hipom_data_mapping/data_preprocess/abbreviations/replacement_dict.py

# substitution mapping for descriptions
# Abbreviations and their replacements
desc_replacement_dict = {
    r'\bLIST\b\b': 'LIST',
    r'\bList\b\b': 'LIST',
    r'\bEXH\.\b': 'EXHAUST',
    r'\bEXH\b\b': 'EXHAUST',
    r'\bEXHAUST\.\b': 'EXHAUST',
    r'\bExhaust\b\b': 'EXHAUST',
    r'\bEXHAUST\b\b': 'EXHAUST',
    r'\bTEMP\.\b': 'TEMPERATURE',
    r'\bTEMP\b\b': 'TEMPERATURE',
    r'\bTEMPERATURE\.\b': 'TEMPERATURE',
    r'\bTEMPERATURE\b\b': 'TEMPERATURE',
    r'\bW\.\b': 'WATER',
    r'\bWATER\b\b': 'WATER',
    r'\bCW\b\b': 'COOLING WATER',
    r'\bCYL\.\b': 'CYLINDER',
    r'\bCyl\b\b': 'CYLINDER',
    r'\bcyl\.\b': 'CYLINDER',
    r'\bCYL\b\b': 'CYLINDER',
    r'\bCYL(?=\d|\W|$)\b': 'CYLINDER',
    r'\bcylinder\b\b': 'CYLINDER',
    r'\bCYLINDER\b\b': 'CYLINDER',
    r'\bCOOL\.\b': 'COOLING',
    r'\bcool\.\b': 'COOLING',
    r'\bcooling\b\b': 'COOLING',
    r'\bCOOLING\b\b': 'COOLING',
    r'\bcooler\b\b': 'COOLER',
    r'\bCOOLER\b\b': 'COOLER',
    r'\bScav\.\b': 'SCAVENGE',
    r'\bSCAV\.\b': 'SCAVENGE',
    r'\bINL\.\b': 'INLET',
    r'\binlet\b\b': 'INLET',
    r'\bINLET\b\b': 'INLET',
    r'\bOUT\.\b': 'OUTLET',
    r'\bOUTL\.\b': 'OUTLET',
    r'\boutlet\b\b': 'OUTLET',
    r'\bOUTLET\b\b': 'OUTLET',
    # bunker tank
    r'\bBK\b': 'BUNKER',
    r'\bTK\b': 'TANK',
    # pressure
    r'\bPRESS\b\b': 'PRESSURE',
    r'\bPRESS\.\b': 'PRESSURE',
    r'\bPress\.\b': 'PRESSURE',
    r'\bpressure\b\b': 'PRESSURE',
    r'\bPRESSURE\b\b': 'PRESSURE',
    # this is a special replacement - it is safe to replace PRS w/o checks
    r'PRS\b': 'PRESSURE',
    r'\bCLR\b\b': 'CLEAR',
    r'\bENG\.\b': 'ENGINE',
    r'\bENG\b\b': 'ENGINE',
    r'\bENGINE\b\b': 'ENGINE',
    r'\bEngine speed\b\b': 'ENGINE SPEED',
    r'\bEngine running\b\b': 'ENGINE RUNNING',
    r'\bEngine RPM pickup\b\b': 'ENGINE RPM PICKUP',
    r'\bEngine room\b\b': 'ENGINE ROOM',
    # main engine
    r'\bM/E\b': 'MAIN_ENGINE',
    r'\bM_E\b': 'MAIN_ENGINE',
    r'\bME(?=\d|\W|$)\b': 'MAIN_ENGINE',
    r'\bMAIN ENGINE\b\b': 'MAIN_ENGINE',
    r'\bGen\b\b': 'GENERATOR_ENGINE',
    # ensure that we substitute only for terms where following GE is num or special
    r'\bGE(?=\d|\W|$)\b': 'GENERATOR_ENGINE',
    r'\bG/E\b': 'GENERATOR_ENGINE',
    r'\bG_E\b': 'GENERATOR_ENGINE',
    r'\bDG\b': 'GENERATOR_ENGINE',
    r'\bD/G\b\b': 'GENERATOR_ENGINE',
    r'\bGEN\.\b': 'GENERATOR_ENGINE',
    r'\bGENERATOR ENGINE\B\b': 'GENERATOR_ENGINE',
    r'\b(\d+)MGE\b\b': r'NO\1 GENERATOR_ENGINE',
    r'\bGEN\.WIND\.TEMP\b\b': 'GENERATOR WINDING TEMPERATURE',
    r'\bENGINE ROOM\b\b': 'ENGINE ROOM',
    r'\bE/R\b\b': 'ENGINE ROOM',
    r'\bFLTR\b\b': 'FILTER',
    # marine gas oil
    r'\bM\.G\.O\b\b': 'MARINE GAS OIL',
    r'\bMGO\b\b': 'MARINE GAS OIL',
    r'\bMDO\b\b': 'MARINE DIESEL OIL',
    # light fuel oil
    r'\bL\.F\.O\b\b': 'LIGHT FUEL OIL',
    r'\bLFO\b\b': 'LIGHT FUEL OIL',
    # heavy fuel oil
    r'\bHFO\b\b': 'HEAVY FUEL OIL',
    r'\bH\.F\.O\b\b': 'HEAVY FUEL OIL',
    # for remaining fuel oil that couldn't be substituted
    r'\bF\.O\b\b': 'FUEL OIL',
    r'\bFO\b\b': 'FUEL OIL',
    # lubricant
    r'\bLUB\.\b': 'LUBRICANT',
    # lubricating oil
    r'\bL\.O\b\b': 'LUBRICATING OIL',
    r'\bLO\b\b': 'LUBRICATING OIL',
    # lubricating oil pressure
    r'\bLO_PRESS\b\b': 'LUBRICATING OIL PRESSURE',
    r'\bLO_PRESSURE\b\b': 'LUBRICATING OIL PRESSURE',
    # temperature
    r'\bL\.T\b\b': 'LOW TEMPERATURE',
    r'\bLT\b\b': 'LOW TEMPERATURE',
    r'\bH\.T\b\b': 'HIGH TEMPERATURE',
    r'\bHT\b\b': 'HIGH TEMPERATURE',
    # auxiliary boiler
    # replace these first before replacing AUXILIARY only
    r'\bAUX\.BOILER\b': 'AUXILIARY BOILER',
    r'\bAUX\. BOILER\b': 'AUXILIARY BOILER',
    r'\bAUX BLR\b': 'AUXILIARY BOILER',
    r'\bAUX\.\b': 'AUXILIARY ',
    # composite boiler
    r'\bCOMP\. BOILER\b\b': 'COMPOSITE BOILER',
    r'\bCOMP\.BOILER\b\b': 'COMPOSITE BOILER',
    r'\bCOMP BOILER\b\b': 'COMPOSITE BOILER',
    r'\bWIND\.\b': 'WINDING',
    r'\bWINDING\b\b': 'WINDING',
    r'\bC\.S\.W\b\b': 'CSW',
    r'\bCSW\b\b': 'CSW',
    r'\bVLOT\.\b': 'VOLTAGE',
    r'\bVOLTAGE\b\b': 'VOLTAGE',
    r'\bVOLT\.\b': 'VOLTAGE',
    r'\bFREQ\.\b': 'FREQUENCY',
    r'\bFREQUENCY\b\b': 'FREQUENCY',
    r'\bCURR\.\b': 'CURRENT',
    r'\bCURRENT\b\b': 'CURRENT',
    r'\bTCA\b\b': 'TURBOCHARGER',
    r'\bTCB\b\b': 'TURBOCHARGER',
    r'\bT/C\b': 'TURBOCHARGER',
    r'\bT_C\b': 'TURBOCHARGER',
    r'\bTC(?=\d|\W|$)\b': 'TURBOCHARGER',
    r'\bTURBOCHAGER\b\b': 'TURBOCHARGER',
    r'\bTURBOCHARGER\b\b': 'TURBOCHARGER',
    # misc spelling errors
    r'\bOPERATOIN\b': 'OPERATION',
    # wrongly attached terms
    r'BOILERMGO': 'BOILER MGO',
    # additional standardizing replacement
    # replace # followed by a number with NO
    r'#(?=\d)\b': 'NO',
    r'\bNO\.(?=\d)\b': 'NO',
    # yes, there was one with two dots - what the hell?
    r'\bNO\.\.(?=\d)\b': 'NO',
    r'\bNo\.(?=\d)\b': 'NO',
}

# substitution mapping for units
# Abbreviations and their replacements
unit_replacement_dict = {
    r'\b%\b': 'PERCENT',
    r'\b-\b': '',
    r'\b-  \b': '',
    # ensure no character after A
    r'\bA(?!\w|/)': 'CURRENT',
    r'\bAmp(?!\w|/)': 'CURRENT',
    r'\bHz\b': 'HERTZ',
    r'\bKG/CM2\b': 'PRESSURE',
    r'\bKG/H\b': 'KILOGRAM PER HOUR',
    r'\bKNm\b': 'RPM',
    r'\bKW\b': 'POWER',
    r'\bKg(?!\w|/)': 'MASS',
    r'\bKw\b': 'POWER',
    r'\bL(?!\w|/)': 'VOLUME',
    r'\bMT/h\b': 'METRIC TONNES PER HOUR',
    r'\bMpa\b': 'PRESSURE',
    r'\bPF\b': 'POWER FACTOR',
    r'\bRPM\b': 'RPM',
    r'\bV(?!\w|/)': 'VOLTAGE',
    r'\bbar(?!\w|/)': 'PRESSURE',
    r'\bbarA\b': 'SCAVENGE PRESSURE',
    r'\bcST\b': 'VISCOSITY',
    r'\bcSt\b': 'VISCOSITY',
    r'\bcst\b': 'VISCOSITY',
    r'\bdeg(?!\w|/|\.)': 'DEGREE',
    r'\bdeg.C\b': 'TEMPERATURE',
    r'\bdegC\b': 'TEMPERATURE',
    r'\bdegree\b': 'DEGREE',
    r'\bdegreeC\b': 'TEMPERATURE',
    r'\bhPa\b': 'PRESSURE',
    r'\bhours\b': 'HOURS',
    r'\bkN\b': 'THRUST',
    r'\bkNm\b': 'TORQUE',
    r'\bkW\b': 'POWER',
    # ensure that kg is not followed by anything
    r'\bkg(?!\w|/)': 'FLOW', # somehow in the data its flow
    r'\bkg/P\b': 'MASS FLOW',
    r'\bkg/cm2\b': 'PRESSURE',
    r'\bkg/cm²\b': 'PRESSURE',
    r'\bkg/h\b': 'MASS FLOW',
    r'\bkg/hr\b': 'MASS FLOW',
    r'\bkg/pulse\b': '',
    r'\bkgf/cm2\b': 'PRESSURE',
    r'\bkgf/cm²\b': 'PRESSURE',
    r'\bkgf/㎠\b': 'PRESSURE',
    r'\bknots\b': 'SPEED',
    r'\bkw\b': 'POWER',
    r'\bl/Hr\b': 'VOLUME FLOW',
    r'\bl/h\b': 'VOLUME FLOW',
    r'\bl_Hr\b': 'VOLUME FLOW',
    r'\bl_hr\b': 'VOLUME FLOW',
    r'\bM\b': 'DRAFT', # for wind draft
    r'm': 'm', # wind draft and trim - not useful
    r'\bm/s\b': 'SPEED',
    r'\bm3\b': 'VOLUME',
    r'\bmH2O\b': 'DRAFT',
    r'\bmWC\b': 'DRAFT',
    r'\bmbar\b': 'PRESSURE',
    r'\bmg\b': 'ACCELERATION',
    r'\bmin-¹\b': '', # data too varied
    r'\bmm\b': '', # data too varied
    r'\bmmH2O\b': 'WATER DRUM LEVEL',
    r'\brev\b': 'RPM',
    r'\brpm\b': 'RPM',
    r'\bx1000min-¹\b': '',
    r'\b°C\b': 'TEMPERATURE',
    r'\bºC\b': 'TEMPERATURE',
    r'\b℃\b': 'TEMPERATURE'
}