zoe_midterm_work.Rmd

---
title: "midterm_work"
author: "Zoe Yoo"
date: "10/8/2021"
output: html_document
---

```{r setup, include=FALSE}

# You can set some global options for knitting chunks

knitr::opts_chunk$set(echo = TRUE)

# Load some libraries

library(tidyverse)
library(sf)
library(spdep)
library(caret)
library(ckanr)
library(FNN)
library(grid)
library(gridExtra)
library(ggcorrplot)
library(kableExtra)
library(jtools)     # for regression model plots
library(ggstance) # to support jtools plots
library(osmdata)

library(knitr)
library(tidycensus)
library(scales)

# functions
root.dir = "C:/Users/zoeny/OneDrive - PennO365/GrSchool/Year1/MUSA 508 Public Policy Analytics/MUSA508/MUSA_Midterm"
source("https://raw.githubusercontent.com/urbanSpatial/Public-Policy-Analytics-Landing/master/functions.r")

palette5 <- c("#25CB10", "#5AB60C", "#8FA108",   "#C48C04", "#FA7800")

```

```{r read_data}
boulder.sf <- 
  st_read(file.path(root.dir,"/studentData.geojson"), ) %>% 
  st_as_sf(coords = c("Longitude", "Latitude"), crs = 'ESRI:102254', agr = "constant") %>%
  st_transform('ESRI:102254')

boulder.sf <- mutate(boulder.sf, Age = 2021 - builtYear) 

#parcels.sf <- 
#  st_read("https://opendata.arcgis.com/datasets/89ae49d4ddf246388ee5f5e952aa84db_0.geojson") %>% 
#  st_transform(st_crs(boulder.sf))
boulder.boundary <- 
  st_read("https://opendata.arcgis.com/datasets/964b8f3b3dbe401bb28d49ac93d29dc4_0.geojson") %>%
  st_transform(st_crs(boulder.sf))

```

```{r}

ggplot() +
  geom_sf(data = boulder.boundary, fill = "grey40") +
  geom_sf(data = boulder.sf, aes(colour = q5(price)), 
          show.legend = "point", size = 2) +
  scale_colour_manual(values = palette5,
                      labels=qBr(Boulder, CO,"price"),
                      name="Quintile\nBreaks") +
  labs(title="Sale price, Boulder") +
  mapTheme()

q <- getbb("Boulder County") %>%
      opq() %>%
      add_osm_feature("feature", "highway")
highway <- osmdata_sf(q)

#final map
ggplot(data=highway$osm_lines)
```

```{r preprocessing}

st_drop_geometry(boulder.sf) %>% 
  mutate(Age = 2021 - builtYear) %>%
  dplyr::select(price, TotalFinishedSF, Age) %>%
  filter(price <= 10000000, Age < 500) %>%
  gather(Variable, Value, -price) %>% 
   ggplot(aes(Value, price)) +
     geom_point(size = .5) + geom_smooth(method = "lm", se=F, colour = "#FA7800") +
     facet_wrap(~Variable, ncol = 3, scales = "free") +
     labs(title = "Price as a function of continuous variables") +
     plotTheme()

```

```{r correlation_matrix, fig.width=12}
numericVars <- 
  select_if(st_drop_geometry(boulder.sf), is.numeric) %>% 
  na.omit()

ggcorrplot(
  round(cor(numericVars), 1), 
  p.mat = cor_pmat(numericVars),
  colors = c("#25CB10", "white", "#FA7800"),
  type="lower",
  insig = "blank") +  
    labs(title = "Correlation across numeric variables") 

```


```{r mutlivariate_regression}
reg1 <- lm(price ~ ., data = st_drop_geometry(boulder.sf) %>% 
                                 dplyr::select(price, Age, TotalFinishedSF, designCodeDscr, 
                                               carStorageType, nbrBedRoom, bsmtType,
                                               qualityCode, nbrRoomsNobath, nbrFullBaths, 
                                               mainfloorSF, AcDscr, playground.Buffer))

summary(reg1)
plot_summs(reg1)
```

```{r}


```