K近邻(KNN)支持向量机(SVM)随机森林(RF)逻辑回归(LR)演示

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import model_selection
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from pandas.plotting import scatter_matrix
from sklearn.datasets import load_iris

#第一步，数据集的获取
iris = load_iris()

#第二步，数据预处理，删除缺失值
iris_d = pd.DataFrame(iris['data'], columns=['Sepal_Length', 'Sepal_Width', 'Petal_Length', 'Petal_Width']) #数据转化为DataFrame类型
iris_d['Species'] = iris.target #目标类型的获取
iris_d.dropna(inplace=True) #数据预处理，删除缺失值
iris_d

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
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
...	...	...	...	...	...
145	6.7	3.0	5.2	2.3	2
146	6.3	2.5	5.0	1.9	2
147	6.5	3.0	5.2	2.0	2
148	6.2	3.4	5.4	2.3	2
149	5.9	3.0	5.1	1.8	2

150 rows × 5 columns

#第三步，数据可视化
iris_d.groupby('Species').size() #数据集的数量

Species
0    50
1    50
2    50
dtype: int64

iris_d.describe()#数据集的描述性统计

	Sepal_Length	Sepal_Width	Petal_Length	Petal_Width	Species
count	150.000000	150.000000	150.000000	150.000000	150.000000
mean	5.843333	3.057333	3.758000	1.199333	1.000000
std	0.828066	0.435866	1.765298	0.762238	0.819232
min	4.300000	2.000000	1.000000	0.100000	0.000000
25%	5.100000	2.800000	1.600000	0.300000	0.000000
50%	5.800000	3.000000	4.350000	1.300000	1.000000
75%	6.400000	3.300000	5.100000	1.800000	2.000000
max	7.900000	4.400000	6.900000	2.500000	2.000000

iris_d.plot(kind = 'box') #变量之间的箱线图，展现数据的离散程度
plt.show()

iris_d.hist() #数据集的直方图，用于展示数据的分布特征
plt.show()

scatter_matrix(iris_d) #展现了变量之间的关系，非线性相关和线性相关
plt.show()

#第四部分，特征工程
array = iris_d.values
X = array[:,0:4]
Y = array[:,4]
#选取模型的特征，本模型选择80%数据量作为训练数据，20%作为测试数据
x_train, x_test, y_train, y_test = model_selection.train_test_split(X, Y, test_size=0.2, random_state=7) 

#第五部分，机器学习模型和评估
#K近邻(KNN)
model = KNeighborsClassifier()
model.fit(x_train,y_train)
predictions = model.predict(x_test)
#模型评估，交叉验证
print(accuracy_score(y_test, predictions))

0.9

#机器学习模型
#支持向量机(SVM)
model = SVC()
model.fit(x_train,y_train)
predictions = model.predict(x_test)
#模型评估，交叉验证
print(accuracy_score(y_test, predictions))

0.8666666666666667

#机器学习模型
#随机森林(RF)
model = RandomForestClassifier()
model.fit(x_train,y_train)
predictions = model.predict(x_test)
#模型评估，交叉验证
print(accuracy_score(y_test, predictions))

0.8666666666666667

#机器学习模型
#逻辑回归(LR)
model = LogisticRegression()
model.fit(x_train,y_train)
predictions = model.predict(x_test)
#模型评估，交叉验证
print(accuracy_score(y_test, predictions))

0.8666666666666667


d:\program files\python3.7\lib\site-packages\sklearn\linear_model\_logistic.py:765: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG)