Update app.py

app.py

@@ -1,11 +1,8 @@
-# Import packages:
-
+# Import packages
 import numpy as np
 import pandas as pd
 import matplotlib.pyplot as plt
 import re
-
-# tensorflow imports:
 import tensorflow as tf
 import pickle
 import gradio as gr
@@ -14,105 +11,82 @@ import spacy
 from spacy import displacy
 import streamlit as st
 import spacy_streamlit
-nlp = spacy.load('en_core_web_sm')
 import torch
-import tensorflow as tf
-from transformers import RobertaTokenizer, RobertaModel, AutoModelForSequenceClassification, TFAutoModelForSequenceClassification
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# Load NLP model
+nlp = spacy.load('en_core_web_sm')
+
+# Load your custom tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("paragon-analytics/bert_resil")
 model = AutoModelForSequenceClassification.from_pretrained("paragon-analytics/bert_resil")
 
-# para_tokenizer = AutoTokenizer.from_pretrained("paragon-analytics/t5_para")
-# para_model = AutoModelForSeq2SeqLM.from_pretrained("paragon-analytics/t5_para")
-
+# Initialize YAKE keyword extractor
 kw_extractor = yake.KeywordExtractor()
 custom_kw_extractor = yake.KeywordExtractor(lan="en", n=2, dedupLim=0.2, top=10, features=None)
 
-max_words = 2000
-max_len = 111
-
+# Initialize the transformers interpret explainer
 from transformers_interpret import SequenceClassificationExplainer
-cls_explainer = SequenceClassificationExplainer(
-    model,
-    tokenizer)
-    
-# load the model from disk
-#filename = 'resil_lstm_model.sav'
-#lmodel = pickle.load(open(filename, 'rb'))
-
-# load the model from disk
-#filename = 'tokenizer.pickle'
-#tok = pickle.load(open(filename, 'rb'))
+cls_explainer = SequenceClassificationExplainer(model, tokenizer)
 
 def process_final_text(text):
     X_test = str(text).lower()
     
+    # Encode the input and get model output
     encoded_input = tokenizer(X_test, return_tensors='pt')
     output = model(**encoded_input)
     scores = output[0][0].detach().numpy()
     scores = tf.nn.softmax(scores)
     
-    # Get Keywords:
+    # Get Keywords
     keywords = custom_kw_extractor.extract_keywords(X_test)
     letter = []
     score = []
     for i in keywords:
-        if i[1]>0.4:
+        if i[1] > 0.4:
             a = "+++"
-        elif (i[1]<=0.4) and (i[1]>0.1):
+        elif (i[1] <= 0.4) and (i[1] > 0.1):
             a = "++"
-        elif (i[1]<=0.1) and (i[1]>0.01):
+        elif (i[1] <= 0.1) and (i[1] > 0.01):
             a = "+"
         else: 
             a = "NA"
-    
         letter.append(i[0])
         score.append(a)
     
-    keywords = [(letter[i], score[i]) for i in range(0, len(letter))]
+    keywords = [(letter[i], score[i]) for i in range(len(letter))]
     
-    # Get NER:
-        # NER: 
+    # Get NER
     doc = nlp(text)
     sp_html = displacy.render(doc, style="ent", page=True, jupyter=False)
-    NER = (
-        ""
-        + sp_html
-        + ""
-    )
+    NER = sp_html
     
-    # Transformer Interpret:
+    # Transformer Interpret
     word_attributions = cls_explainer(X_test)
     letter = []
     score = []
     for i in word_attributions:
-        if i[1]>0.5:
+        if i[1] > 0.5:
             a = "++"
-        elif (i[1]<=0.5) and (i[1]>0.1):
+        elif (i[1] <= 0.5) and (i[1] > 0.1):
             a = "+"
-        elif (i[1]>=-0.5) and (i[1]<-0.1):
+        elif (i[1] >= -0.5) and (i[1] < -0.1):
             a = "-"
-        elif i[1]<-0.5:
+        elif i[1] < -0.5:
             a = "--"
         else: 
             a = "NA"
-    
         letter.append(i[0])
         score.append(a)
     
-    word_attributions = [(letter[i], score[i]) for i in range(0, len(letter))]
+    word_attributions = [(letter[i], score[i]) for i in range(len(letter))]
 
-    # # Paraphraser:
-    # batch = para_tokenizer(X_test, return_tensors='pt')
-    # generated_ids = para_model.generate(batch['input_ids'])
-    # para_list = para_tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
-
-    return {"Inspirational": float(scores.numpy()[1]), "Uninspiring": float(scores.numpy()[0])},keywords,NER,word_attributions
+    return {"Inspirational": float(scores.numpy()[1]), "Uninspiring": float(scores.numpy()[0])}, keywords, NER, word_attributions
     
 def main(prob1):
     text = str(prob1)
     obj = process_final_text(text)
-    return obj[0],obj[1],obj[2],obj[3]
+    return obj[0], obj[1], obj[2], obj[3]
     
 title = "Welcome to **HopeHarbor**! ✨"
 description1 = """
@@ -122,29 +96,47 @@ with gr.Blocks(title=title) as demo:
     gr.Markdown(f"## {title}")
     gr.Markdown(description1)
     gr.Markdown("""---""")
-    prob1 = gr.Textbox(label="Enter Your Text Here:",lines=2, placeholder="Type it here ...")
+    prob1 = gr.Textbox(label="Enter Your Text Here:", lines=2, placeholder="Type it here ...")
     submit_btn = gr.Button("Analyze")
-    #text = gr.Textbox(label="Text:",lines=2, placeholder="Please enter text here ...")
-    #submit_btn2 = gr.Button("Analyze")
 
     with gr.Column(visible=True) as output_col:
-        label = gr.Label(label = "Predicted Label")
-        impplot = gr.HighlightedText(label="Important Words", combine_adjacent=False).style(
-        color_map={"+++": "royalblue","++": "cornflowerblue",
-         "+": "lightsteelblue", "NA":"white"})
-        NER = gr.HTML(label = 'NER:')
-        intp =gr.HighlightedText(label="Word Scores",
-        combine_adjacent=False).style(color_map={"++": "darkgreen","+": "green", 
-                                                "--": "darkred",
-                                                "-": "red", "NA":"white"})
+        label = gr.Label(label="Predicted Label")
+        impplot = gr.HighlightedText(
+            label="Important Words", 
+            combine_adjacent=False,
+            color_map={"+++": "royalblue", "++": "cornflowerblue", "+": "lightsteelblue", "NA": "white"}
+        )
+        NER = gr.HTML(label='NER:')
+        intp = gr.HighlightedText(
+            label="Word Scores",
+            combine_adjacent=False,
+            color_map={"++": "darkgreen", "+": "green", "--": "darkred", "-": "red", "NA": "white"}
+        )
 
     submit_btn.click(
         main,
         [prob1],
-        [label,impplot,NER,intp], api_name="ResText"
+        [label, impplot, NER, intp], 
+        api_name="ResText"
     )
 
     gr.Markdown("### Click on any of the examples below to see to what extent they contain resilience messaging:")
-    gr.Examples([["Please stay at home and avoid unnecessary trips."],["Please stay at home and avoid unnecessary trips. We will survive this."],["We will survive this."],["Watch today’s news briefing with the latest updates on COVID-19 in Connecticut."],["So let's keep doing what we know works. Let's stay strong, and let's beat this virus. I know we can, and I know we can come out stronger on the other side."],["It is really wonderful how much resilience there is in human nature. Let any obstructing cause, no matter what, be removed in any way, even by death, and we fly back to first principles of hope and enjoyment."],["Resilience is accepting your new reality, even if it’s less good than the one you had before. You can fight it, you can do nothing but scream about what you’ve lost, or you can accept that and try to put together something that’s good."],["You survived all of the days you thought you couldn't, never underestimate your resilience."],["Like tiny seeds with potent power to push through tough ground and become mighty trees, we hold innate reserves of unimaginable strength. We are resilient."]], [prob1], [label,impplot,NER,intp], main, cache_examples=True)
+    gr.Examples(
+        examples=[
+            ["Please stay at home and avoid unnecessary trips."],
+            ["Please stay at home and avoid unnecessary trips. We will survive this."],
+            ["We will survive this."],
+            ["Watch today’s news briefing with the latest updates on COVID-19 in Connecticut."],
+            ["So let's keep doing what we know works. Let's stay strong, and let's beat this virus. I know we can, and I know we can come out stronger on the other side."],
+            ["It is really wonderful how much resilience there is in human nature. Let any obstructing cause, no matter what, be removed in any way, even by death, and we fly back to first principles of hope and enjoyment."],
+            ["Resilience is accepting your new reality, even if it’s less good than the one you had before. You can fight it, you can do nothing but scream about what you’ve lost, or you can accept that and try to put together something that’s good."],
+            ["You survived all of the days you thought you couldn't, never underestimate your resilience."],
+            ["Like tiny seeds with potent power to push through tough ground and become mighty trees, we hold innate reserves of unimaginable strength. We are resilient."]
+        ],
+        inputs=[prob1], 
+        outputs=[label, impplot, NER, intp], 
+        fn=main, 
+        cache_examples=True
+    )
     
-demo.launch()
+demo.launch()