Safe Haskell	None
Language	Haskell2010

DataFrame.Operations.Join

Synopsis

data JoinType
- = INNER
- | LEFT
- | RIGHT
- | FULL_OUTER
join :: JoinType -> [Text] -> DataFrame -> DataFrame -> DataFrame
innerJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame
leftJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame
rightJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame
fullOuterJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame

Documentation

data JoinType Source #

Equivalent to SQL join types.

Constructors

INNER
LEFT
RIGHT
FULL_OUTER

join :: JoinType -> [Text] -> DataFrame -> DataFrame -> DataFrame Source #

Join two dataframes using SQL join semantics.

Only inner join is implemented for now.

innerJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame Source #

Performs an inner join on two dataframes using the specified key columns. Returns only rows where the key values exist in both dataframes.

Example

Expand

ghci> df = D.fromNamedColumns [("key", D.fromList [K0, K1, K2, K3]), (A, D.fromList [A0, A1, A2, A3])]
ghci> other = D.fromNamedColumns [("key", D.fromList [K0, K1, K2]), (B, D.fromList [B0, B1, B2])]
ghci> D.innerJoin ["key"] df other

-----------------
 key  |  A  |  B
------|-----|----
 Text | Text| Text
------|-----|----
 K0   | A0  | B0
 K1   | A1  | B1
 K2   | A2  | B2

leftJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame Source #

Performs a left join on two dataframes using the specified key columns. Returns all rows from the left dataframe, with matching rows from the right dataframe. Non-matching rows will have Nothing/null values for columns from the right dataframe.

Example

Expand

ghci> df = D.fromNamedColumns [("key", D.fromList [K0, K1, K2, K3]), (A, D.fromList [A0, A1, A2, A3])]
ghci> other = D.fromNamedColumns [("key", D.fromList [K0, K1, K2]), (B, D.fromList [B0, B1, B2])]
ghci> D.leftJoin ["key"] df other

------------------------
 key  |  A  |     B
------|-----|----------
 Text | Text| Maybe Text
------|-----|----------
 K0   | A0  | Just B0
 K1   | A1  | Just B1
 K2   | A2  | Just B2
 K3   | A3  | Nothing

rightJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame Source #

Performs a right join on two dataframes using the specified key columns. Returns all rows from the right dataframe, with matching rows from the left dataframe. Non-matching rows will have Nothing/null values for columns from the left dataframe.

Example

Expand

ghci> df = D.fromNamedColumns [("key", D.fromList [K0, K1, K2, K3]), (A, D.fromList [A0, A1, A2, A3])]
ghci> other = D.fromNamedColumns [("key", D.fromList [K0, K1]), (B, D.fromList [B0, B1])]
ghci> D.rightJoin ["key"] df other

-----------------
 key  |  A  |  B
------|-----|----
 Text | Text| Text
------|-----|----
 K0   | A0  | B0
 K1   | A1  | B1

fullOuterJoin :: [Text] -> DataFrame -> DataFrame -> DataFrame Source #