pyspark.sql.DataFrame与pandas.DataFrame之间的相互转换实例

# -*- coding: utf-8 -*-import pandas as pdfrom pyspark.sql import SparkSessionfrom pyspark.sql import SQLContextfrom pyspark import SparkContext #初始化数据 #初始化pandas DataFramedf = pd.DataFrame([[1, 2, 3], [4, 5, 6]], index=['row1', 'row2'], columns=['c1', 'c2', 'c3']) #打印数据print df #初始化spark DataFramesc = SparkContext()if __name__ == "__main__": spark = SparkSession/  .builder/  .appName("testDataFrame")/  .getOrCreate() sentenceData = spark.createDataFrame([ (0.0, "I like Spark"), (1.0, "Pandas is useful"), (2.0, "They are coded by Python ")], ["label", "sentence"]) #显示数据sentenceData.select("label").show() #spark.DataFrame 转换成 pandas.DataFramesqlContest = SQLContext(sc)spark_df = sqlContest.createDataFrame(df) #显示数据spark_df.select("c1").show()  # pandas.DataFrame 转换成 spark.DataFramepandas_df = sentenceData.toPandas() #打印数据print pandas_df