BasicStatistics

gistfile1.txt

# calculate 1D stats on data

data = [10, 2, 38, 23, 21, 5, 38, 23]

# sum
dataSum = sum (data)
print ('sum is:  {}'.format(dataSum))

# COUNT 
count = len (data)
print ('count is: {}'.format(count))

# MEAN
avg = dataSum/count
print ('mean is:  {}'.format(avg))

# point-difference from mean
diff = count * [-1]
for i in range(0,count):
    diff[i] = data[i] - avg
print ('point diff from mean is:  {}\n'.format(diff))

# square diff 
squares = count * [-1]
for i in range(0, count):
    squares[i] = diff[i] ** 2
print ('square diffs from mean:  {}\n'.format(squares))

# sum square diffs
sum_squares = sum (squares)
print ('sum squares:  {}\n'.format(sum_squares))

# VARIANCE  divide degrees freedom from history
variance = (1/count) * sum_squares
print ('variance:  {}\n', variance)

# STDDEV  take square root
stddev = variance ** (1/2)
print ('standard dev:  {}\n', stddev)

# RANGE
min = min (data)
max = max (data)
print ('range starts at:  {} to {}\n'.format(min, max))

# MORON ALERT:  ATTN INDEX vs VALUE!

# MEDIAN
orderedData = data.sort()
# print (dir(data))
# print ('Sorted Data is:  {}'.format(orderedData))

# count = len( orderedData )
print('count is:  {}'.format(count))
# print ('10/2 {}'.format(10/2))
# print ('9/2 {}'.format(9/2))
# print ('9 % 2 {}'.format(9 % 2))

midIndex = count/2
# test for Even Number elements
if ((count % 2) == 0):
    median = (data[(midIndex)] + data[(midIndex+1)])/2
else:
    median = data[midIndex]   
    
print('Found Median:  {}'.format(median))

# *********************************************************************************

# MODE
count_freq = dict()
for i in range(0, count):
    if (data[i] in count_freq):
        count_freq[data[i]] += 1
    else:
        count_freq[data[i]] = 1
print ('count freq:  {}\n'.format(count_freq))

# TODO:  repl.it not recognizing Python3 max function on List!
print ('freq.values {}\n'.format(count_freq.values()))
# max_freq = max ( count_freq.values() )
# print ('max freq:  {}\n'.format(max_freq))

# get all values of dictionary
print("\n\n*********")
print ('DEBUGGING:  all methods of collection data structure:  ')
print (dir(count_freq))
print("*********\n\n")

# detect MODE by REVERSE lookup => DATA VALUE to FREQUENCY COUNT goes instead to
#                                  FREQUENCY COUNT to DATA VALUE
accum_mode = dict()
maxCount = 0

# MORON ALERT:  attention to DIRECTION of map!
valueToFreqPairs = count_freq.items()
print( 'full list frequency to value pairs are:  {}'.format(valueToFreqPairs) )

for value, freq in valueToFreqPairs:
    # detect higher max, so throw out prior max, as well as corresponding values
    # where accum_mode has frequency number as key; and values are List of 
    # of multiple possible modes!
    if (freq > maxCount):
        maxCount = freq
        # ATTN:  THROWAWAY - ENTIRE dictionary, including KEYs!
        # accum_mode.clear()
        accum_mode = dict()
        # ATTN:  initialize to a LIST to allow appending!
        accum_mode [maxCount] = [ value ]
    # MORON ALERT:  attention to ALL <, =, > CASES!
    elif (freq == maxCount):
        # accumulate multiple MODEs to List already found for current max frequency
        accum_mode[maxCount].append( value )
    else:
        # do nothing, as count is too low for us to care
        pass

print ("Mode values found for max frequency are:  {}".format(accum_mode))
        
# ************************************************************************************