API tools faq
paste
Advertisement
Guest User

DrvoKolokvium

a guest
Jan 20th, 2018
629
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 13.72 KB | None | 0 0
raw download clone embed print report
  1. data = [[242.0, 23.2, 25.4, 30.0, 38.4, 13.4, 1],
  2.         [290.0, 24.0, 26.3, 31.2, 40.0, 13.8, 1],
  3.         [340.0, 23.9, 26.5, 31.1, 39.8, 15.1, 1],
  4.         [363.0, 26.3, 29.0, 33.5, 38.0, 13.3, 1],
  5.         [430.0, 26.5, 29.0, 34.0, 36.6, 15.1, 1],
  6.         [450.0, 26.8, 29.7, 34.7, 39.2, 14.2, 1],
  7.         [500.0, 26.8, 29.7, 34.5, 41.1, 15.3, 1],
  8.         [390.0, 27.6, 30.0, 35.0, 36.2, 13.4, 1],
  9.         [450.0, 27.6, 30.0, 35.1, 39.9, 13.8, 1],
  10.         [500.0, 28.5, 30.7, 36.2, 39.3, 13.7, 1],
  11.         [475.0, 28.4, 31.0, 36.2, 39.4, 14.1, 1],
  12.         [500.0, 28.7, 31.0, 36.2, 39.7, 13.3, 1],
  13.         [500.0, 29.1, 31.5, 36.4, 37.8, 12.0, 1],
  14.         [500.0, 29.5, 32.0, 37.3, 37.3, 13.6, 1],
  15.         [600.0, 29.4, 32.0, 37.2, 40.2, 13.9, 1],
  16.         [600.0, 29.4, 32.0, 37.2, 41.5, 15.0, 1],
  17.         [700.0, 30.4, 33.0, 38.3, 38.8, 13.8, 1],
  18.         [700.0, 30.4, 33.0, 38.5, 38.8, 13.5, 1],
  19.         [610.0, 30.9, 33.5, 38.6, 40.5, 13.3, 1],
  20.         [650.0, 31.0, 33.5, 38.7, 37.4, 14.8, 1],
  21.         [575.0, 31.3, 34.0, 39.5, 38.3, 14.1, 1],
  22.         [685.0, 31.4, 34.0, 39.2, 40.8, 13.7, 1],
  23.         [620.0, 31.5, 34.5, 39.7, 39.1, 13.3, 1],
  24.         [680.0, 31.8, 35.0, 40.6, 38.1, 15.1, 1],
  25.         [700.0, 31.9, 35.0, 40.5, 40.1, 13.8, 1],
  26.         [725.0, 31.8, 35.0, 40.9, 40.0, 14.8, 1],
  27.         [720.0, 32.0, 35.0, 40.6, 40.3, 15.0, 1],
  28.         [714.0, 32.7, 36.0, 41.5, 39.8, 14.1, 1],
  29.         [850.0, 32.8, 36.0, 41.6, 40.6, 14.9, 1],
  30.         [1000.0, 33.5, 37.0, 42.6, 44.5, 15.5, 1],
  31.         [920.0, 35.0, 38.5, 44.1, 40.9, 14.3, 1],
  32.         [955.0, 35.0, 38.5, 44.0, 41.1, 14.3, 1],
  33.         [925.0, 36.2, 39.5, 45.3, 41.4, 14.9, 1],
  34.         [975.0, 37.4, 41.0, 45.9, 40.6, 14.7, 1],
  35.         [950.0, 38.0, 41.0, 46.5, 37.9, 13.7, 1],
  36.         [270.0, 23.6, 26.0, 28.7, 29.2, 14.8, 2],
  37.         [270.0, 24.1, 26.5, 29.3, 27.8, 14.5, 2],
  38.         [306.0, 25.6, 28.0, 30.8, 28.5, 15.2, 2],
  39.         [540.0, 28.5, 31.0, 34.0, 31.6, 19.3, 2],
  40.         [800.0, 33.7, 36.4, 39.6, 29.7, 16.6, 2],
  41.         [1000.0, 37.3, 40.0, 43.5, 28.4, 15.0, 2],
  42.         [40.0, 12.9, 14.1, 16.2, 25.6, 14.0, 3],
  43.         [69.0, 16.5, 18.2, 20.3, 26.1, 13.9, 3],
  44.         [78.0, 17.5, 18.8, 21.2, 26.3, 13.7, 3],
  45.         [87.0, 18.2, 19.8, 22.2, 25.3, 14.3, 3],
  46.         [120.0, 18.6, 20.0, 22.2, 28.0, 16.1, 3],
  47.         [0.0, 19.0, 20.5, 22.8, 28.4, 14.7, 3],
  48.         [110.0, 19.1, 20.8, 23.1, 26.7, 14.7, 3],
  49.         [120.0, 19.4, 21.0, 23.7, 25.8, 13.9, 3],
  50.         [150.0, 20.4, 22.0, 24.7, 23.5, 15.2, 3],
  51.         [145.0, 20.5, 22.0, 24.3, 27.3, 14.6, 3],
  52.         [160.0, 20.5, 22.5, 25.3, 27.8, 15.1, 3],
  53.         [140.0, 21.0, 22.5, 25.0, 26.2, 13.3, 3],
  54.         [160.0, 21.1, 22.5, 25.0, 25.6, 15.2, 3],
  55.         [169.0, 22.0, 24.0, 27.2, 27.7, 14.1, 3],
  56.         [161.0, 22.0, 23.4, 26.7, 25.9, 13.6, 3],
  57.         [200.0, 22.1, 23.5, 26.8, 27.6, 15.4, 3],
  58.         [180.0, 23.6, 25.2, 27.9, 25.4, 14.0, 3],
  59.         [290.0, 24.0, 26.0, 29.2, 30.4, 15.4, 3],
  60.         [272.0, 25.0, 27.0, 30.6, 28.0, 15.6, 3],
  61.         [390.0, 29.5, 31.7, 35.0, 27.1, 15.3, 3],
  62.         [55.0, 13.5, 14.7, 16.5, 41.5, 14.1, 4],
  63.         [60.0, 14.3, 15.5, 17.4, 37.8, 13.3, 4],
  64.         [90.0, 16.3, 17.7, 19.8, 37.4, 13.5, 4],
  65.         [120.0, 17.5, 19.0, 21.3, 39.4, 13.7, 4],
  66.         [150.0, 18.4, 20.0, 22.4, 39.7, 14.7, 4],
  67.         [140.0, 19.0, 20.7, 23.2, 36.8, 14.2, 4],
  68.         [170.0, 19.0, 20.7, 23.2, 40.5, 14.7, 4],
  69.         [145.0, 19.8, 21.5, 24.1, 40.4, 13.1, 4],
  70.         [200.0, 21.2, 23.0, 25.8, 40.1, 14.2, 4],
  71.         [273.0, 23.0, 25.0, 28.0, 39.6, 14.8, 4],
  72.         [300.0, 24.0, 26.0, 29.0, 39.2, 14.6, 4],
  73.         [6.7, 9.3, 9.8, 10.8, 16.1, 9.7, 5],
  74.         [7.5, 10.0, 10.5, 11.6, 17.0, 10.0, 5],
  75.         [7.0, 10.1, 10.6, 11.6, 14.9, 9.9, 5],
  76.         [9.7, 10.4, 11.0, 12.0, 18.3, 11.5, 5],
  77.         [9.8, 10.7, 11.2, 12.4, 16.8, 10.3, 5],
  78.         [8.7, 10.8, 11.3, 12.6, 15.7, 10.2, 5],
  79.         [10.0, 11.3, 11.8, 13.1, 16.9, 9.8, 5],
  80.         [9.9, 11.3, 11.8, 13.1, 16.9, 8.9, 5],
  81.         [9.8, 11.4, 12.0, 13.2, 16.7, 8.7, 5],
  82.         [12.2, 11.5, 12.2, 13.4, 15.6, 10.4, 5],
  83.         [13.4, 11.7, 12.4, 13.5, 18.0, 9.4, 5],
  84.         [12.2, 12.1, 13.0, 13.8, 16.5, 9.1, 5],
  85.         [19.7, 13.2, 14.3, 15.2, 18.9, 13.6, 5],
  86.         [19.9, 13.8, 15.0, 16.2, 18.1, 11.6, 5],
  87.         [200.0, 30.0, 32.3, 34.8, 16.0, 9.7, 6],
  88.         [300.0, 31.7, 34.0, 37.8, 15.1, 11.0, 6],
  89.         [300.0, 32.7, 35.0, 38.8, 15.3, 11.3, 6],
  90.         [300.0, 34.8, 37.3, 39.8, 15.8, 10.1, 6],
  91.         [430.0, 35.5, 38.0, 40.5, 18.0, 11.3, 6],
  92.         [345.0, 36.0, 38.5, 41.0, 15.6, 9.7, 6],
  93.         [456.0, 40.0, 42.5, 45.5, 16.0, 9.5, 6],
  94.         [510.0, 40.0, 42.5, 45.5, 15.0, 9.8, 6],
  95.         [540.0, 40.1, 43.0, 45.8, 17.0, 11.2, 6],
  96.         [500.0, 42.0, 45.0, 48.0, 14.5, 10.2, 6],
  97.         [567.0, 43.2, 46.0, 48.7, 16.0, 10.0, 6],
  98.         [770.0, 44.8, 48.0, 51.2, 15.0, 10.5, 6],
  99.         [950.0, 48.3, 51.7, 55.1, 16.2, 11.2, 6],
  100.         [1250.0, 52.0, 56.0, 59.7, 17.9, 11.7, 6],
  101.         [1600.0, 56.0, 60.0, 64.0, 15.0, 9.6, 6],
  102.         [1550.0, 56.0, 60.0, 64.0, 15.0, 9.6, 6],
  103.         [1650.0, 59.0, 63.4, 68.0, 15.9, 11.0, 6],
  104.         [5.9, 7.5, 8.4, 8.8, 24.0, 16.0, 7],
  105.         [32.0, 12.5, 13.7, 14.7, 24.0, 13.6, 7],
  106.         [40.0, 13.8, 15.0, 16.0, 23.9, 15.2, 7],
  107.         [51.5, 15.0, 16.2, 17.2, 26.7, 15.3, 7],
  108.         [70.0, 15.7, 17.4, 18.5, 24.8, 15.9, 7],
  109.         [100.0, 16.2, 18.0, 19.2, 27.2, 17.3, 7],
  110.         [78.0, 16.8, 18.7, 19.4, 26.8, 16.1, 7],
  111.         [80.0, 17.2, 19.0, 20.2, 27.9, 15.1, 7],
  112.         [85.0, 17.8, 19.6, 20.8, 24.7, 14.6, 7],
  113.         [85.0, 18.2, 20.0, 21.0, 24.2, 13.2, 7],
  114.         [110.0, 19.0, 21.0, 22.5, 25.3, 15.8, 7],
  115.         [115.0, 19.0, 21.0, 22.5, 26.3, 14.7, 7],
  116.         [125.0, 19.0, 21.0, 22.5, 25.3, 16.3, 7],
  117.         [130.0, 19.3, 21.3, 22.8, 28.0, 15.5, 7],
  118.         [120.0, 20.0, 22.0, 23.5, 26.0, 14.5, 7],
  119.         [120.0, 20.0, 22.0, 23.5, 24.0, 15.0, 7],
  120.         [130.0, 20.0, 22.0, 23.5, 26.0, 15.0, 7],
  121.         [135.0, 20.0, 22.0, 23.5, 25.0, 15.0, 7],
  122.         [110.0, 20.0, 22.0, 23.5, 23.5, 17.0, 7],
  123.         [130.0, 20.5, 22.5, 24.0, 24.4, 15.1, 7],
  124.         [150.0, 20.5, 22.5, 24.0, 28.3, 15.1, 7],
  125.         [145.0, 20.7, 22.7, 24.2, 24.6, 15.0, 7],
  126.         [150.0, 21.0, 23.0, 24.5, 21.3, 14.8, 7],
  127.         [170.0, 21.5, 23.5, 25.0, 25.1, 14.9, 7],
  128.         [225.0, 22.0, 24.0, 25.5, 28.6, 14.6, 7],
  129.         [145.0, 22.0, 24.0, 25.5, 25.0, 15.0, 7],
  130.         [188.0, 22.6, 24.6, 26.2, 25.7, 15.9, 7],
  131.         [180.0, 23.0, 25.0, 26.5, 24.3, 13.9, 7],
  132.         [197.0, 23.5, 25.6, 27.0, 24.3, 15.7, 7],
  133.         [218.0, 25.0, 26.5, 28.0, 25.6, 14.8, 7],
  134.         [300.0, 25.2, 27.3, 28.7, 29.0, 17.9, 7],
  135.         [260.0, 25.4, 27.5, 28.9, 24.8, 15.0, 7],
  136.         [265.0, 25.4, 27.5, 28.9, 24.4, 15.0, 7],
  137.         [250.0, 25.4, 27.5, 28.9, 25.2, 15.8, 7],
  138.         [250.0, 25.9, 28.0, 29.4, 26.6, 14.3, 7],
  139.         [300.0, 26.9, 28.7, 30.1, 25.2, 15.4, 7],
  140.         [320.0, 27.8, 30.0, 31.6, 24.1, 15.1, 7],
  141.         [514.0, 30.5, 32.8, 34.0, 29.5, 17.7, 7],
  142.         [556.0, 32.0, 34.5, 36.5, 28.1, 17.5, 7],
  143.         [840.0, 32.5, 35.0, 37.3, 30.8, 20.9, 7],
  144.         [685.0, 34.0, 36.5, 39.0, 27.9, 17.6, 7],
  145.         [700.0, 34.0, 36.0, 38.3, 27.7, 17.6, 7],
  146.         [700.0, 34.5, 37.0, 39.4, 27.5, 15.9, 7],
  147.         [690.0, 34.6, 37.0, 39.3, 26.9, 16.2, 7],
  148.         [900.0, 36.5, 39.0, 41.4, 26.9, 18.1, 7],
  149.         [650.0, 36.5, 39.0, 41.4, 26.9, 14.5, 7],
  150.         [820.0, 36.6, 39.0, 41.3, 30.1, 17.8, 7],
  151.         [850.0, 36.9, 40.0, 42.3, 28.2, 16.8, 7],
  152.         [900.0, 37.0, 40.0, 42.5, 27.6, 17.0, 7],
  153.         [1015.0, 37.0, 40.0, 42.4, 29.2, 17.6, 7],
  154.         [820.0, 37.1, 40.0, 42.5, 26.2, 15.6, 7],
  155.         [1100.0, 39.0, 42.0, 44.6, 28.7, 15.4, 7],
  156.         [1000.0, 39.8, 43.0, 45.2, 26.4, 16.1, 7],
  157.         [1100.0, 40.1, 43.0, 45.5, 27.5, 16.3, 7],
  158.         [1000.0, 40.2, 43.5, 46.0, 27.4, 17.7, 7],
  159.         [1000.0, 41.1, 44.0, 46.6, 26.8, 16.3, 7]]
  160.  
  161.  
  162. class decisionnode:
  163.     def __init__(self, col=-1, value=None, results=None, tb=None, fb=None):
  164.         self.col = col
  165.         self.value = value
  166.         self.results = results
  167.         self.tb = tb
  168.         self.fb = fb
  169.  
  170.  
  171. def sporedi_broj(row, column, value):
  172.     return row[column] >= value
  173.  
  174.  
  175. def sporedi_string(row, column, value):
  176.     return row[column] == value
  177.  
  178.  
  179.     # Divides a set on a specific column. Can handle numeric
  180.     # or nominal values
  181.  
  182.  
  183. def divideset(rows, column, value):
  184.     # Make a function that tells us if a row is in
  185.     # the first group (true) or the second group (false)
  186.     split_function = None
  187.     if isinstance(value, int) or isinstance(value, float):  # ako vrednosta so koja sporeduvame e od tip int ili float
  188.         # split_function=lambda row:row[column]>=value # togas vrati funkcija cij argument e row i vrakja vrednost true ili false
  189.         split_function = sporedi_broj
  190.     else:
  191.         # split_function=lambda row:row[column]==value # ako vrednosta so koja sporeduvame e od drug tip (string)
  192.         split_function = sporedi_string
  193.  
  194.     # Divide the rows into two sets and return them
  195.     set_false = []
  196.     set_true = []
  197.     for row in rows:
  198.         if split_function(row, column, value):
  199.             set_true.append(row)
  200.         else:
  201.             set_false.append(row)
  202.     set1 = [row for row in rows if
  203.             split_function(row, column, value)]  # za sekoj row od rows za koj split_function vrakja true
  204.     set2 = [row for row in rows if
  205.             not split_function(row, column, value)]  # za sekoj row od rows za koj split_function vrakja false
  206.     # return (set1, set2)
  207.     return (set_true, set_false)
  208.  
  209.  
  210. def uniquecounts(rows):
  211.     results = {}
  212.     for row in rows:
  213.         # The result is the last column
  214.         r = row[-1]
  215.         results.setdefault(r, 0)
  216.         results[r] += 1
  217.  
  218.     return results
  219.  
  220.  
  221. def log2(x):
  222.     from math import log
  223.     l2 = log(x) / log(2)
  224.     return l2
  225.  
  226.  
  227. def entropy(rows):
  228.     results = uniquecounts(rows)
  229.     # Now calculate the entropy
  230.     ent = 0.0
  231.     for r in results.keys():
  232.         p = float(results[r]) / len(rows)
  233.         ent = ent - p * log2(p)
  234.     return ent
  235.  
  236.  
  237. def buildtree(rows, scoref=entropy):
  238.     if len(rows) == 0: return decisionnode()
  239.     current_score = scoref(rows)
  240.  
  241.     # Set up some variables to track the best criteria
  242.     best_gain = 0.0
  243.     best_column = -1
  244.     best_value = None
  245.     best_subsetf = None
  246.     best_subsett = None
  247.  
  248.     column_count = len(rows[0]) - 1
  249.     for col in range(column_count):
  250.         # Generate the list of different values in
  251.         # this column
  252.         column_values = set()
  253.         for row in rows:
  254.             column_values.add(row[col])
  255.         # Now try dividing the rows up for each value
  256.         # in this column
  257.         for value in column_values:
  258.             (set1, set2) = divideset(rows, col, value)
  259.  
  260.             # Information gain
  261.             p = float(len(set1)) / len(rows)
  262.             gain = current_score - p * scoref(set1) - (1 - p) * scoref(set2)
  263.             if gain > best_gain and len(set1) > 0 and len(set2) > 0:
  264.                 best_gain = gain
  265.                 best_column = col
  266.                 best_value = value
  267.                 best_subsett = set1
  268.                 best_subsetf = set2
  269.                 # best_criteria = (col, value)
  270.                 # best_sets = (set1, set2)
  271.  
  272.     # Create the subbranches
  273.     if best_gain > 0:
  274.         trueBranch = buildtree(best_subsett, scoref)
  275.         falseBranch = buildtree(best_subsetf, scoref)
  276.         return decisionnode(col=best_column, value=best_value,
  277.                             tb=trueBranch, fb=falseBranch)
  278.     else:
  279.         return decisionnode(results=uniquecounts(rows))
  280.  
  281.  
  282. def classify(observation, tree):
  283.     if tree.results != None:
  284.         pom=[]
  285.         for k,v in tree.results.items():
  286.             pom=k
  287.         return pom
  288.  
  289.     else:
  290.         vrednost = observation[tree.col]
  291.         branch = None
  292.  
  293.         if isinstance(vrednost, int) or isinstance(vrednost, float):
  294.             if vrednost >= tree.value:
  295.                 branch = tree.tb
  296.             else:
  297.                 branch = tree.fb
  298.         else:
  299.             if vrednost == tree.value:
  300.                 branch = tree.tb
  301.             else:
  302.                 branch = tree.fb
  303.  
  304.         return classify(observation, branch)
  305.  
  306. def printtree(tree, indent=''):
  307.     # Is this a leaf node?
  308.     if tree.results != None:
  309.         print(indent + str(sorted(tree.results.items())))
  310.     else:
  311.         # Print the criteria
  312.         print(indent + str(tree.col) + ':' + str(tree.value) + '? ')
  313.         # Print the branches
  314.         print(indent + 'T->')
  315.         printtree(tree.tb, indent + '  ')
  316.         print(indent + 'F->')
  317.         printtree(tree.fb, indent + '  ')
  318.  
  319. if __name__ == "__main__":
  320.     index = input()
  321.     data2 = data[index]
  322.  
  323.     lista15=[]
  324.     lista25=[]
  325.     lista35=[]
  326.     lista45=[]
  327.     lista55=[]
  328.     lista65=[]
  329.     lista75=[]
  330.  
  331.     eden=1
  332.     dva=2
  333.     tri=3
  334.     cetiri=4
  335.     pet=5
  336.     sest=6
  337.     sedum=7
  338.  
  339.     for i in range(0,len(data)):
  340.         if data[i][6]==eden:
  341.             lista15.append(data[i])
  342.         if data[i][6]==dva:
  343.                     lista25.append(data[i])
  344.         if data[i][6]==tri:
  345.                     lista35.append(data[i])
  346.         if data[i][6]==cetiri:
  347.                     lista45.append(data[i])
  348.         if data[i][6]==pet:
  349.                     lista55.append(data[i])
  350.         if data[i][6]==sest:
  351.                     lista65.append(data[i])
  352.         if data[i][6]==sedum:
  353.                     lista75.append(data[i])
  354.  
  355.     listaSo5=[]
  356.     listaSo5=lista15[:5]+lista25[:5]+lista35[:5]+lista45[:5]+lista55[:5]+lista65[:5]+lista75[:5]
  357.  
  358.     drvoSoPo5 = buildtree(listaSo5)
  359.     printtree
  360.     drvo1c= classify(data2,drvoSoPo5)
  361.  
  362.     print drvo1c
  363.  
  364.  
  365.     #solution = None
  366.     #print solution
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!