版权所有，转帖注明出处
章节
Scikit-learn是一个开源Python库，它使用统一的接口实现了一系列机器学习、预处理、交叉验证和可视化算法。
一个基本例子
from sklearn import neighbors, datasets, preprocessing
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
iris = datasets.load_iris()
X, y = iris.data[:, :2], iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=33)
scaler = preprocessing.StandardScaler().fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)
knn = neighbors.KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)
accuracy_score(y_test, y_pred)
加载数据
数据类型可以是NumPy数组、SciPy稀疏矩阵，或者其他可转换为数组的类型，如panda DataFrame等。
import numpy as np
X = np.random.random((10,5))
y = np.array(['M','M','F','F','M','F','M','M','F','F','F'])
X[X < 0.7] = 0
预处理数据
标准化/Standardization
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler().fit(X_train)
standardized_X = scaler.transform(X_train)
standardized_X_test = scaler.transform(X_test)
归一化/Normalization
from sklearn.preprocessing import Normalizer
scaler = Normalizer().fit(X_train)
normalized_X = scaler.transform(X_train)
normalized_X_test = scaler.transform(X_test)
二值化/Binarization
from sklearn.preprocessing import Binarizer
binarizer = Binarizer(threshold=0.0).fit(X)
binary_X = binarizer.transform(X)
类别特征编码
from sklearn.preprocessing import LabelEncoder
enc = LabelEncoder()
y = enc.fit_transform(y)
缺失值估算
>>>from sklearn.preprocessing import Imputer
>>>imp = Imputer(missing_values=0, strategy='mean', axis=0)
>>>imp.fit_transform(X_train)
生成多项式特征
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(5)
oly.fit_transform(X)
训练与测试数据分组
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y,random_state=0)
创建模型
有监督学习模型
线性回归
from sklearn.linear_model import LinearRegression
lr = LinearRegression(normalize=True)
支持向量机(SVM)
from sklearn.svm import SVC
svc = SVC(kernel='linear')
朴素贝叶斯
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
KNN
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
无监督学习模型
主成分分析(PCA)
from sklearn.decomposition import PCA
pca = PCA(n_components=0.95)
k均值/K Means
from sklearn.cluster import KMeans
k_means = KMeans(n_clusters=3, random_state=0)
模型拟合
有监督学习
lr.fit(X, y)
knn.fit(X_train, y_train)
svc.fit(X_train, y_train)
无监督学习
k_means.fit(X_train)
pca_model = pca.fit_transform(X_train)
模型预测
有监督学习
y_pred = svc.predict(np.random.random((2,5)))
y_pred = lr.predict(X_test)
y_pred = knn.predict_proba(X_test))
无监督学习
y_pred = k_means.predict(X_test)
评估模型性能
分类指标
准确度
knn.score(X_test, y_test)
from sklearn.metrics import accuracy_score
accuracy_score(y_test, y_pred)
分类报告
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred)))
混淆矩阵
from sklearn.metrics import confusion_matrix
print(confusion_matrix(y_test, y_pred)))
回归指标
平均绝对误差
from sklearn.metrics import mean_absolute_error
y_true = [3, -0.5, 2])
mean_absolute_error(y_true, y_pred))
均方差
from sklearn.metrics import mean_squared_error
mean_squared_error(y_test, y_pred))
$R^2$分数
from sklearn.metrics import r2_score
r2_score(y_true, y_pred))
聚类指标
调整兰德系数
from sklearn.metrics import adjusted_rand_score
adjusted_rand_score(y_true, y_pred))
同质性/Homogeneity
from sklearn.metrics import homogeneity_score
homogeneity_score(y_true, y_pred))
调和平均指标/V-measure
from sklearn.metrics import v_measure_score
metrics.v_measure_score(y_true, y_pred))
交叉验证
print(cross_val_score(knn, X_train, y_train, cv=4))
print(cross_val_score(lr, X, y, cv=2))
模型调优
网格搜索
from sklearn.grid_search import GridSearchCV
params = {"n_neighbors": np.arange(1,3), "metric": ["euclidean", "cityblock"]}
grid = GridSearchCV(estimator=knn,param_grid=params)
grid.fit(X_train, y_train)
print(grid.best_score_)
print(grid.best_estimator_.n_neighbors)
随机参数优化
from sklearn.grid_search import RandomizedSearchCV
params = {"n_neighbors": range(1,5), "weights": ["uniform", "distance"]}
rsearch = RandomizedSearchCV(estimator=knn,
param_distributions=params,
cv=4,
n_iter=8,
random_state=5)
rsearch.fit(X_train, y_train)
print(rsearch.best_score_)