Example code for loading a CSV file as a DF in Databricks Community Edition and saving it as a table

MyNotebook.py

# Loading PySpark modules

from pyspark.sql import DataFrame
from pyspark.sql.types import *

#from pyspark.context import SparkContext
#from pyspark.sql.session import SparkSession

# sc = SparkContext('local')
# spark = SparkSession(sc)

# Defining a schema for 'badges' table
badges_schema = StructType([StructField('UserId', IntegerType(), False),
                            StructField('Name', StringType(), False),
                            StructField('Date', TimestampType(), False),
                            StructField('Class', IntegerType(), False)])
                            
source_file_name = "/FileStore/tables/badges_csv.gz"
df = spark.read.csv(source_file_name, sep="\t", header=True, schema=badges_schema)

# Saving the df as a parquet file on DBFS
table_name = "badges"
df.write.format("parquet").option("parquet.enable.dictionary", "true") \
        .option("parquet.page.write-checksum.enabled", "false").mode('overwrite') \
        .saveAsTable(table_name)