scikit-learn KNN实现糖尿病预测

随书代码，阅读笔记。

KNN是一种有监督的机器学习算法，可以解决分类问题，也可以解决回归问题。

算法优点：准确性高，对异常值和噪声有较高的容忍度；

算法缺点：计算量大，内存消耗也比较大。

针对算法计算量大，有一些改进的数据结构，避免重复计算K-D Tree， Ball Tree。

算法变种：根据邻居的距离，分配不同权重。另外一个变种是指定半径。

• KNN进行分类

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd


from sklearn.datasets.samples_generator import make_blobs
# 生成数据
centers = [[-2, 2], [2, 2], [0, 4]]
X, y = make_blobs(n_samples=60, centers=centers, random_state=0, cluster_std=0.60)

# 画出数据
plt.figure(figsize=(16, 10), dpi=144)
c = np.array(centers)
plt.scatter(X[:, 0], X[:, 1], c=y, s=100, cmap='cool');         # 画出样本
plt.scatter(c[:, 0], c[:, 1], s=100, marker='^', c='orange');   # 画出中心点



from sklearn.neighbors import KNeighborsClassifier
# 模型训练
k = 5
clf = KNeighborsClassifier(n_neighbors=k)
clf.fit(X, y);




# 进行预测
X_sample = [0, 2]
y_sample = clf.predict(X_sample);
neighbors = clf.kneighbors(X_sample, return_distance=False);

# 画出示意图
plt.figure(figsize=(16, 10), dpi=144)
plt.scatter(X[:, 0], X[:, 1], c=y, s=100, cmap='cool');    # 样本
plt.scatter(c[:, 0], c[:, 1], s=100, marker='^', c='k');   # 中心点
plt.scatter(X_sample[0], X_sample[1], marker="x", 
            c=y_sample, s=100, cmap='cool')    # 待预测的点

for i in neighbors[0]:
    plt.plot([X[i][0], X_sample[0]], [X[i][1], X_sample[1]], 
             'k--', linewidth=0.6);    # 预测点与距离最近的 5 个样本的连线

• KNN进行回归拟合

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np



# 生成训练样本
n_dots = 40
X = 5 * np.random.rand(n_dots, 1)
y = np.cos(X).ravel()

# 添加一些噪声
y += 0.2 * np.random.rand(n_dots) - 0.1

# 训练模型
from sklearn.neighbors import KNeighborsRegressor
k = 5
knn = KNeighborsRegressor(k)
knn.fit(X, y);

# 生成足够密集的点并进行预测
T = np.linspace(0, 5, 500)[:, np.newaxis]
y_pred = knn.predict(T)
knn.score(X, y)

#output:0.98579189493611052

# 画出拟合曲线
plt.figure(figsize=(16, 10), dpi=144)
plt.scatter(X, y, c='g', label='data', s=100)         # 画出训练样本
plt.plot(T, y_pred, c='k', label='prediction', lw=4)  # 画出拟合曲线
plt.axis('tight')
plt.title("KNeighborsRegressor (k = %i)" % k)
plt.show()

• KNN 实现糖尿病预测

  
  
  %matplotlib inline
  import matplotlib.pyplot as plt
  import numpy as np
  import pandas as pd
  
  # 加载数据
  data = pd.read_csv('datasets/pima-indians-diabetes/diabetes.csv')
  print('dataset shape {}'.format(data.shape))
  data.head()
  
  
  data.groupby("Outcome").size()
  #Outcome
  #0    500 无糖尿病
  #1    268 有糖尿病
  #dtype: int64
  
  
  X = data.iloc[:, 0:8]
  Y = data.iloc[:, 8]
  print('shape of X {}; shape of Y {}'.format(X.shape, Y.shape))
  
  
  
  from sklearn.model_selection import train_test_split
  X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2);
  
  from sklearn.neighbors import KNeighborsClassifier, RadiusNeighborsClassifier
  
  models = []
  models.append(("KNN", KNeighborsClassifier(n_neighbors=2)))
  models.append(("KNN with weights", KNeighborsClassifier(
      n_neighbors=2, weights="distance")))
  models.append(("Radius Neighbors", RadiusNeighborsClassifier(
      n_neighbors=2, radius=500.0)))
  
  
  
  results = []
  for name, model in models:
      model.fit(X_train, Y_train)
      results.append((name, model.score(X_test, Y_test)))
  for i in range(len(results)):
      print("name: {}; score: {}".format(results[i][0],results[i][1]))
  
  #name: KNN; score: 0.681818181818
  #name: KNN with weights; score: 0.636363636364
  #name: Radius Neighbors; score: 0.62987012987
  
  from sklearn.model_selection import KFold
  from sklearn.model_selection import cross_val_score
  
  #kfold 训练10次，计算10次的平均准确率
  results = []
  for name, model in models:
      kfold = KFold(n_splits=10)
      cv_result = cross_val_score(model, X, Y, cv=kfold)
      results.append((name, cv_result))
  for i in range(len(results)):
      print("name: {}; cross val score: {}".format(
          results[i][0],results[i][1].mean()))
  
  #name: KNN; cross val score: 0.714764183185
  #name: KNN with weights; cross val score: 0.677050580998
  #name: Radius Neighbors; cross val score: 0.6497265892
  
  
  #模型训练
  knn = KNeighborsClassifier(n_neighbors=2)
  knn.fit(X_train, Y_train)
  train_score = knn.score(X_train, Y_train)
  test_score = knn.score(X_test, Y_test)
  print("train score: {}; test score: {}".format(train_score, test_score))
  
  
  #画出学习曲线
  from sklearn.model_selection import ShuffleSplit
  from common.utils import plot_learning_curve
  
  knn = KNeighborsClassifier(n_neighbors=2)
  cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
  plt.figure(figsize=(10, 6), dpi=200)
  plot_learning_curve(plt, knn, "Learn Curve for KNN Diabetes", 
                      X, Y, ylim=(0.0, 1.01), cv=cv);
  
  #数据可视化
  # 从8个特征中选择2个最重要的特征进行可视化
  
  from sklearn.feature_selection import SelectKBest
  
  selector = SelectKBest(k=2)
  X_new = selector.fit_transform(X, Y)
  X_new[0:5]
  
  results = []
  for name, model in models:
      kfold = KFold(n_splits=10)
      cv_result = cross_val_score(model, X_new, Y, cv=kfold)
      results.append((name, cv_result))
  for i in range(len(results)):
      print("name: {}; cross val score: {}".format(
          results[i][0],results[i][1].mean()))
  
  
  
  # 画出数据
  plt.figure(figsize=(10, 6), dpi=200)
  plt.ylabel("BMI")
  plt.xlabel("Glucose")
  plt.scatter(X_new[Y==0][:, 0], X_new[Y==0][:, 1], c='r', s=20, marker='o');         # 画出样本
  plt.scatter(X_new[Y==1][:, 0], X_new[Y==1][:, 1], c='g', s=20, marker='^');         # 画出样本
  
  #2个特征和8个特征得到的结果差不多。分类效果达到了瓶颈
  
  
  
  
  
  
  

  

KNN对糖尿病进行测试，无法得到比较高的预测准确性

扩展阅读