Práca s databázou
Nina Majdáková
2025-10-11
data<- read.csv("student_exam_scores.csv",check.names=FALSE)head(data)## student_id hours_studied sleep_hours attendance_percent previous_scores
## 1 S001 8.0 8.8 72.1 45
## 2 S002 1.3 8.6 60.7 55
## 3 S003 4.0 8.2 73.7 86
## 4 S004 3.5 4.8 95.1 66
## 5 S005 9.1 6.4 89.8 71
## 6 S006 8.4 5.1 58.5 75
## exam_score
## 1 30.2
## 2 25.0
## 3 35.8
## 4 34.0
## 5 40.3
## 6 35.7summary(data)## student_id hours_studied sleep_hours attendance_percent
## Length:200 Min. : 1.000 Min. :4.000 Min. : 50.30
## Class :character 1st Qu.: 3.500 1st Qu.:5.300 1st Qu.: 62.20
## Mode :character Median : 6.150 Median :6.700 Median : 75.25
## Mean : 6.325 Mean :6.622 Mean : 74.83
## 3rd Qu.: 9.000 3rd Qu.:8.025 3rd Qu.: 87.42
## Max. :12.000 Max. :9.000 Max. :100.00
## previous_scores exam_score
## Min. :40.0 Min. :17.10
## 1st Qu.:54.0 1st Qu.:29.50
## Median :67.5 Median :34.05
## Mean :66.8 Mean :33.95
## 3rd Qu.:80.0 3rd Qu.:38.75
## Max. :95.0 Max. :51.30viac5<-subset(data,hours_studied > 5) #viac ako 5hod ucenia
print(viac5)## student_id hours_studied sleep_hours attendance_percent previous_scores
## 1 S001 8.0 8.8 72.1 45
## 5 S005 9.1 6.4 89.8 71
## 6 S006 8.4 5.1 58.5 75
## 7 S007 10.8 6.0 54.2 88
## 9 S009 5.6 5.9 81.6 84
## 12 S012 6.6 7.9 87.6 85
## 15 S015 8.1 8.8 60.0 90
## 16 S016 7.0 9.0 51.2 41
## 18 S018 7.5 7.6 73.8 58
## 19 S019 9.9 4.8 92.5 54
## 21 S021 9.9 8.8 70.7 84
## 22 S022 8.7 6.9 81.5 55
## 25 S025 11.5 4.3 74.7 77
## 29 S029 10.3 4.8 87.5 73
## 30 S030 7.6 8.8 88.5 62
## 31 S031 9.9 4.4 55.3 67
## 32 S032 9.0 4.9 71.3 87
## 33 S033 6.9 7.0 58.8 75
## 34 S034 11.7 7.4 97.9 61
## 35 S035 5.2 5.2 75.9 62
## 36 S036 7.1 4.6 52.5 84
## 37 S037 10.1 8.5 62.5 69
## 38 S038 7.8 5.2 92.4 57
## 39 S039 10.5 7.0 72.8 59
## 40 S040 7.4 7.1 90.1 56
## 41 S041 8.8 6.1 83.4 54
## 49 S049 8.0 7.4 91.5 88
## 51 S051 5.1 5.6 94.9 51
## 54 S054 11.3 6.3 63.0 87
## 55 S055 8.1 9.0 62.4 70
## 56 S056 7.7 9.0 81.9 57
## 58 S058 9.0 5.1 76.1 77
## 60 S060 5.2 8.7 63.7 73
## 61 S061 11.9 8.4 53.9 78
## 62 S062 8.0 8.4 64.3 58
## 63 S063 7.1 5.8 63.6 46
## 64 S064 8.5 4.8 66.0 93
## 65 S065 10.3 8.2 77.0 52
## 66 S066 9.5 7.5 56.9 58
## 72 S072 11.4 5.5 77.1 85
## 73 S073 10.6 7.3 70.8 74
## 75 S075 8.2 4.7 71.0 57
## 76 S076 5.4 4.6 95.2 42
## 77 S077 11.1 4.5 79.2 43
## 78 S078 6.0 6.8 84.8 75
## 81 S081 7.2 7.6 69.0 48
## 83 S083 7.4 7.2 67.6 95
## 84 S084 10.9 5.3 87.7 88
## 85 S085 5.4 6.4 92.7 71
## 87 S087 12.0 8.2 71.0 95
## 88 S088 6.6 4.5 87.4 40
## 92 S092 7.9 7.9 61.0 70
## 93 S093 9.7 7.2 71.8 68
## 94 S094 5.6 5.3 51.5 61
## 96 S096 5.2 6.8 84.0 43
## 97 S097 12.0 6.1 70.2 56
## 98 S098 6.8 4.0 58.3 95
## 99 S099 11.7 4.4 73.4 70
## 100 S100 10.5 8.4 56.4 47
## 102 S102 8.9 6.7 51.3 44
## 103 S103 8.5 8.2 69.7 65
## 104 S104 6.9 6.9 78.2 71
## 106 S106 8.1 4.6 82.1 76
## 108 S108 5.8 8.5 73.1 83
## 109 S109 6.0 8.0 52.5 43
## 110 S110 11.5 8.3 69.0 49
## 111 S111 10.6 8.5 60.6 49
## 113 S113 6.5 5.2 88.1 76
## 115 S115 11.0 7.9 87.6 45
## 116 S116 10.6 8.4 91.6 55
## 118 S118 8.0 7.1 54.1 75
## 119 S119 7.7 4.8 51.0 88
## 121 S121 9.4 8.3 100.0 78
## 122 S122 6.9 8.9 67.5 78
## 123 S123 9.6 8.1 82.5 90
## 124 S124 6.8 8.4 89.1 79
## 128 S128 11.2 8.7 60.0 64
## 129 S129 10.7 8.0 51.0 68
## 130 S130 10.1 8.3 57.6 68
## 133 S133 10.7 7.9 78.2 77
## 134 S134 11.4 4.5 60.9 67
## 136 S136 6.3 8.3 88.3 76
## 138 S138 9.4 8.1 80.4 43
## 139 S139 9.4 6.3 87.4 79
## 141 S141 6.2 8.0 91.0 46
## 142 S142 7.0 5.1 98.2 88
## 144 S144 10.6 5.0 51.3 80
## 145 S145 5.7 5.6 65.6 53
## 147 S147 6.9 8.8 97.9 82
## 148 S148 9.0 5.4 69.8 45
## 151 S151 11.9 8.9 84.5 51
## 152 S152 8.1 6.7 81.4 75
## 153 S153 5.8 8.7 55.1 44
## 154 S154 6.7 4.6 88.6 50
## 158 S158 7.5 5.3 99.2 84
## 162 S162 7.9 5.6 68.5 42
## 164 S164 11.0 6.6 67.1 58
## 165 S165 10.5 5.9 92.5 85
## 168 S168 8.4 7.5 98.0 95
## 171 S171 11.3 6.7 85.4 83
## 172 S172 7.3 7.6 71.8 54
## 173 S173 6.2 7.7 86.7 56
## 174 S174 9.6 7.4 98.3 90
## 175 S175 9.9 5.8 63.5 90
## 178 S178 5.7 5.7 74.2 82
## 179 S179 5.7 5.6 71.8 91
## 180 S180 6.1 8.2 86.6 52
## 181 S181 9.0 7.6 63.4 67
## 182 S182 8.4 5.5 92.6 47
## 183 S183 11.8 5.5 91.5 74
## 185 S185 5.4 6.0 94.1 81
## 187 S187 10.5 4.6 73.2 57
## 190 S190 5.9 7.4 51.4 44
## 191 S191 5.6 8.5 92.5 43
## 194 S194 11.2 6.7 89.9 59
## 195 S195 5.9 4.0 67.0 78
## 196 S196 10.5 5.4 94.0 87
## 197 S197 7.1 6.1 85.1 92
## 199 S199 12.0 7.3 50.5 58
## 200 S200 10.2 6.3 97.4 68
## exam_score
## 1 30.2
## 5 40.3
## 6 35.7
## 7 37.9
## 9 34.7
## 12 35.1
## 15 41.1
## 16 34.1
## 18 36.3
## 19 35.6
## 21 46.0
## 22 36.1
## 25 39.2
## 29 37.2
## 30 36.2
## 31 34.5
## 32 41.6
## 33 38.1
## 34 42.7
## 35 32.0
## 36 32.0
## 37 44.7
## 38 38.3
## 39 39.8
## 40 35.0
## 41 34.2
## 49 41.2
## 51 28.8
## 54 46.4
## 55 34.4
## 56 37.0
## 58 38.2
## 60 29.2
## 61 48.6
## 62 36.1
## 63 27.1
## 64 36.1
## 65 39.5
## 66 36.7
## 72 47.9
## 73 41.9
## 75 33.5
## 76 26.3
## 77 39.9
## 78 40.3
## 81 30.8
## 83 39.8
## 84 48.9
## 85 38.0
## 87 51.3
## 88 28.6
## 92 34.0
## 93 37.5
## 94 29.1
## 96 28.7
## 97 36.9
## 98 36.0
## 99 39.9
## 100 37.1
## 102 31.3
## 103 35.7
## 104 32.6
## 106 38.2
## 108 39.2
## 109 23.2
## 110 42.2
## 111 39.6
## 113 34.6
## 115 43.1
## 116 46.4
## 118 31.3
## 119 35.8
## 121 47.9
## 122 40.9
## 123 44.1
## 124 39.3
## 128 42.7
## 129 36.1
## 130 39.2
## 133 45.7
## 134 40.8
## 136 41.1
## 138 35.1
## 139 39.9
## 141 35.0
## 142 43.3
## 144 35.1
## 145 29.9
## 147 45.8
## 148 35.5
## 151 44.1
## 152 42.3
## 153 27.7
## 154 33.4
## 158 37.9
## 162 31.4
## 164 35.8
## 165 40.6
## 168 42.0
## 171 45.3
## 172 31.0
## 173 31.0
## 174 40.9
## 175 44.8
## 178 31.0
## 179 35.0
## 180 31.4
## 181 38.4
## 182 36.1
## 183 44.1
## 185 39.4
## 187 36.2
## 190 28.0
## 191 32.2
## 194 46.7
## 195 33.8
## 196 42.7
## 197 40.4
## 199 42.0
## 200 37.8top10 <-data[order(-data$exam_score), ][1:10, c("student_id","hours_studied","exam_score")]
#top 10 najlepších výsledkov z exam score
top10## student_id hours_studied exam_score
## 87 S087 12.0 51.3
## 84 S084 10.9 48.9
## 61 S061 11.9 48.6
## 72 S072 11.4 47.9
## 121 S121 9.4 47.9
## 194 S194 11.2 46.7
## 54 S054 11.3 46.4
## 116 S116 10.6 46.4
## 21 S021 9.9 46.0
## 147 S147 6.9 45.8mean(data$exam_score, na.rm = TRUE) #priemerne skuskove skore## [1] 33.955mean(data$hours_studied, na.rm = TRUE) # priemerne hodiny ucenia## [1] 6.3255priemer <- mean(data$exam_score, na.rm = TRUE)
data$above_average <- data$exam_score >= priemer
head(data[, c("exam_score","above_average")])## exam_score above_average
## 1 30.2 FALSE
## 2 25.0 FALSE
## 3 35.8 TRUE
## 4 34.0 TRUE
## 5 40.3 TRUE
## 6 35.7 TRUE#ci ma student nadpriemerne skorehist(data$exam_score,
main = "Rozdelenie skúškového skóre",
xlab = "exam_score")