用PySpark1.6为LDA训练准备数据

Question

from pyspark.mllib.clustering import LDA
from pyspark.ml.feature import Tokenizer
from pyspark.ml.feature import CountVectorizer

#read the data
tf = sc.wholeTextFiles("20_newsgroups/*")

#transform into a data frame
df = tf.toDF(schema=['file','text'])

#tokenize
tokenizer = Tokenizer(inputCol="text", outputCol="words")
tokenized = tokenizer.transform(df)

#vectorize
cv = CountVectorizer(inputCol="words", outputCol="vectors")
model = cv.fit(tokenized)
result = model.transform(tokenized)

#transform into a suitable rdd
myrdd = ?

#LDA
model = LDA.train(myrdd, k=2, seed=1)

PS：我使用的是Apache Spark 1.6.3

Answer 1

让我们首先组织导入，读取数据，删除一些简单的特殊字符，并将其转换为dataframe:

import re # needed to remove special character
from pyspark import Row

from pyspark.ml.feature import StopWordsRemover
from pyspark.ml.feature import Tokenizer, CountVectorizer
from pyspark.mllib.clustering import LDA
from pyspark.sql import functions as F
from pyspark.sql.types import StructType, StructField, LongType

pattern = re.compile('[\W_]+') 

rdd = sc.wholeTextFiles("./data/20news-bydate/*/*/*") \
    .mapValues(lambda x: pattern.sub(' ', x)).cache() # ref. https://stackoverflow.com/a/1277047/3415409

df = rdd.toDF(schema=['file', 'text'])

我们需要为每个行添加索引。下面的代码片段来自这个关于使用Apache Spark添加主键的问题：

row_with_index = Row(*["id"] + df.columns)

def make_row(columns):
    def _make_row(row, uid):
        row_dict = row.asDict()
        return row_with_index(*[uid] + [row_dict.get(c) for c in columns])

    return _make_row

f = make_row(df.columns)

indexed = (df.rdd
           .zipWithUniqueId()
           .map(lambda x: f(*x))
           .toDF(StructType([StructField("id", LongType(), False)] + df.schema.fields)))

一旦我们添加了索引，我们就可以继续进行特征清理、提取和转换：

# tokenize
tokenizer = Tokenizer(inputCol="text", outputCol="tokens")
tokenized = tokenizer.transform(indexed)

# remove stop words
remover = StopWordsRemover(inputCol="tokens", outputCol="words")
cleaned = remover.transform(tokenized)

# vectorize
cv = CountVectorizer(inputCol="words", outputCol="vectors")
count_vectorizer_model = cv.fit(cleaned)
result = count_vectorizer_model.transform(cleaned)

现在，让我们将结果数据转换回rdd

corpus = result.select(F.col('id').cast("long"), 'vectors').rdd \
    .map(lambda x: [x[0], x[1]])

我们的数据现在可以训练了：

# training data
lda_model = LDA.train(rdd=corpus, k=10, seed=12, maxIterations=50)
# extracting topics
topics = lda_model.describeTopics(maxTermsPerTopic=10)
# extraction vocabulary
vocabulary = count_vectorizer_model.vocabulary

我们现在可以按以下方式打印主题描述：

for topic in range(len(topics)):
    print("topic {} : ".format(topic))
    words = topics[topic][0]
    scores = topics[topic][1]
    [print(vocabulary[words[word]], "->", scores[word]) for word in range(len(words))]