scikit-learn机器学习常用算法原理及编程实战

第四章K-近邻算法

4.2示例：使用k-近邻算法进行分类

（1）生成已标记的数据集

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)

画出图像

plt.figure(figsize=(16, 10))
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

（2）使用KNeighborsClassifier来对算法进行训练，我们选择的参数是k=5

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

（3）对一个新的样本进行预测

# 进行预测
X_sample = [0, 2]
X_sample = np.array(X_sample).reshape(1, -1)
y_sample = clf.predict(X_sample);
neighbors = clf.kneighbors(X_sample, return_distance=False);

（4）把待预测的样本以及和其最近的5个点标记出来

# 画出示意图
plt.figure(figsize=(16, 10))
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][0], X_sample[0][1], marker="x", 
            s=100, cmap='cool')    # 待预测的点

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

整体代码

# %matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
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))
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]
X_sample = np.array(X_sample).reshape(1, -1)
y_sample = clf.predict(X_sample)
neighbors = clf.kneighbors(X_sample, return_distance=False)
# 画出示意图
plt.figure(figsize=(16, 10))
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][0], X_sample[0][1], marker="x",s=100, cmap='cool')    # 待预测的点
for i in neighbors[0]:
    # 预测点与距离最近的 5 个样本的连线
    plt.plot([X[i][0], X_sample[0][0]], [X[i][1], X_sample[0][1]],'k--', linewidth=0.6)
plt.show()

4.3示例：使用k-近邻算法进行回归拟合

（1）生成数据集，它在余弦曲线的基础上加入了噪音

# 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

（2）训练模型

# 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)

（3）把这些预测点连起来，构成拟合曲线

# 画出拟合曲线
plt.figure(figsize=(16, 10))
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()

整体代码

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)
# 画出拟合曲线
plt.figure(figsize=(16, 10))
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()

4.4实例：糖尿病预测

使用K-近邻算法及其变种，对Pima印第安人的糖尿病进行预测

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
# 加载数据
data = pd.read_csv('diabetes.csv')
print('dataset shape {}'.format(data.shape))
data.head()
data.groupby("Outcome").size()
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]))

from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score

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()))

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))

from sklearn.model_selection import ShuffleSplit
from sklearn.model_selection import learning_curve
# from common.utils import plot_learning_curve

def plot_learning_curve(plt, estimator, title, X, y, ylim=None, cv=None,
                        n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
  
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    plt.grid()

    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1,
                     color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o--', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Cross-validation score")

    plt.legend(loc="best")
    return plt


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);



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))
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

---

第五章  线性回归算法

5.5示例：测算房价

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import load_boston

boston = load_boston()
X = boston.data
y = boston.target
X.shape
X[0]
boston.feature_names
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, random_state=3)
import time
from sklearn.linear_model import LinearRegression

model = LinearRegression()

start = time.clock()
model.fit(X_train, y_train)

train_score = model.score(X_train, y_train)
cv_score = model.score(X_test, y_test)
print('elaspe: {0:.6f}; train_score: {1:0.6f}; cv_score: {2:.6f}'.format(time.clock()-start, train_score, cv_score))
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline

def polynomial_model(degree=1):
    polynomial_features = PolynomialFeatures(degree=degree,
                                             include_bias=False)
    linear_regression = LinearRegression(normalize=True)
    pipeline = Pipeline([("polynomial_features", polynomial_features),
                         ("linear_regression", linear_regression)])
    return pipeline

model = polynomial_model(degree=2)

start = time.clock()
model.fit(X_train, y_train)

train_score = model.score(X_train, y_train)
cv_score = model.score(X_test, y_test)
print('elaspe: {0:.6f}; train_score: {1:0.6f}; cv_score: {2:.6f}'.format(time.clock()-start, train_score, cv_score))
from common.utils import plot_learning_curve
from sklearn.model_selection import ShuffleSplit

cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
plt.figure(figsize=(18, 4))
title = 'Learning Curves (degree={0})'
degrees = [1, 2, 3]

start = time.clock()
plt.figure(figsize=(18, 4), dpi=200)
for i in range(len(degrees)):
    plt.subplot(1, 3, i + 1)
    plot_learning_curve(plt, polynomial_model(degrees[i]), title.format(degrees[i]), X, y, ylim=(0.01, 1.01), cv=cv)

print('elaspe: {0:.6f}'.format(time.clock()-start))

---

第六章 逻辑回归算法

6.5 实例：乳腺癌检测

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
# 载入数据
from sklearn.datasets import load_breast_cancer

cancer = load_breast_cancer()
X = cancer.data
y = cancer.target
print('data shape: {0}; no. positive: {1}; no. negative: {2}'.format(
    X.shape, y[y==1].shape[0], y[y==0].shape[0]))
print(cancer.data[0])
cancer.feature_names
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)
# 模型训练
from sklearn.linear_model import LogisticRegression

model = LogisticRegression(solver='liblinear')
model.fit(X_train, y_train)

train_score = model.score(X_train, y_train)
test_score = model.score(X_test, y_test)
print('train score: {train_score:.6f}; test score: {test_score:.6f}'.format(
    train_score=train_score, test_score=test_score))
# 样本预测
y_pred = model.predict(X_test)
print('matchs: {0}/{1}'.format(np.equal(y_pred, y_test).sum(), y_test.shape[0]))
# 预测概率：找出低于 90% 概率的样本个数
y_pred_proba = model.predict_proba(X_test)
print('sample of predict probability: {0}'.format(y_pred_proba[0]))
y_pred_proba_0 = y_pred_proba[:, 0] > 0.1 
result = y_pred_proba[y_pred_proba_0]
y_pred_proba_1 = result[:, 1] > 0.1
print(result[y_pred_proba_1])
import time
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline

# 增加多项式预处理
def polynomial_model(degree=1, **kwarg):
    polynomial_features = PolynomialFeatures(degree=degree,
                                             include_bias=False)
    logistic_regression = LogisticRegression(**kwarg)
    pipeline = Pipeline([("polynomial_features", polynomial_features),
                         ("logistic_regression", logistic_regression)])
    return pipeline

model = polynomial_model(degree=2, penalty='l1', solver='liblinear')

start = time.clock()
model.fit(X_train, y_train)

train_score = model.score(X_train, y_train)
cv_score = model.score(X_test, y_test)
print('elaspe: {0:.6f}; train_score: {1:0.6f}; cv_score: {2:.6f}'.format(
    time.clock()-start, train_score, cv_score))
logistic_regression = model.named_steps['logistic_regression']
print('model parameters shape: {0}; count of non-zero element: {1}'.format(
    logistic_regression.coef_.shape, 
    np.count_nonzero(logistic_regression.coef_)))

from common.utils import plot_learning_curve
from sklearn.model_selection import ShuffleSplit

cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
title = 'Learning Curves (degree={0}, penalty={1})'
degrees = [1, 2]
penalty = 'l1'

start = time.clock()
plt.figure(figsize=(12, 4), dpi=144)
for i in range(len(degrees)):
    plt.subplot(1, len(degrees), i + 1)
    plot_learning_curve(plt, polynomial_model(degree=degrees[i], penalty=penalty, solver='liblinear', max_iter=300), 
                        title.format(degrees[i], penalty), X, y, ylim=(0.8, 1.01), cv=cv)

print('elaspe: {0:.6f}'.format(time.clock()-start))
import warnings
warnings.filterwarnings("ignore")

penalty = 'l2'

start = time.clock()
plt.figure(figsize=(12, 4), dpi=144)
for i in range(len(degrees)):
    plt.subplot(1, len(degrees), i + 1)
    plot_learning_curve(plt, polynomial_model(degree=degrees[i], penalty=penalty, solver='lbfgs'), 
                        title.format(degrees[i], penalty), X, y, ylim=(0.8, 1.01), cv=cv)

print('elaspe: {0:.6f}'.format(time.clock()-start))