|
from __future__ import annotations |
|
from typing import Iterable |
|
|
|
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 torch |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification, pipeline |
|
import os |
|
import colorsys |
|
import time |
|
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) |
|
|
|
class MPGPoster(Default): |
|
@staticmethod |
|
def create_color_shades(hex_color: str, brightness_control: float = 1.0) -> colors.Color: |
|
base_rgb = hex_to_rgb(hex_color) |
|
shades = {} |
|
|
|
base_factors = { |
|
"c50": 1.6, "c100": 1.4, "c200": 1.3, |
|
"c300": 1.2, "c400": 1, "c500": 0.8, |
|
"c600": 0.5, "c700": 0.35, "c800": 0.2, |
|
"c900": 0.15, "c950": 0.1 |
|
} |
|
|
|
factors = {shade: factor * brightness_control for shade, factor in base_factors.items()} |
|
|
|
for shade, factor in factors.items(): |
|
new_rgb = adjust_brightness(base_rgb, factor) |
|
shades[shade] = rgb_to_hex(new_rgb) |
|
return colors.Color(**shades) |
|
|
|
def __init__( |
|
self, |
|
*, |
|
spacing_size: sizes.Size | str = sizes.spacing_md, |
|
radius_size: sizes.Size | str = sizes.Size( 0, 0, 0, 0, 0, 0, 0, 0), |
|
text_size: sizes.Size | str = sizes.text_lg, |
|
font: fonts.Font |
|
| str |
|
| Iterable[fonts.Font | str] = ( |
|
fonts.GoogleFont("Jost"), |
|
"ui-sans-serif", |
|
"sans-serif", |
|
), |
|
font_mono: fonts.Font |
|
| str |
|
| Iterable[fonts.Font | str] = ( |
|
fonts.GoogleFont("IBM Plex Mono"), |
|
"ui-monospace", |
|
"monospace", |
|
), |
|
): |
|
primary_hue = MPGPoster.create_color_shades("#f47317") |
|
background_hue = MPGPoster.create_color_shades("#006c66") |
|
secondary_dark_hue = MPGPoster.create_color_shades("#6ad5bc") |
|
|
|
|
|
|
|
super().__init__( |
|
primary_hue=primary_hue, |
|
secondary_hue=secondary_dark_hue, |
|
neutral_hue=background_hue, |
|
spacing_size=spacing_size, |
|
radius_size=radius_size, |
|
text_size=text_size, |
|
font=font, |
|
font_mono=font_mono, |
|
) |
|
|
|
mpg_poster = MPGPoster() |
|
|
|
auth_token = os.environ['HF_TOKEN'] |
|
|
|
|
|
tokenizer_bin = AutoTokenizer.from_pretrained("AlGe/deberta-v3-large_token", token=auth_token) |
|
model_bin = AutoModelForTokenClassification.from_pretrained("AlGe/deberta-v3-large_token", token=auth_token) |
|
tokenizer_bin.model_max_length = 512 |
|
pipe_bin = pipeline("ner", model=model_bin, tokenizer=tokenizer_bin) |
|
|
|
|
|
tokenizer_ext = AutoTokenizer.from_pretrained("AlGe/deberta-v3-large_AIS-token", token=auth_token) |
|
model_ext = AutoModelForTokenClassification.from_pretrained("AlGe/deberta-v3-large_AIS-token", token=auth_token) |
|
tokenizer_ext.model_max_length = 512 |
|
pipe_ext = pipeline("ner", model=model_ext, tokenizer=tokenizer_ext) |
|
|
|
|
|
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_ner(text, pipeline): |
|
output = pipeline(text) |
|
entities = [] |
|
current_entity = None |
|
|
|
for token in output: |
|
entity_type = token['entity'][2:] |
|
entity_prefix = token['entity'][:1] |
|
|
|
if current_entity is None or entity_type != current_entity['entity'] or (entity_prefix == 'B' and entity_type == current_entity['entity']): |
|
if current_entity is not None: |
|
entities.append(current_entity) |
|
current_entity = { |
|
"entity": entity_type, |
|
"start": token['start'], |
|
"end": token['end'], |
|
"score": token['score'] |
|
} |
|
else: |
|
current_entity['end'] = token['end'] |
|
current_entity['score'] = max(current_entity['score'], token['score']) |
|
|
|
if current_entity is not None: |
|
entities.append(current_entity) |
|
|
|
return {"text": text, "entities": entities} |
|
|
|
def process_classification(text, model1, model2, tokenizer1): |
|
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)}" |
|
|
|
def all(text): |
|
return process_ner(text, pipe_bin), process_ner(text, pipe_ext), process_classification(text, model1, model2, tokenizer1)[0], process_classification(text, model1, model2, tokenizer1)[1], process_classification(text, model1, model2, tokenizer1)[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 happend or might happen to you ..."), |
|
outputs=[ |
|
gr.HighlightedText(label="Binary Sequence Classification"), |
|
gr.HighlightedText(label="Extended Sequence Classification"), |
|
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= mpg_poster |
|
) |
|
|
|
|
|
iface.launch() |
|
|