Spaces:
Runtime error
Runtime error
File size: 3,510 Bytes
fb22d07 eb56f89 fb22d07 459ba42 fb22d07 459ba42 fb22d07 e043bee 459ba42 e043bee 459ba42 e043bee 459ba42 e043bee 459ba42 e043bee 459ba42 e043bee 459ba42 e043bee fb22d07 459ba42 fb22d07 459ba42 fb22d07 459ba42 fb22d07 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
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")
#)
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")
# subtitle
st.markdown("## A selection of popular sentiment analysis models - hosted on 🤗 Spaces")
model_name = st.selectbox(
"Select a pre-trained model",
[
"finiteautomata/bertweet-base-sentiment-analysis",
"ahmedrachid/FinancialBERT-Sentiment-Analysis",
"finiteautomata/beto-sentiment-analysis",
"NativeVex/custom-fine-tuned",
],
)
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, Dict
import torch
import numpy as np
import pandas as pd
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()}
outputs = model(**encoding)
logits = outputs.logits
sigmoid = torch.nn.Sigmoid()
probs = sigmoid(logits.squeeze().cpu())
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": 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"):
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(
"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(
"Link to the app - [image-to-text-app on 🤗 Spaces](https://huggingface.co/spaces/Amrrs/image-to-text-app)"
)
|