DrishtiSharma commited on
Commit
6b08e4f
1 Parent(s): 20764a9

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +12 -12
app.py CHANGED
@@ -12,22 +12,22 @@ with open('tokenizer.pickle', 'rb') as file:
12
  def decide(text):
13
  tokenized_text = tokenizer.texts_to_sequences([text])
14
  padded_tokens = pad_sequences(tokenized_text, maxlen= 200)
15
- result = model.predict(padded_tokens, verbose=0)
16
- if result[:] > 0.6 :
17
- return f"Positive review with {result[:] : .0%} prediction score"
18
- elif result[:] < 0.4:
19
- return f"Negative review with {result[:] : .0%} prediction score"
20
  else:
21
  return "Neutral Review"
22
 
23
 
24
 
25
- example_sentence_1 = "I hate the movie, they made no effort in making the movie. Waste of time!"
26
- example_sentence_2 = "Awesome movie! Loved the way in which the hero acted."
27
- examples = [[example_sentence_1], [example_sentence_2]]
28
 
29
- description = "Write out a movie review to know the underlying sentiment."
30
 
31
- gr.Interface(decide, inputs= gr.inputs.Textbox( lines=1, placeholder=None, default="", label=None), outputs='text', examples=examples,
32
- title="Sentiment analysis of movie reviews",description=description, allow_flagging="auto",
33
- flagging_dir='flagging records').launch( enable_queue = True, inline=False, share = True)
 
12
  def decide(text):
13
  tokenized_text = tokenizer.texts_to_sequences([text])
14
  padded_tokens = pad_sequences(tokenized_text, maxlen= 200)
15
+ result = model.predict(padded_tokens)[0][0]
16
+ if result > 0.6 :
17
+ return f"Positive review with {result : .0%} prediction score"
18
+ elif result < 0.4:
19
+ return f"Negative review with {result : .0%} prediction score"
20
  else:
21
  return "Neutral Review"
22
 
23
 
24
 
25
+ #example_sentence_1 = "I hate the movie, they made no effort in making the movie. Waste of time!"
26
+ #example_sentence_2 = "Awesome movie! Loved the way in which the hero acted."
27
+ #examples = [[example_sentence_1], [example_sentence_2]]
28
 
29
+ #description = "Write out a movie review to know the underlying sentiment."
30
 
31
+ #gr.Interface(decide, inputs= gr.inputs.Textbox( lines=1, placeholder=None, default="", label=None), outputs='text', examples=examples,
32
+ # title="Sentiment analysis of movie reviews",description=description, allow_flagging="auto",
33
+ # flagging_dir='flagging records').launch( enable_queue = True, inline=False, share = True)