app.py

from __future__ import annotations
from typing import Iterable, List, Dict, Tuple

import gradio as gr
from gradio.themes.base import Base
from gradio.themes.soft import Soft
from gradio.themes.monochrome import Monochrome
from gradio.themes.default import Default
from gradio.themes.utils import colors, fonts, sizes

import spaces
import torch
import os
import io
import colorsys

import numpy as np

from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification, pipeline

import matplotlib.pyplot as plt
import plotly.graph_objects as go
from wordcloud import WordCloud


def hex_to_rgb(hex_color: str) -> tuple[int, int, int]:
    hex_color = hex_color.lstrip('#')
    return tuple(int(hex_color[i:i+2], 16) for i in (0, 2, 4))

def rgb_to_hex(rgb_color: tuple[int, int, int]) -> str:
    return "#{:02x}{:02x}{:02x}".format(*rgb_color)

def adjust_brightness(rgb_color: tuple[int, int, int], factor: float) -> tuple[int, int, int]:
    hsv_color = colorsys.rgb_to_hsv(*[v / 255.0 for v in rgb_color])
    new_v = max(0, min(hsv_color[2] * factor, 1))
    new_rgb = colorsys.hsv_to_rgb(hsv_color[0], hsv_color[1], new_v)
    return tuple(int(v * 255) for v in new_rgb)

monochrome = Monochrome()

auth_token = os.environ['HF_TOKEN']

model1 = AutoModelForSequenceClassification.from_pretrained("AlGe/deberta-v3-large_Int_segment", num_labels=1, token=auth_token)
tokenizer1 = AutoTokenizer.from_pretrained("AlGe/deberta-v3-large_Int_segment", token=auth_token)

model2 = AutoModelForSequenceClassification.from_pretrained("AlGe/deberta-v3-large_seq_ext", num_labels=1, token=auth_token)


def process_classification(text: str, model1, model2, tokenizer1) -> Tuple[str, str, str]:
    inputs1 = tokenizer1(text, max_length=512, return_tensors='pt', truncation=True, padding=True)
    
    with torch.no_grad():
        outputs1 = model1(**inputs1)
        outputs2 = model2(**inputs1)
    
    prediction1 = outputs1[0].item()
    prediction2 = outputs2[0].item()
    score = prediction1 / (prediction2 + prediction1)

    return f"{round(prediction1, 1)}", f"{round(prediction2, 1)}", f"{round(score, 2)}"

@spaces.GPU
def all(text: str):
    classification_output = process_classification(text, model1, model2, tokenizer1)

    return (classification_output[0], classification_output[1], classification_output[2])

examples = [
    ['Bevor ich meinen Hund kaufte bin ich immer alleine durch den Park gelaufen. Gestern war ich aber mit dem Hund losgelaufen. Das Wetter war sehr schön, nicht wie sonst im Winter. Ich weiß nicht genau. Mir fällt sonst nichts dazu ein. Wir trafen auf mehrere Spaziergänger. Ein Mann mit seinem Kind. Das Kind hat ein Eis gegessen.'],
]

iface = gr.Interface(
    fn=all,
    inputs=gr.Textbox(lines=5, label="Input Text", placeholder="Write about how your breakfast went or anything else that happened or might happen to you ..."),
    outputs=[
        gr.Label(label="Internal Detail Count"),
        gr.Label(label="External Detail Count"),
        gr.Label(label="Approximated Internal Detail Ratio"),
    ],
    title="Scoring Demo",
    description="Autobiographical Memory Analysis: This demo combines two text - and two sequence classification models to showcase our automated Autobiographical Interview scoring method. Submit a narrative to see the results.",
    examples=examples,
    theme=monochrome
)

iface.launch()