P5_graph_generator.Rmd

---
 title: "| Data Science With an Eye Towards Sustainability  \n| Activity P5: Data Import and Cleaning\n"
author: "Tane Koh"
output:
  html_document:
  theme:
  bootswatch: solar
bookdown::html_document2:
  split_by: none
toc: yes
toc_float: yes
---

This is an [R Markdown](http://rmarkdown.rstudio.com) Notebook. When you execute code within the notebook, the results appear beneath the code. 

Try executing this chunk by clicking the *Run* button within the chunk or by placing your cursor inside it and pressing *Ctrl+Shift+Enter*. 
```{r}
library(readr)
library(ggplot2)
```



```{r}
# This is a test.
data <- read_csv("Net_generation_for_all_sectors_monthly.csv",show_col_types = FALSE)

data$total_renewable_output <- data$`conventional hydroelectric thousand megawatthours` + data$`other renewables thousand megawatthours`
data$Month <- as.Date(paste0("01-", data$Month), format = "%d-%b-%y")

# Extract year and month
data$year <- as.numeric(format(data$Month, "%Y"))
data$month <- as.numeric(format(data$Month, "%m"))

ggplot(data, aes(x = Month, y = total_renewable_output)) +
  geom_line() +
  labs(x = "Date", y = "Total Renewable Energy Output in MA (x1000 kWh)", title = "Total Renewable Energy Output vs Date")
```

```{r}
file_names <- c("solar1.csv", "solar2.csv", "solar3.csv", "solar4.csv", "solar5.csv")

# Initialize an empty dataframe
combined_df <- data.frame()

# Loop through each file and combine them
for (file in file_names) {
  # Read the CSV file
  df <- read.csv(file)
  
  # Combine the dataframes
  combined_df <- rbind(combined_df, df)
}
combined_df$date <- as.POSIXct(combined_df$LocalTime, format = "%m/%d/%y %H:%M")

# Extract date without time
combined_df$date <- as.Date(combined_df$date)

# Sum up the values within each day
aggregated_df <- combined_df %>%
  group_by(date) %>%
  summarise(total_value = sum(Power.MW.))

ggplot(aggregated_df, aes(x = date, y = total_value)) +
  geom_line() +
  labs(x = "Date", y = "Total Solar Energy Output (mW)", title = "Total Renewable Energy Output vs Date")
```


Add a new chunk by clicking the *Insert Chunk* button on the toolbar or by pressing *Ctrl+Alt+I*.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the *Preview* button or press *Ctrl+Shift+K* to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike *Knit*, *Preview* does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

```{R}
prices <- read_csv("MA_Residential_Installed Prices (2000-2022).csv",show_col_types = FALSE)
tpo <- read_csv("TPO_Penetration.csv",show_col_types = FALSE)

tpo$Share <- as.numeric(gsub("%", "", tpo$Share))

ggplot(prices,aes(x=`Year`,y=`Median`))+
  geom_line() +
  labs(x="Year",y="Installation Prices ($/W)",title="Installation Prices of Solar Panels Over Time")

ggplot(tpo,aes(x=`Year`,y=`Share`))+
  geom_line() +
  labs(x="Year",y="Market Share of Solar Energy",title="Market Penetration of Solar Energy Over Time")
```

```{r}
camden <- read_csv("camdens big dataset.csv",show_col_types = FALSE)
```

```{r}
camden$`Date In Service` <- as.Date(camden$`Date In Service`, format = "%m/%d/%Y")
camden$`Total Cost with Design Fees` <- as.numeric(gsub("[^0-9.]", "", camden$`Total Cost with Design Fees`))
camden$`Total Grant` <- as.numeric(gsub("[^0-9.]", "", camden$`Total Grant`))

```

```{r}
ggplot(camden,aes(x=`Date In Service`,y=`Estimated Annual Production (kWhr)`))+
  geom_line()
```