病例预测---特征筛选

导入库

import numpy as np
import pandas as pd
from sklearn.feature_selection import RFE
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import StandardScaler

数据加载和预处理

train_dataset = CovidDataset('covid.train.csv', mode='train')

相关性分析

df = pd.read_csv("covid.train.csv")
column_names = df.columns.tolist()[1:-1]
correlations = df.corr()['tested_positive'].sort_values()
print(correlations)

RFE（递归特征消除）

x_train = np.array([train_dataset[i][0] for i in range(len(train_dataset))])
y_train = np.array([train_dataset[i][1] for i in range(len(train_dataset))])

estimator = LinearRegression()
selector = RFE(estimator, n_features_to_select=10, step=1)
selector = selector.fit(x_train, y_train)

selected_features = selector.support_
selected_indices = np.where(selected_features)[0]

输出选定的特征

# 输出选定特征的信息
print(f"Selected feature indices: {selected_indices}")

# 打印选定的特征名
selected_column_names = np.array(column_names)[selected_indices]
print(f"Selected feature names: {selected_column_names}")

输出结果：

仅使用选定的特征进行训练

# 仅使用选定的特征
x_train = x_train[:, selected_features]
scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)