Workshop5_S20_Answers.Rmd

---
title: "Workshop5_S20"
output:
  word_document: default
  html_document: default
---

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

```{r}
install.packages("dplyr")
library(dplyr)
```

##Read in CSV
```{r}
bechdel_data_original <- read.csv("bechdel_test_movies_w5.csv", na.strings =c("#N/A") )
bechdel_data <- bechdel_data_original
```


##Cross tab budget category and bechdel test after ordering budget category 
```{r}
##tabulation
x <- table(bechdel_data$budgetcategory, bechdel_data$bechdeltest)
x

##ordering
bechdel_data$budgetcategory<- factor(bechdel_data$budgetcategory, 
                                     levels = c("low", "medium", "high"), 
                                     ordered=TRUE)
##tabulate again
x <- table(bechdel_data$budgetcategory, bechdel_data$bechdeltest)
x
```

##Summary Stats by Group
```{r}
## mean
mean(bechdel_data$budget, na.rm=TRUE)

mean(bechdel_data$budget[ bechdel_data$bechdeltest == "FAIL"]) ## replace to get mean budget for movies that failed the test
mean(bechdel_data$budget[ bechdel_data$bechdeltest=="PASS"]) ## replace to get mean budget for movies that passed the test

mean(bechdel_data$budget[bechdel_data$Year==2012]) ## replace to get mean budget for movies that were released 2012

head(bechdel_data)
```

##Summary statistics by groups another way
```{r}
by(bechdel_data$intgross, bechdel_data$bechdeltest, mean, na.rm=TRUE)

```


##Introducing Dplyr
```{r}

##Some of the things we can do with dplyr
arrange(bechdel_data, desc(budget))

# Using pipes
bechdel_data %>% arrange(desc(budget))

bechdel_data %>% filter(budgetcategory=="low")

arranged_data <- arrange(bechdel_data, desc(budget))
highest_pass_movies <- filter(arranged_data, bechdeltest=="PASS")

##Combining steps
highest_pass_movies <- bechdel_data %>% arrange(desc(budget)) %>% filter(bechdeltest=="PASS")
highest_pass_movies

highest_pass_movies %>% filter(Year>2000)

bechdel_data %>% select(movietitle, ends_with("gross"))
```

## Dplyr Groupings
```{r}
summary1 <- group_by(bechdel_data, budgetcategory, bechdeltest)
summary1
class(summary1)
class(bechdel_data)

summary1 <- summarize(summary1, count = n() )

#combining the steps

budgetcat_bytest <- bechdel_data %>% 
  group_by(budgetcategory, bechdeltest) %>%
  summarize(avgintgross=mean(intgross), count=n())
budgetcat_bytest
```

## Now let's do counts for year by budget category

```{r}
year_bybudgetcat <- bechdel_data %>%
  group_by( "") %>%
  summarize( "" )

year_bybudgetcat 
```

##average profit by budget category and bechdel test

```{r}
budgetcat_bytest_2 <- bechdel_data %>% 
  group_by( "" ) %>%
  summarize( "" )
budgetcat_bytest_2

```

## Combine multiple stats
```{r}
budgetcat_bytest <- bechdel_data %>% 
  group_by( "" ) %>%
  summarize( "" )
budgetcat_bytest
```


```{r}
write.csv(budgetcat_bytest, "BudgetCat_by_TestResults.csv", row.names=F)
```