机器学习-KNN算法

• 
  
  
  import
  numpy
  as
  np
  
  
• 
  
  
  import
  matplotlib.pyplot
  as
  plt
  
  
• 
  
  
  from
  matplotlib.colors
  import
  ListedColormap
  
  
• 
  
  
  from
  sklearn
  import
  neighbors
  
  
• 
  
  
  import
  pandas
  as
  pd
  
  
• 
  
  
  
  
• 
  
  n_neighbors =
  15
  
  
  
• 
  
  
  
  
• 
  
  
  # import some data to play with
  
  
  
• 
  
  path =
  './iris.data'
  
  
  
• 
  
  iris = np.array(pd.read_csv(path, header=
  None
  ))
  
  
• 
  
  
  
  
• 
  
  
  # we only take the first two features. We could avoid this ugly
  
  
  
• 
  
  
  # slicing by using a two-dim dataset
  
  
  
• 
  
  X = iris[:, :
  2
  ]
  
  
• 
  
  y = pd.Categorical(iris[:,
  4
  ]).codes
  
  
• 
  
  
  
  
• 
  
  h =
  .02
  # step size in the mesh
  
  
  
• 
  
  
  
  
• 
  
  
  # Create color maps
  
  
  
• 
  
  cmap_light = ListedColormap([
  '#FFAAAA'
  ,
  '#AAFFAA'
  ,
  '#AAAAFF'
  ])
  
  
• 
  
  cmap_bold = ListedColormap([
  '#FF0000'
  ,
  '#00FF00'
  ,
  '#0000FF'
  ])
  
  
• 
  
  
  
  
• 
  
  
  for
  weights
  in
  [
  'uniform'
  ,
  'distance'
  ]:
  
  
• 
  
  
  # we create an instance of Neighbours Classifier and fit the data.
  
  
  
• 
  
  clf = neighbors.KNeighborsClassifier(n_neighbors, weights=weights)
  
  
• 
  
  clf.fit(X, y)
  
  
• 
  
  
  
  
• 
  
  
  # Plot the decision boundary. For that, we will assign a color to each
  
  
  
• 
  
  
  # point in the mesh [x_min, x_max]x[y_min, y_max].
  
  
  
• 
  
  x_min, x_max = X[:,
  0
  ].min() -
  1
  , X[:,
  0
  ].max() +
  1
  
  
  
• 
  
  y_min, y_max = X[:,
  1
  ].min() -
  1
  , X[:,
  1
  ].max() +
  1
  
  
  
• 
  
  xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
  
  
• 
  
  np.arange(y_min, y_max, h))
  
  
• 
  
  Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
  
  
• 
  
  
  
  
• 
  
  
  # Put the result into a color plot
  
  
  
• 
  
  Z = Z.reshape(xx.shape)
  
  
• 
  
  plt.figure()
  
  
• 
  
  plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
  
  
• 
  
  
  
  
• 
  
  
  # Plot also the training points
  
  
  
• 
  
  plt.scatter(X[:,
  0
  ], X[:,
  1
  ], c=y, cmap=cmap_bold,
  
  
• 
  
  edgecolor=
  'k'
  , s=
  20
  )
  
  
• 
  
  plt.xlim(xx.min(), xx.max())
  
  
• 
  
  plt.ylim(yy.min(), yy.max())
  
  
• 
  
  plt.title(
  "3-Class classification (k = %i, weights = '%s')"
  
  
  
• 
  
  % (n_neighbors, weights))
  
  
• 
  
  plt.show()
  
  
  

• 
  
  
  import
  numpy
  as
  np
  
  
• 
  
  
  import
  operator
  
  
• 
  
  
  
  
• 
  
  
  # Python实现
  
  
  
• 
  
  
  # inx 测试样本
  
  
  
• 
  
  
  # dataSet，labels训练样本及其标签
  
  
  
• 
  
  
  # k最近近邻范围
  
  
  
• 
  
  
  
  
• 
  
  
  
  
• 
  
  def classify0(inX, dataSet, labels, k):
  
  
• 
  
  dataSetSize = dataSet.shape[
  0
  ]
  
  
• 
  
  diffMat = np.tile(inX, (dataSetSize,
  1
  )) - dataSet
  
  
• 
  
  sqDiffMat = diffMat**
  2
  
  
  
• 
  
  sqDistances = sqDiffMat.sum(axis=
  1
  )
  
  
• 
  
  distances = sqDistances**
  0.5
  
  
  
• 
  
  sortedDistIndicies = distances.argsort()
  
  
• 
  
  classCount={}
  
  
• 
  
  
  for
  i
  in
  range(k):
  
  
• 
  
  voteIlabel = labels[sortedDistIndicies]
  
  
• 
  
  classCount[voteIlabel] = classCount.get(voteIlabel,
  0
  ) +
  1
  
  
  
• 
  
  sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(
  1
  ), reverse=
  True
  )
  
  
• 
  
  
  return
  sortedClassCount[
  0
  ][
  0
  ]
  
  

更多免费技术资料可关注：annalin1203