val df = spark.read.parquet("/user/joal/wmf/data/wmf/mediawiki/wikidata_parquet/20190204")
val base_rdd = df.select("labels", "descriptions", "aliases").rdd
//val base_rdd = df.select("labels", "aliases").rdd
//val base_rdd = df.select("labels").rdd
//val base_rdd = df.select("aliases").rdd
//val base_rdd = df.select("descriptions").rdd
val strings = base_rdd.flatMap(r => {
r.getMap[String,String](0).values ++
r.getMap[String,String](1).values ++
r.getMap[String,Seq[String]](2).values.flatMap(l => l)
})
val grouped_strings = strings.map(s => (s, 1)).reduceByKey(_+_)
val total_bytes = grouped_strings.map(t => t._1.getBytes.length * t._2).sum()
val duplicate_bytes = grouped_strings.map(t => t._1.getBytes.length * (t._2 - 1)).sum()
// Triple check usefull bytes for strings:
grouped_strings.map(_._1.getBytes.length).sum() == (total_bytes - duplicate_bytes)
// true
val all_strings = strings.count()
// How many unique strings?
val unique_strings = grouped_strings.count()
// 98,524,732
// How many string with 1 instance?
val oneoc_strings = grouped_strings.filter(t => t._2 == 1).count()
// 72,584,179
// Leaving 25,940,553 unique strings having multiple instances
// --> If we go for table-indirection, we'll need ~100M longs (4 bytes)
// --> 400,000,000 bytes - 1 order of magnitude less than unique string size
println(f"-----------------------------------------------------")
println(f"Total bytes for strings: $total_bytes%15.0f")
println(f"Total duplicate bytes for strings: $duplicate_bytes%15.0f")
println(f"Useful bytes for strings: ${total_bytes - duplicate_bytes}%15.0f")
//Total bytes for strings: 45,724,033,674
//Total duplicate bytes for strings: 41,630,588,801
//Usefull bytes for strings: 4,093,444,873
// Usefull is 1 order of magnitude less than used
println(f"Total strings: $all_strings%15.0f")
println(f"Total unique strings: $unique_strings%15.0f")
println(f"Total one occurrence strings: $oneoc_strings%15.0f")
println(f"-----------------------------------------------------")