from __future__ import print_function

import pandas as pd

from pyspark.sql import HiveContext

from pyspark import SparkContext,SparkConf

from sqlalchemy import create_engine

import datetime

import pyspark.sql.functions as F

 

conf = SparkConf().setAppName("abc")

sc = SparkContext(conf=conf)

hiveCtx = HiveContext(sc)

 

# 创建dataframe

d = [{‘name‘: ‘Alice‘, ‘age‘: 1},{‘name‘: ‘Bob‘, ‘age‘: 5}]

df = sqlContext.createDataFrame(d)

df.show() 

 

sql = "" # 拉数SQL

df  = hiveCtx.sql(sql)

df.show() # 不加参数默认展示前20行

df.count() 

df.printSchema() 

df.columns

df.select(‘age‘,‘name‘) # 带show才能看到结果

df.select(df.age.alias(‘age_value‘),‘name‘)

df.filter(df.name==‘Alice‘)

‘lit‘: ‘Creates a :class:`Column` of literal value.‘,

‘col‘: ‘Returns a :class:`Column` based on the given column name.‘,

‘column‘: ‘Returns a :class:`Column` based on the given column name.‘,

‘asc‘: ‘Returns a sort expression based on the ascending order of the given column name.‘,

‘desc‘: ‘Returns a sort expression based on the descending order of the given column name.‘,

 

‘upper‘: ‘Converts a string expression to upper case.‘,

‘lower‘: ‘Converts a string expression to upper case.‘,

‘sqrt‘: ‘Computes the square root of the specified float value.‘,

‘abs‘: ‘Computes the absolutle value.‘,

 

‘max‘: ‘Aggregate function: returns the maximum value of the expression in a group.‘,

‘min‘: ‘Aggregate function: returns the minimum value of the expression in a group.‘,

‘first‘: ‘Aggregate function: returns the first value in a group.‘,

‘last‘: ‘Aggregate function: returns the last value in a group.‘,

‘count‘: ‘Aggregate function: returns the number of items in a group.‘,

‘sum‘: ‘Aggregate function: returns the sum of all values in the expression.‘,

‘avg‘: ‘Aggregate function: returns the average of the values in a group.‘,

‘mean‘: ‘Aggregate function: returns the average of the values in a group.‘,

‘sumDistinct‘: ‘Aggregate function: returns the sum of distinct values in the expression.‘,

 

---------------------------

 

df.select(F.max(df.age))

df.select(F.min(df.age))

df.select(F.avg(df.age)) # 也可以用mean，一样的效果

df.select(F.countDistinct(df.age)) # 去重后统计

df.select(F.count(df.age)) # 直接统计，经试验，这个函数会去掉缺失值会再统计

 

from pyspark.sql import Window

df.withColumn("row_number", F.row_number().over(Window.partitionBy("a","b","c","d").orderBy("time"))).show() # row_number()函数

all_bike.rdd.map(lambda line: u‘,‘.join(map(lambda x:unicode(x),line))).saveAsTextFile(‘/user/hive/warehouse/bi.db/bikeid_without_3codes_a_d/dt={}‘.format(t0_uf)) #转化为RDD写入HDFS路径

bike_change_2days.registerTempTable(‘bike_change_2days‘)
sqlContext.sql("insert into bi.bike_changes_2days_a_d partition(dt=‘%s‘) select citycode,biketype,detain_bike_flag,bike_tag_onday,bike_tag_yesterday,bike_num from bike_change_2days"%(date))

df_spark.write.mode("append").insertInto(‘bi.pesudo_bike_white_list‘) # 直接使用write.mode方法insert到指定的集群表

如果你熟悉Pandas包，并且PySpark处理的中间数据量不是太大，那么可以直接转换成pandas DataFrame，然后转化成常规操作。
df.toPandas() # PySpark DataFrame转化成Pandas DataFrame



import pandas as pd
df_p = pd.DataFrame(dict(num=range(3),char=[‘a‘,‘b‘,‘c‘]))
df_s = sqlContext.createDataFrame(df_p) # pandas dataframe转化成PySpark DataFrame
type(df_s)