Update app.py

app.py

@@ -39,8 +39,8 @@ def calculate_embeddings_with_gpt3(text, engine="text-similarity-davinci-001", i
   )
   embedding = response['data'][0]['embedding']
   return embedding
-  
-  def quantified_classification(transcript, threshold):
+ 
+def quantified_classification(transcript, threshold):
   
   df_sentences = pd.DataFrame(columns=['line', 'sentence', 'embedding'])
   for idx, sentence in enumerate(transcript_to_sentences(transcript)):
@@ -60,14 +60,14 @@ def calculate_embeddings_with_gpt3(text, engine="text-similarity-davinci-001", i
   df_cosines = pd.DataFrame(columns=['line'])
 
   for i, row in df_sentences.iterrows():
-      line = f'{row["line"]:03}'
-      # print(f'Calculating cosines for [ {line} ] {row["sentence"][:50]}...')
-      source = np.array(row["embedding"])
-      cosine = np.dot(targets,source)/(np.linalg.norm(targets, axis=1)*np.linalg.norm(source))
-      # Create new row
-      new_row = dict([(f"Cosine{f'{key:02}'}", value) for key, value in enumerate(cosine.flatten(), 1)])
-      new_row["line"] = row["line"]
-      df_cosines = df_cosines.append(new_row, ignore_index=True)
+    line = f'{row["line"]:03}'
+    # print(f'Calculating cosines for [ {line} ] {row["sentence"][:50]}...')
+    source = np.array(row["embedding"])
+    cosine = np.dot(targets,source)/(np.linalg.norm(targets, axis=1)*np.linalg.norm(source))
+    # Create new row
+    new_row = dict([(f"Cosine{f'{key:02}'}", value) for key, value in enumerate(cosine.flatten(), 1)])
+    new_row["line"] = row["line"]
+    df_cosines = df_cosines.append(new_row, ignore_index=True)
 
   df_cosines['line'] = df_cosines['line'].astype('int')
   # print(df_cosines.shape)
@@ -115,13 +115,11 @@ def calculate_embeddings_with_gpt3(text, engine="text-similarity-davinci-001", i
     title = f"{transcript[:200]}..."
   )
   fig.add_shape( # add a horizontal "target" line
-      type="line", line_color="salmon", line_width=3, opacity=1, line_dash="dot",
-      x0=0, x1=1, xref="paper", y0=threshold, y1=threshold, yref="y"
+    type="line", line_color="salmon", line_width=3, opacity=1, line_dash="dot",
+    x0=0, x1=1, xref="paper", y0=threshold, y1=threshold, yref="y"
   )
   fig.update_traces(textfont_size=24, textangle=0, textposition="inside", cliponaxis=False)
-  fig.update_yaxes(
-      range=[0, 1]
-  )  
+  fig.update_yaxes(range=[0, 1])  
   # fig.show()
 
   details = df_results.drop(labels='line',axis=1).sort_values(['tag','similarity'],ascending=True,False]).groupby('tag').head(3).reset_index().drop(labels='index',axis=1)
@@ -130,6 +128,8 @@ def calculate_embeddings_with_gpt3(text, engine="text-similarity-davinci-001", i
 
   return res, fig, details
 
+# Gradio UI
+
 with gr.Blocks(css=".gradio-container { background-color: white; background-image: url('file=,/qc-logo.png'); background-size: 75px 75px; background-repeat: no-repeat; background-position: 0px 0px; }") as demo:
   gr.Markdown("# Transcript classifier")
   with gr.Row():