缺失值处理

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.font_manager import FontProperties
from sklearn import datasets

font = FontProperties(fname='/Library/Fonts/Heiti.ttf')

from io import StringIO

iris_data = """
4.7,,1.3,0.2
4.6,3.1,1.5,0.2
5.,3.6,1.4,0.2
5.4,3.9,1.7,0.4
4.6,3.4,,0.3
5.,3.4,1.5,0.2
4.4,2.9,1.4,0.2
4.9,3.1,1.5,0.1
5.4,3.7,1.5,
"""

iris = datasets.load_iris()
df = pd.read_csv(StringIO(iris_data),header=None)
df.columns=iris.feature_names
df=df.iloc[:,:4]
print(df)

from sklearn.impute import SimpleImputer
imputer=SimpleImputer(missing_values=np.nan,strategy='mean')
imputer=imputer.fit_transform(df.values)
df=pd.DataFrame(imputer,columns=iris.feature_names)
print(df)

标准化

最小最大标准化

from sklearn.preprocessing import MinMaxScaler
import numpy as np

test_data = np.array([1,2,3,4,5]).reshape(-1,1).astype(float)
min_max_scaler=MinMaxScaler()
min_max_scaler.fit(test_data)

波士顿房价训练回归

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.font_manager import FontProperties

字体

font = FontProperties(fname='/Library/Fonts/Heiti.ttf')

np小数点位数

np.set_printoptions(precision=3,suppress=True)

url = "https://raw.githubusercontent.com/scikit-learn/scikit-learn/main/sklearn/datasets/data/boston_house_prices.csv"
boston= pd.read_csv(url)
boston=boston.values
x=boston[1:,:-1]
y=boston[1:,-1]
print(x[:5])
print(y[:5])

切割和标准化

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3,random_state=1,shuffle=True)
print('训练集长度：{}'.format(len(y_train)),'测试集长度：{}'.format(len(y_test)))

scaler = MinMaxScaler()
scaler = scaler.fit(x_train)
x_train,x_test=scaler.transform(x_train),scaler.transform(x_test)
print('标准化后训练数据：\n{}'.format(x_train[:5]))
print('标准化后测试数据：\n{}'.format(x_test[:5]))

lasso回归

from sklearn.linear_model import Lasso

reg = Lasso()
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)

print('lasso回归R2分数：{}'.format(reg.score(x_test,y_test)))

弹性网络回归

from sklearn.linear_model import ElasticNet

reg = ElasticNet()
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)
print('弹性网络回归R2分数：{}'.format(reg.score(x_test,y_test)))

岭回归

from sklearn.linear_model import Ridge

reg = Ridge()
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)
print('岭回归R2分数：{}'.format(reg.score(x_test,y_test)))

线性支持向量回归

from sklearn.svm import LinearSVR

reg = LinearSVR(C=100,max_iter=10000)
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)
print('线性支持向量回归R2分数：{}'.format(reg.score(x_test,y_test)))

核支持向量回归

from sklearn.svm import SVR

reg = SVR(C=100,gamma='auto',max_iter=10000,kernel='rbf')
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)
print('核支持向量回归R2分数：{}'.format(reg.score(x_test,y_test)))

决策树回归

from sklearn.tree import DecisionTreeRegressor

reg = DecisionTreeRegressor()
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)
print('决策树回归R2分数：{}'.format(reg.score(x_test,y_test)))

随机森林回归

from sklearn.ensemble import RandomForestRegressor

reg = RandomForestRegressor()
reg = reg.fit(x_train,y_train)
y_pred =reg.predict(x_test)
print('随机森林回归R2分数：{}'.format(reg.score(x_test,y_test)))