knitr::opts_chunk$set(
echo = TRUE,
message = FALSE,
warning = FALSE
)Analýza ropnej geopolitiky 2010–2026
Úloha 1: Načítanie údajov (Read CSV)
Súbor oil_geopolitics_dataset_2010_2026.csv je v podpriečinku udaje. Oddeľovač je čiarka, desatinný znak bodka, prvý riadok obsahuje názvy stĺpcov.
library(dplyr)
library(ggplot2)
library(knitr)
library(kableExtra)
ropa <- read.csv("oil_geopolitics_dataset_2010_2026.csv",
header = TRUE, sep = ",", dec = ".")
ropa$date <- as.Date(ropa$date) # text -> dátum
head(ropa) # prvých šesť riadkov date brent_price wti_price dxy_index vix gpr_index brent_return
1 2010-02-17 76.27 77.33 80.38 21.72 80.72536 0.007795935
2 2010-02-18 77.78 79.06 80.40 20.63 80.72536 0.019798115
3 2010-02-19 78.19 79.81 80.64 20.02 80.72536 0.005271325
4 2010-02-22 78.61 80.16 80.51 19.94 80.72536 0.005371507
5 2010-02-23 77.25 78.86 80.85 21.37 80.72536 -0.017300606
6 2010-02-24 78.09 80.00 80.85 20.27 80.72536 0.010873739
wti_return brent_lag_1 brent_lag_3 brent_lag_7 wti_lag_1 wti_lag_3
1 0.004155300 75.68 73.05 69.59 77.01 75.28
2 0.022371598 76.27 72.90 70.11 77.33 74.13
3 0.009486466 77.78 75.68 72.13 79.06 77.01
4 0.004385492 78.19 76.27 72.54 79.81 77.33
5 -0.016217602 78.61 77.78 73.05 80.16 79.06
6 0.014455990 77.25 78.19 72.90 78.86 79.81
wti_lag_7 brent_volatility_7d brent_volatility_30d wti_volatility_7d
1 71.19 0.01446055 0.01967906 0.01697708
2 71.89 0.01438747 0.02001918 0.01736603
3 73.75 0.01334209 0.01979589 0.01655310
4 74.52 0.01336596 0.01982289 0.01677207
5 75.28 0.01733358 0.02004482 0.01960840
6 74.13 0.01674453 0.02015997 0.01708107
wti_volatility_30d brent_wti_spread event_type event_description
1 0.01928020 -1.060005 none none
2 0.01975580 -1.279999 none none
3 0.01955948 -1.619995 none none
4 0.01956102 -1.550003 none none
5 0.01975645 -1.610001 none none
6 0.01996491 -1.910004 none none
event_severity event_flag
1 0 0
2 0 0
3 0 0
4 0 0
5 0 0
6 0 0colnames(ropa) # názvy premenných [1] "date" "brent_price" "wti_price"
[4] "dxy_index" "vix" "gpr_index"
[7] "brent_return" "wti_return" "brent_lag_1"
[10] "brent_lag_3" "brent_lag_7" "wti_lag_1"
[13] "wti_lag_3" "wti_lag_7" "brent_volatility_7d"
[16] "brent_volatility_30d" "wti_volatility_7d" "wti_volatility_30d"
[19] "brent_wti_spread" "event_type" "event_description"
[22] "event_severity" "event_flag" dim(ropa) # počet riadkov a stĺpcov[1] 4047 23range(ropa$date, na.rm = TRUE) # časové obdobie[1] "2010-02-17" "2026-03-12"Úloha 2: Tabuľka
Ukážka údajov
ropa %>%
select(date, brent_price, wti_price, dxy_index, vix, gpr_index) %>%
head(10) %>%
kable(digits = 2,
caption = "Prvých 10 záznamov databázy",
col.names = c("Dátum", "Brent", "WTI", "DXY", "VIX", "GPR"),
align = "c") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"),
full_width = FALSE, position = "center")| Dátum | Brent | WTI | DXY | VIX | GPR |
|---|---|---|---|---|---|
| 2010-02-17 | 76.27 | 77.33 | 80.38 | 21.72 | 80.73 |
| 2010-02-18 | 77.78 | 79.06 | 80.40 | 20.63 | 80.73 |
| 2010-02-19 | 78.19 | 79.81 | 80.64 | 20.02 | 80.73 |
| 2010-02-22 | 78.61 | 80.16 | 80.51 | 19.94 | 80.73 |
| 2010-02-23 | 77.25 | 78.86 | 80.85 | 21.37 | 80.73 |
| 2010-02-24 | 78.09 | 80.00 | 80.85 | 20.27 | 80.73 |
| 2010-02-25 | 76.29 | 78.17 | 80.79 | 20.10 | 80.73 |
| 2010-02-26 | 77.59 | 79.66 | 80.36 | 19.50 | 80.73 |
| 2010-03-01 | 76.89 | 78.70 | 80.66 | 19.26 | 74.12 |
| 2010-03-02 | 78.18 | 79.68 | 80.52 | 19.06 | 74.12 |
Základné štatistiky cien podľa rokov
ropa.stats <- ropa %>%
mutate(rok = as.integer(format(date, "%Y"))) %>%
group_by(rok) %>%
summarise(
n = n(),
mean = mean(brent_price, na.rm = TRUE),
sd = sd(brent_price, na.rm = TRUE),
min = min(brent_price, na.rm = TRUE),
q25 = quantile(brent_price, 0.25, na.rm = TRUE),
median = median(brent_price, na.rm = TRUE),
q75 = quantile(brent_price, 0.75, na.rm = TRUE),
max = max(brent_price, na.rm = TRUE),
.groups = "drop"
)
ropa.stats %>%
kable(digits = 2,
caption = "Základné štatistiky ceny ropy Brent podľa rokov (USD/barel)") %>%
kable_styling(full_width = FALSE,
bootstrap_options = c("striped", "hover", "condensed")) %>%
column_spec(1, bold = TRUE) %>%
row_spec(0, bold = TRUE, background = "#f2f2f2") %>%
add_header_above(c(" " = 2, "Brent – popisné štatistiky" = 7))| rok | n | mean | sd | min | q25 | median | q75 | max |
|---|---|---|---|---|---|---|---|---|
| 2010 | 222 | 81.04 | 5.74 | 69.55 | 76.69 | 79.90 | 84.83 | 94.75 |
| 2011 | 252 | 110.95 | 6.97 | 93.33 | 107.35 | 111.39 | 115.46 | 126.65 |
| 2012 | 250 | 111.76 | 7.83 | 89.23 | 108.17 | 111.56 | 116.74 | 126.22 |
| 2013 | 252 | 108.72 | 4.25 | 99.13 | 105.78 | 109.22 | 111.22 | 118.90 |
| 2014 | 252 | 99.35 | 14.62 | 57.33 | 93.98 | 106.73 | 108.69 | 115.06 |
| 2015 | 252 | 53.50 | 8.05 | 36.11 | 48.06 | 53.31 | 60.25 | 67.77 |
| 2016 | 253 | 45.13 | 6.70 | 27.88 | 41.20 | 46.83 | 49.69 | 56.22 |
| 2017 | 251 | 54.73 | 4.99 | 44.82 | 51.40 | 54.49 | 56.88 | 67.02 |
| 2018 | 251 | 71.77 | 6.90 | 50.47 | 67.46 | 73.05 | 77.00 | 86.29 |
| 2019 | 252 | 64.16 | 4.16 | 54.91 | 61.18 | 63.39 | 66.91 | 74.57 |
| 2020 | 253 | 43.09 | 10.25 | 19.33 | 38.97 | 43.08 | 48.71 | 68.91 |
| 2021 | 252 | 70.95 | 7.83 | 51.09 | 66.35 | 71.40 | 75.45 | 86.40 |
| 2022 | 251 | 98.97 | 11.76 | 76.10 | 90.54 | 96.78 | 107.56 | 127.98 |
| 2023 | 251 | 82.19 | 5.58 | 71.84 | 77.44 | 82.47 | 85.81 | 96.55 |
| 2024 | 252 | 79.82 | 5.39 | 69.19 | 74.48 | 79.91 | 83.66 | 91.17 |
| 2025 | 253 | 68.09 | 5.06 | 58.92 | 64.44 | 66.99 | 70.78 | 82.03 |
| 2026 | 48 | 70.98 | 9.36 | 59.96 | 65.41 | 68.23 | 71.53 | 98.96 |
Udalosti podľa typu
ropa %>%
filter(event_type != "none") %>%
group_by(event_type) %>%
summarise(
Pocet = n(),
Priem.zavaznost = mean(event_severity, na.rm = TRUE),
Priem.Brent = mean(brent_price, na.rm = TRUE),
.groups = "drop"
) %>%
arrange(desc(Pocet)) %>%
kable(digits = 2,
caption = "Geopolitické udalosti podľa typu",
col.names = c("Typ udalosti", "Počet", "Priem. závažnosť", "Priem. cena Brent")) %>%
kable_styling(full_width = FALSE,
bootstrap_options = c("striped", "hover", "condensed"))| Typ udalosti | Počet | Priem. závažnosť | Priem. cena Brent |
|---|---|---|---|
| sanctions | 6 | 7.83 | 96.21 |
| conflict | 4 | 8.25 | 74.23 |
| opec | 3 | 8.00 | 55.34 |
| war | 3 | 8.67 | 86.64 |
| blockade | 2 | 9.00 | 90.19 |
| annexation | 1 | 8.00 | 106.79 |
| blockage | 1 | 8.00 | 60.79 |
| diplomatic_crisis | 1 | 6.00 | 49.47 |
| disaster | 1 | 7.00 | 84.80 |
| energy_crisis | 1 | 7.00 | 81.26 |
| market_crash | 1 | 10.00 | 25.57 |
| market_shift | 1 | 7.00 | 64.40 |
Úloha 3: Obrázok (graf)
Vývoj cien Brent a WTI v čase
ggplot(ropa, aes(x = date)) +
geom_line(aes(y = brent_price, colour = "Brent"), linewidth = 0.5) +
geom_line(aes(y = wti_price, colour = "WTI"), linewidth = 0.5) +
scale_colour_manual(values = c("Brent" = "darkblue", "WTI" = "darkorange")) +
labs(title = "Vývoj cien ropy Brent a WTI",
x = "Rok", y = "Cena (USD/barel)", colour = "Typ ropy") +
theme_minimal()
Boxplot ceny Brent podľa rokov
ggplot(ropa, aes(x = factor(format(date, "%Y")), y = brent_price)) +
geom_boxplot(fill = "lightblue", color = "darkblue") +
labs(title = "Cena ropy Brent podľa rokov",
x = "Rok", y = "Cena (USD/barel)") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Scatter plot: geopolitické riziko a cena
ggplot(ropa, aes(x = gpr_index, y = brent_price)) +
geom_point(alpha = 0.3, colour = "darkblue") +
geom_smooth(method = "lm", colour = "red", se = TRUE) +
labs(title = "Geopolitické riziko (GPR) a cena ropy Brent",
x = "GPR index", y = "Brent (USD/barel)") +
theme_minimal()