【发布时间】：2017-04-02 13:59:17
【问题描述】：
我正在尝试解决这个超级简单的问题，但我已经厌倦了，我希望有人能帮我解决这个问题。我有一个形状像这样的数据框：
-------------------------- |类别 |产品ID | |------------+------------+ |一个 |产品 1 | |一个 |产品 2 | |一个 |产品 3 | |一个 |产品 1 | |一个 |产品 4 | |乙 |产品 5 | |乙 |产品 6 | --------------------------如何按类别对这些行进行分组并在 Scala 中应用复杂的函数？ 也许是这样的：
val result = df.groupBy("Category").apply(myComplexFunction)
这个 myComplexFunction 应该为每个类别生成下表，并将成对相似性上传到 Hive 表中或将其保存到 HDFS 中：
+-------------------------------------------------- -+ | |产品_1 |产品_2 |产品_3 | +------------+------------+------------------------ -+ |产品_1 | 1.0 | 0.1 | 0.8 | |产品_2 | 0.1 | 1.0 | 0.5 | |产品_3 | 0.8 | 0.5 | 1.0 | +-------------------------------------------------- -+这是我要应用的函数（它只是计算每个类别中的项目余弦相似度）：
def myComplexFunction(context_data : DataFrame, country_name: String,
context_id: String, table_name_correlations: String,
context_layer: String, context_index: String) : Boolean = {
val unique_identifier = country_name + "_" + context_layer + "_" + context_index
val temp_table_vocabulary = "temp_vocabulary_" + unique_identifier
val temp_table_similarities = "temp_similarities_" + unique_identifier
val temp_table_correlations = "temp_correlations_" + unique_identifier
//context.count()
// fit a CountVectorizerModel from the corpus
//println("Creating sparse incidence matrix")
val cvModel: CountVectorizerModel = new CountVectorizer().setInputCol("words").setOutputCol("features").fit(context_data)
val incidence = cvModel.transform(context_data)
// ========================================================================================
// create dataframe of mapping from indices into the item id
//println("Creating vocabulary")
val vocabulary_rdd = sc.parallelize(cvModel.vocabulary)
val rows_vocabulary_rdd = vocabulary_rdd.zipWithIndex.map{ case (s,i) => Row(s,i)}
val vocabulary_field1 = StructField("Product_ID", StringType, true)
val vocabulary_field2 = StructField("Product_Index", LongType, true)
val schema_vocabulary = StructType(Seq(vocabulary_field1, vocabulary_field2))
val df_vocabulary = hiveContext.createDataFrame(rows_vocabulary_rdd, schema_vocabulary)
// ========================================================================================
//println("Computing similarity matrix")
val myvectors = incidence.select("features").rdd.map(r => r(0).asInstanceOf[Vector])
val mat: RowMatrix = new RowMatrix(myvectors)
val sims = mat.columnSimilarities(0.0)
// ========================================================================================
// Convert records of the Matrix Entry RDD into Rows
//println("Extracting paired similarities")
val rowRdd = sims.entries.map{case MatrixEntry(i, j, v) => Row(i, j, v)}
// ========================================================================================
// create dataframe schema
//println("Creating similarity dataframe")
val field1 = StructField("Product_Index", LongType, true)
val field2 = StructField("Neighbor_Index", LongType, true)
var field3 = StructField("Similarity_Score", DoubleType, true)
val schema_similarities = StructType(Seq(field1, field2, field3))
// create the dataframe
val df_similarities = hiveContext.createDataFrame(rowRdd, schema_similarities)
// ========================================================================================
//println("Register vocabulary and correlations as spark temp tables")
df_vocabulary.registerTempTable(temp_table_vocabulary)
df_similarities.registerTempTable(temp_table_similarities)
// ========================================================================================
//println("Extracting Product_ID")
val temp_corrs = hiveContext.sql(
s"SELECT T1.Product_ID, T2.Neighbor_ID, T1.Similarity_Score " +
s"FROM " +
s"(SELECT Product_ID, Neighbor_Index, Similarity_Score " +
s"FROM $temp_table_similarities LEFT JOIN $temp_table_vocabulary " +
s"WHERE $temp_table_similarities.Product_Index = $temp_table_vocabulary.Product_Index) AS T1 " +
s"LEFT JOIN " +
s"(SELECT Product_ID AS Neighbor_ID, Product_Index as Neighbor_Index FROM $temp_table_vocabulary) AS T2 " +
s"ON " +
s"T1.Neighbor_Index = T2.Neighbor_Index")
// ========================================================================================
val context_corrs = temp_corrs.withColumn("Context_Layer", lit(context_layer)).withColumn("Context_ID", lit(context_id)).withColumn("Country", lit(country_name))
context_corrs.registerTempTable(temp_table_correlations)
// ========================================================================================
hiveContext.sql(s"INSERT INTO TABLE $table_name_correlations SELECT * FROM $temp_table_correlations")
// ========================================================================================
// clean up environment
//println("Cleaning up temp tables")
hiveContext.dropTempTable(temp_table_correlations)
hiveContext.dropTempTable(temp_table_similarities)
hiveContext.dropTempTable(temp_table_vocabulary)
return true
}
val partitioned = tokenized.repartition(tokenized("context_id"))
val context_counts = partitioned.mapPartitions()
//val context_counts = model_code_ids.zipWithIndex.map{case (model_code_id, context_index) => compute_similarity(tokenized.filter(tokenized("context_id") === model_code_id), country_name, model_code_id.asInstanceOf[String], table_name_correlations, context_layer, context_index.toString)}
}
我已经尝试过：
val category_ids = df.select("Category").distinct.collect()
val result = category_ids.map(category_id => myComplexFunction(df.filter(df("Category") <=> category_id)))
我不知道为什么，但这种方法是按顺序运行的，而不是并行运行的。
【问题讨论】：
标签： apache-spark dataframe parallel-processing aggregate-functions custom-function