从RDD创建DataFrame

import pandas as pd
import numpy as np
arr = np.arange(6).reshape(-1,3)

df_p=pd.DataFrame(arr)
df_p

df_p.columns=[‘a‘,‘b‘,‘c‘]
df_p

df_s=spark.createDataFrame(df_p)
df_s.show()

df_s.collect()

df_s.toPandas()

from pyspark.sql import Row
people = spark.sparkContext.textFile(‘file:///usr/local/spark/examples/src/main/resources/people.txt‘).map(lambda line:line.split(‘,‘)).map(lambda w:Row(name=w[0],age=int(w[1])))
sPeople = spark.createDataFrame(people)
sPeople.createOrReplaceTempView(‘people‘)

personDF = spark.sql(‘select name,age from people where age>20‘)
personRDD = personDF.rdd.map(lambda p:"Name:"+p.name+","+"Age:"+str(p.age))
personRDD.foreach(print)

sPeople.show()

sPeople.printSchema()

from pyspark.sql.types import *
from pyspark.sql import Row
schemaString = ‘name age‘
fields = [StructField(field_name,StringType(),True) for field_name in schemaString.split(‘ ‘)]
schema = StructType(fields)

lines = spark.sparkContext.textFile(‘file:///usr/local/spark/examples/src/main/resources/people.txt‘)
part = lines.map(lambda w:w.split(","))
peoples = part.map(lambda p:Row(p[0],p[1].strip()))
peoples.collect()

schemaPeople = spark.createDataFrame(people,schema)
schemaPeople.show()
schemaPeople.printSchema()

schemaPeople.write.json(‘file:///home/hadoop/schema_out‘)