Pyspark - Utilities

flatten_schema.py

# source: https://stackoverflow.com/questions/37471346/automatically-and-elegantly-flatten-dataframe-in-spark-sql
from pyspark.sql.types import StructType, ArrayType  

def flatten(schema, prefix=None):
    fields = []
    for field in schema.fields:
        name = prefix + '.' + field.name if prefix else field.name
        dtype = field.dataType
        if isinstance(dtype, ArrayType):
            dtype = dtype.elementType

        if isinstance(dtype, StructType):
            fields += flatten(dtype, prefix=name)
        else:
            fields.append(name)

    return fields


df.select(flatten(df.schema)).show()