Pyton10
2019-11-01 本文已影响0人
C_Z_Q_
jupyter notebook 操作
import numpy as np
#reshape
X = np.arange(15).reshape(5,3)
X
array([[ 0, 1, 2],
[ 3, 4, 5],
[ 6, 7, 8],
[ 9, 10, 11],
[12, 13, 14]])
x = np.arange(10)
x
array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
- 访问
x[2]
2
X[1,2]
5
X[1]
array([3, 4, 5])
X[3]
array([ 9, 10, 11])
X[2,2]
8
- 切片
x[5:]
array([5, 6, 7, 8, 9])
#h行切片，列切片
X[2:4,1:]
array([[ 7, 8],
[10, 11]])
X[2:,:2]
array([[ 6, 7],
[ 9, 10],
[12, 13]])
- 如果说不关心reshape的另外一个参数，我们可以写成-1，numpy自动推导出这个参数
x.reshape(5,-1)
array([[0, 1],
[2, 3],
[4, 5],
[6, 7],
[8, 9]])
- numpy的与运算
#numpy's universal function
X
array([[ 0, 1, 2],
[ 3, 4, 5],
[ 6, 7, 8],
[ 9, 10, 11],
[12, 13, 14]])
X + 1
array([[ 1, 2, 3],
[ 4, 5, 6],
[ 7, 8, 9],
[10, 11, 12],
[13, 14, 15]])
X * 2
array([[ 0, 2, 4],
[ 6, 8, 10],
[12, 14, 16],
[18, 20, 22],
[24, 26, 28]])
np.sin(X)
array([[ 0. , 0.84147098, 0.90929743],
[ 0.14112001, -0.7568025 , -0.95892427],
[-0.2794155 , 0.6569866 , 0.98935825],
[ 0.41211849, -0.54402111, -0.99999021],
[-0.53657292, 0.42016704, 0.99060736]])
- numpy 中 argsort()
x = np.arange(16)
x
array([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15])
#随机打乱
np.random.shuffle(x)
x
array([ 2, 10, 4, 13, 7, 11, 8, 12, 5, 0, 3, 6, 14, 9, 15, 1])
#argsort 元素从小排序所对应的索引
np.argsort(x)
array([ 9, 15, 0, 10, 2, 8, 11, 4, 6, 13, 1, 5, 7, 3, 12, 14],
dtype=int64)
- numpy 中的布尔索引
names = np.array(['Bob','Mor','Will','Joe','Mor','Will','Will'])
names
array(['Bob', 'Mor', 'Will', 'Joe', 'Mor', 'Will', 'Will'], dtype='<U4')
#使用np.random 模块的randn 生成一些正态分布的随机数据
data = np.random.randn(7,4)
data
array([[ 0.30878037, -0.4096957 , -0.83750594, -0.97213605],
[-0.14167727, -0.04756769, 1.97948161, -1.702129 ],
[-1.16628504, -0.4982823 , 1.53364224, -1.15853535],
[-0.11616092, 1.07999647, -0.35885284, -0.84570262],
[-0.12763289, -1.29314938, -0.80078425, -0.08737958],
[ 1.45718967, -1.14880644, 0.09459774, -0.25857695],
[-0.2095555 , -0.53830113, 0.63900549, 0.05845763]])
#假设 每个名字对应data数据的一行
#布尔型索引可以应用于数据的删选
data[names=='Joe']
array([[-0.11616092, 1.07999647, -0.35885284, -0.84570262]])
#布尔型索引应用修改值
#选取所有Mor的行，并且全部值 赋值为0
data[names=='Mor'] = 0
data
array([[ 0.30878037, -0.4096957 , -0.83750594, -0.97213605],
[ 0. , 0. , 0. , 0. ],
[-1.16628504, -0.4982823 , 1.53364224, -1.15853535],
[-0.11616092, 1.07999647, -0.35885284, -0.84570262],
[ 0. , 0. , 0. , 0. ],
[ 1.45718967, -1.14880644, 0.09459774, -0.25857695],
[-0.2095555 , -0.53830113, 0.63900549, 0.05845763]])
data[names=='Will',2:]=0
data
array([[ 0.30878037, -0.4096957 , -0.83750594, -0.97213605],
[ 0. , 0. , 0. , 0. ],
[-1.16628504, -0.4982823 , 0. , 0. ],
[-0.11616092, 1.07999647, -0.35885284, -0.84570262],
[ 0. , 0. , 0. , 0. ],
[ 1.45718967, -1.14880644, 0. , 0. ],
[-0.2095555 , -0.53830113, 0. , 0. ]])
2.鸢尾花散点图
#import warnings
#warnings.filterwarnings('ignore')
from sklearn import datasets
from matplotlib import pyplot as plt
iris = datasets.load_iris()
iris.keys
<function Bunch.keys>
#iris['DESCR']
#print(iris.DESCR)
X= iris.data
X.ndim
2
X.shape
(150, 4)
X.size
600
iris.feature_names
['sepal length (cm)',
'sepal width (cm)',
'petal length (cm)',
'petal width (cm)']
y= iris.target
y
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])
iris.target_names
array(['setosa', 'versicolor', 'virginica'], dtype='<U10')
#绘制萼片额度
X = X[:,:2]
X[y==0,:0]
array([], shape=(50, 0), dtype=float64)
#绘制散点图
plt.scatter(X[y==0,0],X[y==0,1],color = 'r') #setosa
plt.scatter(X[y==1,0],X[y==1,1],color = 'b') #versicolor
plt.scatter(X[y==2,0],X[y==2,1],color = 'g') #virginica
plt.show()
效果图
y= iris.target
y
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])
#绘制萼片维度
X = iris.data[:,2:]
X[y==0,0]
array([1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4,
1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 1.5, 1.7, 1.5, 1. , 1.7, 1.9, 1.6,
1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 1.5, 1.4, 1.5, 1.2, 1.3, 1.5, 1.3,
1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 1.4, 1.6, 1.4, 1.5, 1.4])
plt.scatter(X[y==0,0],X[y==0,1],color = 'r') #setosa
plt.scatter(X[y==1,0],X[y==1,1],color = 'b') #versicolor
plt.scatter(X[y==2,0],X[y==2,1],color = 'g') #virginica
plt.show()
3.机器学习初识
1). 监督学习(supervised learning)，无监督学习(unsupervised learning)，半监督学习(Semi-Supervised Learning)，强化学习（reinforcement Learning ）
2). 监督学习(supervised learning)和无监督学习(unsupervised learning)的判断：
是否有监督（supervised），就看输入数据是否有标签（label）。输入数据有标签，则为有监督学习，没标签则为无监督学习。
3). 监督学习：回归(Regression，连续）、分类（Classification，离散)
无监督学习：聚类（clustering）
分类算法KNN：
K近邻算法，即K-Nearest Neighbor algorithm，简称KNN算法。
可认为是：找最接近K的那个邻居。
实例：肿瘤良，恶性判断(手动实现)
from matplotlib import pyplot as plt
import numpy as np
raw_data_X = [[3.393533211, 2.331273381],
[3.110073483, 1.781539638],
[1.343808831, 3.368360954],
[3.582294042, 4.679179110],
[2.280362439, 2.866990263],
[7.423436942, 4.696522875],
[5.745051997, 3.533989803],
[9.172168622, 2.511101045],
[7.792783481, 3.424088941],
[7.939820817, 0.791637231]
]
raw_data_y = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]
X_train = np.array(raw_data_X)
y_train = np.array(raw_data_y)
预测
# 假设新来一个样本数据判断x是恶性还是良性
x = np.array([8.093607318, 3.365731514])
plt.scatter(X_train[y_train==0,0],X_train[y_train==0,1],color = 'r') #setosa
plt.scatter(X_train[y_train==1,0],X_train[y_train==1,1],color = 'b') #versicolor
plt.scatter(x[0],x[1],color = 'g') #virginica
plt.show()
通过knn算法来预测
from math import sqrt
# 计算x距离所有的是十个个点的距离，然后选距离最近的前k个
# distances = []
# for x_train in X_train:
# d = sqrt(np.sum((x_train-x)**2))
# distances.append(d)
distances = [sqrt(np.sum((x_train-x)**2)) for x_train in X_train]
distances
[4.812566907609877,
5.229270827235305,
6.749798999160064,
4.6986266144110695,
5.83460014556857,
1.4900114024329525,
2.354574897431513,
1.3761132675144652,
0.3064319992975,
2.5786840957478887]
nearst = np.argsort(distances)
nearst
array([8, 7, 5, 6, 9, 3, 0, 1, 4, 2], dtype=int64)
# 假设我们指定K的值是6
k =6
top_k_y =[y_train[i] for i in nearst[:6]]
top_k_y
[1, 1, 1, 1, 1, 0]
# 数据统计量大的话使用的统计办法
from collections import Counter
votes = Counter(top_k_y)
votes
Counter({1: 5, 0: 1})
# 返回数量前 i 的数据信息
votes.most_common(1)
[(1, 5)]
predict_y = votes.most_common(1)[0][0]
predict_y
1
x患者是恶性肿瘤的可能性大
