科大讯飞-学术论文分类挑战赛：ERNIE 准确率0.79

!pip install paddle-ernie > log.log

import numpy as npimport paddle as P# 导入ernie模型from ernie.tokenizing_ernie import ErnieTokenizerfrom ernie.modeling_ernie import ErnieModel

model = ErnieModel.from_pretrained('ernie-1.0')    # Try to get pretrained model from server, make sure you have network connectionmodel.eval()
tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')

ids, _ = tokenizer.encode('hello world')
ids = P.to_tensor(np.expand_dims(ids, 0))  # insert extra `batch` dimensionpooled, encoded = model(ids)                 # eager executionprint(pooled.numpy())

import sysimport numpy as npimport pandas as pdfrom sklearn.metrics import f1_scoreimport paddle as Pfrom ernie.tokenizing_ernie import ErnieTokenizerfrom ernie.modeling_ernie import ErnieModelForSequenceClassification

train_df = pd.read_csv('train.csv', sep='\t')
train_df['title'] = train_df['title'] + ' ' + train_df['abstract']

train_df = train_df.sample(frac=1.0)
train_df.head()

train_df.shape

train_df['categories'].nunique()

train_df['categories'], lbl_list = pd.factorize(train_df['categories'])

# 模型超参数BATCH=32MAX_SEQLEN=300LR=5e-5EPOCH=10# 定义ernie分类模型ernie = ErnieModelForSequenceClassification.from_pretrained('ernie-2.0-en', num_labels=39)
optimizer = P.optimizer.Adam(LR,parameters=ernie.parameters())
tokenizer = ErnieTokenizer.from_pretrained('ernie-2.0-en')

train_df.iterrows()

# 对数据集进行转换，主要操作为文本编码def make_data(df):
    data = []    for i, row in enumerate(df.iterrows()):
        text, label = row[1].title, row[1].categories
        text_id, _ = tokenizer.encode(text) # ErnieTokenizer 会自动添加ERNIE所需要的特殊token，如[CLS], [SEP]
        text_id = text_id[:MAX_SEQLEN]
        text_id = np.pad(text_id, [0, MAX_SEQLEN-len(text_id)], mode='constant')
        data.append((text_id, label))    return data

train_data = make_data(train_df.iloc[:-5000])
val_data = make_data(train_df.iloc[-5000:])

# 获取batch数据def get_batch_data(data, i):
    d = data[i*BATCH: (i + 1) * BATCH]
    feature, label = zip(*d)
    feature = np.stack(feature)  # 将BATCH行样本整合在一个numpy.array中
    label = np.stack(list(label))
    feature = P.to_tensor(feature) # 使用to_variable将numpy.array转换为paddle tensor
    label = P.to_tensor(label)    return feature, label

EPOCH=1# 模型训练for i in range(EPOCH):
    np.random.shuffle(train_data) # 每个epoch都shuffle数据以获得最佳训练效果；
    ernie.train()    for j in range(len(train_data) // BATCH):
        feature, label = get_batch_data(train_data, j)
        loss, _ = ernie(feature, labels=label) 
        loss.backward()
        optimizer.minimize(loss)
        ernie.clear_gradients()        if j % 50 == 0:            print('Train %d: loss %.5f' % (j, loss.numpy()))        
        # 模型验证
        if j % 100 == 0:
            all_pred, all_label = [], []            with P.no_grad():
                ernie.eval()                for j in range(len(val_data) // BATCH):
                    feature, label = get_batch_data(val_data, j)
                    loss, logits = ernie(feature, labels=label)

                    all_pred.extend(logits.argmax(-1).numpy())
                    all_label.extend(label.numpy())
                ernie.train()
            acc = (np.array(all_label) == np.array(all_pred)).astype(np.float32).mean()            print('Val acc %.5f' % acc)

test_df = pd.read_csv('test.csv', sep='\t')
test_df['title'] = test_df['title'] + ' ' + test_df['abstract']
test_df['categories'] = 0test_data = make_data(test_df.iloc[:])

all_pred, all_label = [], []# 模型预测with P.no_grad():
    ernie.eval()    for j in range(len(test_data) // BATCH+1):
        feature, label = get_batch_data(test_data, j)
        loss, logits = ernie(feature, labels=label)

        all_pred.extend(logits.argmax(-1).numpy())
        all_label.extend(label.numpy())

pd.DataFrame({    'paperid': test_df['paperid'],    'categories': lbl_list[all_pred]
}).to_csv('submit.csv', index=None)