# unaryReduceStrided1d
> Perform a reduction over a list of specified dimensions in an input ndarray via a one-dimensional strided array reduction function and assign results to a provided output ndarray.
## Usage
```javascript
var unaryReduceStrided1d = require( '@stdlib/ndarray/base/unary-reduce-strided1d' );
```
#### unaryReduceStrided1d( fcn, arrays, dims\[, options] )
Performs a reduction over a list of specified dimensions in an input ndarray via a one-dimensional strided array reduction function and assigns results to a provided output ndarray.
```javascript
var Float64Array = require( '@stdlib/array/float64' );
var ndarray2array = require( '@stdlib/ndarray/base/to-array' );
var getStride = require( '@stdlib/ndarray/base/stride' );
var getOffset = require( '@stdlib/ndarray/base/offset' );
var getData = require( '@stdlib/ndarray/base/data-buffer' );
var numelDimension = require( '@stdlib/ndarray/base/numel-dimension' );
var gsum = require( '@stdlib/blas/ext/base/gsum' ).ndarray;
function wrapper( arrays ) {
var x = arrays[ 0 ];
return gsum( numelDimension( x, 0 ), getData( x ), getStride( x, 0 ), getOffset( x ) );
}
// Create data buffers:
var xbuf = new Float64Array( [ 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0 ] );
var ybuf = new Float64Array( [ 0.0, 0.0, 0.0 ] );
// Define the array shapes:
var xsh = [ 1, 3, 2, 2 ];
var ysh = [ 1, 3 ];
// Define the array strides:
var sx = [ 12, 4, 2, 1 ];
var sy = [ 3, 1 ];
// Define the index offsets:
var ox = 0;
var oy = 0;
// Create an input ndarray-like object:
var x = {
'dtype': 'float64',
'data': xbuf,
'shape': xsh,
'strides': sx,
'offset': ox,
'order': 'row-major'
};
// Create an output ndarray-like object:
var y = {
'dtype': 'float64',
'data': ybuf,
'shape': ysh,
'strides': sy,
'offset': oy,
'order': 'row-major'
};
// Perform a reduction:
unaryReduceStrided1d( wrapper, [ x, y ], [ 2, 3 ] );
var arr = ndarray2array( y.data, y.shape, y.strides, y.offset, y.order );
// returns [ [ 10.0, 26.0, 42.0 ] ]
```
The function accepts the following arguments:
- **fcn**: function which will be applied to a one-dimensional subarray and should reduce the subarray to a single scalar value.
- **arrays**: array-like object containing one input ndarray and one output ndarray, followed by any additional ndarray arguments.
- **dims**: list of dimensions over which to perform a reduction.
- **options**: function options which are passed through to `fcn` (_optional_).
Each provided ndarray should be an object with the following properties:
- **dtype**: data type.
- **data**: data buffer.
- **shape**: dimensions.
- **strides**: stride lengths.
- **offset**: index offset.
- **order**: specifies whether an ndarray is row-major (C-style) or column major (Fortran-style).
#### TODO: document factory method
## Notes
- The output ndarray is expected to have the same dimensions as the non-reduced dimensions of the input ndarray.
- Any additional ndarray arguments are expected to have the same leading dimensions as the non-reduced dimensions of the input ndarray.
- When calling the reduction function, any additional ndarray arguments are provided as k-dimensional subarrays, where `k = M - N` with `M` being the number of dimensions in an ndarray argument and `N` being the number of non-reduced dimensions in the input ndarray. For example, if an input ndarray has three dimensions, the number of reduced dimensions is two, and an additional ndarray argument has one dimension, thus matching the number of non-reduced dimensions in the input ndarray, the reduction function is provided a zero-dimensional subarray as an additional ndarray argument. In the same scenario but where an additional ndarray argument has two dimensions, thus exceeding the number of non-reduced dimensions in the input ndarray, the reduction function is provided a one-dimensional subarray as an additional ndarray argument.
- The reduction function is expected to have the following signature:
```text
fcn( arrays[, options] )
```
where
- **arrays**: array containing a one-dimensional subarray of the input ndarray and any additional ndarray arguments as subarrays.
- **options**: function options (_optional_).
- For very high-dimensional ndarrays which are non-contiguous, one should consider copying the underlying data to contiguous memory before performing a reduction in order to achieve better performance.
## Examples
```javascript
var discreteUniform = require( '@stdlib/random/array/discrete-uniform' );
var zeros = require( '@stdlib/array/base/zeros' );
var ndarray2array = require( '@stdlib/ndarray/base/to-array' );
var numelDimension = require( '@stdlib/ndarray/base/numel-dimension' );
var getData = require( '@stdlib/ndarray/base/data-buffer' );
var getStride = require( '@stdlib/ndarray/base/stride' );
var getOffset = require( '@stdlib/ndarray/base/offset' );
var gsum = require( '@stdlib/blas/ext/base/gsum' ).ndarray;
var unaryReduceStrided1d = require( '@stdlib/ndarray/base/unary-reduce-strided1d' );
function wrapper( arrays ) {
var x = arrays[ 0 ];
return gsum( numelDimension( x, 0 ), getData( x ), getStride( x, 0 ), getOffset( x ) ); // eslint-disable-line max-len
}
var N = 10;
var x = {
'dtype': 'generic',
'data': discreteUniform( N, -5, 5, {
'dtype': 'generic'
}),
'shape': [ 1, 5, 2 ],
'strides': [ 10, 2, 1 ],
'offset': 0,
'order': 'row-major'
};
var y = {
'dtype': 'generic',
'data': zeros( 2 ),
'shape': [ 1, 2 ],
'strides': [ 2, 1 ],
'offset': 0,
'order': 'row-major'
};
unaryReduceStrided1d( wrapper, [ x, y ], [ 1 ] );
console.log( ndarray2array( x.data, x.shape, x.strides, x.offset, x.order ) );
console.log( ndarray2array( y.data, y.shape, y.strides, y.offset, y.order ) );
```