Topic statistics to estimate factor loading

Usage

asap_pmf_stat_interacting_columns_mtx(
  mtx_file,
  row_file,
  col_file,
  idx_file,
  log_beta,
  beta_row_names,
  W_nm_list,
  mtx_file2 = NULL,
  row_file2 = NULL,
  col_file2 = NULL,
  idx_file2 = NULL,
  A_dd_list = NULL,
  do_stdize_beta = TRUE,
  do_product = FALSE,
  NUM_THREADS = 0L,
  CELL_NORM = 10000,
  BLOCK_SIZE = 1000L,
  MAX_ROW_WORD = 2L,
  ROW_WORD_SEP = "_",
  MAX_COL_WORD = 100L,
  COL_WORD_SEP = "@",
  verbose = FALSE
)

Arguments

mtx_file: matrix-market-formatted data file (D x N, bgzip)
row_file: row names file (D x 1)
col_file: column names file (N x 1)
idx_file: matrix-market colum index file
log_beta: D x K log dictionary/design matrix
beta_row_names: row names log_beta (D vector)
W_nm_list: list(src.index, tgt.index, weights) for columns
A_dd_list: list(src.index, tgt.index, weights) for features
do_stdize_beta: use standardized log_beta (default: TRUE)
do_product: yi * yj for interaction (default: FALSE)
NUM_THREADS: number of threads in data reading
CELL_NORM: normalization constant per each data point
BLOCK_SIZE: disk I/O block size (number of columns)
MAX_ROW_WORD: maximum words per line in row_files[i]
ROW_WORD_SEP: word separation character to replace white space
MAX_COL_WORD: maximum words per line in col_files[i]
COL_WORD_SEP: word separation character to replace white space
verbose: verbosity

Value

a list that contains:

beta dictionary matrix (row x factor)
corr empirical correlation (column x factor)
colsum the sum of each column (column x 1)