Day01-集成学习-机器学习基础(DataWhale)

一、机器学习基础

知识点:

• 机器学习分监督学习和非监督学习。
  
  监督学习：有因变量、有特征向量、目的：预测
  
  非监督学习：无因变量、有特征向量，目的：寻找数据中的结构
• 监督学习分回归和分类
  
  回归：因变量连续
  
  分类：因变量离散

常用的包

#引入科学计算包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline 
#直接在你的python console里面生成图像
plt.style.use("ggplot")
import seaborn  as sns

1.1 回归

from sklearn import datasets

boston = datasets.load_boston()
x = boston.data
y = boston.target
features = boston.feature_names

boston_data = pd.DataFrame(x,columns=features)
boston_data.head(2)

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.9	4.98
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.9	9.14

boston_data["PRICE"] = y
boston_data.head(2)

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	PRICE
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.9	4.98	24.0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.9	9.14	21.6

sns.scatterplot(boston_data['NOX'], boston_data['PRICE'], color="r",alpha=0.6)
plt.title("PRICE~NOX")
plt.show()

1.2 分类

from sklearn import datasets
iris = datasets.load_iris()
x = iris.data
y = iris.target
features = iris.feature_names
iris_data = pd.DataFrame(x, columns=features)
iris_data['target'] = y
iris_data.head()

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)	target
0	5.1	3.5	1.4	0.2	0
1	4.9	3.0	1.4	0.2	0
2	4.7	3.2	1.3	0.2	0
3	4.6	3.1	1.5	0.2	0
4	5.0	3.6	1.4	0.2	0

marker = ['s','x','o']
for index,c in enumerate(np.unique(y)):
    plt.scatter(x=iris_data.loc[y==c,"sepal length (cm)"], y=iris_data.loc[y==c, "sepal width (cm)"], alpha=0.8,
               label=c,marker=marker[c])
plt.xlabel("sepal length (cm)")
plt.ylabel("sepal width (cm)")
plt.legend()
plt.show()

1.3 非监督学习

https://scikit-learn.org/stable/modules/classes.html?highlight=datasets#module-sklearn.datasets

#生成月牙型非凸集
from sklearn import datasets
x, y = datasets.make_moons(n_samples=2000, shuffle=True,
                          noise=0.05, random_state=None)
for index,c in enumerate(np.unique(y)):
    plt.scatter(x[y==c,0], x[y==c, 1],s=7) #s:标记大小
plt.show()

#生成符合正态分布的聚类数据
from sklearn import datasets
x, y = datasets.make_blobs(n_samples=5000,n_features=2,centers=3)
for index,c in enumerate(np.unique(y)):
    plt.scatter(x[y==c, 0], x[y==c, 1], s=7)
plt.show()