CSC 458, Data Mining and Predictive Analytics I, Fall 2019, Assignment 2

CSC 458 - Data Mining and Predictive Analytics I, Fall 2019, Assignment 2

Source datasets for combination-by-join by Dr. Parson as handouts.
    NOTE on these ARFF files below read from XLS -> CSV input:
        Weka can read these CSVs and store as ARFF, but the datetimes and attribute names require
        repair, and we need to eliminate some attributes removed (DB projection) before we
        join raptor counts + weather + sunrise/sunset (DB join). I am using ARFF as the input format
        to this projection, join process (joining over datetime) because I already have code to read/write ARFF.
    HMS_F2017.xls.pdf - original source data supplied by Hawk Mtn.
        HMS_F2017_NORM.arff.txt is ARFF format from HMS_F2017_NORM.csv with a few hand edits.
    HMS_F2018.xls.pdf - original source data supplied by Hawk Mtn.
        HMS_F2018_NORM.arff.txt is ARFF format from HMS_F2018_NORM.csv with a few hand edits.
    HMS_F2017_NORM_SUMS.xls.pdf - Normalized by removing redundant headers amenable to a Weka-readable CSV.
    HMS_F2018_NORM_SUMS.xls.pdf - Normalized by removing redundant headers amenable to a Weka-readable CSV.
        Sub-categories of raptors that were not measured for 2017 are summed into categories aligned with 2017 data.
        Both of the above have SUMS of raptor counts in the bottom row. Removed these before converting to ARFF.
    NOAA_Solar_Calculations_year_HawkMtn2017.xls.pdf
        Time of sunrise, sunset, and other solar attributes. Next file is the same for 2018.
        NOAA_Solar_Calculations_year_HawkMtn2017.arff.txt is ARFF file needing some data type & value repairs.
    NOAA_Solar_Calculations_year_HawkMtn2018.xls.pdf
        NOAA_Solar_Calculations_year_HawkMtn2018.arff.txt is ARFF file needing some data type & value repairs.
    KPAHAMBU4.parson.pdf from Assignment 1, to be replaced by aggregated student-captured weather data ARFF files.

Scientific Publications from the Hawk Mountain web site from the 1990s until 2010.
    Papers that may relate to our data projects include:
        34. Allen, P. E., L. J. Goodrich, and K. L. Bildstein. 1996. Within- and among-year effects of cold fronts on migrating raptors at Hawk Mountain, Pennsylvania, 1934-1991. Auk 113: 329-338.
        50. Atkinson, E. C., L. J. Goodrich, and K. L. Bildstein. 1996. A temporal field guide to autumn raptor migration at Hawk Mountain Sanctuary, Pennsylvania. Pennsylvania Birds 10:134-137.
        61. Aradis, A. 2000. Magnitude and seasonal timing of Northern Harrier (Circus cyaneus) migration at Hawk Mountain Sanctuary, Pennsylvania, 1936-1999. American Hawkwatcher 26:16-20.
        84. Ottinger, J., and K. L. Bildstein. 2000. Autumn raptor migration summary 1999. Pennsylvania Birds 13: 190-196.
        87. Bildstein, K. L. 2001. Why migratory birds of prey make great biological indicators. Hawkwatching in the Americas:169-179.
        95. McCarty, K. and K. L. Bildstein. 2005. Using Autumn Hawk Watch to track raptor migration and monitor populations of North American birds of prey. Pages 718-725 in U. S. Forest Service Technical Publication PSW-GTR-191.
        96. McCarty, K., and K. L. Bildstein. 2001. Autumn raptor migration summary 2001. Pennsylvania Birds 15: 218-224.
        109. McCarty, K. 2004. Autumn raptor migration summary 2003. Pennsylvania Birds 17: 269-276.
        131. Farmer, G. Autumn raptor migration summary 2005. Pennsylvania Birds 19: 198-205.
        149. Zemba, L. Autumn raptor migration summary 2007. Pennsylvania Birds. Pennsylvania Birds 20-177-183.
        156. Bildstein, K. L., J. Smith, and E. Ruelas Inzunza. 2008. The future of raptor migration monitoring in North America. In The State of North America's birds of prey (K. L. Bildstein, J. Smith, and E. Ruelas, eds.). Series in Ornithology No. 3, Nuttall Ornithological Club and American Ornithologists' Union, Washington, D.C.
        159. Farmer, C. J., R. J. Bell, B. Drolet, E. Greenstone, L. Goodrich, D. Grove, D. J. T. Hussell, D. Mizrahi, F. Nicoletti, and J. Sodergren. 2008. Trends in autumn counts of migratory raptors in northeastern North America, 1974-2004. In The State of North America's birds of prey (K. L. Bildstein, J. Smith, and E. Ruelas, eds.). Series in Ornithology No. 3, Nuttall Ornithological Club and American Ornithologists' Union, Washington, D. C.
        178. Goodrich, L.J. Autumn Raptor Migration Summary 2008. Pennsylvania Birds. Pennsylvania Birds 22: 200-206.
        187. Goodrich, L.J. Autumn Raptor Migration Summary 2009. Pennsylvania Birds Vol 23, No. 4.
        202. Goodrich, L.J. Autumn Raptor Migration Summary 2010. Pennsylvania Birds Vol. 24, No. 4.
        249. Goodrich, L. 2014. Autumn Raptor Migration Summary: 1.3 million and counting. Pennsylvania Birds 28(4): 199-205.
        272. Goodrich, L. 2016. 2016 Autumn Raptor Migration Summary. Pennsylvania Birds 30(4): 199-205.
        STOPOVER ECOLOGY OF AUTUMN-MIGRATING RAPTORS IN THE CENTRAL APPALACHIANS, A Dissertation in Ecology By Laurie J. Goodrich, 2010.

Legend for raptor count data
    BV    Black Vulture
    TV    Turkey Vulture
    UV    Unidentified Vulture
    MK    Mississippi Kite
    OS    Osprey
    BE    Bald Eagle
    NH    Northern Harrier
    SS    Sharp-shinned Hawk
    CH    Cooper's Hawk
    NG    Northern Goshawk
    UA    Unidentified Accipiter
    RS    Red-shouldered Hawk
    BW    Broad-winged Hawk
    SW    Swainson's Hawk
    RT    Red-tailed Hawk
    RL    Rough-legged Hawk
    UB    Unidentified Buteo
    GE    Golden Eagle
    UE    Unidentified Eagle
    AK    American Kestrel
    ML    Merlin
    PG    Peregrine Falcon
    UF    Unidentified Falcon
    UR    Unidentified Raptor
    OR Other Raptor

Map of the Kittatinny Ridge