Apply the dplyr verbs you learned in chapter 5
Filter rows
stocks %>% filter(adjusted > 24)
## # A tibble: 1,232 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 TSM 2025-01-02 197 204. 197. 202. 10951400 198.
## 2 TSM 2025-01-03 204. 209. 204. 209. 10261900 205.
## 3 TSM 2025-01-06 219. 222. 216. 220. 24339900 216.
## 4 TSM 2025-01-07 221. 221. 211. 211. 17010000 208.
## 5 TSM 2025-01-08 210. 210. 206. 207. 13262700 203.
## 6 TSM 2025-01-10 208. 210. 203. 208. 17265200 205.
## 7 TSM 2025-01-13 201. 204. 200. 201. 16612400 198.
## 8 TSM 2025-01-14 205. 206. 198. 201. 14182900 198.
## 9 TSM 2025-01-15 202. 209. 199. 207. 18286500 203.
## 10 TSM 2025-01-16 219. 222. 213. 215. 38539600 211.
## # ℹ 1,222 more rows
stocks %>% filter(date > 2024-01-02)
## # A tibble: 1,232 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 TSM 2025-01-02 197 204. 197. 202. 10951400 198.
## 2 TSM 2025-01-03 204. 209. 204. 209. 10261900 205.
## 3 TSM 2025-01-06 219. 222. 216. 220. 24339900 216.
## 4 TSM 2025-01-07 221. 221. 211. 211. 17010000 208.
## 5 TSM 2025-01-08 210. 210. 206. 207. 13262700 203.
## 6 TSM 2025-01-10 208. 210. 203. 208. 17265200 205.
## 7 TSM 2025-01-13 201. 204. 200. 201. 16612400 198.
## 8 TSM 2025-01-14 205. 206. 198. 201. 14182900 198.
## 9 TSM 2025-01-15 202. 209. 199. 207. 18286500 203.
## 10 TSM 2025-01-16 219. 222. 213. 215. 38539600 211.
## # ℹ 1,222 more rows
# Looking at days where the lowest price of the day, where higher than the mean of the high of all days, and where the closing price where higher than opening price (showing that the stock had momentum)
stocks %>% filter(low > mean(high), close > open)
## # A tibble: 143 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 TSM 2026-02-09 349. 360. 348. 355. 14594900 354.
## 2 TSM 2026-02-11 370. 380. 368. 374. 18651300 372.
## 3 TSM 2026-02-17 362. 366. 356. 364. 10063800 362.
## 4 TSM 2026-02-19 360. 363. 357. 360. 6346500 359.
## 5 TSM 2026-02-20 360. 372. 359. 371. 9009200 369.
## 6 TSM 2026-02-23 367. 373. 366. 370. 9550200 368.
## 7 TSM 2026-02-24 379. 389. 376. 386. 13269500 384.
## 8 TSM 2026-02-27 370. 377. 369. 375. 9186600 373.
## 9 TSM 2026-03-02 365. 373. 365. 369. 12571600 367.
## 10 TSM 2026-03-03 350. 356. 344. 353. 18580200 351.
## # ℹ 133 more rows
Arange Rows
stocks %>% arrange(desc(low))
## # A tibble: 1,232 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 SNDK 2026-06-22 2293. 2354. 2251. 2274. 9977600 2274.
## 2 SNDK 2026-06-25 2238. 2348. 2092. 2335 15030200 2335
## 3 SNDK 2026-06-30 2110. 2281. 2070 2274. 11454300 2274.
## 4 SNDK 2026-06-26 2170. 2256. 2063. 2091. 16867100 2091.
## 5 SNDK 2026-06-18 2045. 2192. 2029 2185. 12178300 2185.
## 6 SNDK 2026-06-15 2101. 2120. 2021. 2108. 9156400 2108.
## 7 SNDK 2026-07-01 2085. 2130. 2002. 2032. 11056500 2032.
## 8 SNDK 2026-06-16 2134. 2167. 1980. 1992. 9588500 1992.
## 9 SNDK 2026-06-23 2008. 2060 1950. 1964. 12868300 1964.
## 10 SNDK 2026-06-17 2075. 2075. 1938 1959. 9182500 1959.
## # ℹ 1,222 more rows
stocks %>% arrange(low)
## # A tibble: 1,232 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 SNDK 2025-04-07 29.2 33.0 27.9 31.5 6238600 31.5
## 2 SNDK 2025-04-11 30.6 32.0 28.3 32.0 4856000 32.0
## 3 SNDK 2025-04-04 35.7 35.9 28.4 30.1 11428600 30.1
## 4 SNDK 2025-04-21 31.1 31.1 28.9 29.8 2579400 29.8
## 5 SNDK 2025-04-22 30.3 31.1 29.3 29.6 2883700 29.6
## 6 SNDK 2025-04-23 32.0 32.8 30.2 30.4 2750200 30.4
## 7 SNDK 2025-04-24 30.8 33.0 30.3 32.3 2590500 32.3
## 8 SNDK 2025-04-17 31.8 32.7 30.4 31.3 2057200 31.3
## 9 SNDK 2025-04-10 34.6 35.0 30.5 31.1 4153400 31.1
## 10 SNDK 2025-04-16 32.3 33.1 30.8 32.0 2321000 32.0
## # ℹ 1,222 more rows
stocks %>% arrange(desc(high), desc(low))
## # A tibble: 1,232 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 SNDK 2026-06-22 2293. 2354. 2251. 2274. 9977600 2274.
## 2 SNDK 2026-06-25 2238. 2348. 2092. 2335 15030200 2335
## 3 SNDK 2026-06-30 2110. 2281. 2070 2274. 11454300 2274.
## 4 SNDK 2026-06-26 2170. 2256. 2063. 2091. 16867100 2091.
## 5 SNDK 2026-06-18 2045. 2192. 2029 2185. 12178300 2185.
## 6 SNDK 2026-06-16 2134. 2167. 1980. 1992. 9588500 1992.
## 7 SNDK 2026-07-01 2085. 2130. 2002. 2032. 11056500 2032.
## 8 SNDK 2026-06-15 2101. 2120. 2021. 2108. 9156400 2108.
## 9 SNDK 2026-06-29 2091. 2091. 1895 2050. 11251000 2050.
## 10 SNDK 2026-06-17 2075. 2075. 1938 1959. 9182500 1959.
## # ℹ 1,222 more rows
stocks %>% arrange(desc(close))
## # A tibble: 1,232 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 SNDK 2026-06-25 2238. 2348. 2092. 2335 15030200 2335
## 2 SNDK 2026-06-22 2293. 2354. 2251. 2274. 9977600 2274.
## 3 SNDK 2026-06-30 2110. 2281. 2070 2274. 11454300 2274.
## 4 SNDK 2026-06-18 2045. 2192. 2029 2185. 12178300 2185.
## 5 SNDK 2026-06-15 2101. 2120. 2021. 2108. 9156400 2108.
## 6 SNDK 2026-06-26 2170. 2256. 2063. 2091. 16867100 2091.
## 7 SNDK 2026-06-29 2091. 2091. 1895 2050. 11251000 2050.
## 8 SNDK 2026-07-01 2085. 2130. 2002. 2032. 11056500 2032.
## 9 SNDK 2026-06-16 2134. 2167. 1980. 1992. 9588500 1992.
## 10 SNDK 2026-06-12 1891. 2022. 1865. 1980. 11926100 1980.
## # ℹ 1,222 more rows
Select Colums
stocks %>% select(open, close, date) %>%
arrange(desc(close))
## # A tibble: 1,232 × 3
## open close date
## <dbl> <dbl> <date>
## 1 2238. 2335 2026-06-25
## 2 2293. 2274. 2026-06-22
## 3 2110. 2274. 2026-06-30
## 4 2045. 2185. 2026-06-18
## 5 2101. 2108. 2026-06-15
## 6 2170. 2091. 2026-06-26
## 7 2091. 2050. 2026-06-29
## 8 2085. 2032. 2026-07-01
## 9 2134. 1992. 2026-06-16
## 10 1891. 1980. 2026-06-12
## # ℹ 1,222 more rows
stocks %>% select(symbol:open, close) %>%
filter(open > close) %>%
arrange(open)
## # A tibble: 595 × 4
## symbol date open close
## <chr> <date> <dbl> <dbl>
## 1 SNDK 2025-04-22 30.3 29.6
## 2 SNDK 2025-04-21 31.1 29.8
## 3 SNDK 2025-04-17 31.8 31.3
## 4 SNDK 2025-04-23 32.0 30.4
## 5 SNDK 2025-04-16 32.3 32.0
## 6 SNDK 2025-04-28 32.6 32.3
## 7 SNDK 2025-04-08 33 32.3
## 8 SNDK 2025-04-15 33.3 33.2
## 9 SNDK 2025-04-14 33.8 33.5
## 10 SNDK 2025-05-06 34.0 33.8
## # ℹ 585 more rows
Add columns
#Calculate the percentage gain during the day, and arranged it through highest daily gain to lowest
mutate(stocks,
gain_procent = (close - open) /open*100) %>%
select(symbol:open, gain_procent) %>%
arrange(desc(gain_procent))
## # A tibble: 1,232 × 4
## symbol date open gain_procent
## <chr> <date> <dbl> <dbl>
## 1 SNDK 2026-01-06 289. 21.1
## 2 SNDK 2025-02-18 40.5 16.3
## 3 NVDA 2025-04-09 98.9 15.6
## 4 SNDK 2025-11-07 208. 14.9
## 5 SNDK 2025-04-09 31.9 14.6
## 6 SNDK 2026-08-13 1340. 14.1
## 7 SNDK 2026-03-09 517 13.9
## 8 SNDK 2025-10-23 147. 13.6
## 9 TSM 2025-04-09 140. 13.2
## 10 SNDK 2026-02-02 589. 13.0
## # ℹ 1,222 more rows
Summarize with groups
stocks %>%
#Average gain during day
mutate(
gain_procent = (close - open) /open*100) %>%
summarise(gain = mean(gain_procent))
## # A tibble: 1 × 1
## gain
## <dbl>
## 1 0.210
# Adding the new column to the data set (new)
stocks_gain <- stocks %>%
mutate(
gain_procent = (close - open) /open*100)
group_by(stocks_gain, symbol) %>%
summarise(gain = mean(gain_procent))
## # A tibble: 3 × 2
## symbol gain
## <chr> <dbl>
## 1 NVDA 0.0140
## 2 SNDK 0.651
## 3 TSM -0.00658
Summarize and visualize by group
stocks_gain %>%
filter(date >= max(date) - 365) %>%
group_by(symbol) %>%
mutate(avg_gain = mean(gain_procent)) %>%
ggplot(aes(x = date, y = gain_procent, colour = symbol)) +
geom_line(alpha = 0.6) +
geom_hline(aes(yintercept = avg_gain, colour = symbol),
linetype = "dashed") +
coord_cartesian(ylim = c(-10, 10))
#Separating the stocks
stocks_gain %>%
filter(date >= max(date) - 365) %>%
group_by(symbol) %>%
mutate(avg_gain = mean(gain_procent)) %>%
ggplot(aes(x = date, y = gain_procent, colour = symbol)) +
geom_line(alpha = 0.6) +
geom_hline(aes(yintercept = avg_gain, colour = symbol),
linetype = "dashed") +
coord_cartesian(ylim = c(-10, 10)) +
facet_wrap(~ symbol)
Grouping & Un-grouping
stocks_gain %>%
group_by(symbol) %>%
summarise(count = n())
## # A tibble: 3 × 2
## symbol count
## <chr> <int>
## 1 NVDA 420
## 2 SNDK 392
## 3 TSM 420
stocks_gain %>%
ungroup()
## # A tibble: 1,232 × 9
## symbol date open high low close volume adjusted gain_procent
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 TSM 2025-01-02 197 204. 197. 202. 10951400 198. 2.32
## 2 TSM 2025-01-03 204. 209. 204. 209. 10261900 205. 2.21
## 3 TSM 2025-01-06 219. 222. 216. 220. 24339900 216. 0.567
## 4 TSM 2025-01-07 221. 221. 211. 211. 17010000 208. -4.44
## 5 TSM 2025-01-08 210. 210. 206. 207. 13262700 203. -1.36
## 6 TSM 2025-01-10 208. 210. 203. 208. 17265200 205. 0.371
## 7 TSM 2025-01-13 201. 204. 200. 201. 16612400 198. 0.419
## 8 TSM 2025-01-14 205. 206. 198. 201. 14182900 198. -1.82
## 9 TSM 2025-01-15 202. 209. 199. 207. 18286500 203. 2.13
## 10 TSM 2025-01-16 219. 222. 213. 215. 38539600 211. -1.87
## # ℹ 1,222 more rows
stocks_gain %>%
mutate(gain_procent = (close - open)/ open
*100, month = format(date, "%Y-%m")) %>%
group_by(symbol, month) %>%
summarise(
gain = mean(gain_procent, na.rm = TRUE)
)
## # A tibble: 62 × 3
## # Groups: symbol [3]
## symbol month gain
## <chr> <chr> <dbl>
## 1 NVDA 2025-01 -0.507
## 2 NVDA 2025-02 -0.0756
## 3 NVDA 2025-03 -0.291
## 4 NVDA 2025-04 1.04
## 5 NVDA 2025-05 0.400
## 6 NVDA 2025-06 0.445
## 7 NVDA 2025-07 -0.0154
## 8 NVDA 2025-08 0.150
## 9 NVDA 2025-09 0.356
## 10 NVDA 2025-10 -0.264
## # ℹ 52 more rows
#Transpose the table = pivot wider
stocks_gain %>%
group_by(symbol) %>%
summarise(count = n())
## # A tibble: 3 × 2
## symbol count
## <chr> <int>
## 1 NVDA 420
## 2 SNDK 392
## 3 TSM 420
stocks_gain %>%
ungroup()
## # A tibble: 1,232 × 9
## symbol date open high low close volume adjusted gain_procent
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 TSM 2025-01-02 197 204. 197. 202. 10951400 198. 2.32
## 2 TSM 2025-01-03 204. 209. 204. 209. 10261900 205. 2.21
## 3 TSM 2025-01-06 219. 222. 216. 220. 24339900 216. 0.567
## 4 TSM 2025-01-07 221. 221. 211. 211. 17010000 208. -4.44
## 5 TSM 2025-01-08 210. 210. 206. 207. 13262700 203. -1.36
## 6 TSM 2025-01-10 208. 210. 203. 208. 17265200 205. 0.371
## 7 TSM 2025-01-13 201. 204. 200. 201. 16612400 198. 0.419
## 8 TSM 2025-01-14 205. 206. 198. 201. 14182900 198. -1.82
## 9 TSM 2025-01-15 202. 209. 199. 207. 18286500 203. 2.13
## 10 TSM 2025-01-16 219. 222. 213. 215. 38539600 211. -1.87
## # ℹ 1,222 more rows
stocks_gain %>%
mutate(gain_procent = (close - open)/ open
*100, month = format(date, "%Y-%m")) %>%
group_by(symbol, month) %>%
summarise(
gain = mean(gain_procent, na.rm = TRUE)
) %>%
pivot_wider(
names_from = symbol,
values_from = gain
)
## # A tibble: 21 × 4
## month NVDA SNDK TSM
## <chr> <dbl> <dbl> <dbl>
## 1 2025-01 -0.507 NA -0.00174
## 2 2025-02 -0.0756 1.28 -0.433
## 3 2025-03 -0.291 0.616 -0.0977
## 4 2025-04 1.04 -0.751 0.691
## 5 2025-05 0.400 0.501 0.202
## 6 2025-06 0.445 0.346 0.476
## 7 2025-07 -0.0154 -0.311 -0.0368
## 8 2025-08 0.150 0.797 -0.170
## 9 2025-09 0.356 2.16 0.624
## 10 2025-10 -0.264 1.23 -0.649
## # ℹ 11 more rows
