How to flatten a struct in a Spark dataframe?
Here is function that is doing what you want and that can deal with multiple nested columns containing columns with same name:
import pyspark.sql.functions as F
def flatten_df(nested_df):
flat_cols = [c[0] for c in nested_df.dtypes if c[1][:6] != 'struct']
nested_cols = [c[0] for c in nested_df.dtypes if c[1][:6] == 'struct']
flat_df = nested_df.select(flat_cols +
[F.col(nc+'.'+c).alias(nc+'_'+c)
for nc in nested_cols
for c in nested_df.select(nc+'.*').columns])
return flat_df
Before:
root
|-- x: string (nullable = true)
|-- y: string (nullable = true)
|-- foo: struct (nullable = true)
| |-- a: float (nullable = true)
| |-- b: float (nullable = true)
| |-- c: integer (nullable = true)
|-- bar: struct (nullable = true)
| |-- a: float (nullable = true)
| |-- b: float (nullable = true)
| |-- c: integer (nullable = true)
After:
root
|-- x: string (nullable = true)
|-- y: string (nullable = true)
|-- foo_a: float (nullable = true)
|-- foo_b: float (nullable = true)
|-- foo_c: integer (nullable = true)
|-- bar_a: float (nullable = true)
|-- bar_b: float (nullable = true)
|-- bar_c: integer (nullable = true)
This should work in Spark 1.6 or later:
df.select(df.col("data.*"))
or
df.select(df.col("data.id"), df.col("data.keyNote"), df.col("data.details"))