////////////////////////////////////////////////////////////////////////////////
//
// Default vsdb_analysis configuration file
//
////////////////////////////////////////////////////////////////////////////////

//
// The parameters listed below are used to filter the VSDB data down to the
// desired subset of VSDB lines over which statistics are to be computed.  Only
// those VSDB lines which meet ALL of the parameters will be retained.
//
// The parameters set at the top level before the job list will be applied to
// each of the analysis jobs in the job list.  However, additional filtering
// parameter values may be specified for individual jobs using the appropriate
// option(s) to further refine the VSDB data over which to perform the analysis.
//

//
// Stratify by VSDB Output column 2:
// Specify a comma-separated list of model names to be used for all analyses
// performed.  If multiple models are listed, the analyses will be performed on
// their union.  These selections may be further refined by using the "-model"
// option within the job specification below.
// e.g. model[] = [ "model1", "model2", "model3" ];
//
model[] = [];

//
// Stratify by VSDB Output column 3:
// Specify a comma-separated list of forecast lead times in HH[MMSS] format to
// be used for all analyses performed.  If multiple forecast times are listed,
// the analyses will be performed on their union.  These selections may be
// further refined by using the "-fcst_lead" option within the job
// specification below.
// e.g. fcst_lead[] = [ "06", "12", "180000", "240000" ];
//
fcst_lead[] = [];

//
// Stratify by VSDB Output column 4:
// Specify beginning and ending valid times in YYYYMMDD[_HH[MMSS]] format to be
// used for all analyses performed.  If multiple valid times fall within the
// valid time window the, analyses  will be performed on their union.  These
// selections may be further refined by using the "-valid_time" option within
// the job specification below.
// e.g. valid_beg = "20070102";
//      valid_end = "20070103_000000";
//
valid_beg = "";
valid_end = "";

//
// Stratify by initialization time, derived from VSDB Output columns 3 and 4:
// Specify beginning and ending model initialization times in
// YYYYMMDD[_HH[MMSS]] format to be used for all analyses performed.  If
// multiple initialization times fall within the model initialization time
// window, the analyses  will be performed on their union.  These selections may
// be further refined by using the "-init_time" option within the job
// specification below.
// e.g. init_beg = "20070101_00";
//      init_end = "20070102";
//
init_beg = "";
init_end = "";

//
// Stratify by the initialization hour, derived from VSDB Output columns 3 and 4:
// Specify a comman-separated list of intialization hours (i.e. cycle time)
// in HH[MMSS] format to be used for all analyses performed.  This selection
// may be further refined by using the "-init_hour" option within the job
// specification below.
// e.g. init_hour[] = [ "00", "12" ];
//
init_hour[] = [];

//
// Stratify by VSDB Output column 5:
// Specify a comma-separated list of observation types to be used for all
// analyses performed.  If multiple observation types are listed, the
// analyses  will be performed on their union.  These selections may be
// further refined by using the "-obtype" option within the job specification
// below.
// e.g. obtype[] = [ "ANALYS", "ADPUPA", "ADPSFC" ];
//
obtype[] = [];

//
// Stratify by VSDB Output column 6:
// Specify a comma-separated list of verification masking regions to be used
// for all analyses performed.  If multiple verification masking regions are
// listed, the analyses  will be performed on their union.  These selections
// may be further refined by using the "-vx_mask" option within the job
// specification below.
// e.g. vx_mask[] = [ "G212", "LMV" ];
//
vx_mask[] = [];

//
// Stratify by VSDB Output column 7:
// Specify a comma-separated list of regular expressions for VSDB line types
// to be used for all analyses performed.  If multiple regular expressions for
// VSDB line types are listed, the analyses  will be performed on their union.
// These selections may be further refined by using the "-line_type" option
// within the job specification below.
// e.g. vsdb_type[] = [ "FHO>=0.0000", "CNT/0.050", "SL1L2" ];
//
line_type[] = [];

//
// Stratify by VSDB Output column 8:
// Specify a comma-separated list of model variables to be used for all analyses
// performed.  If multiple model variables are listed, the analyses  will be
// performed on their union.  These selections may be further refined by using
// the "-var" option within the job specification below.
// e.g. var[] = [ "TMP", "APCP/24", "RH" ];
//
var[] = [];

//
// Stratify by VSDB Output column 9:
// Specify a comma-separated list of model levels to be used for all analyses
// performed.  If multiple model levels are listed, the analyses  will be
// performed on their union.  These selections may be further refined by using
// the "-level" option within the job specification below.
// e.g. level[] = [ "SFC", "L10", "P750-950" ];
//
level[] = [];

//
// Stratify by the second to last VSDB Output column:
// Specify a comma-separated list of interpolation methods to be used for all
// analyses performed.  If multiple interpolation methods are listed, the
// analyses  will be performed on their union.  These selections may be further
// refined by using the "-interp_mthd" option within the job specification
// below.
// e.g. interp_mthd[] = [ "MIN", "MAX", "MEDIAN", "UW_MEAN", "DW_MEAN" ];
//
interp_mthd[] = [];

//
// Stratify by the last VSDB Output column:
// Specify a comma-separated list of interpolation points to be used for all
// analyses performed.  If multiple interpolation points are listed, the
// analyses  will be performed on their union.  These selections may be further
// refined by using the "-interp_pnts" option within the job specification
// below.
// e.g. interp_pnts[] = [ 1, 4, 9, 16 ];
//
interp_pnts[] = [];

//
// Specify the analysis jobs to be performed.  Each entry in the joblist
// contains the specifications for a single analysis job to be performed.
// The format for an analysis job is as follows:
//
//    -job job_name
//    OPTIONAL ARGS
//
//    Where "job_name" is set to one of the following:
//
//       "vsdb_job_filter"
//          To filter out the VSDB lines matching the criteria specified
//          above and using the optional arguments below.  The output
//          VSDB lines are written to the file specified using the
//          "-dump_row" option.
//          Required Args: -dump_row
//
//       "vsdb_job_summary"
//          To compute the mean, standard deviation, and percentiles
//          (0th, 10th, 25th, 50th, 75th, 90th, and 100th) for the
//          statistic specified using the "-line_type" and "-column"
//          arguments.
//          Required Args: -line_type, -column
//
//       "vsdb_job_aggr"
//          To aggregate the VSDB data for the VSDB line type specified
//          using the "-line_type" argument.  The output of the job will
//          be in the same format as the input line type specified.
//          Required Args: -line_type
//
//       "vsdb_job_aggr_cts"
//          To aggregate the VSDB data for the VSDB line type specified
//          using the "-line_type" argument.  The line type may be set to
//          FHO, CTC, CTP, CFP, or COP.  The output of the job will be
//          statistics derived from the aggregated contingency table.
//          Required Args: -line_type
//
//       "vsdb_job_aggr_cnt"
//          To aggregate the VSDB data for the VSDB line type specified
//          using the "-line_type" argument.  The line type may be set to
//          SL1L2 or SAL1L2.  The output of the job will be continuous
//          statistics derived from the aggregated partial sums.
//          Required Args: -line_type
//
//       "vsdb_job_aggr_mpr"
//          To aggregate the VSDB MPR line type and create an output line
//          type specified using the "-out_line_type" argument.  The out
//          line type may be set to FHO, CTC, CTP, CFP, COP, CTS, CNT,
//          SL1L2 or SAL1L2.  The "-threshold" argument may be required
//          depending on the output line type specified.
//          Required Args:
//             -var, -out_line_type
//             -threshold (-out_line_type = FHO, CTC, CTP, CFP, COP, CTS)
//          Additional Optional Args:
//             -mask_grid, -mask_poly
//
//       "vsdb_job_go_index"
//          To compute the GO Index for the data.  Note that all twelve of the
//          following fields must be present in the data with lead times of
//          12, 24, 36, and 48 hours to compute the GO Index:
//          Wind Speed at the surface, 850 mB, 400 mB, and 250 mB
//          Dewpoint Temperature at the surface, 850 mB, 700 mB, and 400 mB
//          Temperature at the surface, and 400 mB
//          Height at 400 mB
//          Sea Level Pressure
//          Required Args: -init_beg, -init_end (set to the same value)
//
//    Where the optional arguments are used to further refine the VSDB data
//    indicated by the parameters chosen above.  Each optional argument may be
//    used in the job specification multiple times unless otherwise indicated.
//    When multiple optional arguments of the same type are indicated, the
//    analysis will be performed over their union:
//
//       "-model name" to select the model name for the analysis.
//       "-fcst_lead HHMMSS" to select the forecast lead time for the analysis.
//       "-valid_beg YYYYMMDD[_HH[MMSS]]" to select the beginning of the valid
//          time window for the analysis (use once).
//       "-valid_end YYYYMMDD[_HH[MMSS]]" to select the ending of the valid
//          time window for the analysis (use once).
//       "-init_beg YYYYMMDD[_HH[MMSS]]" to select the beginning of the
//          initialization time window for the analysis (use once).
//       "-init_end YYYYMMDD[_HH[MMSS]]" to select the ending of the
//          initialization time window for the analysis (use once).
//       "-init_hour HH[MMSS]" to select the initialization hour
//          (i.e. cycle time) for the analysis (use once).
//       "-obtype name" to select the observation type for the analysis.
//       "-vx_mask name" to select the verification masking region for the
//          analysis.
//       "-line_type name" to select the VSDB line type for the analysis.
//       "-column name" to select the column of the VSDB line type for the
//          analysis (use once).
//       "-var name" to select the variable for the analysis.
//       "-level name" to select the vertical level for the analysis.
//       "-interp_mthd name" to select the interpolation method for the
//          analysis.
//       "-interp_pnts n" to select the number of interpolation points for the
//          analysis.
//
//       "-dump_row path" to select the filename to which the VSDB lines used
//          for the analysis should be written (use once).
//
//       "-alpha value" to override the default alpha value of 0.05 to be used
//          for the analysis (use once).
//       "-boot_interval value" to override the default bootstrap interval
//          method (use once).
//       "-boot_rep_prop value" to override the default bootstrap replicate
//          proportion size (use once).
//       "-n_boot_rep value" to override the default number of bootstrap
//          replicates to be used (use once).
//       "-boot_rng value" to override the default bootstrap random number
//          generator to be used (use once).
//       "-boot_seed value" to override the default bootstrap random number
//          generator seed value to be used (use once).
//
joblist[] = [
   "-job vsdb_job_aggr_mpr -out_line_type CNT -var RH"
];

//
// Specify the alpha value to be used when computing confidence intervals.
//
alpha = 0.05;

//
// Specify the method to be used for computing bootstrap confidence intervals.
// The value for this is interpreted as follows:
//    (0) Use the BCa interval method (computationally intensive)
//    (1) Use the percentile interval method
//
boot_interval = 1;

//
// Specify a proportion between 0 and 1 to define the replicate sample size
// to be used when computing percentile intervals.  The replicate sample
// size is set to boot_rep_prop * n, where n is the number of raw data points.
//
// e.g boot_rep_prop = 0.80;
//
boot_rep_prop = 1.0;

//
// Specify the number of times each set of matched pair data should be
// resampled when computing bootstrap confidence intervals.  A value of
// zero disables the computation of bootstrap condifence intervals.
//
// e.g. n_boot_rep = 1000;
//
n_boot_rep = 1000;

//
// Specify the name of the random number generator to be used.  See the MET
// Users Guide for a list of possible random number generators.
//
boot_rng = "mt19937";

//
// Specify the seed value to be used when computing bootstrap confidence
// intervals.  If left unspecified, the seed will change for each run and
// the computed bootstrap confidence intervals will not be reproducable.
//
boot_seed = "";

//
// Flag to indicate whether Kendall's Tau and Spearman's Rank Correlation
// Coefficients should be computed.  Computing them over large datasets is
// computationally intensive and slows down the runtime execution significantly.
//    (0) Do not compute these correlation coefficients
//    (1) Compute these correlation coefficients
//
rank_corr_flag = 1;

//
// Directory where temp files should be written by the vsdb_analysis tool
//
tmp_dir = "/tmp";

//
// Indicate a version number for the contents of this configuration file.
// The value should generally not be modified.
//
version = "V1.1";