Práca s databázou

Import údajov

library(readr)

# Načítanie CSV súboru 
Vysledky <- read_csv("student_exam_scores.csv")

tabuľka

library(knitr)

# Základná tabuľka
kable(Vysledky)

student_id	hours_studied	sleep_hours	attendance_percent	previous_scores	exam_score
S001	8.0	8.8	72.1	45	30.2
S002	1.3	8.6	60.7	55	25.0
S003	4.0	8.2	73.7	86	35.8
S004	3.5	4.8	95.1	66	34.0
S005	9.1	6.4	89.8	71	40.3
S006	8.4	5.1	58.5	75	35.7
S007	10.8	6.0	54.2	88	37.9
S008	2.0	4.3	75.8	55	18.3
S009	5.6	5.9	81.6	84	34.7
S010	1.3	8.9	66.8	70	24.7
S011	3.4	5.3	90.9	81	29.3
S012	6.6	7.9	87.6	85	35.1
S013	1.3	6.3	83.6	71	31.2
S014	3.2	6.1	61.2	68	30.2
S015	8.1	8.8	60.0	90	41.1
S016	7.0	9.0	51.2	41	34.1
S017	3.4	6.8	62.2	45	28.9
S018	7.5	7.6	73.8	58	36.3
S019	9.9	4.8	92.5	54	35.6
S020	1.1	5.5	53.6	65	17.1
S021	9.9	8.8	70.7	84	46.0
S022	8.7	6.9	81.5	55	36.1
S023	4.7	6.7	59.7	59	29.6
S024	2.7	7.7	84.8	82	35.9
S025	11.5	4.3	74.7	77	39.2
S026	4.7	6.9	62.2	63	30.0
S027	2.0	6.5	82.8	70	29.0
S028	2.1	8.3	50.3	75	26.5
S029	10.3	4.8	87.5	73	37.2
S030	7.6	8.8	88.5	62	36.2
S031	9.9	4.4	55.3	67	34.5
S032	9.0	4.9	71.3	87	41.6
S033	6.9	7.0	58.8	75	38.1
S034	11.7	7.4	97.9	61	42.7
S035	5.2	5.2	75.9	62	32.0
S036	7.1	4.6	52.5	84	32.0
S037	10.1	8.5	62.5	69	44.7
S038	7.8	5.2	92.4	57	38.3
S039	10.5	7.0	72.8	59	39.8
S040	7.4	7.1	90.1	56	35.0
S041	8.8	6.1	83.4	54	34.2
S042	1.5	6.9	99.4	47	23.1
S043	3.5	6.6	79.8	86	37.2
S044	4.2	8.7	97.5	52	30.3
S045	1.9	5.0	94.6	60	26.1
S046	3.6	7.6	80.6	47	31.8
S047	2.1	5.2	86.0	87	31.6
S048	4.1	6.0	75.2	74	31.1
S049	8.0	7.4	91.5	88	41.2
S050	5.0	5.5	77.4	84	30.6
S051	5.1	5.6	94.9	51	28.8
S052	3.3	7.8	87.2	52	30.7
S053	3.9	4.4	73.7	53	26.9
S054	11.3	6.3	63.0	87	46.4
S055	8.1	9.0	62.4	70	34.4
S056	7.7	9.0	81.9	57	37.0
S057	2.9	4.4	88.3	86	35.2
S058	9.0	5.1	76.1	77	38.2
S059	2.8	5.3	81.3	88	33.0
S060	5.2	8.7	63.7	73	29.2
S061	11.9	8.4	53.9	78	48.6
S062	8.0	8.4	64.3	58	36.1
S063	7.1	5.8	63.6	46	27.1
S064	8.5	4.8	66.0	93	36.1
S065	10.3	8.2	77.0	52	39.5
S066	9.5	7.5	56.9	58	36.7
S067	3.5	7.1	61.6	54	21.7
S068	1.4	8.9	84.7	63	32.2
S069	4.5	7.3	85.3	51	33.5
S070	3.9	4.0	53.2	59	23.9
S071	3.3	8.1	70.4	40	20.8
S072	11.4	5.5	77.1	85	47.9
S073	10.6	7.3	70.8	74	41.9
S074	4.5	8.7	60.3	48	29.5
S075	8.2	4.7	71.0	57	33.5
S076	5.4	4.6	95.2	42	26.3
S077	11.1	4.5	79.2	43	39.9
S078	6.0	6.8	84.8	75	40.3
S079	3.9	5.4	92.8	58	26.5
S080	3.7	7.0	88.3	84	34.2
S081	7.2	7.6	69.0	48	30.8
S082	3.9	5.0	50.3	80	32.4
S083	7.4	7.2	67.6	95	39.8
S084	10.9	5.3	87.7	88	48.9
S085	5.4	6.4	92.7	71	38.0
S086	3.4	8.5	97.7	46	26.5
S087	12.0	8.2	71.0	95	51.3
S088	6.6	4.5	87.4	40	28.6
S089	2.0	6.1	77.3	76	32.1
S090	1.5	5.4	80.2	58	23.9
S091	2.2	4.0	61.0	70	27.3
S092	7.9	7.9	61.0	70	34.0
S093	9.7	7.2	71.8	68	37.5
S094	5.6	5.3	51.5	61	29.1
S095	1.7	7.7	66.8	51	28.1
S096	5.2	6.8	84.0	43	28.7
S097	12.0	6.1	70.2	56	36.9
S098	6.8	4.0	58.3	95	36.0
S099	11.7	4.4	73.4	70	39.9
S100	10.5	8.4	56.4	47	37.1
S101	1.1	8.5	81.1	92	31.4
S102	8.9	6.7	51.3	44	31.3
S103	8.5	8.2	69.7	65	35.7
S104	6.9	6.9	78.2	71	32.6
S105	3.9	4.7	51.4	44	24.1
S106	8.1	4.6	82.1	76	38.2
S107	2.2	5.5	56.8	80	23.7
S108	5.8	8.5	73.1	83	39.2
S109	6.0	8.0	52.5	43	23.2
S110	11.5	8.3	69.0	49	42.2
S111	10.6	8.5	60.6	49	39.6
S112	3.9	5.1	66.3	91	34.8
S113	6.5	5.2	88.1	76	34.6
S114	3.0	4.5	69.0	59	26.4
S115	11.0	7.9	87.6	45	43.1
S116	10.6	8.4	91.6	55	46.4
S117	4.3	6.0	62.6	47	25.2
S118	8.0	7.1	54.1	75	31.3
S119	7.7	4.8	51.0	88	35.8
S120	2.7	8.6	77.0	66	29.8
S121	9.4	8.3	100.0	78	47.9
S122	6.9	8.9	67.5	78	40.9
S123	9.6	8.1	82.5	90	44.1
S124	6.8	8.4	89.1	79	39.3
S125	1.0	4.1	82.6	54	21.2
S126	4.6	7.7	87.7	89	38.6
S127	1.2	5.7	97.5	73	26.8
S128	11.2	8.7	60.0	64	42.7
S129	10.7	8.0	51.0	68	36.1
S130	10.1	8.3	57.6	68	39.2
S131	4.4	8.1	56.3	59	32.9
S132	1.6	5.3	83.5	95	28.8
S133	10.7	7.9	78.2	77	45.7
S134	11.4	4.5	60.9	67	40.8
S135	1.9	8.4	85.0	59	30.6
S136	6.3	8.3	88.3	76	41.1
S137	1.8	5.1	58.4	79	29.0
S138	9.4	8.1	80.4	43	35.1
S139	9.4	6.3	87.4	79	39.9
S140	2.4	5.5	55.7	87	29.9
S141	6.2	8.0	91.0	46	35.0
S142	7.0	5.1	98.2	88	43.3
S143	3.9	4.1	55.4	53	19.0
S144	10.6	5.0	51.3	80	35.1
S145	5.7	5.6	65.6	53	29.9
S146	3.3	8.3	83.9	56	33.0
S147	6.9	8.8	97.9	82	45.8
S148	9.0	5.4	69.8	45	35.5
S149	3.2	7.2	85.8	50	26.4
S150	4.4	6.0	53.8	55	21.9
S151	11.9	8.9	84.5	51	44.1
S152	8.1	6.7	81.4	75	42.3
S153	5.8	8.7	55.1	44	27.7
S154	6.7	4.6	88.6	50	33.4
S155	2.3	8.9	92.5	40	29.7
S156	3.5	4.9	80.0	66	23.6
S157	4.7	8.8	56.1	68	33.6
S158	7.5	5.3	99.2	84	37.9
S159	3.5	4.5	89.1	78	29.5
S160	3.4	6.2	67.4	70	24.7
S161	1.8	7.6	71.4	58	25.2
S162	7.9	5.6	68.5	42	31.4
S163	3.5	7.0	75.3	54	30.0
S164	11.0	6.6	67.1	58	35.8
S165	10.5	5.9	92.5	85	40.6
S166	1.8	6.9	91.1	58	30.1
S167	3.6	5.3	55.3	84	30.3
S168	8.4	7.5	98.0	95	42.0
S169	3.4	4.0	81.8	69	32.1
S170	2.5	8.6	91.4	44	22.8
S171	11.3	6.7	85.4	83	45.3
S172	7.3	7.6	71.8	54	31.0
S173	6.2	7.7	86.7	56	31.0
S174	9.6	7.4	98.3	90	40.9
S175	9.9	5.8	63.5	90	44.8
S176	3.1	4.3	90.4	80	34.4
S177	2.1	7.3	76.9	77	30.7
S178	5.7	5.7	74.2	82	31.0
S179	5.7	5.6	71.8	91	35.0
S180	6.1	8.2	86.6	52	31.4
S181	9.0	7.6	63.4	67	38.4
S182	8.4	5.5	92.6	47	36.1
S183	11.8	5.5	91.5	74	44.1
S184	2.1	6.0	54.3	54	19.4
S185	5.4	6.0	94.1	81	39.4
S186	4.7	5.5	62.2	49	22.9
S187	10.5	4.6	73.2	57	36.2
S188	3.7	6.1	80.5	92	33.4
S189	3.1	8.7	68.9	49	23.4
S190	5.9	7.4	51.4	44	28.0
S191	5.6	8.5	92.5	43	32.2
S192	4.1	7.1	59.1	50	30.7
S193	3.7	5.5	60.6	90	28.8
S194	11.2	6.7	89.9	59	46.7
S195	5.9	4.0	67.0	78	33.8
S196	10.5	5.4	94.0	87	42.7
S197	7.1	6.1	85.1	92	40.4
S198	1.6	6.9	63.8	76	28.2
S199	12.0	7.3	50.5	58	42.0
S200	10.2	6.3	97.4	68	37.8

tabuľka s formatovanim

library(knitr)

kable(Vysledky[1:10, ],        # napr. len prvých 10 riadkov
      caption = "Výsledky študentov z testov",
      align = "c")            # zarovnanie na stred

Výsledky študentov z testov

student_id	hours_studied	sleep_hours	attendance_percent	previous_scores	exam_score
S001	8.0	8.8	72.1	45	30.2
S002	1.3	8.6	60.7	55	25.0
S003	4.0	8.2	73.7	86	35.8
S004	3.5	4.8	95.1	66	34.0
S005	9.1	6.4	89.8	71	40.3
S006	8.4	5.1	58.5	75	35.7
S007	10.8	6.0	54.2	88	37.9
S008	2.0	4.3	75.8	55	18.3
S009	5.6	5.9	81.6	84	34.7
S010	1.3	8.9	66.8	70	24.7

tabuľka 2

library(knitr)

kable(Vysledky[1:10, ],        # napr. len prvých 10 riadkov
      caption = "Výsledky študentov z testov",
      align = "c")            # zarovnanie na stred

Výsledky študentov z testov

student_id	hours_studied	sleep_hours	attendance_percent	previous_scores	exam_score
S001	8.0	8.8	72.1	45	30.2
S002	1.3	8.6	60.7	55	25.0
S003	4.0	8.2	73.7	86	35.8
S004	3.5	4.8	95.1	66	34.0
S005	9.1	6.4	89.8	71	40.3
S006	8.4	5.1	58.5	75	35.7
S007	10.8	6.0	54.2	88	37.9
S008	2.0	4.3	75.8	55	18.3
S009	5.6	5.9	81.6	84	34.7
S010	1.3	8.9	66.8	70	24.7

farebná tabuľka

# Pekná ružová tabuľka
kable(udaje2[1:10, ],                       # napríklad len prvých 10 riadkov
      caption = "💗 Výsledky študentov z testov") %>%
  kable_styling(
    bootstrap_options = c("striped", "hover", "condensed", "responsive"),
    full_width = FALSE,
    position = "center"
  ) %>%
  row_spec(0, bold = TRUE, color = "white", background = "#E75480") %>%   # ružový header
  row_spec(1:nrow(udaje2[1:10, ]), background = "#ffe6f2") %>%            # svetloružové riadky
  column_spec(1, bold = TRUE, color = "#E75480")                          # prvý stĺpec ružovo zvýraznený

💗 Výsledky študentov z testov

student_id	hours_studied	sleep_hours	attendance_percent	previous_scores	exam_score	hours_category	hours_group
S001	8.0	8.8	72.1	45	30.2	Medium	High
S002	1.3	8.6	60.7	55	25.0	Low	Low
S003	4.0	8.2	73.7	86	35.8	Low	Low
S004	3.5	4.8	95.1	66	34.0	Low	Low
S005	9.1	6.4	89.8	71	40.3	High	High
S006	8.4	5.1	58.5	75	35.7	High	High
S007	10.8	6.0	54.2	88	37.9	High	High
S008	2.0	4.3	75.8	55	18.3	Low	Low
S009	5.6	5.9	81.6	84	34.7	Medium	Low
S010	1.3	8.9	66.8	70	24.7	Low	Low

orámovanie

library(knitr)
library(kableExtra)

kable(udaje2[1:10, ],
      caption = "💗 Výsledky študentov z testov") %>%
  kable_styling(
    full_width = FALSE,
    position = "center",
    bootstrap_options = c("condensed", "responsive"),
    htmltable_class = "table table-bordered"
  ) %>%
  row_spec(0, bold = TRUE, color = "white", background = "#E75480") %>%  # ružový header
  row_spec(1:nrow(udaje2[1:10, ]), background = "#fff0f6")               # svetloružové riadky

💗 Výsledky študentov z testov

student_id	hours_studied	sleep_hours	attendance_percent	previous_scores	exam_score	hours_category	hours_group
S001	8.0	8.8	72.1	45	30.2	Medium	High
S002	1.3	8.6	60.7	55	25.0	Low	Low
S003	4.0	8.2	73.7	86	35.8	Low	Low
S004	3.5	4.8	95.1	66	34.0	Low	Low
S005	9.1	6.4	89.8	71	40.3	High	High
S006	8.4	5.1	58.5	75	35.7	High	High
S007	10.8	6.0	54.2	88	37.9	High	High
S008	2.0	4.3	75.8	55	18.3	Low	Low
S009	5.6	5.9	81.6	84	34.7	Medium	Low
S010	1.3	8.9	66.8	70	24.7	Low	Low

Tabuľka zobrazuje údaje o študentoch – počet hodín štúdia, spánku, percento účasti, predchádzajúce skóre a výsledok skúšky. Použitá je ružová farebná schéma s orámovaním pre lepšiu čitateľnosť.

stĺpcový graf

# Top 10 študentov podľa exam_score
Vysledky %>%
  slice_max(order_by = exam_score, n = 10) %>%
  ggplot(aes(x = reorder(student_id, exam_score), y = exam_score, fill = exam_score)) +
  geom_col(color = "white", width = 0.7) +               # biely obrys stĺpcov
  coord_flip() +                                         # horizontálny graf
  scale_fill_gradient(low = "#f8c6c9", high = "#800020") + # burgundy škála
  labs(
    title = "💗 Výsledky študentov z testov",
    x = "Študent",
    y = "Skóre",
    fill = "Skóre"
  ) +
  theme_minimal(base_size = 14) +
  theme(
    plot.title = element_text(face = "bold", hjust = 0.5),
    axis.text.x = element_text(color = "#4d0012"),
    axis.text.y = element_text(color = "#4d0012")
  )

Graf zobrazuje skóre študentov v testoch. Každý stĺpec predstavuje jedného študenta. Tmavšia burgundy farba označuje vyššie skóre, svetlejšia nižšie. Graf umožňuje rýchlo identifikovať najúspešnejších študentov.

HeatMap

library(ggplot2)
library(dplyr)
library(tidyr)
library(reshape2)

# Vyberieme len číselné stĺpce z datasetu
numeric_data <- Vysledky %>%
  select(hours_studied, sleep_hours, attendance_percent, previous_scores, exam_score)

# Spočítame korelačnú maticu
cor_matrix <- cor(numeric_data, use = "complete.obs")

# Premeníme korelačnú maticu do tvaru vhodného pre ggplot
cor_data <- melt(cor_matrix)

# Vytvoríme heatmapu s burgundy škálou 💗
ggplot(cor_data, aes(x = Var1, y = Var2, fill = value)) +
  geom_tile(color = "white", linewidth = 0.8) +
  scale_fill_gradient2(
    low = "#f8c6c9", mid = "white", high = "#800020",
    midpoint = 0, limits = c(-1, 1)
  ) +
  geom_text(aes(label = round(value, 2)), color = "#4d0012", size = 4) +
  labs(
    title = "💗 Korelačná heatmapa – výsledky študentov",
    x = "",
    y = "",
    fill = "Korelácia"
  ) +
  theme_minimal(base_size = 14) +
  theme(
    plot.title = element_text(face = "bold", hjust = 0.5),
    axis.text.x = element_text(angle = 45, hjust = 1, color = "#4d0012"),
    axis.text.y = element_text(color = "#4d0012")
  )

Heatmapa zobrazuje korelácie medzi číselnými premennými datasetu.Tmavšia farba znamená silnejšiu pozitívnu koreláciu,svetloružová slabšiu alebo negatívnu.Z grafu možno vidieť,že počet hodín štúdia súvisí s vyšším skóre na skúške.