Import stock prices
stocks <- tq_get(c("AAPL", "ROKU", "CL=F"),
get = "stock.prices",
from = "2019-01-01",
to = "2020-01-01")
stocks
## # A tibble: 756 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2019-01-02 38.7 39.7 38.6 39.5 148158800 37.9
## 2 AAPL 2019-01-03 36.0 36.4 35.5 35.5 365248800 34.2
## 3 AAPL 2019-01-04 36.1 37.1 36.0 37.1 234428400 35.6
## 4 AAPL 2019-01-07 37.2 37.2 36.5 37.0 219111200 35.5
## 5 AAPL 2019-01-08 37.4 38.0 37.1 37.7 164101200 36.2
## 6 AAPL 2019-01-09 37.8 38.6 37.4 38.3 180396400 36.8
## 7 AAPL 2019-01-10 38.1 38.5 37.7 38.5 143122800 37.0
## 8 AAPL 2019-01-11 38.2 38.4 37.9 38.1 108092800 36.6
## 9 AAPL 2019-01-14 37.7 37.8 37.3 37.5 129756800 36.0
## 10 AAPL 2019-01-15 37.6 38.3 37.5 38.3 114843600 36.8
## # ℹ 746 more rows
Plot stock prices
stocks %>%
ggplot(aes(x = date, y = adjusted, color = symbol)) +
geom_line()
Apply the dplyr verbs you learned in chapter 5
Filter rows
stocks %>% filter(adjusted > 36)
## # A tibble: 750 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2019-01-02 38.7 39.7 38.6 39.5 148158800 37.9
## 2 AAPL 2019-01-08 37.4 38.0 37.1 37.7 164101200 36.2
## 3 AAPL 2019-01-09 37.8 38.6 37.4 38.3 180396400 36.8
## 4 AAPL 2019-01-10 38.1 38.5 37.7 38.5 143122800 37.0
## 5 AAPL 2019-01-11 38.2 38.4 37.9 38.1 108092800 36.6
## 6 AAPL 2019-01-14 37.7 37.8 37.3 37.5 129756800 36.0
## 7 AAPL 2019-01-15 37.6 38.3 37.5 38.3 114843600 36.8
## 8 AAPL 2019-01-16 38.3 39.0 38.2 38.7 122278800 37.2
## 9 AAPL 2019-01-17 38.5 39.4 38.3 39.0 119284800 37.4
## 10 AAPL 2019-01-18 39.4 39.5 39.0 39.2 135004000 37.7
## # ℹ 740 more rows
Arrange rows
arrange(stocks, desc(date), desc(high))
## # A tibble: 756 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 ROKU 2019-12-31 129. 135. 127. 134. 13763900 134.
## 2 AAPL 2019-12-31 72.5 73.4 72.4 73.4 100805600 71.6
## 3 CL=F 2019-12-31 61.7 61.9 60.6 61.1 494535 61.1
## 4 ROKU 2019-12-30 138. 139. 131. 132. 14469100 132.
## 5 AAPL 2019-12-30 72.4 73.2 71.3 72.9 144114400 71.1
## 6 CL=F 2019-12-30 61.7 62.3 61.1 61.7 427149 61.7
## 7 ROKU 2019-12-27 145. 145. 139 140. 13303200 140.
## 8 AAPL 2019-12-27 72.8 73.5 72.0 72.4 146266000 70.7
## 9 CL=F 2019-12-27 61.7 62.0 61.2 61.7 351899 61.7
## 10 ROKU 2019-12-26 147. 149. 144. 145. 14660200 145.
## # ℹ 746 more rows
Select columns
select(stocks, date, symbol, adjusted)
## # A tibble: 756 × 3
## date symbol adjusted
## <date> <chr> <dbl>
## 1 2019-01-02 AAPL 37.9
## 2 2019-01-03 AAPL 34.2
## 3 2019-01-04 AAPL 35.6
## 4 2019-01-07 AAPL 35.5
## 5 2019-01-08 AAPL 36.2
## 6 2019-01-09 AAPL 36.8
## 7 2019-01-10 AAPL 37.0
## 8 2019-01-11 AAPL 36.6
## 9 2019-01-14 AAPL 36.0
## 10 2019-01-15 AAPL 36.8
## # ℹ 746 more rows
Add columns
mutate(stocks,
daily_returns = (adjusted - lag(adjusted))/lag(adjusted)) %>%
# Select symbol, date, daily_returns
select(symbol, date, daily_returns)
## # A tibble: 756 × 3
## symbol date daily_returns
## <chr> <date> <dbl>
## 1 AAPL 2019-01-02 NA
## 2 AAPL 2019-01-03 -0.0996
## 3 AAPL 2019-01-04 0.0427
## 4 AAPL 2019-01-07 -0.00223
## 5 AAPL 2019-01-08 0.0191
## 6 AAPL 2019-01-09 0.0170
## 7 AAPL 2019-01-10 0.00320
## 8 AAPL 2019-01-11 -0.00982
## 9 AAPL 2019-01-14 -0.0150
## 10 AAPL 2019-01-15 0.0205
## # ℹ 746 more rows
Summarise with groups
stocks %>%
group_by(symbol) %>%
summarise(count = n(), avg_monthly_return = mean(adjusted - lag(adjusted))/lag(adjusted), na.rm = TRUE)
## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
## always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `summarise()` has grouped output by 'symbol'. You can override using the
## `.groups` argument.
## # A tibble: 756 × 4
## # Groups: symbol [3]
## symbol count avg_monthly_return na.rm
## <chr> <int> <dbl> <lgl>
## 1 AAPL 252 NA TRUE
## 2 AAPL 252 NA TRUE
## 3 AAPL 252 NA TRUE
## 4 AAPL 252 NA TRUE
## 5 AAPL 252 NA TRUE
## 6 AAPL 252 NA TRUE
## 7 AAPL 252 NA TRUE
## 8 AAPL 252 NA TRUE
## 9 AAPL 252 NA TRUE
## 10 AAPL 252 NA TRUE
## # ℹ 746 more rows