python实现决策树、随机森林的简单原理

# 花萼长度、花萼宽度，花瓣长度，花瓣宽度 
iris_feature_E = 'sepal length', 'sepal width', 'petal length', 'petal width' 
iris_feature = u'花萼长度', u'花萼宽度', u'花瓣长度', u'花瓣宽度' 
iris_class = 'Iris-setosa', 'Iris-versicolor', 'Iris-virginica' 
 
 
if __name__ == "__main__": 
  mpl.rcParams['font.sans-serif'] = [u'SimHei'] 
  mpl.rcParams['axes.unicode_minus'] = False 
 
  path = '..\\8.Regression\\iris.data' # 数据文件路径 
  data = pd.read_csv(path, header=None) 
  x = data[range(4)] 
  y = pd.Categorical(data[4]).codes 
  # 为了可视化，仅使用前两列特征 
  x = x.iloc[:, :2] 
  x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.7, random_state=1) 
  print y_test.shape 
 
  # 决策树参数估计 
  # min_samples_split = 10：如果该结点包含的样本数目大于10，则(有可能)对其分支 
  # min_samples_leaf = 10：若将某结点分支后，得到的每个子结点样本数目都大于10，则完成分支；否则，不进行分支 
  model = DecisionTreeClassifier(criterion='entropy') 
  model.fit(x_train, y_train) 
  y_test_hat = model.predict(x_test)   # 测试数据 
 
  # 保存 
  # dot -Tpng my.dot -o my.png 
  # 1、输出 
  with open('iris.dot', 'w') as f: 
    tree.export_graphviz(model, out_file=f) 
  # 2、给定文件名 
  # tree.export_graphviz(model, out_file='iris1.dot') 
  # 3、输出为pdf格式 
  dot_data = tree.export_graphviz(model, out_file=None, feature_names=iris_feature_E, class_names=iris_class, 
                  filled=True, rounded=True, special_characters=True) 
  graph = pydotplus.graph_from_dot_data(dot_data) 
  graph.write_pdf('iris.pdf') 
  f = open('iris.png', 'wb') 
  f.write(graph.create_png()) 
  f.close() 
 
  # 画图 
  N, M = 50, 50 # 横纵各采样多少个值 
  x1_min, x2_min = x.min() 
  x1_max, x2_max = x.max() 
  t1 = np.linspace(x1_min, x1_max, N) 
  t2 = np.linspace(x2_min, x2_max, M) 
  x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点 
  x_show = np.stack((x1.flat, x2.flat), axis=1) # 测试点 
  print x_show.shape 
 
  # # 无意义，只是为了凑另外两个维度 
  # # 打开该注释前，确保注释掉x = x[:, :2] 
  # x3 = np.ones(x1.size) * np.average(x[:, 2]) 
  # x4 = np.ones(x1.size) * np.average(x[:, 3]) 
  # x_test = np.stack((x1.flat, x2.flat, x3, x4), axis=1) # 测试点 
 
  cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF']) 
  cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b']) 
  y_show_hat = model.predict(x_show) # 预测值 
  print y_show_hat.shape 
  print y_show_hat 
  y_show_hat = y_show_hat.reshape(x1.shape) # 使之与输入的形状相同 
  print y_show_hat 
  plt.figure(facecolor='w') 
  plt.pcolormesh(x1, x2, y_show_hat, cmap=cm_light) # 预测值的显示 
  plt.scatter(x_test[0], x_test[1], c=y_test.ravel(), edgecolors='k', s=150, zorder=10, cmap=cm_dark, marker='*') # 测试数据 
  plt.scatter(x[0], x[1], c=y.ravel(), edgecolors='k', s=40, cmap=cm_dark) # 全部数据 
  plt.xlabel(iris_feature[0], fontsize=15) 
  plt.ylabel(iris_feature[1], fontsize=15) 
  plt.xlim(x1_min, x1_max) 
  plt.ylim(x2_min, x2_max) 
  plt.grid(True) 
  plt.title(u'鸢尾花数据的决策树分类', fontsize=17) 
  plt.show() 

if __name__ == "__main__": 
  N =100 
  x = np.random.rand(N) *6 -3 
  x.sort() 
  y = np.sin(x) + np.random.randn(N) *0.05 
  x = x.reshape(-1,1) 
  print x 
  dt = DecisionTreeRegressor(criterion='mse',max_depth=9) 
  dt.fit(x,y) 
  x_test = np.linspace(-3,3,50).reshape(-1,1) 
  y_hat = dt.predict(x_test) 
 
  plt.plot(x,y,'r*',ms =5,label='Actual') 
  plt.plot(x_test,y_hat,'g-',linewidth=2,label='predict') 
  plt.legend(loc ='upper left') 
  plt.grid() 
  plt.show() 
 
  #比较决策树的深度影响 
  depth =[2,4,6,8,10] 
  clr = 'rgbmy' 
  dtr = DecisionTreeRegressor(criterion='mse') 
  plt.plot(x,y,'ko',ms=6,label='Actual') 
  x_test = np.linspace(-3,3,50).reshape(-1,1) 
  for d,c in zip(depth,clr): 
    dtr.set_params(max_depth=d) 
    dtr.fit(x,y) 
    y_hat = dtr.predict(x_test) 
    plt.plot(x_test,y_hat,'-',color=c,linewidth =2,label='Depth=%d' % d) 
  plt.legend(loc='upper left') 
  plt.grid(b =True) 
  plt.show()

mpl.rcParams['font.sans-serif'] = [u'SimHei'] # 黑体 FangSong/KaiTi 
mpl.rcParams['axes.unicode_minus'] = False 
 
path = 'iris.data' # 数据文件路径 
data = pd.read_csv(path, header=None) 
x_prime = data[range(4)] 
y = pd.Categorical(data[4]).codes 
feature_pairs = [[0, 1]] 
plt.figure(figsize=(10,9),facecolor='#FFFFFF') 
for i,pair in enumerate(feature_pairs): 
  x = x_prime[pair] 
  clf = RandomForestClassifier(n_estimators=200,criterion='entropy',max_depth=3) 
  clf.fit(x,y.ravel()) 
  N, M =50,50 
  x1_min,x2_min = x.min() 
  x1_max,x2_max = x.max() 
  t1 = np.linspace(x1_min,x1_max, N) 
  t2 = np.linspace(x2_min,x2_max, M) 
  x1,x2 = np.meshgrid(t1,t2) 
  x_test = np.stack((x1.flat,x2.flat),axis =1) 
  y_hat = clf.predict(x) 
  y = y.reshape(-1) 
  c = np.count_nonzero(y_hat == y) 
  print '特征：',iris_feature[pair[0]],'+',iris_feature[pair[1]] 
  print '\t 预测正确数目：',c 
  cm_light = mpl.colors.ListedColormap(['#A0FFA0', '#FFA0A0', '#A0A0FF']) 
  cm_dark = mpl.colors.ListedColormap(['g', 'r', 'b']) 
  y_hat = clf.predict(x_test) 
  y_hat = y_hat.reshape(x1.shape) 
  plt.pcolormesh(x1,x2,y_hat,cmap =cm_light) 
  plt.scatter(x[pair[0]],x[pair[1]],c=y,edgecolors='k',cmap=cm_dark) 
  plt.xlabel(iris_feature[pair[0]],fontsize=12) 
  plt.ylabel(iris_feature[pair[1]], fontsize=14) 
  plt.xlim(x1_min, x1_max) 
  plt.ylim(x2_min, x2_max) 
  plt.grid() 
plt.tight_layout(2.5) 
plt.subplots_adjust(top=0.92) 
plt.suptitle(u'随机森林对鸢尾花数据的两特征组合的分类结果', fontsize=18) 
plt.show()