visualization.Rmd

---
title: "cse-assignment-2"
output: html_document
editor_options: 
  chunk_output_type: console
---

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

```{r}
library(readr)
library(tidyverse)
df_ca <- read_csv("df_ca.csv")
#View(df_ca)
```

```{r}
df_ca_f <- df_ca %>%
  drop_na()
```

```{r}
summ_by_price <- df_ca_f %>%
  group_by(price, hour) %>%
  summarise(avg_rating = mean(rating))
  
```

```{r}
# Avg. rating across different price levels across hours of the day
gr_scale = gray.colors(3, start = 0.3, end = 0.6, gamma = 2.2, alpha = NULL, rev = FALSE)
ggplot(summ_by_price, aes(x=hour, y = avg_rating, group = price, color = price)) + 
  geom_point(size = 2) + 
  geom_line() + 
  scale_colour_manual(values = c("$" = "#AEAEAE", "$$" = "#7A7A7A", "$$$" = "#4D4D4D")) + 
  xlab('Hour') + 
  ylab('Avg. Rating') + 
  labs(color='Price') +
  ggtitle('Change in avg. rating for different price levels') + 
  theme_light()
```

```{r}
df_ca_02 <- read_csv("df_ca_02.csv")

df_ca_02 <- df_ca_02 %>%
  drop_na()

```

```{r}
#rev_len_by_rating <- df_ca_02 %>%
df_ca_02 %>%
  filter(rating != 0) %>%
  ggplot(aes(x=reviewLength)) + 
  geom_histogram(breaks=seq(0, 2500, by=1)) +
  xlim(c(0, 500)) + 
  #scale_x_continuous(breaks = seq(0, 1000, 5)) + 
  facet_wrap(~rating) + 
  xlab('Length of review') + 
  ylab('Number of reviews') + 
  ggtitle('Distribution of review lengths from 1 to 5 ratings') + 
  theme_bw()
```