--- title: "探索性数据分析-ames房屋价格" format: html editor: visual toc: true toc-location: right code-tools: true code-fold: false --- # 1、背景介绍  # 2、导入数据 ```{r} library (tidyverse) <- read_csv ("D:/project/R/ames房屋价格_20250105/ames_houseprice.csv" )``` # 3、数据结构 ```{r} library (readxl)library (kableExtra)# 读取Excel文件中的数据 <- read_excel ("D:/project/R/ames房屋价格_20250105/ames_houseprice_explanation.xlsx" , sheet = "Sheet1" )# 将数据框转换为Markdown格式的表格，并添加一些格式化选项 %>% kable (format = "html" , booktabs = TRUE ) %>% kable_styling (bootstrap_options = c ("striped" , "hover" , "condensed" , "responsive" ))``` ```{r} # str(ames) ``` # 4、数据处理 ```{r} # 查看缺失值 <- colSums (is.na (ames))``` ```{r} # 选择分析对象 <- ames %>% select (``` ```{r} # 查看缺失值 <- colSums (is.na (data))``` ```{r} # 删除缺失值 # data <- data %>% # drop_na() # missing3 <- colSums(is.na(data)) # missing3 ``` # 5、数据分析 ## 5.1、**各区域的房屋数量和价格均值** ```{r} # data %>% count(Neighborhood) <- data %>% count (Neighborhood) %>% arrange (desc (n))print (neighborhood_counts)``` ```{r} %>% group_by (Neighborhood) %>% summarise (mean_sale = mean (SalePrice)%>% ggplot (aes (x = mean_sale, y = fct_reorder (Neighborhood, mean_sale))+ geom_col (aes (fill = mean_sale < 180000 ),show.legend = FALSE ) + geom_text (aes (label = round (mean_sale, 0 )), hjust = 1 ) + scale_x_continuous (expand = c (0 , 0 ),labels = scales:: dollar+ #scale_fill_viridis_d(option = "D") + scale_fill_manual (values = c ("TRUE" = "Gray" , "FALSE" = "Pink" )) + theme_classic () + labs (x = "价格" , y = "位置" )``` ## 5.2、房屋价格均值趋势 ```{r} # 对数据进行汇总，计算每年建造房屋的平均售价 <- data %>% group_by (YearBuilt) %>% summarise (AverageSalePrice = mean (SalePrice, na.rm = TRUE ))# 创建时间趋势图 ggplot (summarized_data, aes (x = YearBuilt, y = AverageSalePrice)) + geom_line () + # 绘制线条图 geom_point () + # 在数据点上添加标记 labs (title = "房屋价格均值" ,x = "年份" ,y = "均值" + geom_line (color = "#1f77b4" , size = 0.5 ) + # 设置线条颜色和粗细 geom_point (color = "#1f77b4" , size = 1 ) + # 设置点的颜色和大小 theme (plot.title = element_text (hjust = 0.5 , face = "bold" , size = 16 ), # 自定义标题 axis.title = element_text (size = 14 ), # 自定义轴标题 axis.text = element_text (size = 12 ), # 自定义轴文本 panel.grid.major = element_line (colour = "#d3d3d3" , size = 0.5 ) # 添加网格线 + theme_minimal () + # 使用简洁的主题 scale_y_continuous (labels = scales:: label_dollar ())``` ## 5.3、房屋面积和价格的关系 ```{r} # 创建面积与价格的散点图，并添加拟合曲线 ggplot (data, aes (x = GrLivArea, y = SalePrice)) + geom_point (alpha = 0.6 , color = "#1f77b4" ) + # 绘制半透明散点 geom_smooth (method = "lm" , col = "#ff7f0e" , se = FALSE ) + # 添加线性拟合曲线（无置信区间） labs (title = "房屋面积与价格的关系" ,x = "房屋面积" ,y = "价格" + theme_minimal () + # 应用简洁主题 theme (plot.title = element_text (hjust = 0.5 , face = "bold" , size = 16 ), # 自定义标题样式 axis.title = element_text (size = 14 ), # 自定义轴标题大小 axis.text = element_text (size = 12 ), # 自定义轴文本大小 panel.grid.major = element_line (colour = "#d3d3d3" , size = 0.5 ) # 添加网格线 + scale_y_continuous (labels = scales:: label_dollar ()) + # 格式化y轴标签为美元 coord_cartesian (xlim = c (0 , max (data$ GrLivArea) * 1.1 ), ylim = c (0 , max (data$ SalePrice) * 1.1 )) # 稍微扩展坐标轴范围，避免数据点紧贴边缘 ``` 
