Spaces:
Running
Running
File size: 6,862 Bytes
88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 88f8e2a c24b83f 9a9f7ec c24b83f 88f8e2a 9a9f7ec 88f8e2a 9a9f7ec 88f8e2a 9a9f7ec 88f8e2a 9a9f7ec fcb332b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 |
# -*- coding: utf-8 -*-
# file: app.py
# time: 17:08 2023/3/6
# author: YANG, HENG <[email protected]> (杨恒)
# github: https://github.com/yangheng95
# huggingface: https://huggingface.co/yangheng
# google scholar: https://scholar.google.com/citations?user=NPq5a_0AAAAJ&hl=en
# Copyright (C) 2023. All Rights Reserved.
import random
import gradio as gr
import pandas as pd
from pyabsa import (
download_all_available_datasets,
AspectTermExtraction as ATEPC,
TaskCodeOption,
available_checkpoints,
)
from pyabsa import AspectSentimentTripletExtraction as ASTE
from pyabsa.utils.data_utils.dataset_manager import detect_infer_dataset
download_all_available_datasets()
atepc_dataset_items = {dataset.name: dataset for dataset in ATEPC.ATEPCDatasetList()}
aste_dataset_items = {dataset.name: dataset for dataset in ASTE.ASTEDatasetList()}
def get_atepc_example(dataset):
task = TaskCodeOption.Aspect_Polarity_Classification
dataset_file = detect_infer_dataset(atepc_dataset_items[dataset], task)
for fname in dataset_file:
lines = []
if isinstance(fname, str):
fname = [fname]
for f in fname:
print("loading: {}".format(f))
fin = open(f, "r", encoding="utf-8")
lines.extend(fin.readlines())
fin.close()
for i in range(len(lines)):
lines[i] = (
lines[i][: lines[i].find("$LABEL$")]
.replace("[B-ASP]", "")
.replace("[E-ASP]", "")
.strip()
)
return sorted(set(lines), key=lines.index)
def get_aste_example(dataset):
task = TaskCodeOption.Aspect_Sentiment_Triplet_Extraction
dataset_file = detect_infer_dataset(aste_dataset_items[dataset], task)
for fname in dataset_file:
lines = []
if isinstance(fname, str):
fname = [fname]
for f in fname:
print("loading: {}".format(f))
fin = open(f, "r", encoding="utf-8")
lines.extend(fin.readlines())
fin.close()
return sorted(set(lines), key=lines.index)
available_checkpoints("ASTE", True)
atepc_dataset_dict = {
dataset.name: get_atepc_example(dataset.name)
for dataset in ATEPC.ATEPCDatasetList()
}
aspect_extractor = ATEPC.AspectExtractor(checkpoint="multilingual")
aste_dataset_dict = {
dataset.name: get_aste_example(dataset.name) for dataset in ASTE.ASTEDatasetList()
}
triplet_extractor = ASTE.AspectSentimentTripletExtractor(checkpoint="english")
def perform_atepc_inference(text, dataset):
if not text:
text = atepc_dataset_dict[dataset][
random.randint(0, len(atepc_dataset_dict[dataset]) - 1)
]
result = aspect_extractor.predict(text, pred_sentiment=True)
result = pd.DataFrame(
{
"aspect": result["aspect"],
"sentiment": result["sentiment"],
# 'probability': result[0]['probs'],
"confidence": [round(x, 4) for x in result["confidence"]],
"position": result["position"],
}
)
return result, "{}".format(text)
def perform_aste_inference(text, dataset):
if not text:
text = aste_dataset_dict[dataset][
random.randint(0, len(aste_dataset_dict[dataset]) - 1)
]
result = triplet_extractor.predict(text)
pred_triplets = pd.DataFrame(result["Triplets"])
true_triplets = pd.DataFrame(result["True Triplets"])
return pred_triplets, true_triplets, "{}".format(text)
demo = gr.Blocks()
with demo:
with gr.Row():
with gr.Column():
gr.Markdown("# <p align='center'>Aspect Sentiment Triplet Extraction !</p>")
with gr.Row():
with gr.Column():
aste_input_sentence = gr.Textbox(
placeholder="Leave this box blank and choose a dataset will give you a random example...",
label="Example:",
)
gr.Markdown(
"You can find code and dataset at [ASTE examples](https://github.com/yangheng95/PyABSA/tree/v2/examples-v2/aspect_sentiment_triplet_extration)"
)
aste_dataset_ids = gr.Radio(
choices=[dataset.name for dataset in ASTE.ASTEDatasetList()[:-1]],
value="Restaurant14",
label="Datasets",
)
aste_inference_button = gr.Button("Let's go!")
aste_output_text = gr.TextArea(label="Example:")
aste_output_pred_df = gr.DataFrame(label="Predicted Triplets:")
aste_output_true_df = gr.DataFrame(label="Original Triplets:")
aste_inference_button.click(
fn=perform_aste_inference,
inputs=[aste_input_sentence, aste_dataset_ids],
outputs=[aste_output_pred_df, aste_output_true_df, aste_output_text],
)
with gr.Column():
gr.Markdown(
"# <p align='center'>Multilingual Aspect-based Sentiment Analysis !</p>"
)
with gr.Row():
with gr.Column():
atepc_input_sentence = gr.Textbox(
placeholder="Leave this box blank and choose a dataset will give you a random example...",
label="Example:",
)
gr.Markdown(
"You can find the datasets at [github.com/yangheng95/ABSADatasets](https://github.com/yangheng95/ABSADatasets/tree/v1.2/datasets/text_classification)"
)
atepc_dataset_ids = gr.Radio(
choices=[dataset.name for dataset in ATEPC.ATEPCDatasetList()[:-1]],
value="Laptop14",
label="Datasets",
)
atepc_inference_button = gr.Button("Let's go!")
atepc_output_text = gr.TextArea(label="Example:")
atepc_output_df = gr.DataFrame(label="Prediction Results:")
atepc_inference_button.click(
fn=perform_atepc_inference,
inputs=[atepc_input_sentence, atepc_dataset_ids],
outputs=[atepc_output_df, atepc_output_text],
)
gr.Markdown(
"""### GitHub Repo: [PyABSA V2](https://github.com/yangheng95/PyABSA)
### Author: [Heng Yang](https://github.com/yangheng95) (杨恒)
[](https://pepy.tech/project/pyabsa)
[](https://pepy.tech/project/pyabsa)
"""
)
demo.launch()
|