Class: SpatialStats::Weights::CSRMatrix

Inherits:
Object
  • Object
show all
Defined in:
ext/spatial_stats/spatial_stats.c,
ext/spatial_stats/spatial_stats.c

Overview

CSRMatrix partially implements a compressed sparse row matrix to perform spatial lag and other calculations. This will generally be used to store the weights of an observation set.

See Also:

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(data, num_rows) ⇒ CSRMatrix

A new instance of CSRMatrix. Uses a Dictionary of Keys (DOK) as input to represent a square matrix.

Examples:

weights = {
    'a' => [{ id: 'c', weight: 1 }],
    'b' => [{ id: 'b', weight: 1 }],
    'c' => [{ id: 'a', weight: 1 }]
}
num_rows = 3

csr = CSRMatrix.new(data, num_rows)

Parameters:

  • data (Array) —

    in 1-D format

  • num_rows (Integer) —

    in the 2-D representation



138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
 
# File 'ext/spatial_stats/csr_matrix.c', line 138

VALUE csr_matrix_initialize(VALUE self, VALUE data, VALUE num_rows)
{
    VALUE keys;
    csr_matrix *csr;
    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);
    csr->init = 0;

    Check_Type(data, T_HASH);
    Check_Type(num_rows, T_FIXNUM);

    keys = rb_funcall(data, rb_intern("keys"), 0);

    // check dimensions are correct
    if (NUM2INT(num_rows) != (int)RARRAY_LEN(keys)) // Explicit cast to int
    {
        rb_raise(rb_eArgError, "n_rows != keys.size, check your dimensions");
    }

    mat_to_sparse(csr, data, keys, num_rows);

    rb_iv_set(self, "@n", num_rows);
    rb_iv_set(self, "@nnz", INT2NUM(csr->nnz));

    return self;
}

Instance Attribute Details

#m ⇒ Object (readonly)

#n ⇒ Object (readonly)

#nnz ⇒ Object (readonly)

Instance Method Details

#col_index ⇒ Array

Column indices of the non-zero values.

Returns:

  • (Array) —

    of the column indices.



192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
 
# File 'ext/spatial_stats/csr_matrix.c', line 192

VALUE csr_matrix_col_index(VALUE self)
{
    csr_matrix *csr;
    VALUE result;

    int i;

    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);

    result = rb_ary_new_capa(csr->nnz);
    for (i = 0; i < csr->nnz; i++)
    {
        rb_ary_store(result, i, INT2NUM(csr->col_index[i]));
    }

    return result;
}

#coordinates ⇒ Hash

A hash representation of the matrix with coordinates as keys.

Examples:

data = [
        [0, 1, 0]
        [0, 0, 0],
        [1, 0, 1]
       ]
num_rows = 3
num_cols = 3
data = data.flatten!
csr = CSRMatrix.new(data, num_rows, num_cols)

csr.coordinates
# => {
        [0,1] => 1,
        [2,0] => 1,
        [2,2] => 1
     }

Returns:

  • (Hash) 


348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
 
# File 'ext/spatial_stats/csr_matrix.c', line 348

VALUE csr_matrix_coordinates(VALUE self)
{
    csr_matrix *csr;
    VALUE result;

    int i;
    int k;

    VALUE key;
    VALUE val;
    int row_end;

    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);

    result = rb_hash_new();

    // iterate through every value in the matrix and assign it's coordinates
    // [x,y] as the key to the hash, with the value as the value.
    // Use i to keep track of what row we are on.
    i = 0;
    row_end = csr->row_index[1];
    for (k = 0; k < csr->nnz; k++)
    {
        if (k == row_end)
        {
            i++;
            row_end = csr->row_index[i + 1];
        }

        // store i,j coordinates j is col_index[k]
        key = rb_ary_new_capa(2);
        rb_ary_store(key, 0, INT2NUM(i));
        rb_ary_store(key, 1, INT2NUM(csr->col_index[k]));

        val = DBL2NUM(csr->values[k]);

        rb_hash_aset(result, key, val);
    }

    return result;
}

#dot_row(vec, row) ⇒ Float

Compute the dot product of the given row with the input vector. Equivalent to mulvec(vec)[row].

Parameters:

  • vec (Array) —

    of length n.

  • row (Integer) —

    of the dot product.

Returns:

  • (Float) —

    of the result of the dot product.



291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
 
# File 'ext/spatial_stats/csr_matrix.c', line 291

VALUE csr_matrix_dot_row(VALUE self, VALUE vec, VALUE row)
{
    csr_matrix *csr;
    VALUE result;

    int i;
    int jj;
    double tmp;

    Check_Type(vec, T_ARRAY);
    Check_Type(row, T_FIXNUM);

    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);

    if (RARRAY_LEN(vec) != csr->n)
    {
        rb_raise(rb_eArgError, "Dimension Mismatch CSRMatrix.n != vec.size");
    }

    i = NUM2INT(row);
    if (!(i >= 0 && i < csr->n))
    {
        rb_raise(rb_eArgError, "Index Error row_idx >= m or idx < 0");
    }

    tmp = 0;
    for (jj = csr->row_index[i]; jj < csr->row_index[i + 1]; jj++)
    {
        tmp += csr->values[jj] * NUM2DBL(rb_ary_entry(vec, csr->col_index[jj]));
    }

    result = DBL2NUM(tmp);
    return result;
}

#mulvec(vec) ⇒ Array

Multiply matrix by the input vector.

Parameters:

  • vec (Array) —

    of length n.

Returns:

  • (Array) —

    of the result of the multiplication.

See Also:



247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
 
# File 'ext/spatial_stats/csr_matrix.c', line 247

VALUE csr_matrix_mulvec(VALUE self, VALUE vec)
{
    csr_matrix *csr;
    VALUE result;

    int i;
    int jj;
    double tmp;

    Check_Type(vec, T_ARRAY);

    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);

    if (RARRAY_LEN(vec) != csr->n)
    {
        rb_raise(rb_eArgError, "Dimension Mismatch CSRMatrix.n != vec.size");
    }

    result = rb_ary_new_capa(csr->n);

    // float *vals = (float *)DATA_PTR(result);

    for (i = 0; i < csr->n; i++)
    {
        tmp = 0;
        for (jj = csr->row_index[i]; jj < csr->row_index[i + 1]; jj++)
        {
            tmp += csr->values[jj] * NUM2DBL(rb_ary_entry(vec, csr->col_index[jj]));
        }
        rb_ary_store(result, i, DBL2NUM(tmp));
    }

    return result;
}

#row_index ⇒ Array

Row indices of the non-zero values. Represents the start index of values in a row. For example [0,2,3] would represent a matrix with 2 rows, the first containing 2 non-zero values and the second containing 1. Length is num_rows + 1.

Used for row slicing operations.

Returns:

  • (Array) —

    of the row indices.



220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
 
# File 'ext/spatial_stats/csr_matrix.c', line 220

VALUE csr_matrix_row_index(VALUE self)
{
    csr_matrix *csr;
    VALUE result;

    int i;

    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);

    result = rb_ary_new_capa(csr->n + 1);
    for (i = 0; i <= csr->n; i++)
    {
        rb_ary_store(result, i, INT2NUM(csr->row_index[i]));
    }

    return result;
}

#values ⇒ Array

Non-zero values in the matrix.

Returns:

  • (Array) —

    of the non-zero values.



169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
 
# File 'ext/spatial_stats/csr_matrix.c', line 169

VALUE csr_matrix_values(VALUE self)
{
    csr_matrix *csr;
    VALUE result;

    int i;

    TypedData_Get_Struct(self, csr_matrix, &csr_matrix_type, csr);

    result = rb_ary_new_capa(csr->nnz);
    for (i = 0; i < csr->nnz; i++)
    {
        rb_ary_store(result, i, DBL2NUM(csr->values[i]));
    }

    return result;
}