Question

我正在运行以这种方式定义的logit模型：

diversity_model <- glm(booking_bool ~ df$var_distance + df$var_price + df$var_prop_review_score + 
                             df$var_starrating + srch_hits + min_rating + max_rating + avg_rating + min_review + 
                             max_review + avg_review + min_loc_score + max_loc_score + avg_loc_score + avg_price + min_price + 
                             srch_booking_window + srch_adults_count + random_bool + prop_starrating + prop_review_score + 
                             prop_brand_bool + prop_location_score1 + prop_log_historical_price + position + promotion_flag + 
                             click_bool ,
                           family = binomial(link = "logit"), df)

现在，根据结果，我想预测使用以下代码：

new.ob = with(df, data.frame(var_distance = mean(var_distance), var_price = mean(var_price), 
                var_prop_review_score = mean(var_prop_review_score), 
                var_starrating = mean(var_starrating), srch_hits = mean(srch_hits),
                min_rating = mean(min_rating),max_rating = mean(max_rating), 
                avg_rating = mean(avg_rating), min_review = mean(min_review), 
                max_review = mean(max_review), avg_review = mean(avg_review), 
                min_loc_score = mean(min_loc_score), max_loc_score = mean(max_loc_score), 
                avg_loc_score = mean(avg_loc_score), avg_price = mean(avg_price), 
                min_price = mean(min_price), 
                srch_booking_window = mean(srch_booking_window), srch_adults_count = mean(srch_adults_count), 
                random_bool = mean(random_bool), prop_starrating = mean(prop_starrating), prop_review_score = mean(prop_review_score, na.rm=TRUE), 
                prop_brand_bool = mean(prop_brand_bool), prop_location_score1 = mean(prop_location_score1), 
                prop_log_historical_price = mean(prop_log_historical_price), position = mean(position), promotion_flag = mean(promotion_flag), 
                click_bool = mean(click_bool)))

predict(diversity_model, newdata = new.ob, type = "response")

我收到以下错误消息：

Error in model.frame.default(Terms, newdata, na.action = na.action, xlev =     object$xlevels) :variable lengths differ (found for 'srch_hits')

In addition: Warning message:
'newdata' had 1 row but variables found have 66766 rows

Answer 1

一般情况下，不使用$来访问模型公式中的变量（仅使用变量的名称，并依赖R从传递的数据框中提取它） data参数）。为方便起见，您可以在公式的左侧使用.，这意味着＆＃34;除了响应变量＆＃34;之外的数据框中的所有变量。例如：

dd <- data.frame(state.x77)
fit1 <- glm((Murder>10)~.,data=dd)

如果您想以所有变量的平均值计算预测（这假设所有预测变量都是数字）：

predframe <- as.data.frame(lapply(dd,mean))
predict(fit1,newdata=predframe)

从logit模型预测

1 个答案: