SparkSQL创建DataFrame:Pandas方式

from pyspark import SparkConf, SparkContext
from pyspark.sql import SparkSession
from pyspark.sql.types import *
import os
import pandas as pd

if __name__ == '__main__':

    spark = SparkSession.builder.master('local[*]').appName('create_df').getOrCreate()
    pandas_df = pd.DataFrame({'Local': ['BJ', 'SH', 'SZ'], 'name': ['Jack', 'Pony', 'Rose']})
    print(pandas_df)

    spark_df = spark.createDataFrame(pandas_df)

    spark_df.show()             # 打印表中的数据(列名, 数据)
    spark_df.printSchema()      # 打印表的元数据.