实现功能：
python实现Lasso回归分析（特征筛选、建模预测）
输入结构化数据，含有特征以及相应的标签，采用Lasso回归对特征进行分析筛选，并对数据进行建模预测。
实现代码：
1 | import numpy as np |
2 | import warnings |
3 | warnings.filterwarnings(action='ignore') |
4 | import pandas as pd |
5 | import matplotlib.pyplot as plt |
6 | from sklearn import metrics |
7 | from sklearn.metrics import mean_squared_error |
8 | from sklearn.linear_model import Lasso,LassoCV |
9 | import seaborn as sns |
10 | #==================读取数据================= |
11 | class Solution(): |
12 | def __init__(self): |
13 | feature = ['男', '女', '年龄', 'CCP-正常', 'CCP-异常', 'MCV-正常', 'MCV-异常', |
14 | 'AKA-正常', 'AKA-异常','RF-正常', 'RF-异常', 'ANA-正常', 'ANA-异常', |
15 | 'ds-DNA-正常', 'ds-DNA-异常','CRP-正常', 'CRP-异常', 'ESR-正常', 'ESR-异常', |
16 | '尿蛋白-正常', '尿蛋白-异常', '尿潜血-正常', '尿潜血-异常','尿红细胞-正常', |
17 | '尿红细胞-异常', 'WBC-正常', 'WBC-异常', 'Hb-正常', 'Hb-异常', 'PLT-正常', |
18 | 'PLT-异常', 'ALT-正常', 'ALT-异常', 'AST-正常', 'AST-异常', 'r-GT-正常', |
19 | 'r-GT-异常', 'TBIL-正常', 'TBIL-异常', 'ALB-正常','ALB-异常', 'GLB-正常', |
20 | 'GLB-异常', 'A/O-正常', 'A/O-异常', 'Cr-正常', 'Cr-异常', 'BUN-正常', |
21 | 'BUN-异常', 'UA-正常', 'UA-异常', 'C3-正常', 'C3-异常', 'C4-正常', 'C4-异常', |
22 | 'IgA-正常', 'IgA-异常', 'IgG-正常','IgG-异常', 'IgE-正常', 'IgE-异常', |
23 | '晨僵正常', '晨僵异常', '发热正常', '发热异常', '雷诺正常', '雷诺异常', |
24 | '口眼干正常', '口眼干异常', '头晕正常', '头晕异常', '四肢正常', '四肢异常', |
25 | '胸部CT正常', '胸部CT异常', '肺结节正常', '肺结节异常', '诊断结果'] |
26 | self.feature=feature |
27 | |
28 | def Data_sort(self,file): |
29 | data = pd.read_excel(file) |
30 | data = pd.DataFrame(data) |
31 | random_state_value = 90 # 随机种子 |
32 | sample_number = 82 # 欠采样数目 |
33 | def norm_2(x): |
34 | return (x - stats['min']) / (stats['max']-stats['min']) |
35 | gy_list=['年龄'] |
36 | data_gy=data[gy_list] |
37 | stats = data_gy.describe() |
38 | stats = stats.transpose() |
39 | data[gy_list]=norm_2(data_gy) |
40 | data1 = data[self.feature] |
41 | data1 = data1.dropna() # 删除含缺失值的行 |
42 | data1=data1[~data1['诊断结果'].isin([2])] |
43 | print(len(data1)) |
44 | dataset=data1 |
45 | train_dataset = dataset.sample(frac=0.7, random_state=random_state_value) |
46 | test_dataset = dataset.drop(train_dataset.index) |
47 | print(len(test_dataset)) |
48 | train_dataset[train_dataset['诊断结果'].isin([1])]=\ |
49 | train_dataset[train_dataset['诊断结果'].isin([1])].iloc[:sample_number] |
50 | train_NRA=train_dataset[train_dataset['诊断结果'].isin([0])] |
51 | train_RA=train_dataset[train_dataset['诊断结果'].isin([1])] |
52 | train_dataset=train_NRA.append(train_RA) |
53 | train_dataset=train_dataset.sample(frac=1,random_state=0) |
54 | print(len(train_dataset)) |
55 | train_labels =train_dataset.pop('诊断结果') |
56 | test_labels =test_dataset.pop('诊断结果') |
57 | return train_dataset,train_labels,test_dataset,test_labels |
58 | |
59 | #==============Lasso变量筛选==================== |
60 | def optimal_lambda_value(self): |
61 | Lambdas = np.logspace(-5, 2, 200) #10的-5到10的2次方 |
62 | # 构造空列表，用于存储模型的偏回归系数 |
63 | lasso_cofficients = [] |
64 | for Lambda in Lambdas: |
65 | lasso = Lasso(alpha = Lambda, normalize=True, max_iter=10000) |
66 | lasso.fit(train_dataset, train_labels) |
67 | lasso_cofficients.append(lasso.coef_) |
68 | # 绘制Lambda与回归系数的关系 |
69 | plt.plot(Lambdas, lasso_cofficients) |
70 | # 对x轴作对数变换 |
71 | plt.xscale('log') |
72 | # 设置折线图x轴和y轴标签 |
73 | plt.xlabel('Lambda') |
74 | plt.ylabel('Cofficients') |
75 | # 显示图形 |
76 | plt.show() |
77 | # LASSO回归模型的交叉验证 |
78 | lasso_cv = LassoCV(alphas = Lambdas, normalize=True, cv = 10, max_iter=10000) |
79 | lasso_cv.fit(train_dataset, train_labels) |
80 | # 输出最佳的lambda值 |
81 | lasso_best_alpha = lasso_cv.alpha_ |
82 | print(lasso_best_alpha) |
83 | return lasso_best_alpha |
84 | |
85 | # 基于最佳的lambda值建模 |
86 | def model(self,train_dataset, train_labels,lasso_best_alpha): |
87 | lasso = Lasso(alpha = lasso_best_alpha, normalize=True, max_iter=10000) |
88 | lasso.fit(train_dataset, train_labels) |
89 | return lasso |
90 | |
91 | def feature_importance(self,lasso): |
92 | # 返回LASSO回归的系数 |
93 | dic={'特征':train_dataset.columns,'系数':lasso.coef_} |
94 | df=pd.DataFrame(dic) |
95 | df1=df[df['系数']!=0] |
96 | print(df1) |
97 | coef = pd.Series(lasso.coef_, index=train_dataset.columns) |
98 | imp_coef = pd.concat([coef.sort_values().head(10), coef.sort_values().tail(10)]) |
99 | sns.set(font_scale=1.2) |
100 | # plt.rc('font', family='Times New Roman') |
101 | plt.rc('font', family='simsun') |
102 | imp_coef.plot(kind="barh") |
103 | plt.title("Lasso回归模型") |
104 | plt.show() |
105 | return df1 |
106 | |
107 | def prediction(self,lasso): |
108 | # lasso_predict = lasso.predict(test_dataset) |
109 | lasso_predict = np.round(lasso.predict(test_dataset)) |
110 | print(sum(lasso_predict==test_labels)) |
111 | print(metrics.classification_report(test_labels,lasso_predict)) |
112 | print(metrics.confusion_matrix(test_labels, lasso_predict)) |
113 | RMSE = np.sqrt(mean_squared_error(test_labels,lasso_predict)) |
114 | print(RMSE) |
115 | return RMSE |
116 | |
117 | if __name__=="__main__": |
118 | Object1=Solution() |
119 | train_dataset, train_labels, test_dataset, test_labels=\ |
120 | Object1.Data_sort('F:\医学大数据课题\RA预测\RA预测\特征.xlsx') |
121 | lasso_best_alpha=Object1.optimal_lambda_value() |
122 | lasso=Object1.model(train_dataset, train_labels,lasso_best_alpha) |
123 | feature_choose=Object1.feature_importance(lasso) |
124 | RMSE=Object1.pR[-123]C[-1]:RCrediction(lasso) |
实现效果：
# 绘制Lambda与回归系数的关系
# 基于最佳的lambda值建模进行特征分析
# 基于最佳的lambda值建模进行预测分析
喜欢记得点赞，在看，收藏，加关注（Ｖ订阅号：数据杂坛），将持续更新！