Adding vocabulary level

app.py

@@ -417,6 +417,31 @@ def gen_syns(word, level):
         str_reko+= i
     return str_reko
 
+def get_level(word):
+  with open('balanced_synonym_data.json') as f:
+    word = word.strip(" ")
+    data = json.loads(f.read())
+    level = 0
+    for k, v in data.items():
+      if word in v:
+        level = k
+    if level == 0:
+      return -1
+    return level
+
+def vocab_level_inter(text):
+  text = word_tokenize(text)
+  interp = [('',0)]
+  sum = 0
+  total = 0
+  for idx, i in enumerate(text):
+    lvl = int(get_level(i))/4
+    interp.append((i, lvl))
+    sum+= lvl
+    total += 1
+  interp.append(('', 0))
+  return interp, level(sum/total*4*2.5)
+
 with gr.Blocks(title="Automatic Literacy and Speech Assesmen") as demo:
   gr.HTML("""<center><h7 style="font-size: 35px">Automatic Literacy and Speech Assesment</h7></center>""")
   with gr.Column():
@@ -460,8 +485,12 @@ with gr.Blocks(title="Automatic Literacy and Speech Assesmen") as demo:
         find_sim = gr.Button("Find Similar Words")
         sims = gr.Label()
       with gr.Box():
-          gr.Markdown("Relative Difficulty Heatmap- How confusing the text is in that area") 
-          interpretation2 = gr.components.Interpretation(in_text, label="Difficulty Heatmap")
+        gr.Markdown("Relative Difficulty Heatmap- How confusing the text is in that area") 
+        interpretation2 = gr.components.Interpretation(in_text, label="Difficulty Heatmap")
+      with gr.Box():
+        vocab_output = gr.Label(label='Vocabulary Level', show_label=False)
+        gr.Markdown("Vocabulary Level Heatmap | Darker = Higher Level} Blue cells are not in vocabulary")
+        interpretation3 = gr.components.Interpretation(in_text, label="Interpretation of Text")
   with gr.Row():
     with gr.Box():
       with gr.Group():      
@@ -499,6 +528,7 @@ with gr.Blocks(title="Automatic Literacy and Speech Assesmen") as demo:
   grade.click(reading_difficulty, inputs=in_text, outputs=diff_output)
   grade.click(calculate_diversity, inputs=in_text, outputs=[interpretation, div_output])
   grade.click(sliding_window, inputs=in_text, outputs=[plotter, interpretation2])
+  grade.click(vocab_level_inter, inputs=in_text, outputs=[interpretation3, vocab_output])
   grade1.click(speech_to_score, inputs=audio_file, outputs=diff_output)
   b1.click(speech_to_text, inputs=[audio_file1, target], outputs=[text, some_val, phones])
   get_syns.click(gen_syns, inputs=[words, lvl], outputs=reccos)