6.PK_Main_effect
Qinlu
2024-10-02
setwd("C:/Users/ASUS/Desktop/快手")1.读取处理数据
df = read_csv("All_active_author_first_live_sample.csv")# 检查一天是否只有一个数据
# %>% group_by(author_id,p_date) %>% filter(n()==1)panelview(total_cost_amt ~ is_pk_live, data = df, index = c("author_id","p_date"),
axis.lab = "time", xlab = "Time", ylab = "Unit",
gridOff = TRUE, by.timing = TRUE,
background = "white", main = "Simulated Data: Treatment Status")## Time is not evenly distributed (possibly due to missing data).## If the number of units is more than 500, we randomly select 500 units to present.
## You can set "display.all = TRUE" to show all units.
因变量：
# (1) 打赏
# df$total_cost_amt
# (2) 人均观看时长
df$avg_valid_play_duration= (df$valid_play_duration)/(df$valid_play_user_num + 1)
# (3) 人均互动
df$avg_comment_cnt= (df$comment_cnt)/(df$comment_user_num + 1)
df$avg_like_cnt= (df$like_cnt)/(df$like_user_num + 1)
df$avg_share_success_cnt = (df$share_success_cnt)/(df$share_success_user_num + 1)
# (4) 作者涨粉数
# df$follow_author_cnt
# df$cancel_follow_author_cnt
df$net_author_fans= df$follow_author_cnt - df$cancel_follow_author_cnt
# (5) 观众涨粉数
# df$follow_user_cnt
# df$cancel_follow_user_cnt
# (6) 死忠粉
# df$join_fans_group_cntX
# 将其他分类变量转换为数值
df <- df %>%
mutate(
gender_number = case_when(
gender == "F" ~ 0,
gender == "M" ~ 1
),
# 将 age_range 按区间转换为数字编码
age_range_number = case_when(
age_range == "0-12" ~ 1,
age_range == "12-17" ~ 2,
age_range == "18-23" ~ 3,
age_range == "24-30" ~ 4,
age_range == "31-40" ~ 5,
age_range == "41-49" ~ 6,
age_range == "50+" ~ 7
),
# 将 author_type 转换为数字编码
author_type_number = case_when(
author_type == "大V" ~ 1,
author_type == "电商主播" ~ 2,
author_type == "秀场主播" ~ 3,
author_type == "游戏主播" ~ 4
),
# 将 fre_country_region 转换为数字编码
fre_country_region_number = case_when(
fre_country_region == "UNKNOWN" ~ 0,
fre_country_region == "北方" ~ 1,
fre_country_region == "南方" ~ 2
),
# 将 fre_city_level 转换为数字编码
fre_city_level_number = case_when(
fre_city_level == "UNKNOWN" ~ 0,
fre_city_level == "一线城市" ~ 1,
fre_city_level == "新一线城市" ~ 2,
fre_city_level == "二线城市" ~ 3,
fre_city_level == "三线城市" ~ 4,
fre_city_level == "四线城市" ~ 5,
fre_city_level == "五线城市" ~ 6
)
)
feature_fixed= c("gender_number","age_range_number","author_type_number","fre_country_region","fre_city_level")
feature_continue= c("valid_play_duration")2.TWFE
(1) 打赏:total_cost_amt
model = feols(log(total_cost_amt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(total_cost_amt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.859436 0.008746 98.2697 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.32765 Adj. R2: 0.573486
## Within R2: 0.012017(2) 人均观看时长:avg_valid_play_duration
model = feols(log(avg_valid_play_duration + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(avg_valid_play_duration + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.708047 0.005954 118.929 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.97334 Adj. R2: 0.246144
## Within R2: 0.003723(3) 人均互动
model = feols(log(avg_comment_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(avg_comment_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.303203 0.002506 120.993 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.535646 Adj. R2: 0.41966
## Within R2: 0.009214model = feols(log(avg_like_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(avg_like_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.590871 0.00546 108.213 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 1.20992 Adj. R2: 0.496338
## Within R2: 0.006875(4) 作者涨粉数
model = feols(log(follow_author_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(follow_author_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.326218 0.004313 75.6277 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.701925 Adj. R2: 0.714055
## Within R2: 0.00623model = feols(log(cancel_follow_author_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(cancel_follow_author_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.195565 0.002966 65.9317 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.485713 Adj. R2: 0.741103
## Within R2: 0.004683model = feols(log(net_author_fans + 5336)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(net_author_fans + 5336)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.00097 0.00011 8.83238 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.017013 Adj. R2: 0.455366
## Within R2: 9.432e-5(5) 观众涨粉数
model = feols(log(follow_user_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(follow_user_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.145056 0.003136 46.2585 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.497944 Adj. R2: 0.559581
## Within R2: 0.002457model = feols(log(cancel_follow_user_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(cancel_follow_user_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.011279 0.000746 15.1165 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.109218 Adj. R2: 0.413284
## Within R2: 3.095e-4(6) 死忠粉
model = feols(log(join_fans_group_cnt + 1)~is_pk_live|author_id + p_date,data = df,vcov = ~author_id)
summary(model)## OLS estimation, Dep. Var.: log(join_fans_group_cnt + 1)
## Observations: 2,017,582
## Fixed-effects: author_id: 115,494, p_date: 32
## Standard-errors: Clustered (author_id)
## Estimate Std. Error t value Pr(>|t|)
## is_pk_live 0.066801 0.001925 34.6953 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## RMSE: 0.311536 Adj. R2: 0.605234
## Within R2: 0.0013333.Panel_Macth
(1) mahalanobis distance matching
#library(dplyr)
#df <- df %>% set.seed(1)4, Double ML
# Load necessary library
library(dplyr)
# Assuming df is already a dataframe
# Setting seed for reproducibility
set.seed(1)
# Sample 10% of the rows in the dataframe
df <- df %>% sample_frac(0.1)
# View the sampled dataframe
df## # A tibble: 201,758 × 53
## ...1 author_id live_id p_date is_pk_live pk_id pk_type valid_play_duration
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1597251 1.77e9 1.05e10 2.02e7 0 NA NA 152734
## 2 452736 8.37e8 1.05e10 2.02e7 0 NA NA 6286884
## 3 124412 3.75e8 1.05e10 2.02e7 0 NA NA 6785974
## 4 1485098 5.39e8 1.06e10 2.02e7 0 NA NA 551821
## 5 856017 1.56e9 1.05e10 2.02e7 0 NA NA 8428999
## 6 1715506 1.63e9 1.05e10 2.02e7 0 NA NA 14272800
## 7 25172 5.33e8 1.05e10 2.02e7 0 NA NA 1973012
## 8 1343337 2.39e8 1.05e10 2.02e7 0 NA NA 1865245048
## 9 1441261 2.82e9 1.05e10 2.02e7 0 NA NA 21087
## 10 640774 1.99e8 1.05e10 2.02e7 0 NA NA 89250602
## # ℹ 201,748 more rows
## # ℹ 45 more variables: valid_play_user_num <dbl>, total_cost_amt <dbl>,
## # total_cost_user_num <dbl>, comment_cnt <dbl>, comment_user_num <dbl>,
## # like_cnt <dbl>, like_user_num <dbl>, share_success_cnt <dbl>,
## # share_success_user_num <dbl>, follow_author_cnt <dbl>,
## # cancel_follow_author_cnt <dbl>, follow_user_cnt <dbl>,
## # cancel_follow_user_cnt <dbl>, join_fans_group_cnt <dbl>, …colnames(df) <- make.names(colnames(df), unique = TRUE)
colnames(df)[1]="id"source("DoubleML_function.R")##
## 载入程序包：'data.table'## The following objects are masked from 'package:lubridate':
##
## hour, isoweek, mday, minute, month, quarter, second, wday, week,
## yday, year## The following objects are masked from 'package:dplyr':
##
## between, first, last## The following object is masked from 'package:purrr':
##
## transposelibrary(data.table)
df=as.data.table(df)(1) 打赏
df$log_total_cost_amt = log(df$total_cost_amt + 1)
result = run_dml_plr_models(df, Y = "log_total_cost_amt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [22:50:52.695] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [22:50:54.618] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [22:50:56.204] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [22:50:58.236] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [22:51:02.649] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [22:51:07.328] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [22:51:12.678] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [22:51:27.709] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [22:51:41.345] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [22:51:55.034] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [22:52:07.225] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [22:52:19.254] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [22:52:31.097] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [22:52:31.249] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [22:52:31.381] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [22:52:31.810] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [22:52:32.173] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [22:52:32.397] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [22:52:33.248] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [22:52:34.468] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [22:52:35.685] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [22:52:37.099] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [22:52:38.503] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [22:52:40.043] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 1.412617 1.351267 1.473967
## 2: PLR ranger 1.423932 1.362941 1.484923
## 3: PLR rpart 1.370209 1.308469 1.431950
## 4: PLR xgboost 1.405125 1.344757 1.465494print(result$plot)
## (2) 人均观看时长：log(avg_valid_play_duration + 1)
df$log_avg_valid_play_duration = log(df$avg_valid_play_duration + 1)
result = run_dml_plr_models(df, Y = "log_avg_valid_play_duration", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [22:52:42.376] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [22:52:44.237] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [22:52:45.768] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [22:52:47.549] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [22:52:51.701] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [22:52:56.471] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [22:53:01.988] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [22:53:16.929] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [22:53:31.189] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [22:53:45.025] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [22:53:56.354] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [22:54:08.167] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [22:54:20.261] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [22:54:20.397] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [22:54:20.599] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [22:54:21.218] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [22:54:21.442] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [22:54:21.707] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [22:54:22.608] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [22:54:23.923] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [22:54:25.248] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [22:54:26.846] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [22:54:28.247] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [22:54:29.716] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.6581509 0.6329302 0.6833716
## 2: PLR ranger 0.6638867 0.6386541 0.6891193
## 3: PLR rpart 0.6297498 0.6045446 0.6549550
## 4: PLR xgboost 0.5646739 0.5368506 0.5924972print(result$plot)
(3) 人均评论长：log(avg_comment_cnt + 1)
df$log_avg_comment_cnt = log(df$avg_comment_cnt + 1)
result = run_dml_plr_models(df, Y = "log_avg_comment_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [22:54:32.198] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [22:54:34.150] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [22:54:35.400] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [22:54:36.874] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [22:54:40.918] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [22:54:45.233] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [22:54:49.960] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [22:55:03.412] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [22:55:16.982] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [22:55:32.101] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [22:55:44.741] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [22:56:01.386] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [22:56:18.934] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [22:56:19.113] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [22:56:19.335] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [22:56:19.926] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [22:56:20.309] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [22:56:20.736] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [22:56:21.785] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [22:56:23.510] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [22:56:25.092] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [22:56:27.093] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [22:56:29.092] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [22:56:31.268] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.4197563 0.4049654 0.4345472
## 2: PLR ranger 0.4256816 0.4109830 0.4403803
## 3: PLR rpart 0.4103590 0.3954914 0.4252266
## 4: PLR xgboost 0.4192519 0.4045233 0.4339806print(result$plot)
df$log_avg_like_cnt = log(df$avg_like_cnt + 1)
result = run_dml_plr_models(df, Y = "log_avg_like_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [22:56:34.271] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [22:56:35.947] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [22:56:37.471] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [22:56:38.766] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [22:56:44.515] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [22:56:52.859] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [22:56:59.432] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [22:57:16.563] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [22:57:35.153] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [22:57:54.054] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [22:58:09.486] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [22:58:22.644] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [22:58:36.299] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [22:58:36.517] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [22:58:36.688] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [22:58:37.219] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [22:58:37.491] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [22:58:37.749] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [22:58:38.783] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [22:58:40.438] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [22:58:42.106] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [22:58:44.179] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [22:58:46.078] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [22:58:48.194] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.8785905 0.8442273 0.9129537
## 2: PLR ranger 0.8862321 0.8518690 0.9205953
## 3: PLR rpart 0.8602842 0.8256257 0.8949427
## 4: PLR xgboost 0.8654424 0.8309614 0.8999234print(result$plot)
(4) 作者涨粉数
df$log_follow_author_cnt = log(df$follow_author_cnt + 1)
result = run_dml_plr_models(df, Y = "log_follow_author_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [22:58:51.416] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [22:58:52.611] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [22:58:54.056] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [22:58:55.689] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [22:59:00.973] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [22:59:06.509] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [22:59:13.070] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [22:59:29.057] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [22:59:44.894] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [23:00:01.725] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [23:00:16.894] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [23:00:32.218] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [23:00:48.532] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [23:00:48.727] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [23:00:48.912] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [23:00:49.536] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [23:00:49.868] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [23:00:50.240] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [23:00:51.506] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [23:00:53.196] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [23:00:54.790] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [23:00:56.809] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [23:00:58.772] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [23:01:00.641] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.4585539 0.4256348 0.4914730
## 2: PLR ranger 0.4827970 0.4502421 0.5153518
## 3: PLR rpart 0.4594977 0.4265732 0.4924222
## 4: PLR xgboost 0.4758252 0.4435186 0.5081318print(result$plot)
df$log_cancel_follow_author_cnt = log(df$cancel_follow_author_cnt + 1)
result = run_dml_plr_models(df, Y = "log_cancel_follow_author_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [23:01:03.695] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [23:01:04.705] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [23:01:05.903] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [23:01:07.330] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [23:01:12.350] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [23:01:17.674] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [23:01:24.802] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [23:01:42.171] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [23:01:58.511] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [23:02:15.812] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [23:02:28.028] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [23:02:41.478] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [23:02:55.381] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [23:02:55.633] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [23:02:55.837] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [23:02:56.392] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [23:02:56.747] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [23:02:57.054] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [23:02:58.134] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [23:02:59.658] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [23:03:01.194] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [23:03:03.085] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [23:03:05.024] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [23:03:06.768] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.3491512 0.3240778 0.3742245
## 2: PLR ranger 0.3682913 0.3434952 0.3930875
## 3: PLR rpart 0.3503923 0.3253181 0.3754665
## 4: PLR xgboost 0.3647516 0.3402045 0.3892988print(result$plot)
summary(df$net_author_fans)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -2894.00 0.00 0.00 14.27 1.00 61109.00df$log_net_author_fans = log(df$net_author_fans + 2895)
result = run_dml_plr_models(df, Y = "log_net_author_fans", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [23:03:09.925] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [23:03:11.345] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [23:03:12.449] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [23:03:13.969] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [23:03:19.433] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [23:03:24.583] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [23:03:31.836] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [23:03:48.241] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [23:04:05.096] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [23:04:22.758] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [23:04:37.002] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [23:04:51.401] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [23:05:06.476] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [23:05:06.679] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [23:05:06.898] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [23:05:07.603] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [23:05:07.944] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [23:05:08.305] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [23:05:09.359] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [23:05:10.046] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [23:05:10.711] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [23:05:11.629] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [23:05:13.901] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [23:05:15.973] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.002412408 0.001563795 0.003261020
## 2: PLR ranger 0.002647003 0.001804285 0.003489721
## 3: PLR rpart 0.002472346 0.001624316 0.003320375
## 4: PLR xgboost -0.071047402 -0.076900413 -0.065194392print(result$plot)
(5) 观众涨粉数
df$log_follow_user_cnt = log(df$follow_user_cnt + 1)
result = run_dml_plr_models(df, Y = "log_follow_user_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [23:05:19.600] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [23:05:20.863] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [23:05:22.087] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [23:05:23.889] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [23:05:28.965] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [23:05:35.301] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [23:05:42.978] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [23:06:00.380] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [23:06:15.854] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [23:06:31.332] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [23:06:45.167] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [23:06:59.178] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [23:07:13.935] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [23:07:14.087] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [23:07:14.267] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [23:07:14.906] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [23:07:15.329] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [23:07:15.570] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [23:07:16.551] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [23:07:18.159] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [23:07:19.826] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [23:07:21.795] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [23:07:24.173] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [23:07:26.109] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.2848983 0.2604740 0.3093227
## 2: PLR ranger 0.2861120 0.2617596 0.3104644
## 3: PLR rpart 0.2786546 0.2541996 0.3031097
## 4: PLR xgboost 0.2854051 0.2613832 0.3094269print(result$plot)
df$log_cancel_follow_user_cnt = log(df$cancel_follow_user_cnt + 1)
result = run_dml_plr_models(df, Y = "log_cancel_follow_user_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [23:07:29.424] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [23:07:30.399] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [23:07:31.455] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [23:07:32.897] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [23:07:38.432] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [23:07:44.003] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [23:07:50.952] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [23:08:07.437] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [23:08:22.701] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [23:08:38.617] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [23:08:51.369] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [23:09:05.353] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [23:09:19.421] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [23:09:19.707] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [23:09:19.874] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [23:09:20.467] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [23:09:21.506] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [23:09:22.059] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [23:09:23.223] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [23:09:24.806] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [23:09:26.511] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [23:09:28.656] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [23:09:31.249] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [23:09:33.914] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.02559811 0.02029572 0.03090050
## 2: PLR ranger 0.02565365 0.02038026 0.03092703
## 3: PLR rpart 0.02447302 0.01917743 0.02976860
## 4: PLR xgboost 0.02998872 0.02482526 0.03515217print(result$plot)
(6) 死忠粉
df$log_join_fans_group_cnt = log(df$join_fans_group_cnt + 1)
result = run_dml_plr_models(df, Y = "log_join_fans_group_cnt", D = "is_pk_live", Xs = c("gender_number", "age_range_number", "author_type_number", "fre_country_region_number", "fre_city_level_number"))## INFO [23:09:38.288] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 1/3)
## INFO [23:09:39.681] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 2/3)
## INFO [23:09:41.278] [mlr3] Applying learner 'regr.cv_glmnet' on task 'nuis_l' (iter 3/3)
## INFO [23:09:42.858] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 1/3)
## INFO [23:09:51.182] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 2/3)
## INFO [23:09:59.377] [mlr3] Applying learner 'classif.cv_glmnet' on task 'nuis_m' (iter 3/3)
## INFO [23:10:07.487] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 1/3)
## INFO [23:10:20.769] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 2/3)
## INFO [23:10:34.476] [mlr3] Applying learner 'regr.ranger' on task 'nuis_l' (iter 3/3)
## INFO [23:10:48.596] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 1/3)
## INFO [23:11:00.654] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 2/3)
## INFO [23:11:12.404] [mlr3] Applying learner 'classif.ranger' on task 'nuis_m' (iter 3/3)
## INFO [23:11:24.824] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 1/3)
## INFO [23:11:24.965] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 2/3)
## INFO [23:11:25.103] [mlr3] Applying learner 'regr.rpart' on task 'nuis_l' (iter 3/3)
## INFO [23:11:25.518] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 1/3)
## INFO [23:11:25.747] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 2/3)
## INFO [23:11:26.039] [mlr3] Applying learner 'classif.rpart' on task 'nuis_m' (iter 3/3)
## INFO [23:11:26.869] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 1/3)
## INFO [23:11:28.097] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 2/3)
## INFO [23:11:29.320] [mlr3] Applying learner 'regr.xgboost' on task 'nuis_l' (iter 3/3)
## INFO [23:11:30.748] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 1/3)
## INFO [23:11:32.224] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 2/3)
## INFO [23:11:33.646] [mlr3] Applying learner 'classif.xgboost' on task 'nuis_m' (iter 3/3)print(result$results_table)## model ML Estimate lower upper
## <char> <char> <num> <num> <num>
## 1: PLR glmnet 0.1098779 0.09595900 0.1237968
## 2: PLR ranger 0.1155930 0.10180202 0.1293840
## 3: PLR rpart 0.1071745 0.09323012 0.1211190
## 4: PLR xgboost 0.1179043 0.10426005 0.1315485print(result$plot)