Created
August 4, 2020 10:13
-
-
Save weldpua2008/defc0a2e89b5294b71efdffcf8df1fe5 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark.sql.types import ArrayType, StructField, StructType, StringType, IntegerType | |
from pyspark.sql import SparkSession | |
# Create Spark session | |
spark = SparkSession.builder \ | |
.appName('appName') \ | |
.getOrCreate() | |
# List | |
data = [('Category A', 100, "This is category A"), | |
('Category B', 120, "This is category B"), | |
('Category C', 150, "This is category C")] | |
# Create a schema for the dataframe | |
schema = StructType([ | |
StructField('Category', StringType(), True), | |
StructField('Count', IntegerType(), True), | |
StructField('Description', StringType(), True) | |
]) | |
# Convert list to RDD | |
rdd = spark.sparkContext.parallelize(data) | |
# Create data frame | |
df = spark.createDataFrame(rdd,schema) | |
print(df.schema) | |
df.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment