Publications by Brian

Document

12.07.2020

Produce a line graph using ggplotly that shows how many movies were released over time. geom_line <- movies %>% mutate(year = year(release_date)) %>% filter(year >= 1980) %>% count(year) %>% ggplot() + aes(x = year, y = n) + geom_line() + scale_x_continuous(limits=c(1980, 2018), n.breaks = 20)+ labs(title="Movies Released Over Time", x="Year", y...

1843 sym R (1804 sym/5 pcs) 2 img

Paired Programming Assignment #5

04.12.2020

library(tidyverse) library(e1071) #for naive bayes library(caret) library(scales) library(lemon) library(plotly) #for ggplotly library(factoextra) #for fviz_nbclust library(cluster.datasets) library(DT) library(cluster) library(ggcorrplot) #to make our correlation matrix pima <- read_csv("pima_diabetes.csv") mall_customers <- read_csv("Mall_Cus...

4212 sym R (11256 sym/36 pcs) 5 img

Paired Programming Assignment #4

12.11.2020

library(tidyverse) library(forecast) library(ggcorrplot) library(gapminder) vehicles <- read_csv("vehicles.csv",col_types = "ddddddc") options(scipen = 999) #vehicles$Origin <- as.character(vehicles$Origin)#converting my “Origin” column to type “character” str(vehicles) ## tibble [396 × 7] (S3: spec_tbl_df/tbl_df/tbl/data.frame) ## $ M...

1740 sym R (5877 sym/15 pcs) 2 img

Assignment 3

30.10.2020

Question 1: Use the following dplyr verbs to find produce an output from the dataset. Graph 1 cereal_avg <- cereal %>% group_by(mfr, type) %>% summarize(avg_rating = mean(rating)) %>% arrange(desc(avg_rating))%>% print() ## # A tibble: 9 x 3 ## # Groups: mfr [7] ## mfr type avg_rating ## <chr> <chr> <dbl> ## 1 N C ...

1018 sym R (3759 sym/18 pcs) 4 img

Paired Programming Assignment #6

09.12.2020

library(tidyverse) library(modelr) library(broom) library(caret) library(DT) library(arules) library(RANN) library(lemon) library(plotly) library(dplyr) library(ggplot2) library(e1071) library(rpart) library(rpart.plot) titanic <- read_csv("train.csv") health <-read_csv("health_logistic.csv") customer_behavior <- read_csv("customer_behavior.csv"...

3709 sym R (10565 sym/41 pcs) 1 img

Data Mining Project #2

12.12.2020

#install.packages("") library(tidyverse) library(ggplot2) library(scales) library(forecast) library(ggcorrplot) #to make our correlation matrix library(reshape2) library(factoextra) library(DT) library(cluster) library(cluster.datasets) library(e1071) #for naive bayes library(plotly) #to make interactive visuals library(DT) library(arules) libra...

1260 sym R (10055 sym/30 pcs) 4 img