PROJECT

HASAN ALI

2025-05-23

READING CSV FILE COMPUTER

data <- read.csv("C:/Users/Administrator/Desktop/computers.csv")

HEAD AND TAIL OF THE DATA

head(data)

## X price speed hd ram screen cd multi premium ads trend

## 1 1 1499 25 80 4 14 no no yes 94 1
## 2 2 1795 33 85 2 14 no no yes 94 1
## 3 3 1595 25 170 4 15 no no yes 94 1
## 4 4 1849 25 170 8 14 no no no 94 1
## 5 5 3295 33 340 16 14 no no yes 94 1
## 6 6 3695 66 340 16 14 no no yes 94 1

tail(data)

## X price speed hd ram screen cd multi premium ads trend

## 6254 6254 2154 66 850 16 15 yes no yes 39 35
## 6255 6255 1690 100 528 8 15 no no yes 39 35
## 6256 6256 2223 66 850 16 15 yes yes yes 39 35
## 6257 6257 2654 100 1200 24 15 yes no yes 39 35
## 6258 6258 2195 100 850 16 15 yes no yes 39 35
## 6259 6259 2490 100 850 16 17 yes no yes 39 35

STRUCTURE OF THE DATA

str(data)

## 'data.frame': 6259 obs. of 11 variables:

## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ price : int 1499 1795 1595 1849 3295 3695 1720 1995 2225 2575 ...
## $ speed : int 25 33 25 25 33 66 25 50 50 50 ...
## $ hd : int 80 85 170 170 340 340 170 85 210 210 ...
## $ ram : int 4 2 4 8 16 16 4 2 8 4 ...
## $ screen : int 14 14 15 14 14 14 14 14 14 15 ...
## $ cd : chr "no" "no" "no" "no" ...
## $ multi : chr "no" "no" "no" "no" ...
## $ premium: chr "yes" "yes" "yes" "no" ...
## $ ads : int 94 94 94 94 94 94 94 94 94 94 ...
## $ trend : int 1 1 1 1 1 1 1 1 1 1 ...

MAX,MIN OF THE DATA

max(data$ads) max(data$hd) min(data$trend)

## [1] 339 ## [1] 2100 ## [1] 1

max(data$premium) max(data$speed) min(data$screen)

## [1] "yes" ## [1] 100 ## [1] 14

max(data$multi) max(data$price) min(data$ram)

## [1] "yes" ## [1] 5399 ## [1] 2

max(data$cd) min(data$ads) min(data$hd)

## [1] "yes" ## [1] 39 ## [1] 80

max(data$trend) min(data$premium) min(data$speed)

## [1] 35 ## [1] "no" ## [1] 25

max(data$screen) min(data$multi) min(data$price)

## [1] 17 ## [1] "no" ## [1] 949

max(data$ram) min(data$cd)

## [1] 32 ## [1] "no"

SUMMARY OF THE DATA

summary(data)

## X price speed hd
## Min. : 1 Min. : 949 Min. : 25.00 Min. : 80.0
## 1st Qu.:1566 1st Qu.:1794 1st Qu.: 33.00 1st Qu.: 214.0
## Median :3130 Median :2144 Median : 50.00 Median : 340.0
## Mean :3130 Mean :2220 Mean : 52.01 Mean : 416.6
## 3rd Qu.:4694 3rd Qu.:2595 3rd Qu.: 66.00 3rd Qu.: 528.0
## Max. :6259 Max. :5399 Max. :100.00 Max. :2100.0
## ram screen cd multi
## Min. : 2.000 Min. :14.00 Length:6259 Length:6259
## 1st Qu.: 4.000 1st Qu.:14.00 Class :character Class :character
## Median : 8.000 Median :14.00 Mode :character Mode :character
## Mean : 8.287 Mean :14.61
## 3rd Qu.: 8.000 3rd Qu.:15.00
## Max. :32.000 Max. :17.00

## premium ads trend

## Length:6259 Min. : 39.0 Min. : 1.00
## Class :character 1st Qu.:162.5 1st Qu.:10.00
## Mode :character Median :246.0 Median :16.00
## Mean :221.3 Mean :15.93
## 3rd Qu.:275.0 3rd Qu.:21.50
## Max. :339.0 Max. :35.00

ALL MEDIANS OF COMPUTER DATA

median(data$trend) ## [1] "no" median(data$hd)

## [1] 16 median(data$cd) ## [1] 340

median(data$ads) ## [1] "no" median(data$speed)

## [1] 246 median(data$screen) ## [1] 50

median(data$premium) ## [1] 14 median(data$price)

## [1] "yes" median(data$ram) ## [1] 2144

median(data$multi) ## [1] 8

ALL MEANS OF COMPUTER DATA

mean(data$trend) mean(data$ram) mean(data$price)

## [1] 15.92699 ## [1] 8.286947 ## [1] 2219.577

mean(data$ads) mean(data$speed)

## [1] 221.301 ## [1] 52.01102

ALL VARIENCE OF COMPUTER DATA

var(data$trend) ## [1] 0.8192336 var(data$speed)

## [1] 61.99962 var(data$ram) ## [1] 447.6498

var(data$ads) ## [1] 31.70928 var(data$price)

## [1] 5600.32 var(data$hd) ## [1] 337333.2

var(data$screen) ## [1] 66847.3

ALL STANDARD DEVIATION OF COMPUTER DATA

sd(data$trend) ## [1] 0.9051152 sd(data$speed)

## [1] 7.873984 sd(data$ram) ## [1] 21.15774

sd(data$ads) ## [1] 5.631099 sd(data$price)

## [1] 74.83528 sd(data$hd) ## [1] 580.804

sd(data$screen) ## [1] 258.5484

ALL QUANTILE OF COMPUTER DATA

quantile(data$trend) ## 0% 25% 50% 75% 100%

## 2 4 8 8 32
## 0% 25% 50% 75% 100%
## 1.0 10.0 16.0 21.5 35.0 quantile(data$hd)

quantile(data$ads) ## 0% 25% 50% 75% 100%

## 80 214 340 528 2100
## 0% 25% 50% 75% 100%
## 39.0 162.5 246.0 275.0 339.0 quantile(data$speed)

quantile(data$screen) ## 0% 25% 50% 75% 100%

## 25 33 50 66 100
## 0% 25% 50% 75% 100%
## 14 14 14 15 17 quantile(data$price)

quantile(data$ram) ## 0% 25% 50% 75% 100%

## 949 1794 2144 2595 5399
DNORM,PNORM,QNORM,RNORM

x <- 60
mean <- 50
sd <- 10

dnorm(x, mean, sd)

## [1] 0.02419707

pnorm(60, mean = 50, sd = 10)

## [1] 0.8413447

qnorm(0.84, mean = 50, sd = 10)

## [1] 59.94458

rnorm(5, mean = 50, sd = 10)

## [1] 42.32504 44.71815 56.17285 51.72030 28.35400

DIMENTION of COMPUTER DATA

dim(data)

## [1] 6259 11

NUMBER OF ROWS of COMPUTER DATA

nrow(data)

## [1] 6259

NUMBER OF COLUMNS of COMPUTER DATA

ncol(data)

## [1] 11

ALL TABLES of COMPUTER DATA

table(data$speed)

##
## 25 33 50 66 75 100
## 566 2033 994 2028 122 516

table(data$trend)

##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
## 94 95 100 108 139 176 249 298 246 283 259 275 216 292 267 307 339 273 225 248
## 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
## 205 162 191 182 158 152 163 132 129 75 52 51 40 39 39

table(data$screen)

##
## 14 15 17
## 3661 1992 606

table(data$ram)

##
## 2 4 8 16 24 32
## 394 2236 2320 996 297 16

table(data$price)

##
## 949 999 1049 1088 1099 1119 1139 1149 1175 1195 1199 1238 1239 1245 1249 1259
## 1 4 2 1 2 1 1 3 1 21 26 2 1 3 5 2
## 1260 1268 1275 1279 1288 1290 1295 1299 1329 1339 1344 1345 1349 1354 1359 1368
## 1 3 2 2 4 9 30 45 1 1 4 13 8 5 5 3
## 1369 1375 1379 1388 1389 1390 1395 1398 1399 1404 1408 1418 1425 1429 1430 1438
## 4 2 6 1 1 11 68 6 43 3 4 2 2 1 1 1
## 1440 1444 1445 1448 1449 1454 1459 1465 1468 1469 1470 1475 1479 1488 1489 1490
## 5 7 14 3 13 7 1 3 6 8 2 6 2 5 4 36
## 1494 1495 1498 1499 1500 1504 1509 1515 1518 1519 1520 1525 1528 1529 1535 1538
## 8 69 1 68 1 5 4 2 1 2 3 2 1 6 1 1
## 1539 1540 1544 1545 1548 1549 1550 1554 1555 1558 1559 1567 1568 1569 1570 1574
## 4 7 22 16 4 6 1 10 1 2 13 1 4 1 2 3
## 1575 1578 1579 1580 1588 1589 1590 1594 1595 1598 1599 1604 1605 1608 1609 1615
## 4 3 9 2 2 5 44 19 57 2 58 7 1 1 1 2
## 1618 1619 1625 1628 1629 1635 1638 1639 1640 1644 1645 1648 1649 1654 1655 1659
## 5 2 6 2 2 2 1 4 12 31 20 1 6 7 2 6
## 1660 1666 1667 1669 1670 1675 1679 1680 1682 1685 1688 1689 1690 1694 1695 1698
## 1 1 1 3 2 5 6 2 1 1 2 6 38 15 59 4
## 1699 1704 1705 1708 1709 1715 1718 1719 1720 1723 1724 1725 1728 1729 1730 1735
## 46 12 1 3 5 1 3 2 7 4 4 8 3 2 1 4
## 1738 1739 1740 1744 1745 1748 1749 1754 1755 1758 1759 1765 1768 1769 1773 1775
## 1 3 19 32 16 5 24 7 2 2 6 4 1 5 5 8
## 1778 1779 1784 1785 1788 1789 1790 1794 1795 1797 1798 1799 1804 1805 1808 1809
## 3 5 1 1 2 7 52 22 82 1 6 57 10 1 7 3
## 1810 1813 1815 1818 1819 1823 1824 1825 1828 1829 1835 1838 1839 1840 1844 1845
## 1 1 1 9 7 7 4 6 5 6 1 2 5 14 34 14
## 1848 1849 1854 1855 1858 1859 1865 1868 1870 1873 1875 1878 1879 1880 1881 1885
## 7 11 13 2 2 3 9 1 1 7 4 1 6 1 1 4
## 1888 1889 1890 1891 1893 1894 1895 1898 1899 1904 1908 1909 1914 1915 1918 1919
## 2 3 73 1 2 29 47 7 69 7 9 1 1 2 3 1
## 1920 1923 1925 1928 1929 1935 1938 1939 1940 1943 1944 1945 1948 1949 1950 1954
## 4 5 13 1 10 1 3 7 16 2 45 23 3 8 2 1
## 1955 1958 1960 1964 1965 1968 1969 1970 1973 1974 1975 1979 1982 1983 1985 1988
## 1 1 1 2 2 1 6 4 3 5 14 2 1 1 1 1
## 1989 1990 1993 1994 1995 1998 1999 2004 2009 2014 2015 2018 2019 2020 2024 2025
## 9 32 1 23 78 9 103 9 1 2 7 2 4 1 5 6
## 2029 2035 2039 2040 2044 2045 2048 2049 2050 2054 2055 2058 2059 2063 2065 2069
## 5 4 8 15 42 13 3 15 1 5 4 5 11 1 6 1
## 2075 2078 2079 2088 2090 2093 2094 2095 2098 2099 2100 2104 2105 2108 2109 2115
## 11 2 3 1 64 5 21 62 3 39 1 5 1 4 6 3
## 2118 2119 2120 2124 2125 2127 2128 2129 2134 2135 2138 2139 2140 2143 2144 2145
## 8 1 8 7 10 2 1 2 2 2 3 2 4 4 35 19
## 2148 2149 2154 2155 2158 2159 2164 2165 2168 2170 2174 2175 2179 2182 2185 2189
## 3 5 13 4 1 6 1 3 2 4 1 6 3 1 5 8
## 2190 2194 2195 2197 2198 2199 2204 2208 2209 2214 2215 2218 2219 2220 2223 2224
## 60 14 67 1 6 36 6 6 1 1 4 3 4 9 9 4
## 2225 2228 2229 2238 2239 2240 2243 2244 2245 2248 2249 2250 2254 2255 2258 2259
## 13 1 2 2 1 6 5 44 11 5 11 1 10 2 2 12
## 2265 2268 2273 2274 2275 2279 2285 2290 2294 2295 2298 2299 2304 2305 2308 2309
## 4 2 5 2 4 2 5 55 22 49 3 32 6 1 8 2
## 2315 2318 2319 2320 2323 2325 2328 2329 2334 2335 2338 2339 2340 2343 2344 2345
## 4 4 4 6 7 10 3 6 1 5 3 4 9 6 49 18
## 2348 2349 2354 2355 2358 2359 2364 2365 2369 2373 2374 2375 2378 2379 2384 2385
## 4 5 7 4 1 8 4 4 2 4 3 5 2 1 1 4
## 2388 2389 2390 2393 2394 2395 2397 2398 2399 2404 2405 2408 2409 2414 2415 2417
## 1 2 57 2 13 42 1 2 32 10 7 3 1 1 3 1
## 2419 2420 2423 2425 2427 2429 2435 2439 2440 2443 2444 2445 2448 2449 2454 2455
## 2 7 3 19 5 2 1 3 13 4 37 5 1 10 4 6
## 2459 2465 2469 2470 2473 2475 2478 2479 2485 2489 2490 2493 2494 2495 2498 2499
## 1 3 6 3 5 7 1 4 2 2 44 5 17 58 3 34
## 2504 2505 2509 2515 2520 2525 2529 2534 2535 2539 2540 2543 2544 2545 2549 2550
## 4 1 4 2 3 6 3 2 2 2 9 5 27 14 2 3
## 2554 2555 2558 2559 2563 2565 2568 2569 2574 2575 2578 2579 2585 2589 2590 2593
## 10 2 2 4 1 4 3 4 1 7 1 1 1 1 57 7
## 2594 2595 2598 2599 2604 2605 2608 2609 2615 2618 2620 2623 2625 2627 2628 2629
## 16 57 5 23 5 4 1 5 2 2 4 6 4 5 2 4
## 2630 2634 2635 2640 2643 2644 2645 2648 2649 2654 2658 2665 2669 2673 2674 2675
## 1 3 2 4 6 36 15 2 1 9 1 1 6 4 2 4
## 2685 2688 2690 2693 2694 2695 2698 2699 2704 2705 2715 2718 2720 2723 2725 2729
## 2 3 53 2 14 20 3 30 1 2 1 2 6 6 1 2
## 2738 2740 2743 2744 2745 2749 2754 2755 2758 2768 2769 2773 2774 2775 2779 2784
## 1 7 3 52 15 4 3 1 1 1 6 1 1 7 3 1
## 2785 2790 2794 2795 2798 2799 2804 2805 2815 2818 2819 2825 2830 2834 2840 2844
## 5 24 15 33 1 35 8 1 8 4 6 1 1 3 12 25
## 2845 2848 2849 2854 2855 2859 2868 2869 2873 2875 2885 2889 2890 2893 2894 2895
## 16 1 4 7 1 1 1 4 3 3 2 4 47 2 6 19
## 2898 2899 2904 2905 2915 2924 2925 2927 2929 2935 2938 2940 2943 2944 2945 2949
## 5 19 6 2 2 1 1 2 8 1 1 9 8 21 7 1
## 2954 2955 2969 2970 2975 2985 2988 2989 2990 2993 2994 2995 2998 2999 3004 3015
## 2 1 1 3 4 5 3 4 22 3 12 46 1 38 3 4
## 3019 3025 3029 3035 3039 3040 3043 3044 3045 3048 3049 3054 3055 3065 3075 3078
## 4 2 2 1 1 7 2 25 3 4 2 5 1 2 2 1
## 3085 3089 3090 3093 3094 3095 3097 3098 3099 3104 3105 3108 3115 3123 3125 3127
## 1 4 32 3 11 9 1 1 7 3 1 2 1 3 2 1
## 3129 3135 3140 3143 3144 3145 3148 3149 3154 3158 3165 3169 3175 3188 3189 3190
## 6 2 6 2 17 2 1 5 2 1 1 1 2 1 1 11
## 3193 3194 3195 3198 3199 3204 3205 3208 3220 3225 3229 3239 3240 3243 3244 3249
## 3 9 2 3 6 1 2 2 3 1 4 8 3 2 15 2
## 3265 3275 3290 3293 3294 3295 3299 3304 3315 3319 3334 3340 3344 3345 3348 3349
## 1 1 5 2 4 4 8 3 1 1 7 1 2 1 3 4
## 3354 3358 3365 3379 3385 3390 3394 3395 3397 3398 3399 3415 3439 3440 3443 3454
## 2 2 2 4 2 5 2 4 5 1 6 1 4 3 1 3
## 3485 3490 3495 3499 3515 3540 3543 3544 3564 3565 3589 3594 3595 3599 3609 3628
## 2 5 10 6 5 1 3 5 2 1 2 1 9 7 3 2
## 3634 3644 3649 3659 3670 3678 3694 3695 3699 3708 3714 3720 3745 3749 3768 3778
## 1 3 1 4 1 1 1 3 3 1 2 3 1 1 1 1
## 3789 3790 3794 3795 3799 3814 3849 3872 3890 3895 3899 3904 3914 3928 3948 3984
## 4 1 1 7 4 1 1 1 1 9 6 2 1 2 2 2
## 3990 3994 3995 3999 4020 4048 4095 4098 4104 4188 4195 4248 4292 4295 4348 4395
## 3 1 5 4 3 1 2 1 1 1 1 3 1 1 2 2
## 4398 4494 4495 4594 4694 4799 4999 5399
## 1 1 1 1 1 1 2 3

table(data$hd)

##
## 80 85 100 107 120 125 128 130 170 200 210 212 213 214 230 240
## 10 25 6 377 183 4 1 71 207 5 109 306 10 556 30 36
## 245 250 256 260 270 320 330 340 345 364 365 405 420 424 425 426
## 129 220 1 1 73 12 4 764 32 18 6 5 180 119 103 383
## 428 450 452 470 500 520 525 527 528 530 540 545 630 720 728 730
## 64 51 88 1 25 1 2 103 674 16 224 140 2 158 13 81
## 810 850 1000 1060 1080 1100 1200 1260 1370 1600 2100
## 1 140 372 2 14 6 65 1 10 16 3

table(data$ads)

##
## 39 40 51 52 75 94 95 100 108 129 132 139 152 158 162 163 176 182 191 205
## 78 40 51 52 75 94 95 100 108 129 132 139 152 158 162 163 176 182 191 205
## 216 225 246 248 249 259 267 273 275 283 292 298 307 339
## 216 225 246 248 249 259 267 273 275 283 292 298 307 339

table(data$premium)

##
## no yes
## 612 5647

table(data$multi)

##
## no yes
## 5386 873

table(data$cd)

##
## no yes
## 3351 2908
CHECK NON-NUMERIC COLUMNS

sapply(data, class)

## X price speed hd ram screen

## "integer" "integer" "integer" "integer" "integer" "integer"

## cd multi premium ads trend

## "character" "character" "character" "integer" "integer"

GRAPHS

BARPLOTS
barplot(table(data$ram),
main = "RAM",
xlab = "RAM (GB)",
ylab = "X")

barplot(table(data$price),
main = "PRICE",
xlab = "PRICE",
ylab = "X")
barplot(table(data$price,
names.arg = data$ram),
main = "RAM vs Price",
xlab = "RAM",
ylab = "Price (PKR)")
PI CHART
pie(table(data$ram),
main = "RAM")

pie(table(data$premium),
main = "PRICE")
pie(table(data$ram,
names.arg = data$premium),
main = "RAM vs Price")

BOX PLOT
boxplot(table(data$ram),
horizontal = TRUE,
main = "RAM",
xlab = "RAM")
Overall Summary of Computer Data
About Data
The data is about computers, and different types of computers, including their price, features and a few
marketing attributes. The data will allow us to explore how components and some marketing influences
might impact the complete price of a computer.

o Price: The price of the computer in dollars.

o Speed: The speed of the processor in MHz – faster is better.
o Hard Disk (HD): How much storage space the computer has in MB.
o RAM: The memory in MB – allows for more multitasking.
o Screen: The size of the screen in inches.
o CD: The presence of a CD drive (yes or no)
o Multi: The presence of multimedia (yes or no).
o Premium: Whether it is a premium computer or not (yes or no).
o Ads: The advertising budget (the advertising budget is the same for all computers: 94).

Example
One very basic computer in the data set cost $1499, has a 25 MHz processor, an 80 MB hard drive, 4 MB
RAM and a 14 in screen. It did not have a CD drive, nor does it include multimedia, but it was labelled as a
premium product.

Data Summary

o Computers with better speed, more storage, and bigger RAM cost more.
o Some computers are marked “premium” even if they don’t have all features.
o The ad budget and trend are the same for all, so the focus is more on hardware specs.
READING CSV CS_STUDENT
data2 <- read.csv("C:/Users/Administrator/Desktop/cs_students.csv")

HEAD AND TAIL OF THE DATA2

head(data2)

## Student.ID Name Gender Age GPA Major

## 1 1 John Smith Male 21 3.5 Computer Science
## 2 2 Alice Johnson Female 20 3.2 Computer Science
## 3 3 Robert Davis Male 22 3.8 Computer Science
## 4 4 Emily Wilson Female 21 3.7 Computer Science
## 5 5 Michael Brown Male 23 3.4 Computer Science
## 6 6 Laura Lee Female 22 3.9 Computer Science

## Interested.Domain Projects Future.Career

## 1 Artificial Intelligence Chatbot Development Machine Learning Researcher
## 2 Data Science Data Analytics Data Scientist
## 3 Software Development E-commerce Website Software Engineer
## 4 Web Development Full-Stack Web App Web Developer
## 5 Cybersecurity Network Security Information Security Analyst
## 6 Machine Learning Image Recognition Machine Learning Engineer

## Python SQL Java

## 1 Strong Strong Weak
## 2 Average Strong Weak
## 3 Strong Strong Average
## 4 Weak Strong Strong
## 5 Average Weak Strong
## 6 Strong Average Weak

tail(data2)

## Student.ID Name Gender Age GPA Major

## 175 175 Matthew Hall Male 23 3.8 Computer Science
## 176 176 Elijah Davis Male 22 3.7 Computer Science
## 177 177 Emma Johnson Female 20 3.6 Computer Science
## 178 178 Liam Wilson Male 21 3.4 Computer Science
## 179 179 Sophia Johnson Female 22 3.5 Computer Science
## 180 180 Michael Brown Male 23 3.7 Computer Science
## Interested.Domain Projects
## 175 Artificial Intelligence Natural Language Processing
## 176 Web Development Full-Stack Web App
## 177 Cybersecurity Security Auditing
## 178 Machine Learning Natural Language Processing
## 179 Database Management SQL Database Administration
## 180 Cloud Computing Cloud Solution Architecture
## Future.Career Python SQL Java
## 175 NLP Research Scientist Strong Weak Weak
## 176 Web Developer Weak Strong Strong
## 177 Information Security Analyst Strong Average Weak
## 178 Machine Learning Engineer Strong Average Weak
## 179 Database Administrator Weak Strong Average
## 180 Cloud Solutions Architect Strong Strong Weak

STRUCTURE OF THE DATA2

str(data2)

## 'data.frame': 180 obs. of 12 variables:

## $ Student.ID : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Name : chr "John Smith" "Alice Johnson" "Robert Davis" "Emily
Wilson" ...
## $ Gender : chr "Male" "Female" "Male" "Female" ...
## $ Age : int 21 20 22 21 23 22 20 21 23 22 ...
## $ GPA : num 3.5 3.2 3.8 3.7 3.4 3.9 3.6 3.7 3.3 3.5 ...
## $ Major : chr "Computer Science" "Computer Science" "Computer
Science" "Computer Science" ...
## $ Interested.Domain: chr "Artificial Intelligence" "Data Science" "Software
Development" "Web Development" ...
## $ Projects : chr "Chatbot Development" "Data Analytics" "E-commerce
Website" "Full-Stack Web App" ...
## $ Future.Career : chr "Machine Learning Researcher" "Data Scientist"
"Software Engineer" "Web Developer" ...
## $ Python : chr "Strong" "Average" "Strong" "Weak" ...
## $ SQL : chr "Strong" "Strong" "Strong" "Strong" ...
## $ Java : chr "Weak" "Weak" "Average" "Strong" ...

MAX,MIN OF THE DATA2

max(data2$Java) max(data2$Projects) ## [1] 3.9

## [1] "Weak" ## [1] "Web Application max(data2$Age)

Development"
max(data2$SQL) ## [1] 37
max(data2$Interested.Dom
## [1] "Weak" ain) max(data2$Gender)

max(data2$Python) ## [1] "Web Development" ## [1] "Male"

## [1] "Weak" max(data2$Major) max(data2$Name)

max(data2$Future.Career) ## [1] "Computer ## [1] "William Smith"

Science"
## [1] "Web Developer" max(data2$Student.ID)
max(data2$GPA)
## [1] 180 min(data2$Projects) ## [1] 3.2

min(data2$Java) ## [1] "3D Animation" min(data2$Age)

## [1] "Average" min(data2$Interested.Dom ## [1] 20

ain)
min(data2$SQL) min(data2$Gender)
## [1] "Artificial
## [1] "Average" Intelligence" ## [1] "Female"

min(data2$Python) min(data2$Major) min(data2$Name)

## [1] "Average" ## [1] "Computer ## [1] "Agent Bobbi

Science" Morse"
min(data2$Future.Career)
min(data2$GPA) min(data2$Student.ID)
## [1] "AI Researcher"
## [1] 1

SUMMARY OF THE DATA2

summary(data2)

## Student.ID Name Gender Age

## Min. : 1.00 Length:180 Length:180 Min. :20.00
## 1st Qu.: 45.75 Class :character Class :character 1st Qu.:21.00
## Median : 90.50 Mode :character Mode :character Median :22.00
## Mean : 90.50 Mean :22.12
## 3rd Qu.:135.25 3rd Qu.:22.25
## Max. :180.00 Max. :37.00

## GPA Major Interested.Domain Projects

## Min. :3.200 Length:180 Length:180 Length:180
## 1st Qu.:3.500 Class :character Class :character Class :character
## Median :3.600 Mode :character Mode :character Mode :character
## Mean :3.615
## 3rd Qu.:3.700
## Max. :3.900

## Future.Career Python SQL Java

## Length:180 Length:180 Length:180 Length:180
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
ALL MEDIANS OF STUDENT_CS DATA2

median(data2$Age)

## [1] 22

median(data2$GPA)

## [1] 3.6

ALL MEANS OF STUDENT_CS DATA2

mean(data2$GPA)

## [1] 3.615

mean(data2$Age)

## [1] 22.11667

ALL VARIENCE OF STUDENT_CS DATA2

var(data2$GPA)

## [1] 0.03144972

var(data2$Age)

## [1] 7.969553

ALL STANDARD DEVIATION OF STUDENT_CS DATA2

sd(data2$Age)

## [1] 2.82304

sd(data2$GPA)
## [1] 0.1773407

ALL QUANTILE OF STUDENT_CS DATA2

quantile(data2$Age)

## 0% 25% 50% 75% 100%

## 20.00 21.00 22.00 22.25 37.00

quantile(data2$GPA)

## 0% 25% 50% 75% 100%

## 3.2 3.5 3.6 3.7 3.9

DIMENTION of STUDENT_CS DATA2

dim(data2)

## [1] 180 12

NUMBER OF ROWS of STUDENT_CS DATA2

nrow(data2)

## [1] 180

NUMBER OF COLUMNS of STUDENT_CS DATA2

ncol(data2)

## [1] 12
ALL TABLES of STUDENT_CS DATA2

table(data2$Java)

##
## Average Strong Weak
## 47 69 64

table(data2$SQL)

##
## Average Strong Weak
## 60 79 41

table(data2$Python)

##
## Average Strong Weak
## 46 70 64

table(data2$Future.Career)

##
## AI Researcher Bioinformatician
## 6 2
## Blockchain Engineer Cloud Solutions Architect
## 1 16
## Computer Vision Engineer Data Analyst
## 1 6
## Data Privacy Specialist Data Scientist
## 1 8
## Database Administrator DevOps Engineer
## 16 1
## Digital Forensics Specialist Distributed Systems Engineer
## 1 1
## Embedded Software Engineer Ethical Hacker
## 1 1
## Game Developer Geospatial Analyst
## 4 1
## Graphics Programmer Healthcare IT Specialist
## 9 2
## Information Security Analyst IoT Developer
## 17 1
## Machine Learning Engineer Machine Learning Researcher
## 13 1
## Mobile App Developer NLP Engineer
## 17 1
## NLP Research Scientist Quantum Computing Researcher
## 11 2
## Robotics Engineer Security Analyst
## 1 1
## SEO Specialist Software Engineer
## 1 14
## UX Designer VR Developer
## 2 1
## Web Developer
## 19

table(data2$Projects)

##
## 3D Animation 3D Modeling
## 4 2
## 3D Rendering Android App
## 3 3
## Android App Development Android Game
## 1 4
## AWS Deployment Big Data Analytics
## 8 2
## Chatbot Development Cloud Infrastructure Management
## 2 3
## Cloud Migration Specialist Cloud Solution Architecture
## 1 3
## Computer Forensic Analyst Computer Vision
## 1 3
## Cross-Platform App Development Data Analytics
## 2 1
## Data Mining Data Warehouse Design
## 2 1
## Deep Learning Models DevOps
## 1 1
## Distributed Systems Architect E-commerce Website
## 1 13
## Embedded Systems Enterprise Software Development
## 1 1
## Firewall Management Front-End Development
## 1 3
## Full-Stack Web App Game Development
## 7 3
## GCP Deployment Genomic Data Analysis
## 1 1
## GIS Mapping Healthcare Data Analyst
## 1 1
## Image Classification Image Recognition
## 3 4
## iOS App iOS App Development
## 3 3
## iOS Game Machine Learning
## 1 7
## Market Analysis Medical Imaging Analysis
## 1 1
## Mobile App Development Mobile Game Development
## 3 1
## Natural Language Processing Network Security
## 14 14
## Neural Network Development Object Detection
## 2 1
## Penetration Testing Privacy Compliance Officer
## 1 1
## Protein Structure Prediction Quantum Algorithm Development
## 1 2
## Reinforcement Learning Robotics
## 3 1
## Search Engine Optimization Security Auditing
## 1 3
## Smart Contracts Developer Smart Home Automation
## 1 1
## Social Media Platform SQL Database Administration
## 5 3
## SQL Database Design SQL Query Optimization
## 3 9
## Statistical Analysis Usability Testing
## 1 1
## User Experience Researcher Virtual Reality Development
## 1 1
## Web Application Development
## 1

table(data2$Interested.Domain)

##
## Artificial Intelligence Bioinformatics
## 19 2
## Biomedical Computing Blockchain Technology
## 2 1
## Cloud Computing Computer Graphics
## 16 13
## Computer Vision Cybersecurity
## 1 18
## Data Mining Data Privacy
## 1 1
## Data Science Database Management
## 13 16
## Digital Forensics Distributed Systems
## 1 1
## Game Development Geographic Information Systems
## 1 1
## Human-Computer Interaction Information Retrieval
## 2 1
## IoT (Internet of Things) Machine Learning
## 1 13
## Mobile App Development Natural Language Processing
## 17 1
## Network Security Quantum Computing
## 1 2
## Software Development Software Engineering
## 11 5
## Web Development
## 19

table(data2$Major)

##
## Computer Science
## 180

table(data2$GPA)

##
## 3.2 3.3 3.4 3.5 3.6 3.7 3.8 3.9
## 2 21 7 33 29 44 31 13
table(data2$Age)

##
## 20 21 22 23 29 31 33 35 37
## 34 48 53 36 2 1 2 2 2

table(data2$Gender)

##
## Female Male
## 78 102

table(data2$Name)

##
## Agent Bobbi Morse Agent Coulson Agent Daisy Johnson Agent Fitz
## 1 1 1 1
## Agent Hill Agent Lance Hunter Agent Mack Agent Melinda May
## 1 1 1 1
## Agent Simmons AIM Alice Johnson Andrew Hall
## 1 2 4 5
## Ava Miller Betty Brant Black Cat Carnage
## 2 1 1 1
## Charles Miller Charlotte Davis David Brown David Jones
## 4 4 1 4
## David Lee Doctor Octopus Eddie Brock Electro
## 1 1 1 1
## Elijah Davis Elijah Smith Elizabeth Williams Emily Johnson
## 2 1 4 1
## Emily Lee Emily Wilson Emma Clark Emma Johnson
## 3 3 1 3
## Emma Wilson Flash Thompson Fred Myers Grace Smith
## 2 1 1 1
## Green Goblin Gwen Stacy Harry Osborn Hydra
## 1 1 1 1
## Hydro-Man Isabella Brown James Miller James Wilson
## 1 1 1 8
## Jason Macendale Jessica Jones John Brown John Smith
## 1 1 4 4
## Joseph Miller Kingpin Kraven the Hunter Laura Lee
## 2 1 1 6
## Liam Wilson Liz Allan Lizard Mary Jane Watson
## 4 1 2 1
## Matthew Hall Matthew Lee Michael Brown Michael Johnson
## 3 1 6 1
## Michelle Williams MODOK Morbius Mysterio
## 1 1 1 1
## Ned Leeds Oliver Brown Oliver Davis Olivia Brown
## 1 2 2 3
## Olivia Clark Olivia Davis Peter Parker Rhino
## 7 2 1 1
## Robert Davis Sandman Sarah Miller Scorpion
## 2 1 5 1
## Shocker Silver Sable Sophia Johnson Sophia Miller
## 1 1 6 1
## Sophia Wilson Susan Davis Taskmaster Venom
## 1 4 1 1
## Vulture William Brown William Davis William Johnson
## 1 1 3 5
## William Smith
## 3

CHECK NON-NUMERIC COLUMNS

sapply(data2,class)

## Student.ID Name Gender Age

## "integer" "character" "character" "integer"
## GPA Major Interested.Domain Projects
## "numeric" "character" "character" "character"
## Future.Career Python SQL Java
## "character" "character" "character" "character"

GRAPHS

BARPLOTS
barplot(table(data2$Age),
main = "AGE",
xlab = "AGE",
ylab = "X")
barplot(table(data2$Projects),
main = "PROJECTS",
xlab = "PROJECT",
ylab = "X")

barplot(table(data2$Interested.Domain),
main = "INTERESTED DOMAIN",
xlab = "INTERESTED MONAIN",
ylab = "X")
PI CHART
pie(table(data2$GPA),
main = "GPA")

pie(table(data2$Java),
main = "JAVA")

pie(table(data2$GPA,
names.arg = data2$Java),
main = "GPA and JAVA")
HISTOGRAMS
hist(table(data2$GPA),
main = "AGE",
xlab = "AGE",
ylab = "X")
POLIGON
plot(data2$GPA, type = "o",
main = "Frequency Polygon",
xlab = "X",
ylab = "GPA")

BOX PLOT
boxplot(table(data2$Age),
horizontal = TRUE,
main = "AGE",
xlab = "AGE")
Overall Summary of Computer Data
About
This data contains information about Computer Science students. It helps us understand their interests,
skills, and future career plans based on their academic background.

o Student ID: A unique number for each student.

o Name: The student's full name.
o Gender: Whether the student is male or female.
o Age: The student's age.
o GPA: Their grade point average (out of 4.0).
o Major: All students are from the Computer Science department.

o Interested Domain: The field the student wants to specialize in, like AI, Web Development, or
Cybersecurity.
o Projects: What kind of project the student has worked on, showing their practical experience.
o Future Career: What job the student wants in the future.
o Skills in Python, SQL, and Java: Each skill is marked as Weak, Average, or Strong.

Example
John Smith (Age 21) is interested in Artificial Intelligence, worked on Chatbot Development, and wants to
become a Machine Learning Researcher. He is strong in Python and SQL but weak in Java.
Emily Wilson (Age 21) prefers Web Development, made a Full-Stack Web App, and plans to be a Web
Developer. She is strong in SQL and Java but weak in Python.

Data Summary

o Most students have different interests even though they study the same subject.
o Projects and skills match their future goals, like someone good at Python aiming for AI.
o This kind of data helps teachers, advisors, or recruiters understand each student better and guide
them based on their strengths.