Source Code for Module haizea.common.stats

  1  # -------------------------------------------------------------------------- # 
  2  # Copyright 2006-2009, University of Chicago                                 # 
  3  # Copyright 2008-2009, Distributed Systems Architecture Group, Universidad   # 
  4  # Complutense de Madrid (dsa-research.org)                                   # 
  5  #                                                                            # 
  6  # Licensed under the Apache License, Version 2.0 (the "License"); you may    # 
  7  # not use this file except in compliance with the License. You may obtain    # 
  8  # a copy of the License at                                                   # 
  9  #                                                                            # 
 10  # http://www.apache.org/licenses/LICENSE-2.0                                 # 
 11  #                                                                            # 
 12  # Unless required by applicable law or agreed to in writing, software        # 
 13  # distributed under the License is distributed on an "AS IS" BASIS,          # 
 14  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.   # 
 15  # See the License for the specific language governing permissions and        # 
 16  # limitations under the License.                                             # 
 17  # -------------------------------------------------------------------------- # 
 18   
 19  import random 
 20  import operator  
 21   
 22  TESTDIST_NUM_ITERS=10000 
 23   
 24 -class DiscreteDistributionBase(object): 
 25 -    def __init__(self, values, probabilities): 
 26          self.values = values 
 27          self.probabilities = probabilities[:] 
 28          self.accumprobabilities = probabilities[:] 
 29          accum = 0.0 
 30          for i, prob in enumerate(self.probabilities): 
 31              accum += prob 
 32              self.accumprobabilities[i] = accum 
 33          self.numValues = len(self.values) 
 34           
 35 -    def getAvg(self): 
 36          return reduce(operator.add, [x[0]*x[1] for x in zip(self.values, self.probabilities)]) 
 37   
 38 -    def getValueFromProb(self, prob): 
 39          pos = None 
 40          for i, p in enumerate(self.accumprobabilities): 
 41              if prob < p: 
 42                  pos = i 
 43                  break #Ugh 
 44          return self.values[pos] 
 45       
 46 -    def testDistribution(self): 
 47          vals = [] 
 48          histogram = {} 
 49          for v in self.values: 
 50              histogram[v]=0 
 51          for i in xrange(1,TESTDIST_NUM_ITERS): 
 52              v = self.get() 
 53              vals.append(v) 
 54              histogram[v] += 1 
 55   
 56          for k in histogram: 
 57              histogram[k] = float(histogram[k]) / float(TESTDIST_NUM_ITERS) 
 58           
 59          print histogram 
 60   
 61       
 62       
 63 -class DiscreteDistribution(DiscreteDistributionBase): 
 64 -    def __init__(self, values, probabilities): 
 65          DiscreteDistributionBase.__init__(self, values, probabilities) 
 66           
 67 -    def get(self): 
 68          return self.getValueFromProb(random.random()) 
 69   
 70           
 71 -class DiscreteUniformDistribution(DiscreteDistributionBase): 
 72 -    def __init__(self, values): 
 73          probabilities= [1.0/len(values)] * len(values) 
 74          DiscreteDistributionBase.__init__(self, values, probabilities) 
 75           
 76 -    def get(self): 
 77          return self.getValueFromProb(random.random()) 
 78   
 79           
 80 -class ContinuousDistributionBase(object): 
 81 -    def __init__(self, min, max): 
 82          self.min = float(min) 
 83          self.max = float(max) 
 84           
 85 -    def getList(self, n): 
 86          l = [] 
 87          for i in xrange(1, n): 
 88              l.append(self.get()) 
 89          return l 
 90       
 91 -class ContinuousUniformDistribution(ContinuousDistributionBase): 
 92 -    def __init__(self, min, max): 
 93          ContinuousDistributionBase.__init__(self, min, max) 
 94           
 95 -    def get(self): 
 96          return random.uniform(self.min, self.max) 
 97                       
 98 -class ContinuousNormalDistribution(ContinuousDistributionBase): 
 99 -    def __init__(self, min, max, mu, sigma): 
100          ContinuousDistributionBase.__init__(self, min, max) 
101          self.mu = mu 
102          self.sigma = sigma 
103           
104 -    def get(self): 
105          valid = False 
106          while not valid: 
107              number = random.normalvariate(self.mu, self.sigma) 
108              if number >= self.min and number <= self.max: 
109                  valid = True 
110          return number 
111       
112 -class ContinuousParetoDistribution(ContinuousDistributionBase): 
113 -    def __init__(self, min, max, alpha): 
114          ContinuousDistributionBase.__init__(self, min, max) 
115          self.alpha = alpha 
116           
117 -    def get(self): 
118          return random.paretovariate(self.alpha) 
119