[MRG] Lda training visualization in visdom

docs/notebooks/Training_visualizations.ipynb

@@ -131,7 +131,7 @@
     "\n",
     "**Coherence**\n",
     "\n",
-    "Coherence is a measure used to evaluate topic models. A good model will generate coherent topics, i.e., topics         with high topic coherence scores. Good topics are topics that can be described by a short label based on the topic     terms they spit out. \n",
+    "Coherence measures are generally based on the idea of computing the sum of pairwise scores of top *n* top words w<sub>1</sub>, ...,w<sub>n</sub> used to describe the topic. There are four coherence measure available in gensim: `u_mass, c_v, c_uci, c_npmi`. A good model will generate coherent topics, i.e., topics with high topic coherence scores. Good topics can be described by a short label based on the topic terms they spit out. \n",
     "\n",
     "<img src=\"Coherence.gif\">\n",
     "\n",
@@ -140,11 +140,11 @@
     "\n",
     "**Perplexity**\n",
     "\n",
-    "Perplexity is a measurement of how well a probability distribution or probability model predicts a sample. In LDA, topics are described by a probability distribution over vocabulary words. So, perplexity can be used to compare probabilistic models like LDA.\n",
+    "Perplexity is a measurement of how well a probability distribution or probability model predicts a sample. In LDA, topics are described by a probability distribution over vocabulary words. So, perplexity can be used to evaluate the topic-term distribution output by LDA.\n",
     "\n",
     "<img src=\"Perplexity.gif\">\n",
     "\n",
-    "For a good model, perplexity should be as low as possible.\n",
+    "For a good model, perplexity should be low.\n",
     "\n",
     "\n",
     "**Topic Difference**\n",
@@ -153,7 +153,7 @@
     "\n",
     "<img src=\"Diff.gif\">\n",
     "\n",
-    "In the heatmap, X-axis define the Epoch no. and Y-axis define the distance between the identical topic from consecutive epochs. For ex. a particular cell in the heatmap with values (x=3, y=5, z=0.4) represent the distance(=0.4) between the topic 5 from 3rd epoch and topic 5 from 2nd epoch. With increasing epochs, the distance between the identical topics should decrease.\n",
+    "In the heatmap, X-axis define the Epoch no. and Y-axis define the distance between identical topics from consecutive epochs. For ex. a particular cell in the heatmap with values (x=3, y=5, z=0.4) represent the distance(=0.4) between the topic 5 from 3rd epoch and topic 5 from 2nd epoch. With increasing epochs, the distance between the identical topics should decrease.\n",
     "  \n",
     "  \n",
     "**Convergence**\n",
@@ -293,15 +293,6 @@
    "source": [
     "model.metrics"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

gensim/models/callbacks.py

@@ -21,8 +21,14 @@ class Metric(object):
     """
     Base Metric class for topic model evaluation metrics
     """
-    def __init__(self):
-        pass
+    def __str__(self):
+        """
+        Return a string representation of Metric class
+        """
+        if self.title is not None:
+            return self.title
+        else:
+            return type(self).__name__[:-6]
 
     def set_parameters(self, **parameters):
         """
@@ -87,6 +93,9 @@ def __init__(self, corpus=None, texts=None, dictionary=None, coherence=None, win
         self.viz_env = viz_env
         self.title = title
 
+    def __str__(self):
+        return super(CoherenceMetric, self).__str__()
+
     def get_value(self, **kwargs):
         """
         Args:
@@ -125,6 +134,9 @@ def __init__(self, corpus=None, logger=None, viz_env=None, title=None):
         self.viz_env = viz_env
         self.title = title
 
+    def __str__(self):
+        return super(PerplexityMetric, self).__str__()
+
     def get_value(self, **kwargs):
         """
         Args:
@@ -168,6 +180,9 @@ def __init__(self, distance="jaccard", num_words=100, n_ann_terms=10, diagonal=T
         self.viz_env = viz_env
         self.title = title
 
+    def __str__(self):
+        return super(DiffMetric, self).__str__()
+
     def get_value(self, **kwargs):
         """
         Args:
@@ -211,6 +226,9 @@ def __init__(self, distance="jaccard", num_words=100, n_ann_terms=10, diagonal=T
         self.viz_env = viz_env
         self.title = title
 
+    def __str__(self):
+        return super(ConvergenceMetric, self).__str__()
+
     def get_value(self, **kwargs):
         """
         Args:
@@ -272,11 +290,8 @@ def on_epoch_end(self, epoch, topics=None):
 
         # plot all metrics in current epoch
         for i, metric in enumerate(self.metrics):
+            label = str(metric)
             value = metric.get_value(topics=topics, model=self.model, other_model=self.previous)
-            if metric.title is not None:
-                label = metric.title
-            else:
-                label = type(metric).__name__[:-6]
 
             current_metrics[label] = value
 
@@ -311,4 +326,3 @@ def on_epoch_end(self, epoch, topics=None):
             self.previous = copy.deepcopy(self.model)
 
         return current_metrics
-