第二章 scikit-learn 统计学习中数据处理
2.1 统计学习 关于统计量和配置
2.11 数据集
>>>fromsklearnimportdatasets
>>>iris=datasets.load_iris()
>>>data=iris.data
>>>data.shape
显示数据量和特征维度
这个是二维度数组作为特征的情况。
>>>digits=datasets.load_digits()
>>>digits.images.shape
(1797, 8, 8)
使用分类，回归或者其他方法对目标进行估计预测，同时要对特征进行处理
>>>estimator.fit(data)
2.2 监督学习:从高纬度变量中l预测一个输出变量
2.2.1 最近邻与维度灾难 （花瓣类型的预测）
>>> import numpy as np
>>> from sklearn import datasets
>>> iris = datasets.load_iris()
>>> iris_X = iris.data
>>> iris_y = iris.target
>>> np.unique(iris_y)
array([0, 1, 2])
>>> # Split iris data in train and test data
>>> # A random permutation, to split the data randomly
>>> np.random.seed(0)
>>> indices = np.random.permutation(len(iris_X))
>>> iris_X_train = iris_X[indices[:-10]]
>>> iris_y_train = iris_y[indices[:-10]]
>>> iris_X_test = iris_X[indices[-10:]]
>>> iris_y_test = iris_y[indices[-10:]]
>>> # Create and fit a nearest-neighbor classifier
>>> from sklearn.neighbors import KNeighborsClassifier
>>> knn = KNeighborsClassifier()
>>> knn.fit(iris_X_train, iris_y_train)
输出KNN的参数KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',
metric_params=None, n_neighbors=5, p=2, weights='uniform')
>>> knn.predict(iris_X_test)
array([1, 2, 1, 0, 0, 0, 2, 1, 2, 0])
>>> iris_y_test
array([1, 1, 1, 0, 0, 0, 2, 1, 2, 0])
2.2.2 线性模型 从回归到稀疏
>>> diabetes = datasets.load_diabetes()
>>> diabetes_X_train = diabetes.data[:-20]
>>> diabetes_X_test = diabetes.data[-20:]
>>> diabetes_y_train = diabetes.target[:-20]
>>> diabetes_y_test = diabetes.target[-20:]
这个任务就是预测疾病。1.使用线性回归
>>> regr = linear_model.LinearRegression()#线性回归
>>> regr.fit(diabetes_X_train, diabetes_y_train)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
>>> print(regr.coef_)#输出的应该是参数
[ 0.30349955 -237.63931533 510.53060544 327.73698041 -814.13170937
492.81458798 102.84845219 184.60648906 743.51961675 76.09517222]
>>> # The mean square error均方误差
>>> np.mean((regr.predict(diabetes_X_test)-diabetes_y_test)**2)
2004.56760268...
>>> # 1 代表准确的预测，0代表没有线性关系
>>> regr.score(diabetes_X_test, diabetes_y_test)
0.5850753022690...
>>> logistic.fit(iris_X_train, iris_y_train)
>>> from sklearn import svm
>>> svc = svm.SVC(kernel='linear')
>>> svc.fit(iris_X_train, iris_y_train)
... degree=3)
>>> # gamma: inverse of size of
>>> # radial kernel
>>> digits = datasets.load_digits()
>>> X_digits = digits.data
>>> y_digits = digits.target
>>> svc = svm.SVC(C=1, kernel='linear')
>>> svc.fit(X_digits[:-100], y_digits[:-100]).score(X_digits[-100:], y_digits[-100:])
0.97999999999999998
>>> X_folds = np.array_split(X_digits, 3)
>>> y_folds = np.array_split(y_digits, 3)
>>> scores = list()
>>> for k in range(3):
... # We use 'list' to copy, in order to 'pop' later on
... X_train = list(X_folds)
... X_test = X_train.pop(k)
... X_train = np.concatenate(X_train)
... y_train = list(y_folds)
... y_test = y_train.pop(k)
... y_train = np.concatenate(y_train)
... scores.append(svc.fit(X_train, y_train).score(X_test, y_test))
>>> print(scores)
[0.93489148580968284, 0.95659432387312182, 0.93989983305509184]
>>> k_fold = cross_validation.KFold(n=6, n_folds=3)
>>> for train_indices, test_indices in k_fold:
... print('Train: %s | test: %s' % (train_indices, test_indices))
Train: [2 3 4 5] | test: [0 1]
Train: [0 1 4 5] | test: [2 3]
Train: [0 1 2 3] | test: [4 5]
The cross-validation can then be implemented easily:
>>> kfold = cross_validation.KFold(len(X_digits), n_folds=3)
>>> [svc.fit(X_digits[train], y_digits[train]).score(X_digits[test], y_digits[test])
... for train, test in kfold]
2.3.3 Grid-search and cross-validated estimators 网格搜索与交叉验证
sklearn提供网格搜索，可以自行找到最优参数
>>> from sklearn.grid_search import GridSearchCV
>>> Cs = np.logspace(-6, -1, 10)
>>> clf = GridSearchCV(estimator=svc, param_grid=dict(C=Cs),... n_jobs=-1)
>>> clf.fit(X_digits[:1000], y_digits[:1000])GridSearchCV(cv=None,...
>>> clf.best_score_
0.925...
>>> clf.best_estimator_.C
0.0077...
或者
>>> from sklearn import linear_model, datasets
>>> lasso = linear_model.LassoCV()
>>> diabetes = datasets.load_diabetes()
>>> X_diabetes = diabetes.data
>>> y_diabetes = diabetes.target
>>> lasso.fit(X_diabetes, y_diabetes)
LassoCV(alphas=None, copy_X=True, cv=None, eps=0.001, fit_intercept=True,
max_iter=1000, n_alphas=100, n_jobs=1, normalize=False, positive=False,
precompute='auto', random_state=None, selection='cyclic', tol=0.0001,
verbose=False)
>>> # The estimator chose automatically its lambda:>>> lasso.alpha_
0.01229...
2.4无监督学习：
2.4.1 聚类
K-means clustering
>>> from sklearn import cluster, datasets>>> iris = datasets.load_iris()
>>> X_iris = iris.data
>>> y_iris = iris.target
>>> k_means = cluster.KMeans(n_clusters=3)>>> k_means.fit(X_iris)KMeans(copy_x=True, init='k-means++', ...>>> print(k_means.labels_[::10])
Principal component analysis: PCA 主成分分析
找到最主要的元素
其他的数据可以用单独的一个数据进行表示
>>> # Create a signal with only 2 useful dimensions
>>> x1 = np.random.normal(size=100)
>>> x2 = np.random.normal(size=100)
>>> x3 = x1 + x2
>>> X = np.c_[x1, x2, x3]
>>> from sklearn import decomposition
>>> pca = decomposition.PCA()
>>> pca.fit(X)
PCA(copy=True, n_components=None, whiten=False)>>> print(pca.explained_variance_)
[ 2.18565811e+00 1.19346747e+00 8.43026679e-32]
>>> # As we can see, only the 2 first components are useful>>> pca.n_components = 2
>>> X_reduced = pca.fit_transform(X)
>>> X_reduced.shape
(100, 2)
Independent Component Analysis: ICA 独立成分分析
>>> # Generate sample data
>>> time = np.linspace(0, 10, 2000)
>>> s1 = np.sin(2 * time) # Signal 1 : sinusoidal signal
>>> s2 = np.sign(np.sin(3 * time)) # Signal 2 : square signal>>> S = np.c_[s1, s2]
>>> S += 0.2 * np.random.normal(size=S.shape) # Add noise
>>> S /= S.std(axis=0) # Standardize data
>>> # Mix data
>>> A = np.array([[1, 1], [0.5, 2]]) # Mixing matrix
>>> X = np.dot(S, A.T) # Generate observations
>>> # Compute ICA
>>> ica = decomposition.FastICA()
>>> S_ = ica.fit_transform(X) # Get the estimated sources>>> A_ = ica.mixing_.T
>>> np.allclose(X, np.dot(S_, A_) + ica.mean_)
True