Week 2: Apply 1
Kyle Shearer
2023-02-01
Finance Club Portfolio
10 Year Historical Prices (Excluding “UVXY”)
stocks <- tq_get(c("HLIT", "ABR", "RYLD", "GM", "COPX", "AMLP", "XYLD", "FDRR", "DBP", "PRFT", "IUSV", "BSV", "FRC", "META", "JPM", "JNJ", "NXST", "SPY"),
get = "stock.prices",
from = "2013-02-01")
stocks## # A tibble: 42,750 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 HLIT 2013-02-01 5.24 5.38 5.17 5.34 620900 5.34
## 2 HLIT 2013-02-04 5.27 5.36 5.24 5.29 524100 5.29
## 3 HLIT 2013-02-05 5.35 5.39 5.29 5.36 352000 5.36
## 4 HLIT 2013-02-06 5.31 5.35 5.25 5.35 359800 5.35
## 5 HLIT 2013-02-07 5.33 5.39 5.33 5.35 328700 5.35
## 6 HLIT 2013-02-08 5.38 5.38 5.32 5.35 314900 5.35
## 7 HLIT 2013-02-11 5.37 5.45 5.33 5.44 305900 5.44
## 8 HLIT 2013-02-12 5.46 5.5 5.4 5.46 408100 5.46
## 9 HLIT 2013-02-13 5.5 5.54 5.42 5.48 668400 5.48
## 10 HLIT 2013-02-14 5.45 5.73 5.45 5.7 832100 5.7
## # … with 42,740 more rowsPlot stock prices
stocks %>%
ggplot(aes(x = date, y = adjusted, color = symbol)) +
geom_line()
Applying the dyplyr verbs learned in Ch.5
Filter rows
# Days with low trading volume
stocks %>%
filter(volume < 10000000) %>%
ggplot(mapping = aes(x = date, y = volume, color = symbol)) +
geom_boxplot() +
coord_flip()
Arrange rows
# Arrange the stocks by descending order for highs & lows
stocks %>%
arrange(desc(open), desc(close))## # A tibble: 42,750 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 SPY 2022-01-04 479. 480. 476. 478. 71178700 470.
## 2 SPY 2021-12-30 478. 479 476. 476. 55329000 469.
## 3 SPY 2021-12-28 478. 479. 476. 477. 47274600 469.
## 4 SPY 2022-01-05 477. 478. 468. 468. 104538900 461.
## 5 SPY 2021-12-29 477. 479. 476. 477. 54503000 470.
## 6 SPY 2022-01-03 476. 478. 474. 478. 72668200 470.
## 7 SPY 2021-12-31 476. 477. 475. 475. 65237400 467.
## 8 SPY 2021-12-16 473. 473. 465. 466. 116568600 457.
## 9 SPY 2022-01-13 472. 473. 463. 465. 91173100 457.
## 10 SPY 2021-12-27 472. 477. 472. 477. 56808600 470.
## # … with 42,740 more rowsSelect columns
# Selecting desired columns
select(stocks,
date, open, close, high, low)## # A tibble: 42,750 × 5
## date open close high low
## <date> <dbl> <dbl> <dbl> <dbl>
## 1 2013-02-01 5.24 5.34 5.38 5.17
## 2 2013-02-04 5.27 5.29 5.36 5.24
## 3 2013-02-05 5.35 5.36 5.39 5.29
## 4 2013-02-06 5.31 5.35 5.35 5.25
## 5 2013-02-07 5.33 5.35 5.39 5.33
## 6 2013-02-08 5.38 5.35 5.38 5.32
## 7 2013-02-11 5.37 5.44 5.45 5.33
## 8 2013-02-12 5.46 5.46 5.5 5.4
## 9 2013-02-13 5.5 5.48 5.54 5.42
## 10 2013-02-14 5.45 5.7 5.73 5.45
## # … with 42,740 more rowsAdd columns
# Creating a new variable called "gain_loss"
mutate(stocks,
gain_loss = close - open) %>% select (close, open, gain_loss)## # A tibble: 42,750 × 3
## close open gain_loss
## <dbl> <dbl> <dbl>
## 1 5.34 5.24 0.100
## 2 5.29 5.27 0.0200
## 3 5.36 5.35 0.0100
## 4 5.35 5.31 0.0400
## 5 5.35 5.33 0.0200
## 6 5.35 5.38 -0.0300
## 7 5.44 5.37 0.0700
## 8 5.46 5.46 0
## 9 5.48 5.5 -0.0200
## 10 5.7 5.45 0.25
## # … with 42,740 more rowsSummazrize groups
# Average
summarise(stocks, avg_high = mean(high, na.rm = TRUE))## # A tibble: 1 × 1
## avg_high
## <dbl>
## 1 75.0# Finding the average high for each asset
stocks %>%
# Group by asset
group_by(symbol) %>%
# Calculate
summarise(avg_high = mean(high, na.rm = TRUE)) %>%
# Sort it
arrange(avg_high)## # A tibble: 18 × 2
## symbol avg_high
## <chr> <dbl>
## 1 HLIT 6.68
## 2 ABR 10.5
## 3 RYLD 22.8
## 4 COPX 25.4
## 5 FDRR 34.3
## 6 GM 37.8
## 7 PRFT 37.9
## 8 DBP 42.1
## 9 XYLD 46.4
## 10 IUSV 53.5
## 11 AMLP 56.9
## 12 BSV 80.1
## 13 NXST 86.4
## 14 JPM 96.3
## 15 FRC 98.7
## 16 JNJ 130.
## 17 META 158.
## 18 SPY 278.