#! /usr/bin/env python3

import re
import numpy as np

InFileName="CRPSS.data"
OutFileName="CRPSS_orank.txt"

# Using readlines()
InFile = open(InFileName, 'r')
Lines = InFile.readlines()
OutFile = open(OutFileName, 'w')

count = 0
for line in Lines:
  count += 1
  if count < 3:
    continue
  words = re.split('\s+', line)
  if len(words) == 25:
    obs_idx=words[1]
    obs_sid="sid_" + words[1]
    ens_raw=words[2:22]
    ens_val=np.asarray(words[2:22], dtype='float64')
    obs_val=words[22]
  elif len(words) == 14:
    clm_val=np.asarray(words[3:12], dtype='float64')
    orank="V10.0.0 TEST NA 00 20210101 20210101 00 20210101 20210101 TMP K NA TMP K NA ANLSYS FULL NEAREST 1 NA NA NA NA ORANK 14760 " + obs_idx + " " + obs_sid + " NA NA NA NA " + obs_val + " NA 1 20 20 " + " ".join(ens_raw) + " NA " + str(np.mean(ens_val)) + " " + str(np.mean(clm_val)) + " " + str(np.std(ens_val)) + " NA NA NA " + str(np.std(clm_val)) + "\n"
    OutFile.write(orank)

# VERSION MODEL DESC       FCST_LEAD FCST_VALID_BEG  FCST_VALID_END  OBS_LEAD OBS_VALID_BEG   OBS_VALID_END   FCST_VAR FCST_UNITS FCST_LEV OBS_VAR OBS_UNITS OBS_LEV OBTYPE VX_MASK INTERP_MTHD INTERP_PNTS FCST_THRESH OBS_THRESH COV_THRESH ALPHA LINE_TYPE TOTAL INDEX OBS_SID OBS_LAT OBS_LON   OBS_LVL OBS_ELV OBS   PIT       RANK N_ENS_VLD N_ENS ENS_1 ENS_2 ENS_3 ENS_4 ENS_5 OBS_QC ENS_MEAN CLIMO_MEAN SPREAD     ENS_MEAN_OERR SPREAD_OERR SPREAD_PLUS_OERR CLIMO_STDEV

# time ../bin/stat_analysis -lookin CRPSS_orank.txt -job aggregate_stat -line_type ORANK -out_line_type ECNT -v 4 -out_bin_size 0.1 -out orank_to_ecnt.out