使用BERT在Kaggle上使用NLP入门

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()

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'})

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)

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)}

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)