pySpark dataframe列中获取最大值的最佳方法

转载

https://www.itranslater.com/qa/details/2582633432329225216

from pyspark.sql.functions import mean, min, max

result = df.select([mean("A"), min("A"), max("A")])
result.show()
+------+------+------+
|avg(A)|min(A)|max(A)|
+------+------+------+
|   2.0|   1.0|   3.0|

import pandas as pd
import time

time_dict = {}

dfff = self.spark.createDataFrame([(1., 4.), (2., 5.), (3., 6.)], ["A", "B"])
#--  For bigger/realistic dataframe just uncomment the following 3 lines
#lst = list(np.random.normal(0.0, 100.0, 100000))
#pdf = pd.DataFrame({'A': lst, 'B': lst, 'C': lst, 'D': lst})
#dfff = self.sqlContext.createDataFrame(pdf)

tic1 = int(round(time.time() * 1000))
# Method 1: Use describe()
max_val = float(dfff.describe("A").filter("summary = 'max'").select("A").collect()[0].asDict()['A'])
tac1 = int(round(time.time() * 1000))
time_dict['m1']= tac1 - tic1
print (max_val)

tic2 = int(round(time.time() * 1000))
# Method 2: Use SQL
dfff.registerTempTable("df_table")
max_val = self.sqlContext.sql("SELECT MAX(A) as maxval FROM df_table").collect()[0].asDict()['maxval']
tac2 = int(round(time.time() * 1000))
time_dict['m2']= tac2 - tic2
print (max_val)

tic3 = int(round(time.time() * 1000))
# Method 3: Use groupby()
max_val = dfff.groupby().max('A').collect()[0].asDict()['max(A)']
tac3 = int(round(time.time() * 1000))
time_dict['m3']= tac3 - tic3
print (max_val)

tic4 = int(round(time.time() * 1000))
# Method 4: Convert to RDD
max_val = dfff.select("A").rdd.max()[0]
tac4 = int(round(time.time() * 1000))
time_dict['m4']= tac4 - tic4
print (max_val)

tic5 = int(round(time.time() * 1000))
# Method 4: Convert to RDD
max_val = dfff.agg({"A": "max"}).collect()[0][0]
tac5 = int(round(time.time() * 1000))
time_dict['m5']= tac5 - tic5
print (max_val)

print time_dict