小开

df_concat = df_1.union(df_2)

The dataframes may need to have identical columns, in which case you can use withColumn() to create normal_1 and normal_2

小开

Maybe you can try creating the unexisting columns and calling union (unionAll for Spark 1.6 or lower):

from pyspark.sql.functions import lit


cols = ['id', 'uniform', 'normal', 'normal_2']


df_1_new = df_1.withColumn("normal_2", lit(None)).select(cols)
df_2_new = df_2.withColumn("normal", lit(None)).select(cols)


result = df_1_new.union(df_2_new)


# To remove the duplicates:


result = result.dropDuplicates()

小开

Here is one way to do it, in case it is still useful: I ran this in pyspark shell, Python version 2.7.12 and my Spark install was version 2.0.1.

PS: I guess you meant to use different seeds for the df_1 df_2 and the code below reflects that.

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


df_1 = sqlContext.range(0, 10)
df_2 = sqlContext.range(11, 20)
df_1 = df_1.select("id", rand(seed=10).alias("uniform"), randn(seed=27).alias("normal"))
df_2 = df_2.select("id", rand(seed=11).alias("uniform"), randn(seed=28).alias("normal_2"))


def get_uniform(df1_uniform, df2_uniform):
if df1_uniform:
return df1_uniform
if df2_uniform:
return df2_uniform


u_get_uniform = F.udf(get_uniform, FloatType())


df_3 = df_1.join(df_2, on = "id", how = 'outer').select("id", u_get_uniform(df_1["uniform"], df_2["uniform"]).alias("uniform"), "normal", "normal_2").orderBy(F.col("id"))

Here are the outputs I get:

df_1.show()
+---+-------------------+--------------------+
| id|            uniform|              normal|
+---+-------------------+--------------------+
|  0|0.41371264720975787|  0.5888539012978773|
|  1| 0.7311719281896606|  0.8645537008427937|
|  2| 0.1982919638208397| 0.06157382353970104|
|  3|0.12714181165849525|  0.3623040918178586|
|  4| 0.7604318153406678|-0.49575204523675975|
|  5|0.12030715258495939|  1.0854146699817222|
|  6|0.12131363910425985| -0.5284523629183004|
|  7|0.44292918521277047| -0.4798519469521663|
|  8| 0.8898784253886249| -0.8820294772950535|
|  9|0.03650707717266999| -2.1591956435415334|
+---+-------------------+--------------------+


df_2.show()
+---+-------------------+--------------------+
| id|            uniform|            normal_2|
+---+-------------------+--------------------+
| 11| 0.1982919638208397| 0.06157382353970104|
| 12|0.12714181165849525|  0.3623040918178586|
| 13|0.12030715258495939|  1.0854146699817222|
| 14|0.12131363910425985| -0.5284523629183004|
| 15|0.44292918521277047| -0.4798519469521663|
| 16| 0.8898784253886249| -0.8820294772950535|
| 17| 0.2731073068483362|-0.15116027592854422|
| 18| 0.7784518091224375| -0.3785563841011868|
| 19|0.43776394586845413| 0.47700719174464357|
+---+-------------------+--------------------+


df_3.show()
+---+-----------+--------------------+--------------------+
| id|    uniform|              normal|            normal_2|
+---+-----------+--------------------+--------------------+
|  0| 0.41371265|  0.5888539012978773|                null|
|  1|  0.7311719|  0.8645537008427937|                null|
|  2| 0.19829196| 0.06157382353970104|                null|
|  3| 0.12714182|  0.3623040918178586|                null|
|  4|  0.7604318|-0.49575204523675975|                null|
|  5|0.120307155|  1.0854146699817222|                null|
|  6| 0.12131364| -0.5284523629183004|                null|
|  7| 0.44292918| -0.4798519469521663|                null|
|  8| 0.88987845| -0.8820294772950535|                null|
|  9|0.036507078| -2.1591956435415334|                null|
| 11| 0.19829196|                null| 0.06157382353970104|
| 12| 0.12714182|                null|  0.3623040918178586|
| 13|0.120307155|                null|  1.0854146699817222|
| 14| 0.12131364|                null| -0.5284523629183004|
| 15| 0.44292918|                null| -0.4798519469521663|
| 16| 0.88987845|                null| -0.8820294772950535|
| 17| 0.27310732|                null|-0.15116027592854422|
| 18|  0.7784518|                null| -0.3785563841011868|
| 19| 0.43776396|                null| 0.47700719174464357|
+---+-----------+--------------------+--------------------+

小开

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()

小开

Above answers are very elegant. I have written this function long back where i was also struggling to concatenate two dataframe with distinct columns.

Suppose you have dataframe sdf1 and sdf2

from pyspark.sql import functions as F
from pyspark.sql.types import *


def unequal_union_sdf(sdf1, sdf2):
s_df1_schema = set((x.name, x.dataType) for x in sdf1.schema)
s_df2_schema = set((x.name, x.dataType) for x in sdf2.schema)


for i,j in s_df2_schema.difference(s_df1_schema):
sdf1 = sdf1.withColumn(i,F.lit(None).cast(j))


for i,j in s_df1_schema.difference(s_df2_schema):
sdf2 = sdf2.withColumn(i,F.lit(None).cast(j))


common_schema_colnames = sdf1.columns
sdk = \
sdf1.select(common_schema_colnames).union(sdf2.select(common_schema_colnames))
return sdk


sdf_concat = unequal_union_sdf(sdf1, sdf2)

小开

Maybe, you want to concatenate more of two Dataframes. I found a issue which use pandas Dataframe conversion.

Suppose you have 3 spark Dataframe who want to concatenate.

The code is the following:

list_dfs = []
list_dfs_ = []


df = spark.read.json('path_to_your_jsonfile.json',multiLine = True)
df2 = spark.read.json('path_to_your_jsonfile2.json',multiLine = True)
df3 = spark.read.json('path_to_your_jsonfile3.json',multiLine = True)


list_dfs.extend([df,df2,df3])


for df in list_dfs :


df = df.select([column for column in df.columns]).toPandas()
list_dfs_.append(df)


list_dfs.clear()


df_ = sqlContext.createDataFrame(pd.concat(list_dfs_))

小开

To make it more generic of keeping both columns in df1 and df2:

import pyspark.sql.functions as F


# Keep all columns in either df1 or df2
def outter_union(df1, df2):


# Add missing columns to df1
left_df = df1
for column in set(df2.columns) - set(df1.columns):
left_df = left_df.withColumn(column, F.lit(None))


# Add missing columns to df2
right_df = df2
for column in set(df1.columns) - set(df2.columns):
right_df = right_df.withColumn(column, F.lit(None))


# Make sure columns are ordered the same
return left_df.union(right_df.select(left_df.columns))

小开

I would solve this in this way:

from pyspark.sql import SparkSession
df_1.createOrReplaceTempView("tab_1")
df_2.createOrReplaceTempView("tab_2")
df_concat=spark.sql("select tab_1.id,tab_1.uniform,tab_1.normal,tab_2.normal_2  from tab_1 tab_1 left join tab_2 tab_2 on tab_1.uniform=tab_2.uniform\
union\
select tab_2.id,tab_2.uniform,tab_1.normal,tab_2.normal_2  from tab_2 tab_2 left join tab_1 tab_1 on tab_1.uniform=tab_2.uniform")
df_concat.show()

小开

You can use unionByName to make this:

df = df_1.unionByName(df_2)

unionByName is available since Spark 2.3.0.

小开

To concatenate multiple pyspark dataframes into one:

from functools import reduce


reduce(lambda x,y:x.union(y), [df_1,df_2])

And you can replace the list of [df_1, df_2] to a list of any length.

小开

I was trying to implement pandas append functionality in pyspark and what I created a custom function where we can concat 2 or more data frame even they are having different no. of columns only condition is if dataframes have identical name then their datatype should be same/match.

I have written a custom function to merge 2 dataframes.

def append_dfs(df1,df2):
list1 = df1.columns
list2 = df2.columns
for col in list2:
if(col not in list1):
df1 = df1.withColumn(col, F.lit(None))
for col in list1:
if(col not in list2):
df2 = df2.withColumn(col, F.lit(None))
return df1.unionByName(df2)

usage:

concate 2 dataframes

final_df = append_dfs(df1,df2)
1. concate more than 2(say3) dataframes
final_df = append_dfs(append_dfs(df1,df2),df3)

example:

df1:

df2:

result=append_dfs(df1,df2)

result :

Hope this will useful.

小开

unionByName is a built-in option available in spark which is available from spark 2.3.0.

with spark version 3.1.0, there is allowMissingColumns option with the default value set to False to handle missing columns. Even if both dataframes don't have the same set of columns, this function will work, setting missing column values to null in the resulting dataframe.

df_1.unionByName(df_2, allowMissingColumns=True).show()


+---+--------------------+--------------------+--------------------+
| id|             uniform|              normal|            normal_2|
+---+--------------------+--------------------+--------------------+
|  0|  0.8122802274304282|  1.2423430583597714|                null|
|  1|  0.8642043127063618|  0.3900018344856156|                null|
|  2|  0.8292577771850476|  1.8077401259195247|                null|
|  3|   0.198558705368724| -0.4270585782850261|                null|
|  4|0.012661361966674889|   0.702634599720141|                null|
|  5|  0.8535692890157796|-0.42355804115129153|                null|
|  6|  0.3723296190171911|  1.3789648582622995|                null|
|  7|  0.9529794127670571| 0.16238718777444605|                null|
|  8|  0.9746632635918108| 0.02448061333761742|                null|
|  9|   0.513622008243935|  0.7626741803250845|                null|
| 11|  0.3221262660507942|                null|  1.0269298899109824|
| 12|  0.4030672316912547|                null|   1.285648175568798|
| 13|  0.9690555459609131|                null|-0.22986601831364423|
| 14|0.011913836266515876|                null|  -0.678915153834693|
| 15|  0.9359607054250594|                null|-0.16557488664743034|
| 16| 0.45680471157575453|                null| -0.3885563551710555|
| 17|  0.6411908952297819|                null|  0.9161177183227823|
| 18|  0.5669232696934479|                null|  0.7270125277020573|
| 19|   0.513622008243935|                null|  0.7626741803250845|
+---+--------------------+--------------------+--------------------+

连接两个 PySpark 数据框架

usage:

example:

df1:

df2:

result :