nudge display settings

language_models_project/app.py

@@ -2,15 +2,22 @@ import streamlit as st  # Web App
 from main import classify
 import pandas as pd
 
-#demo_phrases = """ Here are some examples:
-#this is a phrase
-#is it neutral
-#nothing else to say
-#man I'm so damn angry
-#sarcasm lol
-#I love this product
-#"""
-demo_phrases = pd.read_csv('./train.csv')['comment_text'].head(6).astype(str).str.cat(sep='\n')
+# demo_phrases = """ Here are some examples:
+# this is a phrase
+# is it neutral
+# nothing else to say
+# man I'm so damn angry
+# sarcasm lol
+# I love this product
+# """
+#demo_phrases = (
+#    pd.read_csv("./train.csv")["comment_text"].head(6).astype(str).str.cat(sep="\n")
+#)
+
+df = pd.read_csv("./train.csv")
+toxic = df[df['Toxic'] == 1]['comment_text'].head(3)
+normal = df[df['Toxic'] == 0]['comment_text'].head(3)
+demo_phrases = pd.concat([toxic, normal]).astype(str).str.cat(sep="\n")
 # title
 st.title("Sentiment Analysis")
 
@@ -23,7 +30,7 @@ model_name = st.selectbox(
         "finiteautomata/bertweet-base-sentiment-analysis",
         "ahmedrachid/FinancialBERT-Sentiment-Analysis",
         "finiteautomata/beto-sentiment-analysis",
-        "NativeVex/custom-fine-tuned"
+        "NativeVex/custom-fine-tuned",
     ],
 )
 
@@ -32,18 +39,30 @@ input_sentences = st.text_area("Sentences", value=demo_phrases, height=200)
 data = input_sentences.split("\n")
 
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
 model_path = "bin/model4"
 model = AutoModelForSequenceClassification.from_pretrained(model_path)
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
-from typing import List
+from typing import List, Dict
 import torch
 import numpy as np
 import pandas as pd
 
-def infer(text: str) -> List[float]:
+
+def infer(text: str) -> List[Dict[str, float]]:
+    """Use custom model to infer sentiment
+
+    Args:
+        text (str): text to infer
+
+    Returns:
+        List[Dict[str, float]]: list of dictionaries with {sentiment:
+        probability} score pairs
+
+    """
     encoding = tokenizer(text, return_tensors="pt")
-    encoding = {k: v.to(model.device) for k,v in encoding.items()}
+    encoding = {k: v.to(model.device) for k, v in encoding.items()}
     outputs = model(**encoding)
     logits = outputs.logits
     sigmoid = torch.nn.Sigmoid()
@@ -51,27 +70,47 @@ def infer(text: str) -> List[float]:
     predictions = np.zeros(probs.shape)
     predictions[np.where(probs >= 0.5)] = 1
     predictions = pd.Series(predictions == 1)
-    predictions.index = ["toxic", "severe_toxic", "obscene", "threat", "insult", "identity_hate"]
-    return [{"label": str(predictions), "score": str(probs)}]
+    predictions.index = [
+        "toxic",
+        "severe_toxic",
+        "obscene",
+        "threat",
+        "insult",
+        "identity_hate",
+    ]
+    return [{"label": predictions, "score": probs}]
 
 
 def wrapper(*args, **kwargs):
+    """Wrapper function to use custom model
+
+    Behaves as a switchboard to redirect if custom model is selected
+    """
     if args[0] != "NativeVex/custom-fine-tuned":
         return classify(*args, **kwargs)
     else:
         return infer(text=args[1])
 
-    
 
 if st.button("Classify"):
-    st.write("Please allow a few minutes for the model to run/download")
-    for i in range(len(data)):
-        j = wrapper(model_name.strip(), data[i])[0]
-        sentiment = j["label"]
-        confidence = j["score"]
+    if not model_name.strip() == "NativeVex/custom-fine-tuned":
+        st.write("Please allow a few minutes for the model to run/download")
+        for i in range(len(data)):
+            # j = wrapper(model_name.strip(), data[i])[0]
+            j = classify(model_name.strip(), data[i])[0]
+            sentiment = j["label"]
+            confidence = j["score"]
+            st.write(
+                f"{i}. {data[i]} :: Classification - {sentiment} with confidence {confidence}"
+            )
+    else:
         st.write(
-            f"{i}. {data[i]} :: Classification - {sentiment} with confidence {confidence}"
+            "To render the dataframe, all inputs must be sequentially"
+            "processed before displaying. Please allow a few minutes for longer"
+            "inputs."
         )
+        j = pd.DataFrame([infer(text=i) for i in data])
+        st.dataframe(data=j)
 
 
 st.markdown(