利用逻辑回归建立模型，建立训练集和测试集
from pyspark.ml import Pipeline
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.feature import HashingTF, Tokenizer
# 从(id, text, label)元祖列表得到一个训练样本（DataFrame）.
training = spark.createDataFrame([
(0, "a b c d e spark", 1.0),
(1, "b d", 0.0),
(2, "spark f g h", 1.0),
(3, "hadoop mapreduce", 0.0)
], ["id", "text", "label"])
# 配置 ML pipeline,包含三个阶段: tokenizer, hashingTF, 和 lr.
tokenizer = Tokenizer(inputCol="text", outputCol="words")
hashingTF = HashingTF(inputCol=tokenizer.getOutputCol(), outputCol="features")
lr = LogisticRegression(maxIter=10, regParam=0.001)
pipeline = Pipeline(stages=[tokenizer, hashingTF, lr])
#现在构建的Pipeline本质上是一个Estimator，在它的fit()方法运行之后，它将产生一个PipelineModel，#它是一个Transformer。
# 使用训练样本建立模型.
model = pipeline.fit(training)
# 构建测试数据.
test = spark.createDataFrame([
(4, "spark i j k"),
(5, "l m n"),
(6, "spark hadoop spark"),
(7, "apache hadoop")
], ["id", "text"])
# 调用之前训练好的PipelineModel的transform()方法，让测试数据按顺序通过拟合的工作流，生成预测结
#果
prediction = model.transform(test)
selected = prediction.select("id", "text", "probability", "prediction")
for row in selected.collect():
rid, text, prob, prediction = row
print("(%d, %s) --> prob=%s, prediction=%f" % (rid, text, str(prob), prediction))
#(4, spark i j k) --> prob=[0.1596407738787475,0.8403592261212525], #prediction=1.000000
#(5, l m n) --> prob=[0.8378325685476744,0.16216743145232562], prediction=0.000000
#(6, spark hadoop spark) --> prob=[0.06926633132976037,0.9307336686702395], #prediction=1.000000
#(7, apache hadoop) --> prob=[0.9821575333444218,0.01784246665557808],
#prediction=0.000000
