Spaces:
Sleeping
Sleeping
File size: 8,690 Bytes
3c77d98 27be2d9 cb58c8d 3c77d98 cb58c8d 3c77d98 27be2d9 cb58c8d 481f13d 27be2d9 481f13d 3c77d98 d2324b7 3c77d98 cb58c8d 27be2d9 3c77d98 7ba3a06 27be2d9 3c77d98 27be2d9 |
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 |
import gradio as gr
import pandas as pd
import torch
from data_collect import collect
from model_predict import predict_text
from wide_analysis.data.process_data import prepare_dataset
model_dict = {
"Outcome Prediction": "outcome",
"Stance Detection": "stance",
"Policy Prediction": "policy",
"Sentiment Analysis": "sentiment",
"Offensive Language Detection": "offensive"
}
platform_dict = ["wikipedia", "wikidata_entity", "wikidata_property", "wikinews", "wikiquote"]
lang_dict = ["en", "es", "gr"]
title = 'Wide-Analysis: A Wikipedia Deletion Discussion Analysis Suite'
desc = """ Wide-Analysis is a suite of tools for analyzing deletion discussions across various Wikimedia platforms in multiple languages... """
def process_url(url, task_name, lang, platform, date):
model_name = model_dict[task_name]
derived_date = url.split('/')[-1].split('#')[0]
derived_title = url.split('#')[-1]
if model_name == 'outcome':
if lang == 'en' and platform == 'wikipedia':
df = prepare_dataset(mode='title', start_date=derived_date, url=url, title=derived_title)
if df.empty:
return "", "", "", {"error": "No data found"}
processed_text = df['discussion'].iloc[0]
else:
if lang == 'es' and platform == 'wikipedia':
df = collect(mode='title', start_date=derived_date, url=url, title=derived_title, platform=platform, lang=lang, date='')
elif lang == 'gr' and platform == 'wikipedia':
if not date or len(date.split('/')) != 2:
return "", "", "", {"error": "For Greek Wikipedia (title mode), please provide 'date' in 'mm/yyyy' format."}
df = collect(mode='title', start_date=derived_date, url=url, title=derived_title, platform=platform, lang=lang, date=date, years=[date])
elif lang == 'en' and platform == 'wikidata_entity':
df = collect(mode='url', url=url, platform=platform, lang=lang)
elif lang == 'en' and platform == 'wikidata_property':
df = collect(mode='url', start_date=derived_date, url=url, title=derived_title, platform=platform, lang=lang, date=date)
elif lang == 'en' and platform == 'wikinews':
df = collect(mode='url', start_date=derived_date, url=url, title=derived_title, platform=platform, lang=lang, date=date)
elif lang == 'en' and platform == 'wikiquote':
df = collect(mode='title', start_date=derived_date, url=url, title=derived_title, platform=platform, lang=lang, date=date)
else:
return "", "", "", {"error": f"No implementation detail for lang={lang} platform={platform} provided."}
if isinstance(df, str) or df.empty:
return "", "", "", {"error": "No data returned from collect function."}
processed_text = df['discussion'].iloc[0]
else:
if lang == 'en' and platform == 'wikipedia':
df = prepare_dataset(mode='title', start_date=derived_date, url=url, title=derived_title)
if df.empty:
return "", "", "", {"error": "No data found"}
processed_text = df['discussion'].iloc[0]
else:
return "", "", "", {"error": f"Currently only English Wikipedia supported for {task_name}."}
final_scores = predict_text(processed_text, model_name, lang=lang, platform=platform, date=date)
if model_name == 'outcome':
highest_prob_item = max(final_scores, key=lambda x: x['score'])
highest_prob_label = highest_prob_item['outcome']
highest_prob = highest_prob_item['score']
progress_bars = {item['outcome']: item['score'] for item in final_scores}
return processed_text, highest_prob_label, str(highest_prob), progress_bars
else:
return processed_text, "", "", final_scores
url_input = gr.Textbox(label="URL")
model_name_input = gr.Dropdown(label="Choose the Task", choices=list(model_dict.keys()), value=list(model_dict.keys())[0])
lang_input = gr.Dropdown(label="Language", choices=lang_dict, value="en")
platform_input = gr.Dropdown(label="Platform", choices=platform_dict, value="wikipedia")
date_input = gr.Textbox(label="Date (if required)", placeholder="For ES year mode: dd/mm/yyyy, for GR title mode: mm/yyyy")
outputs = [
gr.Textbox(label="Processed Text"),
gr.Textbox(label="Label with Highest Probability"), # Only for outcome
gr.Textbox(label="Probability"), # Only for outcome
gr.JSON(label="All Labels and Probabilities") # For all tasks
]
demo = gr.Interface(fn=process_url,
inputs=[url_input, model_name_input, lang_input, platform_input, date_input],
outputs=outputs,
title=title,
description=desc)
demo.launch(share=True)
# import data_prep
# import model_predict
# import gradio as gr
# # model_dict = {
# # "BERT-Base": "research-dump/bert-base-uncased_deletion_multiclass_complete_Final",
# # "BERT-Large": "research-dump/bert-large-uncased_deletion_multiclass_complete_final",
# # "RoBERTa-Base": "research-dump/roberta-base_deletion_multiclass_complete_final",
# # "RoBERTa-Large": "research-dump/roberta-large_deletion_multiclass_complete_final"
# # }
# model_dict = {
# "Outcome Prediction": "outcome",
# "Stance Detection": "stance",
# "Policy Prediction": "policy",
# "Sentiment Analysis": "sentiment",
# "Offensive Language Detection": "offensive"
# }
# def process_url(url, model_name):
# model_name = model_dict[model_name]
# processed_text = data_prep.process_data(url)
# final_scores = model_predict.predict_text(processed_text, model_name)
# if model_name == 'outcome':
# highest_prob_item = max(final_scores, key=lambda x: x['score'])
# highest_prob_label = highest_prob_item['outcome']
# highest_prob = highest_prob_item['score']
# progress_bars = {item['outcome']: item['score'] for item in final_scores}
# return processed_text, highest_prob_label, highest_prob, progress_bars
# else:
# return processed_text, "", "", final_scores
# title = 'Wide-Analysis: A Wikipedia Deletion Discussion Analysis Suite'
# desc = """ Wide-Analysis is a suite of tools for analyzing Wikipedia deletion discussions. It is designed to help researchers and practitioners to understand the dynamics of deletion discussions, and to develop tools for supporting the decision-making process in Wikipedia. The suite includes a set of tools for collecting, processing, and analyzing deletion discussions. The package contains the following functionalities
# - Outcome Prediction: Predicting the outcome of a deletion discussion, the outcome can be the decision made with the discussion (e.g., keep, delete, merge, etc.) (determined from the complete discussion)
# - Stance Detection: Identifying the stance of the participants in the discussion, in relation to the deletion decision.(determined from each individual comment in discussion)
# - Policy Prediction: Predicting the policy that is most relevant to the comments of the participants in the discussion.(determined from each individual comment in discussion)
# - Sentiment Prediction: Predicting the sentiment of the participants in the discussion, in relation to the deletion decision.(determined from each individual comment in discussion)
# - Offensive Language Detection: Detecting offensive language in the comments of the participants in the discussion.(determined from each individual comment in discussion)
# The input to the classifier is a URL of a Wikipedia deletion discussion page with the task listed in the drop-down box, and the output is the predicted label of the discussion, along with the probability of the predicted label, and the probabilities of all the labels.
# """
# url_input = gr.Textbox(label="URL")
# model_name_input = gr.Dropdown(label="Choose the Task", choices=list(model_dict.keys()), value=list(model_dict.keys())[0])
# outputs = [
# gr.Textbox(label="Processed Text"),
# gr.Textbox(label="Label with Highest Probability"), # This will only be used for the outcome task
# gr.Textbox(label="Probability"), # This will only be used for the outcome task
# gr.JSON(label="All Labels and Probabilities") # This will be used for all tasks
# ]
# demo = gr.Interface(fn=process_url, inputs=[url_input, model_name_input], outputs=outputs, title=title, description=desc)
# demo.launch() # share=True
|