我正在尝试创建垃圾邮件分类器,并且我使用以下代码来做到这一点。
但是问题是我收到一条错误消息,指出我的程序有一个“空库”,并且“我的文档除了停用词外什么都没有”。
您知道是什么原因造成的吗?
import os
import io
from pandas import DataFrame
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
def readFiles(path):
for root, dirnames, filenames in os.walk(path):
for filename in filenames:
path = os.path.join(root, filename)
inBody = False
lines = []
f = io.open(path, 'r', encoding='latin1')
for line in f:
if inBody:
lines.append(line)
elif line == '\n':
inBody = True
f.close()
message = '\n'.join(lines)
yield path, message
def dataFrameFromDirectory(path, classification):
rows = []
index = []
for filename, message in readFiles(path):
rows.append({'message': message, 'class': classification})
index.append(filename)
return DataFrame(rows, index=index)
data = DataFrame({'message': [], 'class': []})
data = data.append(dataFrameFromDirectory('C:/Users/Tapan/Desktop/enron/enron1/spam', 'spam'))
data = data.append(dataFrameFromDirectory('C:/Users/Tapan/Desktop/enron/enron1/ham', 'ham'))
vectorizer = CountVectorizer()
counts = vectorizer.fit_transform(data['message'].values)
classifier = MultinomialNB()
targets = data['class'].values
classifier.fit(counts, targets)
examples = ['prescribed online and shipped overnight to your door', 'vastar owns 68% of the gross production']
examples_counts = vectorizer.transform(examples)
predictions = classifier.predict(examples_counts)
print(predictions)