# -*- coding: utf-8 -*- import pandas as pd from pyspark.sql import SparkSession from pyspark.sql import SQLContext from pyspark import SparkContext#初始化數據#初始化pandas DataFrame df = pd.DataFrame([[1, 2, 3], [4, 5, 6]], index=['row1', 'row2'], columns=['c1', 'c2', 'c3'])#打印數據 print( df)#初始化spark DataFrame sc = 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"])#顯示數據 sentenceData.select("label").show()#spark.DataFrame 轉換成 pandas.DataFrame sqlContest = SQLContext(sc) spark_df = sqlContest.createDataFrame(df)#顯示數據 spark_df.select("c1").show()# pandas.DataFrame 轉換成 spark.DataFrame pandas_df = sentenceData.toPandas()#打印數據 print (pandas_df)

原文

總結

以上是生活随笔為你收集整理的pyspark.sql.DataFrame与pandas.DataFrame之间的相互转换的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。