Safe Haskell	None
Language	Haskell2010

DataFrame.Typed.Statistics

Description

Typed statistical reducers over a TypedDataFrame.

These mirror the untyped reducers in DataFrame.Operations.Statistics, taking a schema-checked TExpr instead of a raw Expr. The names (sum, mean, median, …) deliberately collide with the aggregation-expression combinators in DataFrame.Typed.Expr, so this module is meant to be imported qualified:

import qualified DataFrame.Typed.Statistics as TS

avg = TS.mean (col @"salary") employees

Synopsis

mean :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double
meanMaybe :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a) => TExpr cols (Maybe a) -> TypedDataFrame cols -> Double
median :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double
medianMaybe :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a) => TExpr cols (Maybe a) -> TypedDataFrame cols -> Double
percentile :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => Int -> TExpr cols a -> TypedDataFrame cols -> Double
genericPercentile :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Ord a) => Int -> TExpr cols a -> TypedDataFrame cols -> a
standardDeviation :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double
skewness :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double
variance :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double
interQuartileRange :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double
sum :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Num a) => TExpr cols a -> TypedDataFrame cols -> a
correlation :: forall (c1 :: Symbol) (c2 :: Symbol) a b (cols :: [(Symbol, Type)]). (KnownSymbol c1, KnownSymbol c2, a ~ SafeLookup c1 cols, b ~ SafeLookup c2 cols, Columnable a, Columnable b, Real a, Real b, Unbox a, Unbox b, AssertPresent c1 cols, AssertPresent c2 cols) => TypedDataFrame cols -> Maybe Double
frequencies :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Ord a) => TExpr cols a -> TypedDataFrame cols -> DataFrame
imputeWith :: forall a (cols :: [(Symbol, Type)]). (ImputeOp a, Columnable (BaseType a)) => (TExpr cols (BaseType a) -> TExpr cols (BaseType a)) -> TExpr cols a -> TypedDataFrame cols -> TypedDataFrame cols
summarize :: forall (cols :: [(Symbol, Type)]). TypedDataFrame cols -> DataFrame
describeColumns :: forall (cols :: [(Symbol, Type)]). TypedDataFrame cols -> DataFrame

Documentation

mean :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double Source #

Mean of a column.

meanMaybe :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a) => TExpr cols (Maybe a) -> TypedDataFrame cols -> Double Source #

Mean of a nullable column, ignoring Nothing.

median :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double Source #

Median of a column.

medianMaybe :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a) => TExpr cols (Maybe a) -> TypedDataFrame cols -> Double Source #

Median of a nullable column, ignoring Nothing.

percentile :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => Int -> TExpr cols a -> TypedDataFrame cols -> Double Source #

The n-th percentile of a column.

genericPercentile :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Ord a) => Int -> TExpr cols a -> TypedDataFrame cols -> a Source #

The n-th percentile of a column of any Ord type.

standardDeviation :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double Source #

Standard deviation of a column.

skewness :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double Source #

Skewness of a column.

variance :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double Source #

Variance of a column.

interQuartileRange :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Real a, Unbox a) => TExpr cols a -> TypedDataFrame cols -> Double Source #

Inter-quartile range of a column.

sum :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Num a) => TExpr cols a -> TypedDataFrame cols -> a Source #

Sum of a column.

correlation :: forall (c1 :: Symbol) (c2 :: Symbol) a b (cols :: [(Symbol, Type)]). (KnownSymbol c1, KnownSymbol c2, a ~ SafeLookup c1 cols, b ~ SafeLookup c2 cols, Columnable a, Columnable b, Real a, Real b, Unbox a, Unbox b, AssertPresent c1 cols, AssertPresent c2 cols) => TypedDataFrame cols -> Maybe Double Source #

Pearson's correlation coefficient between two columns, named by type application. Both columns must exist in the schema and be numeric — these are checked at compile time via SafeLookup on each name.

TS.correlation @"height" @"weight" people

frequencies :: forall a (cols :: [(Symbol, Type)]). (Columnable a, Ord a) => TExpr cols a -> TypedDataFrame cols -> DataFrame Source #

Frequency table for a column. The result schema is data-dependent (one column per distinct value), so an untyped DataFrame is returned.

imputeWith :: forall a (cols :: [(Symbol, Type)]). (ImputeOp a, Columnable (BaseType a)) => (TExpr cols (BaseType a) -> TExpr cols (BaseType a)) -> TExpr cols a -> TypedDataFrame cols -> TypedDataFrame cols Source #

Impute missing values in a column using a derived scalar (e.g. the mean). Schema-preserving: the imputed column keeps its type-level Maybe even though its runtime values are now fully populated.

summarize :: forall (cols :: [(Symbol, Type)]). TypedDataFrame cols -> DataFrame Source #

Descriptive statistics of the numeric columns. Returns an untyped DataFrame (the result is a fixed set of statistic rows, not the input schema).

describeColumns :: forall (cols :: [(Symbol, Type)]). TypedDataFrame cols -> DataFrame Source #

Per-column summary (non-null/null counts, unique values, type). Returns an untyped DataFrame.