使用BERT在Kaggle上使用NLP入门

1，进口和eda

import os
iskaggle = os.environ.get('kaggle_kernel_run_type', '')
from pathlib import path
if iskaggle:
    path = path('/kaggle/input/us-patent-phrase-to-phrase-matching')

import pandas as pd
df = pd.read_csv(path/'train.csv')
df['input'] = 'text1: ' + df.context + '; text2: ' + df.target + '; anc1: ' + df.anchor
df.input.head()

2，令牌化

from datasets import dataset, datasetdict
ds = dataset.from_pandas(df)
import warnings,logging,torch
warnings.simplefilter('ignore')
logging.disable(logging.warning)
model_nm = 'anferico/bert-for-patents'
# load model directly
from transformers import automodelforsequenceclassification, autotokenizer
model = automodelforsequenceclassification.from_pretrained(model_nm, num_labels=1)
tokenizer = autotokenizer.from_pretrained('anferico/bert-for-patents')

def tok_func(x):
    return tokenizer(x['input'])
# tokenize all the sentences using the tokenizer
tok_ds = ds.map(tok_func, batched=true)
tok_ds = tok_ds.rename_columns({'score':'labels'})

3，测试和验证集

eval_df = pd.read_csv(path/'test.csv')
dds = tok_ds.train_test_split(0.25, seed=42)
eval_df['input'] = 'text1: ' + eval_df.context + '; text2: ' + eval_df.target + '; anc1: ' + eval_df.anchor
eval_ds = dataset.from_pandas(eval_df).map(tok_func, batched=true)

4，指标和相关性

import numpy as np
def corr(x,y): 
    ## change the 2-d array into 1-d array
    return np.corrcoef(x.flatten(), y)[0,1]
def corr_d(eval_pred): return {'pearson': corr(*eval_pred)}

5，训练我们的模型

佳可商务购物程序 2004

在原版的基础上做了一下修正评论没有提交正文的问题特价商品的调用连接问题去掉了一个后门补了SQL注入补了一个过滤漏洞浮动价不能删除的问题不能够搜索问题收藏时放入购物车时出错点放入购物车弹出2个窗口修正主题添加问题商家注册页导航连接问题销售排行不能显示更多问题热点商品不能显示更多问题增加了服务器探测 增加了空间使用查看 增加了在线文件编辑增加了后台管理里两处全选功能更新说明：后台的部分功能已经改过前台

下载

6，在测试集中获取预测

preds = trainer.predict(eval_ds).predictions.astype(float)
preds = np.clip(preds, 0, 1)
import datasets

submission = datasets.Dataset.from_dict({
    'id': eval_ds['id'],
    'score': preds
})

submission.to_csv('submission.csv', index=False)