Skip to content

Update pyspark-add-month.py Straight forward solution to add months. #19

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
MdShahidAfridiP wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Update pyspark-add-month.py Straight forward solution to add months. #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3b9e388
Update pyspark-add-month.py
MdShahidAfridiP Feb 21, 2024
a99994b
Update pyspark-dataframe-flatMap.py
MdShahidAfridiP Feb 23, 2024
0e42a64
Update pyspark-dataframe-flatMap.py
MdShahidAfridiP Feb 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 2 additions & 5 deletions pyspark-add-month.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,6 @@
from pyspark.sql import SparkSession
spark = SparkSession.builder.appName('SparkByExamples.com').getOrCreate()

from pyspark.sql.functions import col,expr
from pyspark.sql.functions import add_months, to_date
data=[("2019-01-23",1),("2019-06-24",2),("2019-09-20",3)]
spark.createDataFrame(data).toDF("date","increment") \
.select(col("date"),col("increment"), \
expr("add_months(to_date(date,'yyyy-MM-dd'),cast(increment as int))").alias("inc_date")) \
.show()
spark.createDataFrame(data,schema=["date","increment"]).select(['date','increment',add_months(to_date('date'),'increment').alias("inc_date")]).show()
19 changes: 14 additions & 5 deletions pyspark-dataframe-flatMap.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,26 @@
"""


from pyspark.sql import SparkSession
from pyspark.sql import SparkSession, Row
spark = SparkSession.builder.appName('SparkByExamples.com').getOrCreate()

columns = ["name","languagesAtSchool","currentState"]
data = [("James,,Smith",["Java","Scala","C++"],"CA"), \
("Michael,Rose,",["Spark","Java","C++"],"NJ"), \
("Robert,,Williams",["CSharp","VB"],"NV")]

df = spark.createDataFrame(data=data,schema=columns)
df.printSchema()
df.show(truncate=False)
# Convert data to a DataFrame
rdd = spark.sparkContext.parallelize(data)
row_rdd = rdd.map(lambda x: Row(name=x[0], languagesAtSchool=x[1], currentState=x[2]))
df = spark.createDataFrame(row_rdd, columns)

#Flatmap
# Apply flatMap transformation
flat_mapped_df = df.rdd.flatMap(lambda x: [(x["name"], lang, x["currentState"]) for lang in x["languagesAtSchool"]])

# Convert result to DataFrame
result_columns = ["name", "language", "currentState"]
result_df = flat_mapped_df.toDF(result_columns)

# Show the result
result_df.show()