In [2]:
# coding: utf-8
from sklearn import datasets
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score
iris = datasets.load_iris() # 加载鸢尾花数据库
X = iris.data[:, [2, 3]] # 选择花萼长度、花萼宽度、花瓣长度、花瓣宽度4个属性中的后2个
y = iris.target
# 将数据集的30%置为测试集，70%置为训练集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
sc = StandardScaler() # 标准化数据，大幅度提高准确性
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)
ppn = Perceptron(tol=40, eta0=0.1, random_state=0) # 使用sklearn感知器训练数据
ppn.fit(X_train_std, y_train)
y_pred = ppn.predict(X_test_std)
print('Misclassified samples: %d' % (y_test != y_pred).sum()) # 输出误判数
print('Accuracy: %.2f' % accuracy_score(y_test, y_pred)) # 输出准确率
机器学习模型的学习效果评价基于测试集，而不依赖于训练集；过拟合的含义是模型可以很好的匹配训练集，但是对于未知的训练集数据效果不佳；下面的代码是之前的分类器模型可视化：
In [4]:
from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot all samples
X_test, y_test = X[test_idx, :], y[test_idx]
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=cmap(idx), marker=markers[idx], label=cl)
# highlight test samples
if test_idx:
X_test, y_test = X[test_idx, :], y[test_idx]
plt.scatter(X_test[:, 0], X_test[:, 1], c='',
alpha=1.0, linewidth=1, marker='o', s=55, label='test set')
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X=X_combined_std, y=y_combined, classifier=ppn, test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
感知器算法对于无法线性分割的数据集，是不收敛的，因此实际中很少只用感知器算法。后面将会介绍更强大的线性分类器，对无法线性分割的数据集可以收敛到最佳程度
In [6]:
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=lr, test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
In [7]:
from sklearn.svm import SVC
svm = SVC(kernel='linear', C=1.0, random_state=0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=svm, test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
In [8]:
np.random.seed(0)
X_xor = np.random.randn(200, 2)
y_xor = np.logical_xor(X_xor[:, 0] > 0, X_xor[:, 1] > 0)
y_xor = np.where(y_xor, 1, -1)
plt.scatter(X_xor[y_xor==1, 0], X_xor[y_xor==1, 1], c='b', marker='x', label='1')
plt.scatter(X_xor[y_xor==-1, 0], X_xor[y_xor==-1, 1], c='r', marker='s', label='-1')
plt.ylim(-3.0)
plt.legend()
plt.show()
In [9]:
svm = SVC(kernel='rbf', random_state=0, gamma=0.10, C=10.0)
svm.fit(X_xor, y_xor)
plot_decision_regions(X_xor, y_xor, classifier=svm)
plt.legend(loc='upper left')
plt.show()
In [10]:
svm = SVC(kernel='rbf', random_state=0, gamma=0.2, C=1.0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=svm, test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
调整gamma参数
In [11]:
svm = SVC(kernel='rbf', random_state=0, gamma=100.0, C=1.0)
svm.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=svm, test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.show()
In [13]:
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion='entropy', max_depth=3, random_state=0)
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined, y_combined, classifier=tree, test_idx=range(105,150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc='upper left')
plt.show()
from sklearn.tree import export_graphviz
export_graphviz(tree, out_file='tree.dot', feature_names=['petal length', 'petal width'])
In [19]:
from sklearn.tree import export_graphviz
from IPython.display import Image
from sklearn.externals.six import StringIO
import pydot
dot_data = StringIO()
export_graphviz(tree, out_file=dot_data, feature_names=['petal length', 'petal width'])
graph = pydot.graph_from_dot_data(dot_data.getvalue())
Image(graph[0].create_png())
Out[19]:
In [20]:
from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(criterion='entropy', n_estimators=10, random_state=1, n_jobs=2)
forest.fit(X_train, y_train)
plot_decision_regions(X_combined, y_combined, classifier=forest, test_idx=range(105,150))
plt.xlabel('petal length')
plt.ylabel('petal width')
plt.legend(loc='upper left')
plt.show()
In [21]:
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=5, p=2, metric='minkowski')
knn.fit(X_train_std, y_train)
plot_decision_regions(X_combined_std, y_combined, classifier=knn, test_idx=range(105,150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.show()
In [46]:
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.cross_validation import train_test_split
df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data', header=None)
df_wine.columns = ['Class label', 'Alcohol', 'Malic acid', 'Ash', 'Alcalinity of ash', 'Magnesium',
'Total phenols', 'Flavanoids', 'Nonflavanoid phenols', 'Proanthocyanins', 'Color intensity', 'Hue',
'OD280/OD315 of diluted wines', 'Proline']
print('Class labels', np.unique(df_wine['Class label']))
df_wine.head()
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
stdsc = StandardScaler()
X_train_std = stdsc.fit_transform(X_train)
X_test_std = stdsc.transform(X_test)
lr = LogisticRegression()
lr.fit(X_train_std, y_train)
print('Training accuracy:', lr.score(X_train_std, y_train))
print('Test accuracy:', lr.score(X_test_std, y_test))
lr1 = LogisticRegression(penalty='l1',C=5)
lr1.fit(X_train_std, y_train)
print('Training accuracy(With L1 regularzition):', lr1.score(X_train_std, y_train))
print('Test accuracy(With L1 regularzition):', lr1.score(X_test_std, y_test))
In [47]:
from sklearn.base import clone
from itertools import combinations
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.metrics import accuracy_score
class SBS():
def __init__(self, estimator, k_features, scoring=accuracy_score, test_size=0.25, random_state=1):
self.scoring = scoring
self.estimator = clone(estimator)
self.k_features = k_features
self.test_size = test_size
self.random_state = random_state
def fit(self, X, y):
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=self.test_size, random_state=self.random_state)
dim = X_train.shape[1]
self.indices_ = tuple(range(dim))
self.subsets_ = [self.indices_]
score = self._calc_score(X_train, y_train, X_test, y_test, self.indices_)
self.scores_ = [score]
while dim > self.k_features:
scores = []
subsets = []
for p in combinations(self.indices_, r=dim-1):
score = self._calc_score(X_train, y_train, X_test, y_test, p)
scores.append(score)
subsets.append(p)
best = np.argmax(scores)
self.indices_ = subsets[best]
self.subsets_.append(self.indices_)
dim -= 1
self.scores_.append(scores[best])
self.k_score_ = self.scores_[-1]
return self
def transform(self, X):
return X[:, self.indices_]
def _calc_score(self, X_train, y_train, X_test, y_test, indices):
self.estimator.fit(X_train[:, indices], y_train)
y_pred = self.estimator.predict(X_test[:, indices])
score = self.scoring(y_test, y_pred)
return score
In [48]:
from sklearn.neighbors import KNeighborsClassifier
import matplotlib.pyplot as plt
knn = KNeighborsClassifier(n_neighbors=2)
sbs = SBS(knn, k_features=1)
sbs.fit(X_train_std, y_train)
k_feat = [len(k) for k in sbs.subsets_]
plt.plot(k_feat, sbs.scores_, marker='o')
plt.ylim([0.7, 1.1])
plt.ylabel('Accuracy')
plt.xlabel('Number of features')
plt.grid()
plt.show()
我们挑选5个特征检查是否带来改善,从结果可以看出，使用更少的属性，测试集的准确率提高了2%
In [50]:
k5 = list(sbs.subsets_[8])
print(df_wine.columns[1:][k5])
knn.fit(X_train_std, y_train)
print('Training accuracy:', knn.score(X_train_std, y_train))
print('Test accuracy:', knn.score(X_test_std, y_test))
knn.fit(X_train_std[:, k5], y_train)
print('Training accuracy(select 5):', knn.score(X_train_std[:, k5], y_train))
print('Test accuracy(select 5):', knn.score(X_test_std[:, k5], y_test))
In [52]:
from sklearn.ensemble import RandomForestClassifier
feat_labels = df_wine.columns[1:]
forest = RandomForestClassifier(n_estimators=10000, random_state=0, n_jobs=-1)
forest.fit(X_train, y_train)
importances = forest.feature_importances_
indices = np.argsort(importances)[::-1]
for f in range(X_train.shape[1]):
print("%2d) %-*s %f" % (f + 1, 30, feat_labels[f], importances[indices[f]]))
plt.title('Feature Importances')
plt.bar(range(X_train.shape[1]), importances[indices], color='lightblue', align='center')
plt.xticks(range(X_train.shape[1]), feat_labels, rotation=90)
plt.xlim([-1, X_train.shape[1]])
plt.tight_layout()
plt.show()
In [10]:
from matplotlib.colors import ListedColormap
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
def plot_decision_regions(X, y, classifier, resolution=0.02):
# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())
# plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=cmap(idx), marker=markers[idx], label=cl)
df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data', header=None)
X, y = df_wine.iloc[:, 1:].values, df_wine.iloc[:, 0].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.fit_transform(X_test)
pca = PCA(n_components=2)
lr = LogisticRegression()
X_train_pca = pca.fit_transform(X_train_std)
X_test_pca = pca.transform(X_test_std)
lr.fit(X_train_pca, y_train)
plot_decision_regions(X_train_pca, y_train, classifier=lr)
plt.xlabel('PC1 train')
plt.ylabel('PC2 train')
plt.legend(loc='lower left')
plt.show()
In [11]:
plot_decision_regions(X_test_pca, y_test, classifier=lr)
plt.xlabel('PC1 test')
plt.ylabel('PC2 test')
plt.legend(loc='lower left')
plt.show()
In [ ]: