API tools faq
paste
cimona

LabDrva

cimona
Sep 14th, 2018
333
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 12.66 KB | None | 0 0
raw download clone embed print report
  1. my_data = [['slashdot', 'USA', 'yes', 18, 'None'],
  2. ['google', 'France', 'yes', 23, 'Premium'],
  3. ['digg', 'USA', 'yes', 24, 'Basic'],
  4. ['kiwitobes', 'France', 'yes', 23, 'Basic'],
  5. ['google', 'UK', 'no', 21, 'Premium'],
  6. ['(direct)', 'New Zealand', 'no', 12, 'None'],
  7. ['(direct)', 'UK', 'no', 21, 'Basic'],
  8. ['google', 'USA', 'no', 24, 'Premium'],
  9. ['slashdot', 'France', 'yes', 19, 'None'],
  10. ['digg', 'USA', 'no', 18, 'None'],
  11. ['google', 'UK', 'no', 18, 'None'],
  12. ['kiwitobes', 'UK', 'no', 19, 'None'],
  13. ['digg', 'New Zealand', 'yes', 12, 'Basic'],
  14. ['slashdot', 'UK', 'no', 21, 'None'],
  15. ['google', 'UK', 'yes', 18, 'Basic'],
  16. ['kiwitobes', 'France', 'yes', 19, 'Basic']]
  17.  
  18. test_cases = [['google', 'MK', 'no', 24, 'Unknown'],
  19. ['google', 'MK', 'no', 15, 'Unknown'],
  20. ['digg', 'UK', 'yes', 21, 'Unknown'],
  21. ['digg', 'UK', 'no', 25, 'Unknown']]
  22.  
  23.  
  24. # my_data=[line.split('\t') for line in file('decision_tree_example.txt')]
  25.  
  26. class decisionnode:
  27. def __init__(self, col=-1, value=None, results=None, tb=None, fb=None):
  28. self.col = col
  29. self.value = value
  30. self.results = results
  31. self.tb = tb
  32. self.fb = fb
  33.  
  34.  
  35. def sporedi_broj(row, column, value):
  36. return row[column] >= value
  37.  
  38.  
  39. def sporedi_string(row, column, value):
  40. return row[column] == value
  41.  
  42.  
  43. # Divides a set on a specific column. Can handle numeric
  44. # or nominal values
  45. def divideset(rows, column, value):
  46. # Make a function that tells us if a row is in
  47. # the first group (true) or the second group (false)
  48. split_function = None
  49. if isinstance(value, int) or isinstance(value, float): # ako vrednosta so koja sporeduvame e od tip int ili float
  50. # split_function=lambda row:row[column]>=value # togas vrati funkcija cij argument e row i vrakja vrednost true ili false
  51. split_function = sporedi_broj
  52. else:
  53. # split_function=lambda row:row[column]==value # ako vrednosta so koja sporeduvame e od drug tip (string)
  54. split_function = sporedi_string
  55.  
  56. # Divide the rows into two sets and return them
  57. # set1=[row for row in rows if split_function(row)] # za sekoj row od rows za koj split_function vrakja true
  58. # set2=[row for row in rows if not split_function(row)] # za sekoj row od rows za koj split_function vrakja false
  59. set1 = [row for row in rows if
  60. split_function(row, column, value)] # za sekoj row od rows za koj split_function vrakja true
  61. set2 = [row for row in rows if
  62. not split_function(row, column, value)] # za sekoj row od rows za koj split_function vrakja false
  63. return (set1, set2)
  64.  
  65.  
  66. # Create counts of possible results (the last column of
  67. # each row is the result)
  68. def uniquecounts(rows):
  69. results = {}
  70. for row in rows:
  71. # The result is the last column
  72. r = row[len(row) - 1]
  73. if r not in results: results[r] = 0
  74. results[r] += 1
  75. return results
  76.  
  77.  
  78. # Probability that a randomly placed item will
  79. # be in the wrong category
  80. def giniimpurity(rows):
  81. total = len(rows)
  82. counts = uniquecounts(rows)
  83. imp = 0
  84. for k1 in counts:
  85. p1 = float(counts[k1]) / total
  86. for k2 in counts:
  87. if k1 == k2: continue
  88. p2 = float(counts[k2]) / total
  89. imp += p1 * p2
  90. return imp
  91.  
  92.  
  93. # Entropy is the sum of p(x)log(p(x)) across all
  94. # the different possible results
  95. def entropy(rows):
  96. from math import log
  97. log2 = lambda x: log(x) / log(2)
  98. results = uniquecounts(rows)
  99. # Now calculate the entropy
  100. ent = 0.0
  101. for r in results.keys():
  102. p = float(results[r]) / len(rows)
  103. ent = ent - p * log2(p)
  104. return ent
  105.  
  106.  
  107. def buildtree(rows, scoref=entropy):
  108. if len(rows) == 0: return decisionnode()
  109. current_score = scoref(rows)
  110.  
  111. # Set up some variables to track the best criteria
  112. best_gain = 0.0
  113. best_criteria = None
  114. best_sets = None
  115.  
  116. column_count = len(rows[0]) - 1
  117. for col in range(0, column_count):
  118. # Generate the list of different values in
  119. # this column
  120. column_values = {}
  121. for row in rows:
  122. column_values[row[col]] = 1
  123. # print
  124. # Now try dividing the rows up for each value
  125. # in this column
  126. for value in column_values.keys():
  127. (set1, set2) = divideset(rows, col, value)
  128.  
  129. # Information gain
  130. p = float(len(set1)) / len(rows)
  131. gain = current_score - p * scoref(set1) - (1 - p) * scoref(set2)
  132. if gain > best_gain and len(set1) > 0 and len(set2) > 0:
  133. best_gain = gain
  134. best_criteria = (col, value)
  135. best_sets = (set1, set2)
  136.  
  137. # Create the subbranches
  138. if best_gain > 0:
  139. trueBranch = buildtree(best_sets[0])
  140. falseBranch = buildtree(best_sets[1])
  141. return decisionnode(col=best_criteria[0], value=best_criteria[1],
  142. tb=trueBranch, fb=falseBranch)
  143. else:
  144. return decisionnode(results=uniquecounts(rows))
  145.  
  146.  
  147. def printtree(tree, indent=''):
  148. # Is this a leaf node?
  149. if tree.results != None:
  150. print(str(tree.results))
  151. else:
  152. # Print the criteria
  153. print(str(tree.col) + ':' + str(tree.value) + '? ')
  154. # Print the branches
  155. print(indent + 'T->'),
  156. printtree(tree.tb, indent + ' ')
  157. print(indent + 'F->'),
  158. printtree(tree.fb, indent + ' ')
  159.  
  160.  
  161. def classify(observation, tree):
  162. if tree.results != None:
  163. return tree.results
  164. else:
  165. vrednost = observation[tree.col]
  166. branch = None
  167.  
  168. if isinstance(vrednost, int) or isinstance(vrednost, float):
  169. if vrednost >= tree.value:
  170. branch = tree.tb
  171. else:
  172. branch = tree.fb
  173. else:
  174. if vrednost == tree.value:
  175. branch = tree.tb
  176. else:
  177. branch = tree.fb
  178.  
  179. return classify(observation, branch)
  180.  
  181.  
  182. trainingData = [
  183. [6.3, 2.9, 5.6, 1.8, 'I. virginica'],
  184. [6.5, 3.0, 5.8, 2.2, 'I. virginica'],
  185. [7.6, 3.0, 6.6, 2.1, 'I. virginica'],
  186. [4.9, 2.5, 4.5, 1.7, 'I. virginica'],
  187. [7.3, 2.9, 6.3, 1.8, 'I. virginica'],
  188. [6.7, 2.5, 5.8, 1.8, 'I. virginica'],
  189. [7.2, 3.6, 6.1, 2.5, 'I. virginica'],
  190. [6.5, 3.2, 5.1, 2.0, 'I. virginica'],
  191. [6.4, 2.7, 5.3, 1.9, 'I. virginica'],
  192. [6.8, 3.0, 5.5, 2.1, 'I. virginica'],
  193. [5.7, 2.5, 5.0, 2.0, 'I. virginica'],
  194. [5.8, 2.8, 5.1, 2.4, 'I. virginica'],
  195. [6.4, 3.2, 5.3, 2.3, 'I. virginica'],
  196. [6.5, 3.0, 5.5, 1.8, 'I. virginica'],
  197. [7.7, 3.8, 6.7, 2.2, 'I. virginica'],
  198. [7.7, 2.6, 6.9, 2.3, 'I. virginica'],
  199. [6.0, 2.2, 5.0, 1.5, 'I. virginica'],
  200. [6.9, 3.2, 5.7, 2.3, 'I. virginica'],
  201. [5.6, 2.8, 4.9, 2.0, 'I. virginica'],
  202. [7.7, 2.8, 6.7, 2.0, 'I. virginica'],
  203. [6.3, 2.7, 4.9, 1.8, 'I. virginica'],
  204. [6.7, 3.3, 5.7, 2.1, 'I. virginica'],
  205. [7.2, 3.2, 6.0, 1.8, 'I. virginica'],
  206. [6.2, 2.8, 4.8, 1.8, 'I. virginica'],
  207. [6.1, 3.0, 4.9, 1.8, 'I. virginica'],
  208. [6.4, 2.8, 5.6, 2.1, 'I. virginica'],
  209. [7.2, 3.0, 5.8, 1.6, 'I. virginica'],
  210. [7.4, 2.8, 6.1, 1.9, 'I. virginica'],
  211. [7.9, 3.8, 6.4, 2.0, 'I. virginica'],
  212. [6.4, 2.8, 5.6, 2.2, 'I. virginica'],
  213. [6.3, 2.8, 5.1, 1.5, 'I. virginica'],
  214. [6.1, 2.6, 5.6, 1.4, 'I. virginica'],
  215. [7.7, 3.0, 6.1, 2.3, 'I. virginica'],
  216. [6.3, 3.4, 5.6, 2.4, 'I. virginica'],
  217. [5.1, 3.5, 1.4, 0.2, 'I. setosa'],
  218. [4.9, 3.0, 1.4, 0.2, 'I. setosa'],
  219. [4.7, 3.2, 1.3, 0.2, 'I. setosa'],
  220. [4.6, 3.1, 1.5, 0.2, 'I. setosa'],
  221. [5.0, 3.6, 1.4, 0.2, 'I. setosa'],
  222. [5.4, 3.9, 1.7, 0.4, 'I. setosa'],
  223. [4.6, 3.4, 1.4, 0.3, 'I. setosa'],
  224. [5.0, 3.4, 1.5, 0.2, 'I. setosa'],
  225. [4.4, 2.9, 1.4, 0.2, 'I. setosa'],
  226. [4.9, 3.1, 1.5, 0.1, 'I. setosa'],
  227. [5.4, 3.7, 1.5, 0.2, 'I. setosa'],
  228. [4.8, 3.4, 1.6, 0.2, 'I. setosa'],
  229. [4.8, 3.0, 1.4, 0.1, 'I. setosa'],
  230. [4.3, 3.0, 1.1, 0.1, 'I. setosa'],
  231. [5.8, 4.0, 1.2, 0.2, 'I. setosa'],
  232. [5.7, 4.4, 1.5, 0.4, 'I. setosa'],
  233. [5.4, 3.9, 1.3, 0.4, 'I. setosa'],
  234. [5.1, 3.5, 1.4, 0.3, 'I. setosa'],
  235. [5.7, 3.8, 1.7, 0.3, 'I. setosa'],
  236. [5.1, 3.8, 1.5, 0.3, 'I. setosa'],
  237. [5.4, 3.4, 1.7, 0.2, 'I. setosa'],
  238. [5.1, 3.7, 1.5, 0.4, 'I. setosa'],
  239. [4.6, 3.6, 1.0, 0.2, 'I. setosa'],
  240. [5.1, 3.3, 1.7, 0.5, 'I. setosa'],
  241. [4.8, 3.4, 1.9, 0.2, 'I. setosa'],
  242. [5.0, 3.0, 1.6, 0.2, 'I. setosa'],
  243. [5.0, 3.4, 1.6, 0.4, 'I. setosa'],
  244. [5.2, 3.5, 1.5, 0.2, 'I. setosa'],
  245. [5.2, 3.4, 1.4, 0.2, 'I. setosa'],
  246. [5.5, 2.3, 4.0, 1.3, 'I. versicolor'],
  247. [6.5, 2.8, 4.6, 1.5, 'I. versicolor'],
  248. [5.7, 2.8, 4.5, 1.3, 'I. versicolor'],
  249. [6.3, 3.3, 4.7, 1.6, 'I. versicolor'],
  250. [4.9, 2.4, 3.3, 1.0, 'I. versicolor'],
  251. [6.6, 2.9, 4.6, 1.3, 'I. versicolor'],
  252. [5.2, 2.7, 3.9, 1.4, 'I. versicolor'],
  253. [5.0, 2.0, 3.5, 1.0, 'I. versicolor'],
  254. [5.9, 3.0, 4.2, 1.5, 'I. versicolor'],
  255. [6.0, 2.2, 4.0, 1.0, 'I. versicolor'],
  256. [6.1, 2.9, 4.7, 1.4, 'I. versicolor'],
  257. [5.6, 2.9, 3.6, 1.3, 'I. versicolor'],
  258. [6.7, 3.1, 4.4, 1.4, 'I. versicolor'],
  259. [5.6, 3.0, 4.5, 1.5, 'I. versicolor'],
  260. [5.8, 2.7, 4.1, 1.0, 'I. versicolor'],
  261. [6.2, 2.2, 4.5, 1.5, 'I. versicolor'],
  262. [5.6, 2.5, 3.9, 1.1, 'I. versicolor'],
  263. [5.9, 3.2, 4.8, 1.8, 'I. versicolor'],
  264. [6.1, 2.8, 4.0, 1.3, 'I. versicolor'],
  265. [6.3, 2.5, 4.9, 1.5, 'I. versicolor'],
  266. [6.1, 2.8, 4.7, 1.2, 'I. versicolor'],
  267. [6.4, 2.9, 4.3, 1.3, 'I. versicolor'],
  268. [6.6, 3.0, 4.4, 1.4, 'I. versicolor'],
  269. [6.8, 2.8, 4.8, 1.4, 'I. versicolor'],
  270. [6.7, 3.0, 5.0, 1.7, 'I. versicolor'],
  271. [6.0, 2.9, 4.5, 1.5, 'I. versicolor'],
  272. [5.7, 2.6, 3.5, 1.0, 'I. versicolor'],
  273. [5.5, 2.4, 3.8, 1.1, 'I. versicolor'],
  274. [5.5, 2.4, 3.7, 1.0, 'I. versicolor'],
  275. [5.8, 2.7, 3.9, 1.2, 'I. versicolor'],
  276. [6.0, 2.7, 5.1, 1.6, 'I. versicolor'],
  277. [5.4, 3.0, 4.5, 1.5, 'I. versicolor'],
  278. [6.0, 3.4, 4.5, 1.6, 'I. versicolor'],
  279. [6.7, 3.1, 4.7, 1.5, 'I. versicolor'],
  280. [6.3, 2.3, 4.4, 1.3, 'I. versicolor'],
  281. [5.6, 3.0, 4.1, 1.3, 'I. versicolor'],
  282. [5.5, 2.5, 4.0, 1.3, 'I. versicolor'],
  283. [5.5, 2.6, 4.4, 1.2, 'I. versicolor'],
  284. [6.1, 3.0, 4.6, 1.4, 'I. versicolor'],
  285. [5.8, 2.6, 4.0, 1.2, 'I. versicolor'],
  286. [5.0, 2.3, 3.3, 1.0, 'I. versicolor'],
  287. [5.6, 2.7, 4.2, 1.3, 'I. versicolor'],
  288. [5.7, 3.0, 4.2, 1.2, 'I. versicolor'],
  289. [5.7, 2.9, 4.2, 1.3, 'I. versicolor'],
  290. [6.2, 2.9, 4.3, 1.3, 'I. versicolor'],
  291. [5.1, 2.5, 3.0, 1.1, 'I. versicolor'],
  292. [5.7, 2.8, 4.1, 1.3, 'I. versicolor'],
  293. [6.4, 3.1, 5.5, 1.8, 'I. virginica'],
  294. [6.0, 3.0, 4.8, 1.8, 'I. virginica'],
  295. [6.9, 3.1, 5.4, 2.1, 'I. virginica'],
  296. [6.7, 3.1, 5.6, 2.4, 'I. virginica'],
  297. [6.9, 3.1, 5.1, 2.3, 'I. virginica'],
  298. [5.8, 2.7, 5.1, 1.9, 'I. virginica'],
  299. [6.8, 3.2, 5.9, 2.3, 'I. virginica'],
  300. [6.7, 3.3, 5.7, 2.5, 'I. virginica'],
  301. [6.7, 3.0, 5.2, 2.3, 'I. virginica'],
  302. [6.3, 2.5, 5.0, 1.9, 'I. virginica'],
  303. [6.5, 3.0, 5.2, 2.0, 'I. virginica'],
  304. [6.2, 3.4, 5.4, 2.3, 'I. virginica'],
  305. [4.7, 3.2, 1.6, 0.2, 'I. setosa'],
  306. [4.8, 3.1, 1.6, 0.2, 'I. setosa'],
  307. [5.4, 3.4, 1.5, 0.4, 'I. setosa'],
  308. [5.2, 4.1, 1.5, 0.1, 'I. setosa'],
  309. [5.5, 4.2, 1.4, 0.2, 'I. setosa'],
  310. [4.9, 3.1, 1.5, 0.2, 'I. setosa'],
  311. [5.0, 3.2, 1.2, 0.2, 'I. setosa'],
  312. [5.5, 3.5, 1.3, 0.2, 'I. setosa'],
  313. [4.9, 3.6, 1.4, 0.1, 'I. setosa'],
  314. [4.4, 3.0, 1.3, 0.2, 'I. setosa'],
  315. [5.1, 3.4, 1.5, 0.2, 'I. setosa'],
  316. [5.0, 3.5, 1.3, 0.3, 'I. setosa'],
  317. [4.5, 2.3, 1.3, 0.3, 'I. setosa'],
  318. [4.4, 3.2, 1.3, 0.2, 'I. setosa'],
  319. [5.0, 3.5, 1.6, 0.6, 'I. setosa'],
  320. [5.1, 3.8, 1.9, 0.4, 'I. setosa'],
  321. [4.8, 3.0, 1.4, 0.3, 'I. setosa'],
  322. [5.1, 3.8, 1.6, 0.2, 'I. setosa'],
  323. [5.9, 3.0, 5.1, 1.8, 'I. virginica']
  324. ]
  325.  
  326.  
  327. def first(trainingData):
  328. return trainingData[:int(len(trainingData)/2)]
  329.  
  330.  
  331. def second(trainingData):
  332. return trainingData[int(len(trainingData)/2):]
  333.  
  334.  
  335. if __name__ == "__main__":
  336. att1 = input()
  337. att2 = input()
  338. att3 = input()
  339. att4 = input()
  340. planttype = input()
  341. testCase = [att1, att2, att3, att4, planttype]
  342. t1 = first(trainingData)
  343. t2 = second(trainingData)
  344.  
  345. tree1 = buildtree(t1)
  346. tree2 = buildtree(t2)
  347.  
  348. c1 = classify(testCase, tree1)
  349. c2 = classify(testCase, tree2)
  350.  
  351. if c1.keys() != c2.keys():
  352. print("KONTRADIKCIJA")
  353. else:
  354. for key,value in c1.items():
  355. print key
Add Comment
Please, Sign In to add comment
Public Pastes
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!