A LASSO-Based Prediction Model for Child Influenza Epidemics: A Case Study of Shanghai, China

Figure 3

Heat map of dynamic regression coefficients of LASSO between week 1 of 2017 and week 20 of 2020. These regression coefficients were computed using the rolling-origin recalibration evaluation method. The X-axis represents the date and the Y-axis corresponds to the regression coefficient of features. Positive coefficients are indicated in red, negative coefficients are indicated in blue, and zero is indicated in white. The feature, num_lag_x, denoted the ILI number with lag (x) and temp_lag_x denoted the average temperature with lag (x). The green vertical dashed line represents January 23, 2020, when the Chinese government closed Wuhan down to prevent the COVID-19 epidemic from spreading outside Wuhan.