_x-win_size))\n",
     "col_offset = int(0.5*(num_y-win_size))\n",
-    "plt.figure()\n",
-    "plt.imshow(raw_image_mat[row_offset:row_offset+win_size,\n",
-    "                         col_offset:col_offset+win_size], \n",
-    "           cmap=px.plot_utils.cmap_jet_white_center(),\n",
-    "           origin='lower');\n",
-    "\n",
+    "fig, axis = plt.subplots(figsize=(5, 5))\n",
+    "px.plot_utils.plot_map(axis, raw_image_mat[row_offset:row_offset+win_size,\n",
+    "                                           col_offset:col_offset+win_size], \n",
+    "                       cmap=px.plot_utils.cmap_jet_white_center())\n",
     "# the result should be about the size of a unit cell\n",
     "# if it is the wrong size, just choose on manually by setting the win_size\n",
-    "plt.show()"
+    "axis.set_title('Example window', fontsize=18);"
    ]
   },
   {
@@ -273,7 +284,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "windowing_parms = {\n",
@@ -310,7 +323,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "# Peek at a few random windows\n",
@@ -322,7 +337,7 @@
     "    example_wins[:, :, rand_ind] = np.reshape(h5_wins[rand_pos], (windowing_parms['win_x'], windowing_parms['win_y']))\n",
     "    \n",
     "px.plot_utils.plot_map_stack(example_wins, heading='Example Windows', cmap=px.plot_utils.cmap_jet_white_center(),\n",
-    "                             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);"
    ]
   },
   {
@@ -338,7 +353,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "# check to make sure number of components is correct:\n",
@@ -346,15 +363,14 @@
     "num_comp = min(num_comp, \n",
     "                min(h5_wins.shape)*len(h5_wins.dtype))\n",
     "\n",
-    "proc = px.SVD(h5_main, num_comps=num_comp)\n",
+    "proc = px.processing.SVD(h5_wins, num_components=num_comp)\n",
     "\n",
-    "# First check if SVD was already computed on this dataset:\n",
     "if proc.duplicate_h5_groups is None:\n",
-    "    print('SVD was either not performed or was performed with different parameters')\n",
+    "    print('SVD not performed with these parameters')\n",
     "    h5_svd = proc.compute()\n",
     "else:\n",
-    "    print('Taking previous SVD results already present in file')\n",
-    "    h5_svd = proc.duplicate_h5_groups[-1]\n",
+    "    print('Taking existing results!')\n",
+    "    h5_svd = proc.duplicate_h5_groups  \n",
     "    \n",
     "h5_U = h5_svd['U']\n",
     "h5_S = h5_svd['S']\n",
@@ -392,10 +408,12 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
-    "fig_S, ax_S = px.plot_utils.plotScree(h5_S[()]);"
+    "fig_S, ax_S = px.plot_utils.plot_scree(h5_S[()]);"
    ]
   },
   {
@@ -410,7 +428,8 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "scrolled": true
+    "collapsed": false,
+    "scrolled": false
    },
    "outputs": [],
    "source": [
@@ -431,7 +450,8 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "scrolled": true
+    "collapsed": false,
+    "scrolled": false
    },
    "outputs": [],
    "source": [
@@ -456,7 +476,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "clean_components = range(36) # np.append(range(5,9),(17,18))\n",
@@ -486,7 +508,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# Building a stack of images from here:\n",
@@ -522,7 +546,8 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "scrolled": true
+    "collapsed": false,
+    "scrolled": false
    },
    "outputs": [],
    "source": [
@@ -544,6 +569,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "collapsed": false,
     "scrolled": false
    },
    "outputs": [],
@@ -608,19 +634,16 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
-    "num_comps = 12\n",
+    "num_comps = 24\n",
     "\n",
     "fig, axis = plt.subplots(figsize=(7, 7))\n",
     "clean_image_mat = image_components[:, :, num_comps]\n",
-    "img_clean = axis.imshow(clean_image_mat, cmap=px.plot_utils.cmap_jet_white_center(), origin='lower')\n",
-    "mean_val = np.mean(clean_image_mat)\n",
-    "std_val = np.std(clean_image_mat)\n",
-    "img_clean.set_clim(vmin=mean_val-img_stdevs*std_val, vmax=mean_val+img_stdevs*std_val)\n",
-    "axis.get_yaxis().set_visible(False)\n",
-    "axis.get_xaxis().set_visible(False)\n",
+    "_ = px.plot_utils.plot_map(axis, clean_image_mat, cmap=px.plot_utils.cmap_jet_white_center())\n",
     "axis.set_title('Cleaned Image', fontsize=16);"
    ]
   },
@@ -641,25 +664,22 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "collapsed": false,
     "scrolled": false
    },
    "outputs": [],
    "source": [
-    "clean_components = 32\n",
-    "num_clusters = 32\n",
+    "num_clusters = 4\n",
+    "estimator = px.Cluster(h5_U, KMeans(n_clusters=num_clusters), num_comps=num_comps)\n",
     "\n",
-    "proc = px.Cluster(h5_U, KMeans(n_clusters=num_clusters), num_comps=clean_components)\n",
-    "\n",
-    "# Check for existing Clustering results\n",
-    "if proc.duplicate_h5_groups is None:\n",
-    "    print('No k-Means computation found. Doing K-Means now')\n",
+    "if estimator.duplicate_h5_groups is None:\n",
     "    t0 = time()\n",
-    "    h5_kmeans = proc.compute()\n",
+    "    h5_kmeans = estimator.compute()\n",
     "    print('kMeans took {} seconds.'.format(round(time()-t0, 2)))\n",
     "else:\n",
-    "    print('Taking existing results of previous K-Means computation')\n",
-    "    h5_kmeans = proc.duplicate_h5_groups[-1]\n",
-    "\n",
+    "    h5_kmeans = estimator.duplicate_h5_groups[-1]\n",
+    "    print( 'Using existing results.') \n",
+    "    \n",
     "print( 'Clustering results in {}.'.format(h5_kmeans.name))\n",
     "\n",
     "half_wind = int(win_size*0.5)\n",
@@ -691,14 +711,16 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# Plot dendrogram here\n",
-    "# Get the distrance between cluster means \n",
+    "#Get the distrance between cluster means \n",
     "distance_mat = pdist(h5_kmeans['Mean_Response'][()]) \n",
     " \n",
-    "# get hierachical pairings of clusters \n",
+    "#get hierachical pairings of clusters \n",
     "linkage_pairing = linkage(distance_mat,'weighted') \n",
     "\n",
     "# Normalize the pairwise distance with the maximum distance\n",
@@ -708,7 +730,7 @@
     "fig = plt.figure(figsize=(10,3)) \n",
     "retval = dendrogram(linkage_pairing, count_sort=True, \n",
     "           distance_sort=True, leaf_rotation=90) \n",
-    "# fig.axes[0].set_title('Dendrogram') \n",
+    "#fig.axes[0].set_title('Dendrogram') \n",
     "fig.axes[0].set_xlabel('Cluster number', fontsize=20) \n",
     "fig.axes[0].set_ylabel('Cluster separation', fontsize=20)\n",
     "px.plot_utils.set_tick_font_size(fig.axes[0], 12)"
@@ -728,6 +750,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "collapsed": true,
     "scrolled": false
    },
    "outputs": [],
@@ -827,6 +850,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "collapsed": true,
     "scrolled": false
    },
    "outputs": [],
@@ -882,7 +906,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "motif_match_coeffs = list()\n",
@@ -915,7 +941,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "show_legend = True\n",
@@ -962,6 +990,7 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "collapsed": true,
     "scrolled": false
    },
    "outputs": [],
@@ -1036,7 +1065,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "print(thresholds)\n",
@@ -1061,7 +1092,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# overlay atom positions on original image\n",
@@ -1101,7 +1134,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "h5_file.close()"
@@ -1110,7 +1145,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }
@@ -1119,7 +1156,7 @@
   "anaconda-cloud": {},
   "celltoolbar": "Raw Cell Format",
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [default]",
    "language": "python",
    "name": "python3"
   },
@@ -1133,61 +1170,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.3"
-  },
-  "widgets": {
-   "state": {
-    "29604cba705348bebab931e8c5a8f33b": {
-     "views": [
-      {
-       "cell_index": 41.0
-      }
-     ]
-    },
-    "3148e6a4894e42d2856f6c31aa70805a": {
-     "views": [
-      {
-       "cell_index": 33.0
-      }
-     ]
-    },
-    "4c6e4e0c659542ca937b2ca85f7f33cf": {
-     "views": [
-      {
-       "cell_index": 49.0
-      }
-     ]
-    },
-    "9236753466b34d9eb471907b4a33fd73": {
-     "views": [
-      {
-       "cell_index": 38.0
-      }
-     ]
-    },
-    "ba247d838fef4411b7c74d7055033284": {
-     "views": [
-      {
-       "cell_index": 38.0
-      }
-     ]
-    },
-    "bafd596f9f254b4a8652bbf8e7bdc096": {
-     "views": [
-      {
-       "cell_index": 41.0
-      }
-     ]
-    },
-    "e687973fb1ff41949de8de5587ad6461": {
-     "views": [
-      {
-       "cell_index": 38.0
-      }
-     ]
-    }
-   },
-   "version": "1.2.0"
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,