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。
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)
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
from sklearn.preprocessing import StandardScaler scaler = StandardScaler().fit(X_train) standardized_X = scaler.transform(X_train) standardized_X_test = scaler.transform(X_test)
from sklearn.preprocessing import Normalizer scaler = Normalizer().fit(X_train) normalized_X = scaler.transform(X_train) normalized_X_test = scaler.transform(X_test)
from sklearn.preprocessing import Binarizer binarizer = Binarizer(threshold=0.0).fit(X) binary_X = binarizer.transform(X)
from sklearn.preprocessing import LabelEncoder enc = LabelEncoder() y = enc.fit_transform(y)
>>>from sklearn.preprocessing import Imputer >>>imp = Imputer(missing_values=0, strategy=‘mean‘, axis=0) >>>imp.fit_transform(X_train)
from sklearn.preprocessing import PolynomialFeatures poly = PolynomialFeatures(5) oly.fit_transform(X)
from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X,y,random_state=0)
from sklearn.linear_model import LinearRegression lr = LinearRegression(normalize=True)
from sklearn.svm import SVC svc = SVC(kernel=‘linear‘)
from sklearn.metrics import mean_absolute_error y_true = [3, -0.5, 2]) mean_absolute_error(y_true, y_pred))
原文:https://www.cnblogs.com/huanghanyu/p/13158920.html