Added more documentation

app.py

@@ -6,12 +6,15 @@ from transformers import BertTokenizerFast
 
 st.set_page_config(page_title="AI Project", page_icon=":tada:", layout="wide")
 
+# Defining the list of pre-trained models from other people's HuggingFace spaces
 pre_trained_models = ["finiteautomata/bertweet-base-sentiment-analysis",
                       'bhadresh-savani/distilbert-base-uncased-emotion',
                       "nlptown/bert-base-multilingual-uncased-sentiment"]
 
+# My fine-tuned model from my personal HuggingFace space
 fine_tuned_model = "corykhal/twitter-finetuned"
 
+# Dictionary that maps the output labels of my fine-tuned model to the actual labels to present
 fine_tuned_labels = {"LABEL_0": "Toxic",
                      "LABEL_1": "Severe Toxic",
                      "LABEL_2": "Obscene",
@@ -19,6 +22,7 @@ fine_tuned_labels = {"LABEL_0": "Toxic",
                      "LABEL_4": "Insult",
                      "LABEL_5": "Identity Hate"}
 
+# List of all four models
 models = pre_trained_models + [fine_tuned_model]
 
 with st.container():
@@ -28,6 +32,7 @@ with st.container():
 with st.container():
     st.write("---")
 
+    # Take in user text to input into model
     text = st.text_input("Please enter the text of a tweet to use for the sentiment analysis:",
                          value="Hello! It is a pleasure to meet you!")
 
@@ -36,28 +41,33 @@ with st.container():
     st.write("The first 3 models in the select box are for any sentiment analysis.")
     st.write("The last model (which is finetuned) in the select box is specifically for toxicity analysis.")
 
+    # Display a select box for the user to select a model name
     model = st.selectbox("Please select one of the following pre-trained models:", models)
 
     
-
 with st.container():
     st.write("---")
+    # If the button is pressed
     if st.button("Analyze!"):
         # If the user selects a pre-trained model
         if model in pre_trained_models:
+            # Load the model pipeline using the model name
             analysis = pipeline("sentiment-analysis", model=model)
+            # Run the model using user input text and store the predicted result
             result = analysis(text)
+            # Extract the label and score of prediction
             sentiment = result[0]["label"] 
             score = result[0]["score"]
             
             # Create a table for the label and score
             data = pd.DataFrame({"Tweet": [text], "Sentiment": [sentiment], "Confidence Score": [score]})
-
             st.table(data)
         
         # If the user selects the finetuned model
         else:
+            # Load the model pipeline using the model name and return the top 2 results
             analysis = pipeline("sentiment-analysis", model=model, top_k=2)
+            # Run the model using user input text and store the predicted result
             result = analysis(text)
             
             # Get the top two labels and scores
@@ -70,8 +80,6 @@ with st.container():
             # Create a table for the labels and scores
             data = pd.DataFrame({"Tweet": [text], "Toxic": [sentiment1], "Toxic Confidence Score": [score1],
                                  "Type of Toxicity": [sentiment2], "Toxicity Type Confidence Score": [score2]})
-
-
             st.table(data)