zillow_1.Rmd

---
title: "Zillow_1"
author: "Aishwarya Hariharan"
date: "9/28/2017"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)

library(ggplot2)
library(tidyverse)
library(dplyr)
library(tidyr)
library(readr)


properties <- read_csv('properties_2016.csv')
transactions <- read_csv('train_2016_v2.csv')



```

```{r renaming}
# More descriptive names for properties data set
properties <- properties %>% rename(
  id_parcel = parcelid,
  build_year = yearbuilt,
  area_basement = basementsqft,
  area_patio = yardbuildingsqft17,
  area_shed = yardbuildingsqft26, 
  area_pool = poolsizesum,  
  area_lot = lotsizesquarefeet, 
  area_garage = garagetotalsqft,
  area_firstfloor_finished = finishedfloor1squarefeet,
  area_total_calc = calculatedfinishedsquarefeet,
  area_base = finishedsquarefeet6,
  area_live_finished = finishedsquarefeet12,
  area_liveperi_finished = finishedsquarefeet13,
  area_total_finished = finishedsquarefeet15,  
  area_unknown = finishedsquarefeet50,
  num_unit = unitcnt, 
  num_story = numberofstories,  
  num_room = roomcnt,
  num_bathroom = bathroomcnt,
  num_bedroom = bedroomcnt,
  num_bathroom_calc = calculatedbathnbr,
  num_bath = fullbathcnt,  
  num_75_bath = threequarterbathnbr, 
  num_fireplace = fireplacecnt,
  num_pool = poolcnt,  
  num_garage = garagecarcnt,  
  region_county = regionidcounty,
  region_city = regionidcity,
  region_zip = regionidzip,
  region_neighbor = regionidneighborhood,  
  tax_total = taxvaluedollarcnt,
  tax_building = structuretaxvaluedollarcnt,
  tax_land = landtaxvaluedollarcnt,
  tax_property = taxamount,
  tax_year = assessmentyear,
  tax_delinquency = taxdelinquencyflag,
  tax_delinquency_year = taxdelinquencyyear,
  zoning_property = propertyzoningdesc,
  zoning_landuse = propertylandusetypeid,
  zoning_landuse_county = propertycountylandusecode,
  flag_fireplace = fireplaceflag, 
  flag_tub = hashottuborspa,
  quality = buildingqualitytypeid,
  framing = buildingclasstypeid,
  material = typeconstructiontypeid,
  deck = decktypeid,
  story = storytypeid,
  heating = heatingorsystemtypeid,
  aircon = airconditioningtypeid,
  architectural_style= architecturalstyletypeid
)
transactions <- transactions %>% rename(
  id_parcel = parcelid,
  date = transactiondate
)


```


```{r combine both tables}

all_data <- transactions %>% left_join(properties,by = "id_parcel")

```

```{r divide into train and test}

n <- dim(all_data)[1]

# number of observations that go in the training st
n_tr <- floor(n * .8)


# randomly select n_tr numbers, without replacement, from 1...n
set.seed(42)
tr_indices <- sample(x=1:n, size=n_tr, replace=FALSE)

# break the data into a non-overlapping train and test set
train <- all_data[tr_indices, ]
test <- all_data[-tr_indices, ]

```


```{r}

missing_values <- all_data %>% summarize_each(funs(sum(is.na(.))/n()))

missing_values <- gather(missing_values, key="feature", value="missing_pct")

good_features <- filter(missing_values, missing_pct<0.75)

```

```{r}
#Num of properties with 0 bathrooms and 0 bedrooms
bath_0 <- all_data %>% filter(num_bathroom == 0 & num_bedroom == 0)

all_data <- all_data %>% mutate(b)

```


```{r}

head(all_data)
summary(all_data)

```


```{r}

  ggplot(data = train_2016_v2_csv, aes(transactiondate, logerror)) + 
    geom_point()

```