"""
lab.14
"""

#input: nothing
#output: prints each state and number of customers per state
#description: go through customer data file one line at a time
# and generate state distributions.
def getStateDistributions():
    customerFile = open("FakeCustomerData.txt","r")

    #make an empty dictionary
    stateDict = {}

    #skip the header
    header = customerFile.readline()

    #go through each line
    for line in customerFile:
        #split into a list
        lineList = line.split(",")

        state = lineList[7]

        # add to dictionary

        # if not in dictionary
        if state not in stateDict:
            stateDict[state] = 1
        # else is in dictionary
        else: 
            stateDict[state] += 1

    #If we printed out the dictionary here, items would print
    #out of order.
    #for key in stateDict:
    #    print(key, "->", stateDict[key])
    
    #Sort the keys by placing them in a sorted keys list.
    keyList = sorted(stateDict)

    for key in keyList:
        print(key, "->", stateDict[key])

    customerFile.close()

#input: csv file to open and a column number to process
#output: prints each state and number of customers per stat at columnNum
#description: go through customer data file one line at a time
# and generate columnNum distributions.
def getColumnDistribution(filename, columnNum):
    customerFile = open(filename,"r")

    #make an empty dictionary
    statDict = {}

    #use the header to figure out if columnNum is too big
    header = customerFile.readline()
    headerList = header.split(",")
    if columnNum >= len(headerList):
        print("There is no column number", columnNum)
        return None

    #go through each line
    for line in customerFile:
        #split into a list
        lineList = line.split(",")

        stat = lineList[columnNum]

        # add to dictionary

        # if not in dictionary
        if stat not in statDict:
            statDict[stat] = 1
        # else is in dictionary
        else: 
            statDict[stat] += 1

   
    #Sort the keys by placing them in a sorted keys list.
    keyList = sorted(statDict)

    for key in keyList:
        print(key, "->", statDict[key])

    customerFile.close()


#input: nothing
#output: prints each birth year and number of customers per birth year
#description: go through customer data file one line at a time
# and generate birth year distributions.
def getBirthYearDistributions():
    customerFile = open("FakeCustomerData.txt","r")

    #make an empty dictionary
    birthDict = {}

    #skip the header
    header = customerFile.readline()

    #go through each line
    for line in customerFile:
        #split into a list
        lineList = line.split(",")

        birthday = lineList[13]

        #Now get only the year
        bdayList = birthday.split("/")
        year = bdayList[2]

        # add to dictionary

        # if not in dictionary
        if year not in birthDict:
            birthDict[year] = 1
        # else is in dictionary
        else: 
            birthDict[year] += 1

    #Sort the keys by placing them in a sorted keys list.
    keyList = sorted(birthDict)

    for key in keyList:
        print(key, "->", birthDict[key])

    customerFile.close()