Calculating duration by subtracting two datetime columns in string format

Question

I have a Spark Dataframe in that consists of a series of dates:

from pyspark.sql import SQLContext
from pyspark.sql import Row
from pyspark.sql.types import          


        

Answer 1

datediff(Column end, Column start)

Returns the number of days from start to end.

https://spark.apache.org/docs/1.6.2/api/java/org/apache/spark/sql/functions.html

Answer 2

As of Spark 1.5 you can use unix_timestamp:

from pyspark.sql import functions as F
timeFmt = "yyyy-MM-dd'T'HH:mm:ss.SSS"
timeDiff = (F.unix_timestamp('EndDateTime', format=timeFmt)
            - F.unix_timestamp('StartDateTime', format=timeFmt))
df = df.withColumn("Duration", timeDiff)

Note the Java style time format.

>>> df.show()
+---+--------------------+--------------------+--------+
| ID|         EndDateTime|       StartDateTime|Duration|
+---+--------------------+--------------------+--------+
|X01|2014-02-13T12:36:...|2014-02-13T12:31:...|     258|
|X02|2014-02-13T12:35:...|2014-02-13T12:32:...|     204|
|X03|2014-02-13T12:36:...|2014-02-13T12:32:...|     228|
|XO4|2014-02-13T12:37:...|2014-02-13T12:32:...|     269|
|XO5|2014-02-13T12:36:...|2014-02-13T12:33:...|     202|
+---+--------------------+--------------------+--------+

Answer 3

This can be done in spark-sql by converting the string date to timestamp and then getting the difference.

1: Convert to timestamp:

CAST(UNIX_TIMESTAMP(MY_COL_NAME,'dd-MMM-yy') as TIMESTAMP

2: Get the difference between dates using datediff function.

This will be combined in a nested function like:

spark.sql("select COL_1, COL_2, datediff( CAST( UNIX_TIMESTAMP( COL_1,'dd-MMM-yy') as TIMESTAMP), CAST( UNIX_TIMESTAMP( COL_2,'dd-MMM-yy') as TIMESTAMP) ) as LAG_in_days from MyTable")

Below is the result:

+---------+---------+-----------+
|    COL_1|    COL_2|LAG_in_days|
+---------+---------+-----------+
|24-JAN-17|16-JAN-17|          8|
|19-JAN-05|18-JAN-05|          1|
|23-MAY-06|23-MAY-06|          0|
|18-AUG-06|17-AUG-06|          1|
+---------+---------+-----------+

Reference: https://docs-snaplogic.atlassian.net/wiki/spaces/SD/pages/2458071/Date+Functions+and+Properties+Spark+SQL

Answer 4

Thanks to David Griffin. Here's how to do this for future reference.

from pyspark.sql import SQLContext, Row
sqlContext = SQLContext(sc)
from pyspark.sql.types import StringType, IntegerType, StructType, StructField
from pyspark.sql.functions import udf

# Build sample data
rdd = sc.parallelize([('X01','2014-02-13T12:36:14.899','2014-02-13T12:31:56.876'),
                      ('X02','2014-02-13T12:35:37.405','2014-02-13T12:32:13.321'),
                      ('X03','2014-02-13T12:36:03.825','2014-02-13T12:32:15.229'),
                      ('XO4','2014-02-13T12:37:05.460','2014-02-13T12:32:36.881'),
                      ('XO5','2014-02-13T12:36:52.721','2014-02-13T12:33:30.323')])
schema = StructType([StructField('ID', StringType(), True),
                     StructField('EndDateTime', StringType(), True),
                     StructField('StartDateTime', StringType(), True)])
df = sqlContext.createDataFrame(rdd, schema)

# define timedelta function (obtain duration in seconds)
def time_delta(y,x): 
    from datetime import datetime
    end = datetime.strptime(y, '%Y-%m-%dT%H:%M:%S.%f')
    start = datetime.strptime(x, '%Y-%m-%dT%H:%M:%S.%f')
    delta = (end-start).total_seconds()
    return delta

# register as a UDF 
f = udf(time_delta, IntegerType())

# Apply function
df2 = df.withColumn('Duration', f(df.EndDateTime, df.StartDateTime)) 

Applying time_delta() will give you duration in seconds:

>>> df2.show()
ID  EndDateTime          StartDateTime        Duration
X01 2014-02-13T12:36:... 2014-02-13T12:31:... 258     
X02 2014-02-13T12:35:... 2014-02-13T12:32:... 204     
X03 2014-02-13T12:36:... 2014-02-13T12:32:... 228     
XO4 2014-02-13T12:37:... 2014-02-13T12:32:... 268     
XO5 2014-02-13T12:36:... 2014-02-13T12:33:... 202 

Answer 5

Use DoubleType instead of IntegerType

from pyspark.sql import SQLContext, Row
sqlContext = SQLContext(sc)
from pyspark.sql.types import StringType, IntegerType, StructType, StructField
from pyspark.sql.functions import udf


# Build sample data
rdd = sc.parallelize([('X01','2014-02-13T12:36:14.899','2014-02-13T12:31:56.876'),
                      ('X02','2014-02-13T12:35:37.405','2014-02-13T12:32:13.321'),
                      ('X03','2014-02-13T12:36:03.825','2014-02-13T12:32:15.229'),
                      ('XO4','2014-02-13T12:37:05.460','2014-02-13T12:32:36.881'),
                      ('XO5','2014-02-13T12:36:52.721','2014-02-13T12:33:30.323')])
schema = StructType([StructField('ID', StringType(), True),
                     StructField('EndDateTime', StringType(), True),
                     StructField('StartDateTime', StringType(), True)])
df = sqlContext.createDataFrame(rdd, schema)

# define timedelta function (obtain duration in seconds)
def time_delta(y,x): 
    from datetime import datetime
    end = datetime.strptime(y, '%Y-%m-%dT%H:%M:%S.%f')
    start = datetime.strptime(x, '%Y-%m-%dT%H:%M:%S.%f')
    delta = (end-start).total_seconds()
    return delta

# register as a UDF 
f = udf(time_delta, DoubleType())

# Apply function
df2 = df.withColumn('Duration', f(df.EndDateTime, df.StartDateTime))

Answer 6

Here is a working version for spark 2.x derived from jason's answer

from pyspark import SparkContext, SparkConf
from pyspark.sql import SparkSession,SQLContext
from pyspark.sql.types import StringType, StructType, StructField

sc = SparkContext()
sqlContext = SQLContext(sc)
spark = SparkSession.builder.appName("Python Spark SQL basic example").getOrCreate()

rdd = sc.parallelize([('X01','2014-02-13T12:36:14.899','2014-02-13T12:31:56.876'),
                      ('X02','2014-02-13T12:35:37.405','2014-02-13T12:32:13.321'),
                      ('X03','2014-02-13T12:36:03.825','2014-02-13T12:32:15.229'),
                      ('XO4','2014-02-13T12:37:05.460','2014-02-13T12:32:36.881'),
                      ('XO5','2014-02-13T12:36:52.721','2014-02-13T12:33:30.323')])
schema = StructType([StructField('ID', StringType(), True),
                     StructField('EndDateTime', StringType(), True),
                     StructField('StartDateTime', StringType(), True)])
df = sqlContext.createDataFrame(rdd, schema)

# register as a UDF 
from datetime import datetime
sqlContext.registerFunction("time_delta", lambda y,x:(datetime.strptime(y, '%Y-%m-%dT%H:%M:%S.%f')-datetime.strptime(x, '%Y-%m-%dT%H:%M:%S.%f')).total_seconds())

df.createOrReplaceTempView("Test_table")

spark.sql("SELECT ID,EndDateTime,StartDateTime,time_delta(EndDateTime,StartDateTime) as time_delta FROM Test_table").show()

sc.stop()