sklearn作弊手册

1，数据集

from sklearn.datasets import load_boston

from sklearn.datasets import load_iris

from sklearn.datasets import load_digits

from sklearn.datasets import fetch_20newsgroups

 

boston = load_boston()

iris = load_iris()

digits = load_digits()

news = fetch_20newsgroups(subset = 'all')

 

digits.data       .shape

digits.target

digits.DESCR

digits.target_names

 

2，训练/测试数据集划分

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target, test_size = 0.25, random_state = 42)

 

3，数据预处理

标准缩放预处理，一位有效编码预处理

from sklearn.preprocessing import StandardScaler 

from sklearn.preprocessing import OneHotEncoder

 

ss = StandardScaler()

X_train = ss.fit_transform(X_train)

X_test = ss.transform(X_test)

 

特征提取：字典向量，文本计数向量，文本Tfidf向量

from sklearn.feature_extraction import DictVectorizer

from sklearn.feature_extraction.text import CountVectorizer

from sklearn.feature_extraction.text import TfidfVectorizer

 

4，有监督学习：分类器与回归器

线性模型：逻辑斯蒂回归，随机梯度下降

from sklearn.linear_model import LogisticRegression, LinearRegression, SGDClassifier, SGDRegressor

from sklearn.svm import SVC, SVR, LinearSVC

from sklearn.naive_bayes import MultinomialNB

from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor

 

先有决策树，再有随机森林，在森林的基础上作梯度提升

        DecisionTree < RandomForest < GradientBoosting

from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor

from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor

from sklearn.ensemble import GradientBoostingClassifier, GradientBoostingRegressor

 

5，无监督学习

聚类：K均值

from sklearn.cluster import KMeans

6，度量/评价

from sklearn.metrics import classification_report

from sklearn.metrics import r2_score

均方差MSE，平均绝对偏差MAE

from sklearn.metrics import mean_squared_error, mean_absolute_error