sklearn_01

 

 

1.DictVectorize特征提取¶

 

DictVectorize的处理对象是符号化(非数字化)的但是具有一定结构的特征数据，如字典等，将符号转成数字0/1表示。¶

In [62]:

from sklearn.feature_extraction import DictVectorizer
myonehot = DictVectorizer() # 如果结果不用toarray，请开启sparse=False
instances = [{'city': '北京','temperature':100},{'city': '上海','temperature':60}, {'city': '深圳','temperature':30}]
X = myonehot.fit_transform(instances).toarray()
X
myonehot.inverse_transform(X)

Out[62]:

array([[   0.,    1.,    0.,  100.],
       [   1.,    0.,    0.,   60.],
       [   0.,    0.,    1.,   30.]])

Out[62]:

[{'city=北京': 1.0, 'temperature': 100.0},
 {'city=上海': 1.0, 'temperature': 60.0},
 {'city=深圳': 1.0, 'temperature': 30.0}]

 

2.sklearn的train_test_split¶

In [4]:

import numpy as np
from sklearn.model_selection import train_test_split
x, y = np.arange(10).reshape((5, 2)), list(range(5))
print("x:",x)
print("y:",y)

 

x: [[0 1]
 [2 3]
 [4 5]
 [6 7]
 [8 9]]
y: [0, 1, 2, 3, 4]

In [51]:

#x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42) 
# random_state=0 保证程序每次运行都分割一样的训练集和测试集。否则，同样的算法模型在不同的训练集和测试集上的效果不一样。
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=0) 
x_train
y_train

Out[51]:

array([[2, 3],
       [6, 7],
       [8, 9]])

Out[51]:

[1, 3, 4]

In [52]:

x_test
y_test

Out[52]:

array([[4, 5],
       [0, 1]])

Out[52]:

[2, 0]

 

3.train_test_split--数据集切分¶

In [38]:

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn import datasets
from sklearn import svm
iris = datasets.load_iris()

In [53]:

iris.data.shape
iris.target

Out[53]:

(150, 4)

Out[53]:

array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])

In [58]:

X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=0)
X_train.shape,y_train.shape
X_test.shape, y_test.shape

Out[58]:

((120, 4), (120,))

Out[58]:

((30, 4), (30,))

In [61]:

clf = svm.SVC(kernel='linear', C=0.1).fit(X_train, y_train)
clf.score(X_test, y_test)

Out[61]:

1.0