| from .cleaning import remove_citations, split_data, split_text, chunk_data | |
| import pandas as pd | |
| import numpy as np | |
| import json | |
| with open("utils/id2label.json", "r") as j: | |
| id2label = json.loads(j.read()) | |
| with open("utils/label2id.json", "r") as j: | |
| label2id = json.loads(j.read()) | |
| def average_text(text, model): | |
| # result = classifier(df_train[(df_train.case_name==case) & (df_train.category=='per_curiam')]['clean_text'].to_list()) | |
| result = model(text) | |
| pred = {} | |
| for c in result: | |
| for d in c: | |
| if d["label"] not in pred: | |
| pred[d["label"]] = [round(d["score"], 2)] | |
| else: | |
| pred[d["label"]].append(round(d["score"], 2)) | |
| sumary = {k: round(sum(v) / len(v), 2) for k, v in pred.items()} | |
| result = [{dct["label"]: round(dct["score"], 2) for dct in lst} for lst in result] | |
| return dict(sorted(sumary.items(), key=lambda x: x[1], reverse=True)), result | |
| # def find_case_by_name(df, name): | |
| # return display( | |
| # HTML( | |
| # df[df["case_name"].str.contains(name)] | |
| # .iloc[:, :-1] | |
| # .to_html(render_links=True, escape=False) | |
| # ) | |
| # ) | |
| # def head_df(df): | |
| # return display( | |
| # HTML(df.iloc[:, :-1].head().to_html(render_links=True, escape=False)) | |
| # ) | |