假设有一个日期框架,其中一列包含日期作为字符串.对于该假设,我们创建以下dataFrame作为示例:
# Importing sql types
from pyspark.sql.types import StringType, IntegerType, StructType, StructField, DoubleType, FloatType, DateType
from pyspark.sql.functions import date_format
import random
import time
def strTimeProp(start, end, format, prop):
stime = time.mktime(time.strptime(start, format)) # Parse a string representing a time according to a format
etime = time.mktime(time.strptime(end, format))
ptime = stime + prop * (etime - stime)
return time.strftime(format, time.localtime(ptime))
def randomDate(start, end, prop):
return strTimeProp(start, end, '%m-%d-%Y', prop)
# Creación de un dataframe de prueba:
schema = StructType(
[
StructField("dates1", …Run Code Online (Sandbox Code Playgroud)