Práca s databázou

Import údajov z mojej bakalárskej práce

Načítam si csv súbor s dátami o elektromobilite vo V4

data<-read.csv("data_r_comma_utf8.csv")

library(dplyr)
library(ggplot2)

dim(data) #počet riadkov a stĺpcov

[1] 50 12

names(data) #názvy 

 [1] "Krajina"          "Rok"              "BEV"             
 [4] "EPI"              "HDP"              "BEV_PHEV"        
 [7] "co2"              "res_develop"      "r_sources"       
[10] "unvest_man"       "invest_sources"   "invest_transport"

dplyr::glimpse(data)

Rows: 50
Columns: 12
$ Krajina          <chr> "CZ", "CZ", "CZ", "CZ", "CZ", "CZ", "CZ", "CZ",…
$ Rok              <int> 2023, 2022, 2021, 2020, 2019, 2018, 2017, 2016,…
$ BEV              <dbl> 22451, 13928, 9969, 7109, 3897, 3047, 2309, 176…
$ EPI              <dbl> 60.700, 59.900, 65.450, 71.000, 69.340, 67.680,…
$ HDP              <int> 21660, 21910, 21830, 20980, 22050, 21320, 20760…
$ BEV_PHEV         <dbl> 33448, 22646, 15128, 9835, 5223, 3906, 2877, 21…
$ co2              <dbl> 98918217, 116453963, 121829204, 119492626, 1262…
$ res_develop      <dbl> 1.83, 1.89, 1.93, 1.95, 1.90, 1.88, 1.75, 1.65,…
$ r_sources        <dbl> 510.170, 534.492, 546.272, 529.730, 496.716, 44…
$ unvest_man       <dbl> 0.08, 0.09, 0.10, 0.11, 0.12, 0.08, 0.08, 0.07,…
$ invest_sources   <dbl> 0.05, 0.06, 0.09, 0.09, 0.08, 0.06, 0.07, 0.08,…
$ invest_transport <dbl> 0.20, 0.21, 0.24, 0.30, 0.25, 0.31, 0.23, 0.27,…

library(knitr)
library(kableExtra)

head(data, 10) |>
  kbl(caption = "Prvých 10 riadkov", booktabs = TRUE) |>
  kable_styling(
    full_width = FALSE,
    bootstrap_options = c("striped", "condensed"),
    stripe_color = "#ECFDF5"   # veľmi svetlá zelená
  ) |>
  row_spec(0, bold = TRUE, color = "white", background = "#10B981")  # smaragdový header

Prvých 10 riadkov

Krajina	Rok	BEV	EPI	HDP	BEV_PHEV	co2	res_develop	r_sources	unvest_man	invest_sources	invest_transport
CZ	2023	22451	60.700	21660	33448	98918217	1.83	510.170	0.08	0.05	0.20
CZ	2022	13928	59.900	21910	22646	116453963	1.89	534.492	0.09	0.06	0.21
CZ	2021	9969	65.450	21830	15128	121829204	1.93	546.272	0.10	0.09	0.24
CZ	2020	7109	71.000	20980	9835	119492626	1.95	529.730	0.11	0.09	0.30
CZ	2019	3897	69.340	22050	5223	126296221	1.90	496.716	0.12	0.08	0.25
CZ	2018	3047	67.680	21320	3906	125679525	1.88	442.219	0.08	0.06	0.31
CZ	2017	2309	76.175	20760	2877	123141318	1.75	462.759	0.08	0.07	0.23
CZ	2016	1762	84.670	19760	2102	120794086	1.65	492.898	0.07	0.08	0.27
CZ	2015	1326	81.385	19270	1530	117895260	1.91	487.991	0.08	0.10	0.36
CZ	2014	855	78.100	18370	934	117541172	1.94	460.295	0.09	0.11	0.32

 #náhľad prvých 10 riadkov

Frekvenčná tabuľka podľa stĺpca

library(dplyr)
library(knitr)
library(kableExtra)
library(scales)

tab_krajina <- data %>%
  count(Krajina, sort = TRUE, name = "Počet") %>%
  mutate(Podiel = percent(Počet / sum(Počet), accuracy = 0.1))

kbl(tab_krajina, caption = "Počty a podiely podľa krajiny",
    col.names = c("Krajina","Počet","Podiel")) %>%
  kable_styling(full_width = FALSE, bootstrap_options = c("striped","condensed")) %>%
  row_spec(0, bold = TRUE, color = "white", background = "#10B981")

Počty a podiely podľa krajiny

Krajina	Počet	Podiel
CZ	10	20.0%
EU-avrg	10	20.0%
MR	10	20.0%
PL	10	20.0%
SK	10	20.0%

NA

Deskriptívna štatistika dát

library(dplyr)
library(gt)

# 1) Deskriptíva pre všetky numerické premenné

num_vars <- names(Filter(is.numeric, data))

get_stats <- function(x) data.frame(
n      = sum(!is.na(x)),
mean   = mean(x, na.rm = TRUE),
sd     = sd(x, na.rm = TRUE),
min    = min(x, na.rm = TRUE),
q25    = as.numeric(quantile(x, 0.25, na.rm = TRUE)),
median = median(x, na.rm = TRUE),
q75    = as.numeric(quantile(x, 0.75, na.rm = TRUE)),
max    = max(x, na.rm = TRUE)
)

stats_table <- do.call(
rbind,
lapply(num_vars, function(v) cbind(Premenna = v, get_stats(data[[v]])))
)

# 2) Pekná tabuľka – zelený header, kompletné orámovanie, páskovanie

gt(stats_table) |>
cols_label(
Premenna = "Premenná",
n        = "n",
mean     = "Priemer",
sd       = "SD",
min      = "Min",
q25      = "P25",
median   = "Medián",
q75      = "P75",
max      = "Max"
) |>
fmt_number(columns = c(Priemer = mean, SD = sd, Min = min, P25 = q25,
Medián = median, P75 = q75, Max = max),
decimals = 2, sep_mark = " ", dec_mark = ",") |>
fmt_number(columns = n, decimals = 0, sep_mark = " ", dec_mark = ",") |>
tab_header(title = md("**Deskriptívna štatistika (numerické premenné)**")) |>
tab_style(
style = list(cell_fill(color = "#10B981"),
cell_text(color = "white", weight = "bold")),
locations = cells_column_labels(everything())
) |>
opt_row_striping() |>
tab_options(
row.striping.background_color = "#ECFDF5",
table.border.top.style = "solid",  table.border.top.width = px(1),
table.border.bottom.style = "solid", table.border.bottom.width = px(1),
column_labels.border.top.style = "solid",
column_labels.border.bottom.style = "solid",
table_body.hlines.style = "solid", table_body.hlines.width = px(1),
table_body.vlines.style = "solid", table_body.vlines.width = px(1)
)

Deskriptívna štatistika (numerické premenné)
Premenná	n	Priemer	SD	Min	P25	Medián	P75	Max
Rok	50	2.018500e+03	2.901442e+00	2014.000	2.016000e+03	2.018500e+03	2.021000e+03	2.023000e+03
BEV	50	1.592708e+04	3.018585e+04	113.000	9.110000e+02	4.155426e+03	1.407975e+04	1.632455e+05
EPI	50	6.788088e+01	9.180603e+00	46.000	6.350000e+01	6.830000e+01	7.328125e+01	8.542000e+01
HDP	50	1.947160e+04	6.655541e+03	11360.000	1.452250e+04	1.732500e+04	2.178750e+04	3.330000e+04
BEV_PHEV	50	2.771188e+04	5.478741e+04	201.000	1.575500e+03	7.198500e+03	2.848325e+04	2.902244e+05
co2	50	7.344969e+08	1.319764e+09	28339113.568	5.459271e+07	1.177182e+08	1.294116e+08	3.565184e+09
res_develop	50	1.523600e+00	4.820101e-01	0.790	1.067500e+00	1.450000e+00	1.925000e+00	2.310000e+00
r_sources	50	6.284690e+02	5.298468e+02	129.454	3.178076e+02	4.373183e+02	5.248400e+02	2.010715e+03
unvest_man	50	1.468000e-01	2.043550e-01	0.030	5.000000e-02	7.500000e-02	1.100000e-01	1.000000e+00
invest_sources	50	1.470000e-01	7.412758e-02	0.040	9.000000e-02	1.400000e-01	1.900000e-01	3.500000e-01
invest_transport	50	2.660000e-01	1.256168e-01	0.090	1.700000e-01	2.600000e-01	3.200000e-01	7.200000e-01

NA
NA

Histogram

library(ggplot2)

ggplot(data, aes(x = BEV)) +
geom_histogram(bins = 20, fill = "#10B981", color = "white") +
labs(title = "Histogram: BEV", x = "BEV", y = "Počet") +
theme_minimal() +
theme(plot.title = element_text(color = "#10B981", face = "bold"))

NA
NA

Log-mierka (ukáže rozdelenie prehľadnejšie)

ggplot(data, aes(BEV)) +
  geom_histogram(bins = 20, fill = "#10B981", color = "white") +
  scale_x_log10() +
  labs(title = "Histogram: BEV (log škála)", x = "BEV (log10)", y = "Počet")

BoxPlot

library(dplyr)
library(ggplot2)
library(scales)

# zoradíme krajiny podľa mediánu BEV

data_bp <- data %>% mutate(Krajina = reorder(Krajina, BEV, FUN = median, na.rm = TRUE))

ggplot(data_bp, aes(x = Krajina, y = BEV)) +
geom_boxplot(fill = "#10B981", color = "#0B7D63", width = 0.6, outlier.shape = NA, alpha = 0.9) +
geom_jitter(width = 0.15, height = 0, alpha = 0.35, size = 1.8, color = "#065F46") +
labs(
title = "BEV podľa krajiny",
subtitle = "Krajiny zoradené podľa mediánu BEV",
x = NULL, y = "BEV (kusy)"
) +
scale_y_continuous(labels = label_number(big.mark = " ", accuracy = 1)) +
theme_minimal(base_size = 13) +
theme(
plot.title = element_text(face = "bold", color = "#10B981"),
axis.text.x = element_text(angle = 0, hjust = 0.5),
panel.grid.minor = element_blank()
)

NA
NA

Vzťah HDP a BEV

library(ggplot2)
library(scales)

ggplot(data, aes(x = HDP, y = BEV)) +
  geom_point(color = "#10B981", alpha = 0.8, size = 2.3) +
  geom_smooth(method = "lm", se = TRUE, color = "#065F46") +
  labs(title = "HDP vs. BEV", x = "HDP", y = "BEV") +
  scale_x_continuous(labels = label_number(big.mark = " ")) +
  scale_y_continuous(labels = label_number(big.mark = " ")) +
  theme_minimal(base_size = 13) +
  theme(
    plot.title = element_text(face = "bold", color = "#10B981"),
    panel.grid.minor = element_blank()
  )

Vývoj BEV v čase podľa krajín - samostatné grafy

library(ggplot2)

ggplot(data, aes(x = Rok, y = BEV, color = Krajina)) +
  geom_line(linewidth = 1) +
  geom_point(size = 1.6) +
  facet_wrap(~ Krajina, scales = "free_y") +
  scale_color_viridis_d(option = "G", end = 0.9) +  # pekná paleta
  labs(title = "Vývoj BEV v čase podľa krajiny", x = NULL, y = "BEV", color = "Krajina") +
  theme_minimal(base_size = 13) +
  theme(plot.title = element_text(face = "bold", color = "#10B981"),
        panel.grid.minor = element_blank(),
        legend.position = "none")               

Vývoj BEV v čase podľa krajín - spoločný graf

ggplot(data, aes(Rok, BEV, color = Krajina)) +
  geom_line(linewidth = 1) +
  geom_point(size = 1.6) +
  scale_color_viridis_d(option = "G", end = 0.9) +
  labs(title = "Vývoj BEV v čase (farby podľa krajiny)", x = NULL, y = "BEV", color = "Krajina") +
  theme_minimal(base_size = 13) +
  theme(plot.title = element_text(face = "bold", color = "#10B981"),
        panel.grid.minor = element_blank(),
        legend.position = "bottom")

BEV po rokoch spolu za všetky krajiny

bev_year <- data %>%
group_by(Rok) %>%
summarise(BEV = sum(BEV, na.rm = TRUE), .groups = "drop") %>%
arrange(Rok)

gt(bev_year) |>
fmt_number(columns = BEV, decimals = 0, sep_mark = " ") |>
tab_header(title = md("**BEV po rokoch (spolu)**")) |>
data_color(
columns = BEV,
colors = scales::col_numeric(
palette = viridis(10),
domain = range(bev_year$BEV, na.rm = TRUE)
)
) |>
tab_options(table.font.size = px(14))

BEV po rokoch (spolu)
Rok	BEV
2014	3 930
2015	6 174
2016	9 161
2017	14 909
2018	23 620
2019	64 093
2020	69 313
2021	121 908
2022	191 646
2023	291 601

NA

1 faktorová ANOVA

library(gt); library(broom)

data$Krajina <- as.factor(data$Krajina)

fit_aov <- aov(BEV ~ Krajina, data = data)
aov_tbl <- tidy(fit_aov)   # stĺpce: term, df, sumsq, meansq, statistic, p.value

tab <- gt(aov_tbl)
tab <- cols_label(tab,
                  term = "Zdroj", df = "df",
                  sumsq = "SS", meansq = "MS",
                  statistic = "F", p.value = "p-hodnota")
tab <- fmt_number(tab, columns = c(sumsq, meansq, statistic, p.value),
                  decimals = 3, sep_mark = " ")
tab <- tab_header(tab, title = md("**Jednofaktorová ANOVA: BEV ~ Krajina**"))
tab <- tab_style(tab,
                 style = list(cell_fill(color = "#10B981"),
                              cell_text(color = "white", weight = "bold")),
                 locations = cells_column_labels(everything()))
tab <- opt_row_striping(tab)
tab <- tab_options(tab,
                   row.striping.background_color = "#ECFDF5",
                   table.border.top.style = "solid",
                   table.border.bottom.style = "solid",
                   column_labels.border.top.style = "solid",
                   column_labels.border.bottom.style = "solid")
tab    # zobraz tabuľku

Jednofaktorová ANOVA: BEV ~ Krajina
Zdroj	df	SS	MS	F	p-hodnota
Krajina	4	11 750 642 287.144	2 937 660 571.786	4.018	0.007
Residuals	45	32 897 463 152.073	731 054 736.713	NA	NA

NA
NA

Korelačná matica a heatmap

library(dplyr); library(gt); library(viridisLite)

# numerické stĺpce + korelácie
num <- dplyr::select_if(data, is.numeric)
cm  <- round(cor(num, use = "pairwise.complete.obs"), 2)

# zoradenie premenných podľa klastrovania (prehľadnejšie)
ord <- hclust(dist(cm))$order
cm  <- cm[ord, ord]

# priprav data.frame pre gt
tbl <- cbind(Premenná = rownames(cm), as.data.frame(cm), row.names = NULL)

g <- gt(tbl)
g <- tab_header(g, title = md("**Korelačná matica (numerické premenné)**"))
g <- tab_style(g,
       style = list(cell_fill(color = "#10B981"),
                    cell_text(color = "white", weight = "bold")),
       locations = cells_column_labels(everything()))
g <- fmt_number(g, columns = -Premenná, decimals = 2)
g <- data_color(g, columns = -Premenná,
       colors = scales::col_numeric(palette = viridis(11, option = "G"),
                                    domain = c(-1, 1)))
g

Korelačná matica (numerické premenné)
Premenná	HDP	res_develop	Rok	BEV	BEV_PHEV	EPI	invest_transport	invest_sources	unvest_man	co2	r_sources
HDP	1.00	0.81	0.19	0.52	0.54	−0.02	−0.03	0.20	−0.30	−0.42	−0.31
res_develop	0.81	1.00	0.15	0.45	0.46	−0.06	0.24	−0.26	−0.04	−0.30	−0.20
Rok	0.19	0.15	1.00	0.54	0.53	−0.62	−0.49	−0.07	0.32	−0.03	0.04
BEV	0.52	0.45	0.54	1.00	1.00	−0.33	−0.05	0.12	0.06	−0.06	−0.04
BEV_PHEV	0.54	0.46	0.53	1.00	1.00	−0.33	−0.05	0.14	0.01	−0.05	−0.04
EPI	−0.02	−0.06	−0.62	−0.33	−0.33	1.00	0.22	−0.02	−0.35	−0.20	−0.21
invest_transport	−0.03	0.24	−0.49	−0.05	−0.05	0.22	1.00	−0.46	−0.03	−0.14	−0.25
invest_sources	0.20	−0.26	−0.07	0.12	0.14	−0.02	−0.46	1.00	−0.22	−0.06	−0.05
unvest_man	−0.30	−0.04	0.32	0.06	0.01	−0.35	−0.03	−0.22	1.00	−0.03	−0.07
co2	−0.42	−0.30	−0.03	−0.06	−0.05	−0.20	−0.14	−0.06	−0.03	1.00	0.97
r_sources	−0.31	−0.20	0.04	−0.04	−0.04	−0.21	−0.25	−0.05	−0.07	0.97	1.00

NA
NA

library(ggplot2)

# voliteľné: pre krajšie poradie premenných (clustering)

ord <- hclust(dist(cor_mat))$order
cor_reord <- cor_mat[ord, ord]

df <- as.data.frame(as.table(cor_reord))
names(df) <- c("Var1", "Var2", "Corr")

ggplot(df, aes(Var1, Var2, fill = Corr)) +
geom_tile() +
geom_text(aes(label = Corr), size = 3) +
scale_fill_gradient2(limits = c(-1, 1)) +
coord_fixed() +
labs(title = "Korelačná matica (heatmapa)", x = NULL, y = NULL, fill = "r") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))