[Kaggle] Spam/Ham Email Classification 垃圾邮件分类（spacy）

import pandas as pd
import spacy
train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")

train.head(10)
train = train.fillna(" ")
test = test.fillna(" ")

train['all'] = train['subject']+train['email']
train['label'] = [{"spam": bool(y), "ham": not bool(y)}
                  for y in train.spam.values]
train.head(10)

from sklearn.model_selection import StratifiedShuffleSplit
# help(StratifiedShuffleSplit)
splt = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=1)
for train_idx, valid_idx in splt.split(train, train['spam']): 
											# 按照后者分层抽样
    train_set = train.iloc[train_idx]
    valid_set = train.iloc[valid_idx]

# 查看分布
print(train_set['spam'].value_counts()/len(train_set))
print(valid_set['spam'].value_counts()/len(valid_set))

0    0.743636
1    0.256364
Name: spam, dtype: float64
0    0.743713
1    0.256287
Name: spam, dtype: float64

train_text = train_set['all'].values
train_label = train_set['label']
valid_text = valid_set['all'].values
valid_label = valid_set['label']

# 标签还要做以下处理，添加一个 'cats' key，'cats' 也是内置的关键字
train_label = [{"cats": label} for label in train_label]
valid_label = [{"cats": label} for label in valid_label]

# 训练数据打包，再转为list
train_data = list(zip(train_text, train_label)) 

test_text = (test['subject']+test['email']).values

print(train_label[0])

{'cats': {'spam': False, 'ham': True}}

nlp = spacy.blank('en') # 建立空白的英语模型
email_cat = nlp.create_pipe('textcat', 
#                             config=
#                             {
#     "exclusive_classes": True, # 排他的，二分类
#     "architecture": "bow"
#                             }
                           )
# 参数 'textcat' 不能随便写，是接口内置的 字符串
# 上面的 config 不要也可以，没找到文档说明，该怎么配置
help(nlp.create_pipe)

nlp.add_pipe(email_cat)

# 注意顺序，ham是 0， spam 是 1
email_cat.add_label('ham')
email_cat.add_label('spam')

from spacy.util import minibatch
import random
def train(model, train, optimizer, batch_size=8):
    loss = {}
    random.seed(1)
    random.shuffle(train) # 随机打乱
    batches = minibatch(train, size=batch_size) # 数据分批
    for batch in batches:
        text, label = zip(*batch)
        model.update(text, label, sgd=optimizer, losses=loss)
    return loss

def predict(model, text):
    docs = [model.tokenizer(txt) for txt in text] # 先把文本令牌化
    emailpred = model.get_pipe('textcat')
    score, _ = emailpred.predict(docs)
    pred_label = score.argmax(axis=1)
    return pred_label

def evaluate(model, text, label):
    pred = predict(model, text)
    true_class = [int(lab['cats']['spam']) for lab in label]
    correct = (pred == true_class)
    acc = sum(correct)/len(correct) # 准确率
    return acc

n = 20
opt = nlp.begin_training() # 定义优化器
for i in range(n):
    loss = train(nlp, train_data, opt)
    acc = evaluate(nlp, valid_text, valid_label)
    print(f"Loss: {loss['textcat']:.3f} \t Accuracy: {acc:.3f}")

Loss: 1.132 	 Accuracy: 0.941
Loss: 0.283 	 Accuracy: 0.988
Loss: 0.121 	 Accuracy: 0.993
Loss: 0.137 	 Accuracy: 0.993
Loss: 0.094 	 Accuracy: 0.982
Loss: 0.069 	 Accuracy: 0.995
Loss: 0.060 	 Accuracy: 0.990
Loss: 0.010 	 Accuracy: 0.992
Loss: 0.004 	 Accuracy: 0.992
Loss: 0.004 	 Accuracy: 0.992
Loss: 0.004 	 Accuracy: 0.992
Loss: 0.004 	 Accuracy: 0.992
Loss: 0.004 	 Accuracy: 0.992
Loss: 0.004 	 Accuracy: 0.991
Loss: 0.004 	 Accuracy: 0.991
Loss: 0.308 	 Accuracy: 0.981
Loss: 0.158 	 Accuracy: 0.987
Loss: 0.014 	 Accuracy: 0.990
Loss: 0.007 	 Accuracy: 0.990
Loss: 0.043 	 Accuracy: 0.990

pred = predict(nlp, test_text)

id = test['id']
output = pd.DataFrame({'id':id, 'Class':pred})
output.to_csv("submission.csv",  index=False)