本文主要是介绍[转] R 代码 00003 18.06.19，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
# 知识来源于网络，仅供交流使用，如有侵权请及时联系予以删除# Libraries library(data.table) # 高效数据操作 library(magrittr) # 管道操作 library(ggplot2) # 数据可视化 library(stringr) # 字符串处理 # library(quanteda) 该包在加载时出现错误 library(gridExtra) # 多图 library(dplyr) # 数据操作 library(tidyr) # 数据操作 library(caTools) # 工具：移动窗口统计 library(xgboost) # 极限梯度提升 library(quanteda) # 文本数据的定量分析 library(SnowballC) # 基于C libstemmer UTF-8库的雪球词干分析器 library(tm) # 文本挖掘软件包 library(corrplot) # 相关矩阵的可视化# Data Overview setwd("e:/") system.time(train <- fread('../input/train.tsv', showProgress = T , data.table=F))# 读取数据，包括工具条、读取时间 str(train)# train_id、name、item_condition_id、category_name、brand_name、price、shipping、item_description dim(train) # 记录多少print(object.size(train), units = 'Mb') # 数据存储大小# 0: Variable Analysis：Price :价格、及其分布 length(train$price[train$price==""]) length(train$price[is.na(train$price)]) range(train$price) ggplot(train,aes(x=price))+geom_histogram(fill = 'orangered2') # 分布范围大，但是不均衡，变换log()表示 ggplot(data = train, aes(x = log(price+1,base=10))) + geom_histogram(fill = 'orangered2')# e = 2.718281828459; log(8,2)===>3; base=exp(1)，即e# 1: Variable Analysis：item_condition_id ：产品状况分类情况、及其对价格的影响length(train$item_condition_id[train$item_condition_id==""]) length(train$item_condition_id[is.na(train$item_condition_id)]) table(train$item_condition_id) # 查看分类分布、与价格关系p1<-train %>% # 画柱状图 group_by(item_condition_id) %>% summarise(count=length(price),median=median(price)) %>% ggplot(aes(x = item_condition_id, y = count)) + geom_bar(stat = 'identity',fill = "orangered2") p2<-train %>% # 画箱体图 ggplot(aes(x = as.factor(item_condition_id), y = log(price+1,base=10))) + stat_boxplot(geom = "errorbar") + geom_boxplot(fill = "skyblue") grid.arrange(p1,p2,nrow=1)# 以下为箱体图的解读样本
# 2：Variable Analysis：Shipping ：运费状况，及对价格分布的影响 length(train$shipping[train$shipping==""]) length(train$shipping[is.na(train$shipping)]) table(train$shipping) # 分布状况 train %>% ggplot(aes(x = log(price+1), fill = as.factor(shipping))) + geom_density(adjust=2,alpha= 0.6)# 3：Variable Analysis：brand_name ：品牌名称，及对价格分布的影响 length(train$brand_name[train$brand_name==""]) length(train$brand_name[is.na(train$brand_name)]) length(table(train$brand_name)) # 分布状况 train %>% group_by(brand_name) %>% summarise(median_price = median(price)) %>% arrange(desc(median_price)) %>% head(25) %>% ggplot(aes(x = reorder(brand_name,median_price), y = median_price)) + geom_point()+coord_flip()# 4：Variable Analysis：category_name ：产品分类名称，及对价格分布的影响 length(train$category_name[train$category_name==""]) length(train$category_name[is.na(train$category_name)]) length(unique(train$category_name))# 等价于 length(table(train$category_name)) # 分布状况 sort(table(train$category_name), decreasing = TRUE)[1:10]#分类初始分析train %>% group_by(category_name) %>% summarise(median_price = median(price)) %>% arrange(desc(median_price)) %>% head(25) %>%ggplot(aes(x = reorder(category_name,median_price), y = median_price)) + geom_point()+coord_flip()# 分类分析，进一步细分splitVar = str_split(train$cat, "/")cat1 = sapply(splitVar,'[',1)cat2 = sapply(splitVar,'[',2)train['cat1'] = cat1train['cat2'] = cat2train$cat1[is.na(train$cat2)] = -1train$cat2[is.na(train$cat3)] = -1train['train$category_name'][is.na(train$train$category_name)] = -1# cat1 分析1train %>% ggplot(aes(x = cat1, y = log(price+1,base=10))) + stat_boxplot(geom = "errorbar")+ geom_boxplot(fill = 'cyan2', color = 'darkgrey') + coord_flip() + labs(y="",title = 'category_name: cat1 观察方法1' )# cat1 分析2 p1 <-train %>%group_by(cat1, item_condition_id) %>%summarise(count=length(train_id)) %>%ggplot(aes(x = item_condition_id, y = cat1, fill = count/1000)) +geom_tile() +scale_fill_gradient(low = 'lightblue', high = 'cyan4') +labs(x = 'Condition', y = '', fill = 'Number of items (000s)', title = 'cat1: Item count by category and condition') + theme_bw() + theme(legend.position = 'bottom') p2 <-train %>% group_by(cat1, item_condition_id) %>% summarise(median_price=median(price)) %>% ggplot(aes(x = item_condition_id, y = cat1, fill = median_price)) + geom_tile() + scale_fill_gradient(low = 'lightblue', high = 'cyan4') + labs(x = 'Condition', y = '', fill = 'median_price', title = 'cat1: Item price by category and condition') + theme_bw() + theme(legend.position = 'bottom', axis.text.y = element_blank()) grid.arrange(p1, p2, ncol = 2)# cat2 分析ss<- train %>% group_by(cat2) %>%summarise(median=median(price)) %>% arrange(desc(median)) %>% head(15)train %>% filter(cat2 %in% ss$cat2) %>% select(c("price","cat1","cat2","category_name")) %>% ggplot(aes(x = cat2, y = log(price+1))) + stat_boxplot(geom = "errorbar") + geom_boxplot(fill = 'cyan2', color = 'darkgrey') + coord_flip()# 5：Variable Analysis：item_despription ：产品分描述train['desclength'] = str_length(train$item_description)train$desclength[train$item_description == 'No description yet']<- NAcor(train$price,train$desc_length,use='complete.obs') # 以下为部分文本分析内容，等待学习 corpus = Corpus(VectorSource(train$item_description)) #将要分析的变量加载到适当的格式中。 corpus = tm_map(corpus, tolower) # 小写所有单词 corpus = tm_map(corpus, removePunctuation) # 删除标点符号 corpus = tm_map(corpus, removeWords, stopwords("english")) #去停用词 dataframe <- data.frame(text=sapply(corpus, identity),stringsAsFactors=F) #转换为数据框 train$item_description = dataframe$text #附加到原数据中
这篇关于[转] R 代码 00003 18.06.19的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
