DataMiningExtended1.py

#RB = Running Back
#OL = Outside Linebacker
#WR = Wide Receiver
#TE = Tight End
#FB = Full Back **************** merged with RB
#DB = Defensive Back
#QB = Quarter Back
#LB = Linebacker
#DL = Defensive Lineman

def middle(L):
    L = sorted(L)
    n = len(L)
    m = n - 1
    return (L[n/2] + L[m/2]) / 2.0

def main():
    masterDict = {} # will only be added to, not reset
    #with open('tester.txt') as f:
    with open('DataSet_DEADNFLPLAYERS.txt') as f:
        for line in f:
            current_line = line.split(',')
            masterDict.update({len(masterDict) : current_line})

    #print masterDict

    total_lifeSpan = 0 # will hold total lifespan of all players
    listAges = [] # will hold a list of all player's ages

    # lists for ages of each role
    fullBackAges = []
    #runningBackAges = [] # full back and runningBack are the same in our dataset
    outsideLineBackerAges = []
    wideReceiverAges = []
    tightEndAges = []
    defensiveBackAges = []
    quarterBackAges = []
    lineBackerAges = []
    defensiveLinemanAges = []

    cleanedUpAges = []
    modernAges = []

    for key, value in masterDict.items():
        if(key != 0):
            deathYear = int(float(value[10].strip())) #10th element
            birthYear = int(float(value[len(value)-1].strip())) #last element
            age = deathYear - birthYear # determines the age at death
            listAges.append(age) # adds age to a list
            total_lifeSpan = total_lifeSpan + age # the combinded age of all players at death

            if "FB" in value[8]:
                fullBackAges.append(age)
            #elif "RB" in value[8]: # full back and runningBack are the same in our dataset
                #runningBackAges.append(age)
            elif "OL" in value[8]:
                outsideLineBackerAges.append(age)
            elif "WR" in value[8]:
                wideReceiverAges.append(age)
            elif "TE" in value[8]:
                tightEndAges.append(age)
            elif "DB" in value[8]:
                 defensiveBackAges.append(age)
            elif "QB" in value[8]:
                quarterBackAges.append(age)
            elif "LB" in value[8]:
                lineBackerAges.append(age)
            elif "DL" in value[8]:
                defensiveLinemanAges.append(age)

            if((age < 80) and (age > 50)):
                cleanedUpAges.append(age)

            if birthYear >= 1940:
                modernAges.append(age)



    #---------------------------FOR ALL ROLES----------------------------------

    #mean, average age across all players
    #print "MEAN OF ALL"
    average_age = total_lifeSpan / (len(masterDict) -1)
    #print average_age
    #print "----------"

    #mode, the most commonly occuring value
    #print "MODE OF ALL"
    from collections import Counter
    data = Counter(listAges)
    modeData = data.most_common(1)
    newModeData = [x[0] for x in modeData]
    #print data.most_common(1)
    #print "----------"

    #median, the least extreme value or the middle value
    #print "MEDIAN OF ALL"
    #print middle(listAges)
    #print "----------"

    #mid-range, the mean of the highest and lowest value
    #print "MIDRANGE OF ALL"
    midrange = min(listAges) + max(listAges)
    midrange = midrange / 2
    #print midrange
    #print "----------"
    #print "----------"
    #print "----------"

    #print newModeData
    #newMode = (3 * midrange) - (2 * newModeData[0])
    newMode = (3 * middle(listAges)) - ( 2 * average_age)
    print "MEAN OF ALL"
    print newMode

    print "MEDIAN OF ALL"
    newMedian =  newModeData[0] + (2 * (average_age - newModeData[0]) / 3)
    print newMedian

    print "MEAN - MODE"
    newValue =  average_age - newModeData[0]
    print newValue

    #-------------------------FOR THE NINE ROLES-----------------------------
    printingList = []

    printingList.append(fullBackAges)
    #printingList.append(runningBackAges)# full back and runningBack are the same in our dataset
    printingList.append(outsideLineBackerAges)
    printingList.append(wideReceiverAges)
    printingList.append(tightEndAges)
    printingList.append(defensiveBackAges)
    printingList.append(quarterBackAges)
    printingList.append(lineBackerAges)
    printingList.append(defensiveLinemanAges)

    printingList.append(cleanedUpAges)
    printingList.append(modernAges)

    for playerList in printingList:

        #mean, average age across all players
        #print ("MEAN OF ")#, playerList)
        average_age = sum(playerList) / (len(playerList) -1)
        #print average_age
        #print "----------"

        #mode, the most commonly occuring value
        #print ("MODE OF ")# % playerList)
        from collections import Counter
        data = Counter(playerList)
        #print data.most_common(1)
        #print "----------"

        #median, the least extreme value or the middle value
        #print ("MEDIAN OF)# " % playerList)
        #print middle(playerList)
        #print "----------"

        #mid-range, the mean of the highest and lowest value
        #print ("MIDRANGE OF ")# % playerList
        midrange = min(playerList) + max(playerList)
        midrange = midrange / 2
        #print midrange
        #print "----------"
        #print "----------"
        #print "----------"