Applied Data Week 2
Chris Burpeau
2022-09-07
Set UP
library(tidyverse)
library(quantmod)
library(plotly)
library(tidyquant)Data
Analzing Apple and Walmart
# Import stock prices
stocks <- tq_get(c("AAPL", "WMT"),
get = "stock.prices",
from = "2016-01-01",
to = "2017-01-01")
stocks## # A tibble: 504 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-01-04 25.7 26.3 25.5 26.3 270597600 24.2
## 2 AAPL 2016-01-05 26.4 26.5 25.6 25.7 223164000 23.5
## 3 AAPL 2016-01-06 25.1 25.6 25.0 25.2 273829600 23.1
## 4 AAPL 2016-01-07 24.7 25.0 24.1 24.1 324377600 22.1
## 5 AAPL 2016-01-08 24.6 24.8 24.2 24.2 283192000 22.2
## 6 AAPL 2016-01-11 24.7 24.8 24.3 24.6 198957600 22.6
## 7 AAPL 2016-01-12 25.1 25.2 24.7 25.0 196616800 22.9
## 8 AAPL 2016-01-13 25.1 25.3 24.3 24.3 249758400 22.3
## 9 AAPL 2016-01-14 24.5 25.1 23.9 24.9 252680400 22.8
## 10 AAPL 2016-01-15 24.0 24.4 23.8 24.3 319335600 22.3
## # … with 494 more rowsPlots for Walmart and Apple
g <- ggplot(data = stocks) +
geom_point(mapping = aes(x = volume, y = adjusted, color = symbol))
g
Revenue by Category
Interactive Plot
- Comparison of Apple and Walmart
ggplotly(g)Static Plot
g <- ggplot(data = stocks) +
geom_point(mapping = aes(x = volume, y = adjusted, color = symbol))
gRevenue by Category
Apply the dplyr verbs learned in chapter five
Filter rows
stocks %>% filter(adjusted > 24)## # A tibble: 392 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-01-04 25.7 26.3 25.5 26.3 270597600 24.2
## 2 AAPL 2016-03-15 26.0 26.3 26.0 26.1 160270800 24.1
## 3 AAPL 2016-03-16 26.2 26.6 26.1 26.5 153214000 24.4
## 4 AAPL 2016-03-17 26.4 26.6 26.2 26.5 137682800 24.4
## 5 AAPL 2016-03-18 26.6 26.6 26.3 26.5 176820800 24.4
## 6 AAPL 2016-03-21 26.5 26.9 26.3 26.5 142010800 24.4
## 7 AAPL 2016-03-22 26.3 26.8 26.3 26.7 129777600 24.6
## 8 AAPL 2016-03-23 26.6 26.8 26.5 26.5 102814000 24.5
## 9 AAPL 2016-03-24 26.4 26.6 26.2 26.4 104532000 24.4
## 10 AAPL 2016-03-28 26.5 26.5 26.3 26.3 77645600 24.2
## # … with 382 more rowsfilter(stocks, open > 26.5)## # A tibble: 371 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-03-18 26.6 26.6 26.3 26.5 176820800 24.4
## 2 AAPL 2016-03-23 26.6 26.8 26.5 26.5 102814000 24.5
## 3 AAPL 2016-03-30 27.2 27.6 27.2 27.4 182404400 25.3
## 4 AAPL 2016-03-31 27.4 27.5 27.2 27.2 103553600 25.1
## 5 AAPL 2016-04-01 27.2 27.5 27.0 27.5 103496000 25.4
## 6 AAPL 2016-04-04 27.6 28.0 27.6 27.8 149424800 25.6
## 7 AAPL 2016-04-05 27.4 27.7 27.4 27.5 106314800 25.3
## 8 AAPL 2016-04-06 27.6 27.7 27.3 27.7 105616400 25.6
## 9 AAPL 2016-04-07 27.5 27.6 27.0 27.1 127207600 25.0
## 10 AAPL 2016-04-08 27.2 27.4 27.0 27.2 94326800 25.0
## # … with 361 more rowsArrange rows
arrange(stocks, desc(date), high, low)## # A tibble: 504 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-12-30 29.2 29.3 28.9 29.0 122345200 27.1
## 2 WMT 2016-12-30 69.1 69.4 68.8 69.1 6889500 61.7
## 3 AAPL 2016-12-29 29.1 29.3 29.1 29.2 60158000 27.4
## 4 WMT 2016-12-29 69.2 69.5 69.1 69.3 4298400 61.8
## 5 AAPL 2016-12-28 29.4 29.5 29.0 29.2 83623600 27.4
## 6 WMT 2016-12-28 69.9 70 69.3 69.3 4875700 61.9
## 7 AAPL 2016-12-27 29.1 29.5 29.1 29.3 73187600 27.5
## 8 WMT 2016-12-27 69.3 69.8 69.2 69.7 4435700 62.2
## 9 AAPL 2016-12-23 28.9 29.1 28.9 29.1 56998000 27.3
## 10 WMT 2016-12-23 69.4 69.8 69.4 69.5 4803900 62.1
## # … with 494 more rowsSelect columns
select(stocks, symbol:close)## # A tibble: 504 × 6
## symbol date open high low close
## <chr> <date> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-01-04 25.7 26.3 25.5 26.3
## 2 AAPL 2016-01-05 26.4 26.5 25.6 25.7
## 3 AAPL 2016-01-06 25.1 25.6 25.0 25.2
## 4 AAPL 2016-01-07 24.7 25.0 24.1 24.1
## 5 AAPL 2016-01-08 24.6 24.8 24.2 24.2
## 6 AAPL 2016-01-11 24.7 24.8 24.3 24.6
## 7 AAPL 2016-01-12 25.1 25.2 24.7 25.0
## 8 AAPL 2016-01-13 25.1 25.3 24.3 24.3
## 9 AAPL 2016-01-14 24.5 25.1 23.9 24.9
## 10 AAPL 2016-01-15 24.0 24.4 23.8 24.3
## # … with 494 more rowsAdd colums
mutate(stocks,
daygain = open - close) %>%
# Select day gain
select(symbol:close, daygain) %>%
mutate(stocks,
fluctuation = high - low) %>%
# Select day fluctuation
select(symbol:close, fluctuation, daygain)## # A tibble: 504 × 8
## symbol date open high low close fluctuation daygain
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-01-04 25.7 26.3 25.5 26.3 0.843 -0.685
## 2 AAPL 2016-01-05 26.4 26.5 25.6 25.7 0.860 0.760
## 3 AAPL 2016-01-06 25.1 25.6 25.0 25.2 0.625 -0.0350
## 4 AAPL 2016-01-07 24.7 25.0 24.1 24.1 0.925 0.558
## 5 AAPL 2016-01-08 24.6 24.8 24.2 24.2 0.587 0.398
## 6 AAPL 2016-01-11 24.7 24.8 24.3 24.6 0.430 0.110
## 7 AAPL 2016-01-12 25.1 25.2 24.7 25.0 0.463 0.148
## 8 AAPL 2016-01-13 25.1 25.3 24.3 24.3 0.973 0.732
## 9 AAPL 2016-01-14 24.5 25.1 23.9 24.9 1.19 -0.390
## 10 AAPL 2016-01-15 24.0 24.4 23.8 24.3 0.587 -0.233
## # … with 494 more rowsSumarize with groups
mutate(stocks,
daygain = open - close) %>%
# Select day gain
select(symbol:close, daygain) %>%
mutate(stocks,
fluctuation = high - low) %>%
# Select day fluctuation
select(symbol:close, fluctuation, daygain)%>%
mutate(stocks,
daygain = open - close) %>%
# Select day gain
select(symbol:close, daygain) %>%
mutate(stocks,
fluctuation = high - low) %>%
# Select day fluctuation
summarise(stocks, daygain, fluctuation, avepricegain = mean(daygain, na.rm = TRUE))%>%
select(symbol:close, daygain, fluctuation, avepricegain)## # A tibble: 504 × 9
## symbol date open high low close daygain fluctuation avepricegain
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2016-01-04 25.7 26.3 25.5 26.3 -0.685 0.843 -0.0449
## 2 AAPL 2016-01-05 26.4 26.5 25.6 25.7 0.760 0.860 -0.0449
## 3 AAPL 2016-01-06 25.1 25.6 25.0 25.2 -0.0350 0.625 -0.0449
## 4 AAPL 2016-01-07 24.7 25.0 24.1 24.1 0.558 0.925 -0.0449
## 5 AAPL 2016-01-08 24.6 24.8 24.2 24.2 0.398 0.587 -0.0449
## 6 AAPL 2016-01-11 24.7 24.8 24.3 24.6 0.110 0.430 -0.0449
## 7 AAPL 2016-01-12 25.1 25.2 24.7 25.0 0.148 0.463 -0.0449
## 8 AAPL 2016-01-13 25.1 25.3 24.3 24.3 0.732 0.973 -0.0449
## 9 AAPL 2016-01-14 24.5 25.1 23.9 24.9 -0.390 1.19 -0.0449
## 10 AAPL 2016-01-15 24.0 24.4 23.8 24.3 -0.233 0.587 -0.0449
## # … with 494 more rowsGroup Stocks
mutate(stocks,
daygain = open - close) %>%
mutate(stocks,
avepricegain = mean(daygain)) %>%
select(symbol, date, close, open, daygain, avepricegain) %>%
group_by(symbol) %>%
summarize(count = n(),
date = date, na.rm = TRUE,
daygain = daygain, na.rm = TRUE) %>%
# Plot
ggplot(mapping = aes(x = date, y = daygain, color = symbol)) + geom_point(aes(size = count) + geom_smooth(se = FALSE))