读学生课程分数文件chapter4-data01.txt,创建DataFrame。
>>> url = "file:///usr/local/spark/mycode/rdd/chapter4-data01.txt"
>>> rdd = spark.sparkContext.textFile(url).map(lambda line:line.split(','))
>>> rdd.take(3)
[['Aaron', 'OperatingSystem', '100'], ['Aaron', 'Python', '50'], ['Aaron', 'ComputerNetwork', '30']]
>>> from pyspark.sql.types import IntegerType,StringType,StructField,StructType
>>> from pyspark.sql import Row
>>> fields = [StructField('name',StringType(),True),StructField('course',StringType(),True),StructField('score',IntegerType(),True)]
>>> schema = StructType(fields)
>>> data = rdd.map(lambda p:Row(p[0],p[1],int(p[2])))
>>> df_scs = spark.createDataFrame(data,schema)
>>> df_scs.printSchema()
>>> df_scs.show()
用DataFrame的操作或SQL语句完成以下数据分析要求,并和用RDD操作的实现进行对比:
>>> df_scs.select('name','course',df_scs.score+5).show()
>>> df_scs.select('name').distinct().count()
>>> df_scs.select('course').distinct().show()
>>> df_scs.groupBy('name').count().show()
>>> df_scs.groupBy('course').count().show()
>>> df_scs.filter(df_scs.score>95).groupBy('course').count().show()
>>> df_scs.filter(df_scs.name=='Tom').show()
>>> df_scs.filter(df_scs.name=='Tom').orderBy(df_scs.score).show()
>>> df_scs.filter(df_scs.name=='Tom').agg({"score":"mean"}).show()
>>> df_scs.groupBy('course').avg('score').show()
>>> df_scs.groupBy('course').max('score').show()
>>> df_scs.groupBy('course').min('score').show()
>>> from pyspark.sql.functions import *
>>> df_scs.select(countDistinct('name').alias('学生人数'),countDistinct('course').alias('课程数'),round(mean('score'),2).alias('所有课的平均分')).show()
>>> df_scs.filter(df_scs.score<60).groupBy('course').count().show()
from pyspark.sql.types import IntegerType, StringType, StructField, StructType
fields = [StructField(...), ...]
schema = StructType(fields)
类型:http://spark.apache.org/docs/latest/sql-ref-datatypes.html
from pyspark.sql import Row
data = rdd.map(lambda p: Row(...))
Spark SQL DataFrame 操作
df.show()
df.printSchema()
df.count()
df.head(3)
df.collect()
df[‘name’]
df.name
df.first().asDict()
df.describe().show()
df.distinct()
df.filter(df['age'] > 21).show()
df.groupBy("age").count().show()
df.select('name', df['age‘] + 1).show()
df_scs.groupBy("course").avg('score').show()
df_scs.agg({"score": "mean"}).show()
df_scs.groupBy("course").agg({"score": "mean"}).show()