朴素贝叶斯
from sklearn import datasets
iris = datasets.load_iris()
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
y_pred = gnb.fit(iris.data, iris.target).predict(iris.data)
支持向量机
from sklearn import svm
X = [[0, 0], [1, 1]]
y = [0, 1]
clf = svm.SVC()
clf.fit(X, y)
>>> # get support vectors
>>> clf.support_vectors_
array([[ 0., 0.],
[ 1., 1.]])
>>> # get indices of support vectors
>>> clf.support_
array([0, 1]...)
>>> # get number of support vectors for each class
>>> clf.n_support_
array([1, 1]...)
决策树
from sklearn.datasets import load_iris
from sklearn import tree
iris = load_iris()
clf = tree.DecisionTreeClassifier()
clf = clf.fit(iris.data, iris.target)
线性回归的核心代码
from sklearn.linear_model import LinearRegression
reg = LinearRegression()
reg.fit(ages_train,net_worths_train) # 训练回归直线
reg.coef_可以获取斜率
reg.intercept_可以获取截距
reg.score(target,data)可以获取r平方分数,这个是用来衡量这个拟合程度的一个变量.
这个数值介于0-1之间,如果是接近于1,意味着越好.
文本学习
# 提取词干的操作.
from nltk.stem.snowball import SnowballStemmer
stemmer = SnowballStemmer("english")
for word in word_list:
words = words + ' ' + stemmer.stem(word)
# 获取词袋的操作.
from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer()
bags_of_words = vectorizer.fit(word_data)
bags_of_words = vectorizer.transform(word_data)
from sklearn.feature_extraction.text import CountVectorizer
#语料
corpus = [
'This is the first document.',
'This is the second second document.',
'And the third one.',
'Is this the first document?',
]
#将文本中的词语转换为词频矩阵
vectorizer = CountVectorizer()
#计算个词语出现的次数
X = vectorizer.fit_transform(corpus)
#获取词袋中所有文本关键词
word = vectorizer.get_feature_names()
print word
#查看词频结果
print X.toarray()
from sklearn.feature_extraction.text import TfidfTransformer
#类调用
transformer = TfidfTransformer()
print transformer
#将词频矩阵X统计成TF-IDF值
tfidf = transformer.fit_transform(X)
#查看数据结构 tfidf[i][j]表示i类文本中的tf-idf权重
print tfidf.toarray()
[u'and', u'document', u'first', u'is', u'one', u'second', u'the', u'third', u'this']
[[0 1 1 1 0 0 1 0 1]
[0 1 0 1 0 2 1 0 1]
[1 0 0 0 1 0 1 1 0]
[0 1 1 1 0 0 1 0 1]]
TfidfTransformer(norm=u'l2', smooth_idf=True, sublinear_tf=False,
use_idf=True)
[[ 0. 0.43877674 0.54197657 0.43877674 0. 0.
0.35872874 0. 0.43877674]
[ 0. 0.27230147 0. 0.27230147 0. 0.85322574
0.22262429 0. 0.27230147]
[ 0.55280532 0. 0. 0. 0.55280532 0.
0.28847675 0.55280532 0. ]
[ 0. 0.43877674 0.54197657 0.43877674 0. 0.
0.35872874 0. 0.43877674]]
偏差,方差以及特征选择的状况
高偏差差对训练数据关系很少,是一种过度的简化.
高方差相反.它不能很好的推广到没有见过的情况.(往往会过拟合的状况.)
总结:
image.png
image.png
在回归中使用正则化（lasso回归）
image.png
使用sklearn lasso回归代码
import sklearn.linear_model.Lasso
regression = Lasso()
regression.fit(feature,labels)
regression.predict([2,4])
print regression.ceof_
为什么要使用lasso回归：
image.png
主要成分分析（PCA）
成分转换之后的形式：
image.png
PCA的sklearn代码形式:
image.png
使用PCA成分分析的作用:
image.png
交叉验证
直接从sklearn中导入的情况:
from sklearn.model_selection import train_test_split
iris = datasets.load_iris() # 导入数据
features = iris.data # 特征
labels = iris.target # 标记
features_train, features_test, labels_train, labels_test = train_test_split(features,labels,test_size=0.4,random_state=0) # 直接运用这个方法
clf = SVC(kernel="linear", C=1.)
clf.fit(features_train, labels_train)# 训练
print clf.score(features_test, labels_test) # 测试成绩
一般的步骤:
image.png
交叉验证的代码:
image.png
import numpy as np
from sklearn.model_selection import KFold
X = np.array([[1, 2], [3, 4], [1, 2], [3, 4]])
y = np.array([1, 2, 3, 4])
kf = KFold(n_splits=4) # 这个n_splits是指把整体的数据分为多少个小的子集
print kf.get_n_splits(X)
print list(kf.split(X))
for train_index, test_index in kf.split(X):
print("TRAIN:", train_index, "TEST:", test_index)
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
>>>
4
[(array([1, 2, 3]), array([0])), (array([0, 2, 3]), array([1])), (array([0, 1, 3]), array([2])), (array([0, 1, 2]), array([3]))]
('TRAIN:', array([1, 2, 3]), 'TEST:', array([0]))
('TRAIN:', array([0, 2, 3]), 'TEST:', array([1]))
('TRAIN:', array([0, 1, 3]), 'TEST:', array([2]))
('TRAIN:', array([0, 1, 2]), 'TEST:', array([3]))
自动调整算法的参数
from sklearn import svm, datasets
from sklearn.model_selection import GridSearchCV
iris = datasets.load_iris()
parameters = {'kernel': ('linear', 'rbf'), 'C': [1, 10]}
svc = svm.SVC()
clf = GridSearchCV(svc, parameters)
clf.fit(iris.data, iris.target)
print sorted(clf.cv_results_.keys())
print clf.best_params_ # 直接打印最佳的参数
