Concatenate two PySpark dataframes

Question

I\'m trying to concatenate two PySpark dataframes with some columns that are only on each of them:

from pyspark.sql.functions import randn, rand

df_1 = sqlC         


        

Answer 1

This should do it for you ...

from pyspark.sql.types import FloatType
from pyspark.sql.functions import randn, rand, lit, coalesce, col
import pyspark.sql.functions as F

df_1 = sqlContext.range(0, 6)
df_2 = sqlContext.range(3, 10)
df_1 = df_1.select("id", lit("old").alias("source"))
df_2 = df_2.select("id")

df_1.show()
df_2.show()
df_3 = df_1.alias("df_1").join(df_2.alias("df_2"), df_1.id == df_2.id, "outer")\
  .select(\
    [coalesce(df_1.id, df_2.id).alias("id")] +\
    [col("df_1." + c) for c in df_1.columns if c != "id"])\
  .sort("id")
df_3.show()