pyspark dataframe 字段类型转换 pandas和pyspark的dataframe互转

知识点：

1、使用pyspark读取csv：spark.read.format("csv").load('/user/data.csv',header=True, inferSchema="true")

2、dataframe补充空值：fillna()

3、dataframe字段表示方式："APP_HOBY_CASH_LOAN"或df.APP_HOBY_CASH_LOAN或data_df["APP_HOBY_CASH_LOAN"]

pyspark dataframe使用astype实现dataframe字段类型转换

# 两种读取csv文件的方式
data_df = spark.read.format('com.databricks.spark.csv').options(header='true', inferschema='true').load("/user/data.csv")
data_df = spark.read.format("csv").load('/user/data.csv',header=True, inferSchema="true")
# 补充空值方法
data_df = data_df.fillna(0)
# 打印表结构 第一种执行较快
print(df_from_java.columns)
data_df.printSchema()
print(df_from_java.schema())
# 第一种方式
data_df = df.withColumn("APP_HOBY_CASH_LOAN", df.APP_HOBY_CASH_LOAN.cast('float'))
# 第二种方式
from pyspark.sql.types import IntegerType
data_df = data_df.withColumn("APP_HOBY_CASH_LOAN", data_df["APP_HOBY_CASH_LOAN"].cast(IntegerType()))
           

pandas dataframe使用astype实现dataframe字段类型转换

# -*- coding: UTF-8 -*-
import pandas as pd
df = pd.DataFrame([{'col1':'a', 'col2':'1'}, {'col1':'b', 'col2':'2'}])

print df.dtypes

df['col2'] = df['col2'].astype('int')
print '-----------'
print df.dtypes

df['col2'] = df['col2'].astype('float64')
print '-----------'
print df.dtypes
           

pandas和pyspark的dataframe互转

#!/usr/bin/python
# -*- coding: utf-8 -*-
from pyspark import SparkConf
from pyspark.sql import SparkSession
import pandas as pd


# pyspark dataframe转pandas dataframe
conf = SparkConf()
conf.set("spark.yarn.queue", "root") \
    .set("spark.app.name", "lbs_coordinate")
spark = SparkSession.builder.config(conf=conf).enableHiveSupport().getOrCreate()
pyspark_df = spark.sql("select * from tmp.test_table")
pandas_pd=pyspark_df.toPandas()


# pandas dataframe转pyspark dataframe
pandas_df = pd.DataFrame([{'col1':'a', 'col2':'1'}, {'col1':'b', 'col2':'2'}])
pyspark_df = spark.createDataFrame(pandas_df)