Introduction to Data science

Lab Manual

IYear (I/II semester)

Batch: 2020-21

School of Computer Science and Engineering

And
School of Computer Science and Information Technology
(Common for all programmes)

Name
SRN
Branch
Semester
Section
Academic Year
Introduction to Data Science Lab REVA University

Index
Sl.No. Particulars Page no.
1 Continuous Assessment Form 3
2 Semester End Examination Practical evaluation 5
procedure 2020-21
3 Course Description 6

4 Course Objectives 6

5 Course Outcomes 6

6 List of experiments 7

7 Part-A- Experiments 10

8 Part B – Mini Project 62

9 Additional Data Science Projects 69

10 Appendix-Installation Guide 70

2
Introduction to Data Science Lab REVA University

CONTINUOUS ASSESMENT

PART-A

Slno. Experiment Name Max. Obtained Sign

Marks Marks

3 a.

5.

10

11

12

Total Marks 10

3
Introduction to Data Science Lab REVA University

PART-B

Slno. Experiment Name Max. Obtained Sign

Marks Marks

Total Marks 10

Internal Assesment / Additional Assignments Max. Obtained Sign

Marks Marks
05

Total Marks Obtained : /25

4
Introduction to Data Science Lab REVA University

Internal Assessment/Examination Evaluation Procedure 2020-21 (ODD / EVEN)

DS Lab (Part A and Part B):

Q. Parameters to be Considered Marks Total
Distribution
A. Write UP Manual Calculation- Steps 5 20
Result obtained from manual calculation
Conduction Results obtained using Excel tool 5
& Results
B Write UP Manual Calculation- Steps 5
Result obtained from manual calculation
Conduction Results obtained using Excel tool 5
& Results
C Viva 05 05
TOTAL 25

Note: Lab course is conducted for a total of 50 Marks:

a. 25 Marks Continuous Evaluation

b. 25 Marks Internal Assessment

5
Introduction to Data Science Lab REVA University

COURSE Description
Data Science is an interdisciplinary, problem-solving oriented subject that is used to apply scientific
techniques to practical problems. The course orients on preparation of datasets and programming of data
analysis tasks. This course covers the topics: ML algorithms, SQL and demonstration of experiments by
using MS-Excel and MySQL

COURSE OBJECTIVE (S):

The objectives of this course are to:
1. Explain the fundamental concepts of Excel.
2. Explain the algorithms of Machine learning.
3. Demonstrate the use of SQL commands in real world applications.
4. Discuss the functional components of Data Science for real world applications

COURSEOUTCOMES(COs)
After the completion of the course, the student will be able to:

CO# Course Outcomes POs PSOs

CO1 Make use of the concepts of Data Science in developing the real 1, 2, 4,10 1,2,3
world applications.

CO2 Apply the SQL commands in developing the real-world applications. 1,2, 3,9,10 2, 3

CO3 Build the solutions for real world problems, perform analysis, 2,3, 4, 8,9, 10 1, 2, 3
interpretation and reporting of data using regression alogorithms.

C04 Design ER diagrams for database. 2,3, 4,8, 9, 10 1, 2, 3

6
Introduction to Data Science Lab REVA University

TABLE OF CONTENTS

Tools Expected Page No.

No Titleof the Experiment andTechniq Skill/Ability
ues
Create 11
The height(in cm) of a group of fathers and sons are given below,Find and
the lines of regression and estimate the height of son when the height of perform
father is 164 cm. operation
Plot the s on
graph.H Excel
1 158 166 163 165 167 170 167 172 177 181 MS Excel
gt of data set
Fathers by
applying
Hgt of
163 158 167 170 160 180 170 175 172 175 Linear
Sons
regressio
n
17
Using the data file DISPOSABLE INCOME AND VEHICLE SALES,
perform the following:
Perform
i) Plot a scatter diagram.
predictio
ii) Determine the regression equation.
n and
2 iii) Plot the regression line (hint: use MS Excel's Add Trendline feature). MS Excel
visualiza
iv) Compute the predicted vehicle sales for disposable income of
tion of
$16,500 and of $17,900.
data
v) Compute the coefficient of determination and the coefficient of
correlation

25
Managers model costs in order to make predictions. The cost data in the
data file INDIRECT COSTS AND MACHINE HOURS show the
indirect manufacturing costs of an ice-skate manufacturer. Indirect
manufacturing costs include maintenance costs and setup costs. Indirect
manufacturing costs depend on the number of hours the machines are
used, called machine hours. Based on the data for January to December, Perform
perform the following operations. predictio
n and
3 MS Excel
i) Plot a scatter diagram. visualiza
ii) Determine the regression equation. tion of
iii) Plot the regression line (hint: use MS Excel's Add Trendline data
feature).
iv) Compute the predicted indirect manufacturing costs for 300
machine hours and for 430 machine hours.
v) Compute the coefficient of determination and the coefficient of
correlation

7
Introduction to Data Science Lab REVA University

32
Apply multiple linear regression to predict the stock index price which is
a dependent variable of a fictitious economy based on two independent /
input variablesinterest rateand unemployment rate.
Perform
predictio
n and
4 MS Excel
visualiza
interest unemployment stock index tion of
year month
rate rate price data

2020 10 2.75 5.3 1464

36
Calculate the total interest paid on a car loan which has been availed from
HDFC bank. For example, Rs.10,00,000 has been borrowed from a bank
with annual interest rate of 5.2% and the customer needs to pay every
month as shown in table below. Calculate the total interest rate paid for a

Sl No. A B
Create
1 Principal Rs.10,00,000 Excel
2 Annual interest rate 5.20% data and
5. MS Excel
3 Year of the loan 3 perform
EMI
4 Starting payment number 1 estimator

5 Ending payment number 36

6 total interest paid during period ?

loan availed of Rs.10,00,000during 3 years.

Create a supplier database of 10 records with SUPPLIER_ID as primary 38

key, SUPPLIER_NAME, PRODUCTS, QUANTITY, ADDRESS, Creating
6 CITY,PHONE_NO and PINCODE, Where SUPPLIER_NAME, SQL
Tables
PRODUCTS, QUANTITY and PHONE_NO, should not be NULL.
40
Create the customer database of a big Market withCUSTOMER_IDas
Creating
primary key,CUSTOMER_NAME, PHONE_NO, EMAIL_ID,
and
7 ADDRESS, CITY and PIN_CODE.Store at least twenty customers details SQL
retrievin
where CUSTOMER_NAME and PHONE_NO are mandatory and
g Tables
display the customer data in alphabetical order.
46
Apply linear regression to find the weather (temperature) of a city with
the amount of rain in centimeters. Create your own database with
following details. Apply
Linear
8 CITY Temperature in Rain in MS Excel
regressio
Centigrade Centimeters n

8
Introduction to Data Science Lab REVA University

Use the linear regression technique to compare the age of humans with 50
Apply
the amount of sleep in hours.
Linear
9 Name Age in Years Sleep in hours MS Excel
regressio
Create your own database with above details.
n

Apply the linear regression, compare the average salaries of batsman Apply 54
10 depending on the run rate scored/ recorded in the matches.Assume your MS Excel Linear
own database. regressio
n
Design the ER diagram and create schema of the REVA library Entity Entity 58
11 Relations
management system. Relationship
hip
Design the ER diagram and create schema for Hospital Management Entity diagrams
Schema 60
12
system. Relationship design

PART_B:Projects
Tools Expected Page No.
No Titleof the Experiment andTechniq Skill/Ability
ues
Apply Linear 63
1 Big Mart sales forecasting MS Excel regression

Apply Linear 66
2 Bangalore crime analysis MS Excel regression

9
Introduction to Data Science Lab REVA University

PART-A
Experiments

10
Introduction to Data Science Lab REVA University

1. The height(in cm) of a group of fathers and sons are given below,Find the lines of regression and
estimate the height of son when the height of father is 164 cm.

Hgt of
158 166 163 165 167 170 167 172 177 181
Fathers
Hgt of
163 158 167 170 160 180 170 175 172 175
Sons
Solution:

Step 1: Height data have been taken from dataset.

Hgt of Hgt of
Fathers Sons
158 163
166 158
163 167
165 170
167 160
170 180
167 170
172 175
177 172
181 175

Step 2: Enter the data for Independent Variable x and dependent variable y as shown above 11 values

11
Introduction to Data Science Lab REVA University

Step 3: Then click on the Data Analysis button

Step 4: Then click on the Regression button

12
Introduction to Data Science Lab REVA University

Step 5: Then select the range of dependent variable as shown above

Step 6: After selecting both ranges click on ok button

13
Introduction to Data Science Lab REVA University

Step 7: We will get the output as shown with residual plot graph

14
Introduction to Data Science Lab REVA University

The height of son when son of father is 164cm is as follows:

Y=A+Bx

15
Introduction to Data Science Lab REVA University

=66.11417+164*0.610236

=166.1929

Manual calculation

Sl. height of father (x) height of x-mean(x) y-mean(y) x-mean(x) * y- x-

No. son(y) mean(y) mean(x)^2
1 158 163 -10.6 -6 63.6 112.36
2 166 158 -2.6 -11 28.6 6.76
3 163 167 -5.6 -2 11.2 31.36
4 165 170 -3.6 1 -3.6 12.96
5 167 160 -1.6 -9 14.4 2.56
6 170 180 1.4 11 15.4 1.96
7 167 170 -1.6 1 -1.6 2.56
8 172 175 3.4 6 20.4 11.56
9 177 172 8.4 3 25.2 70.56
10 181 175 12.4 6 74.4 153.76

sum(x) sum(y) 0.00 0 248 406.40

1686 1690
mean(x) mean(y)
168.6 169

((sum(x-
mean(x) *y-
mean(y)) ) /
coefficient of (x-
regression=byx mean(x)^2) 0.61023622 0.61023622

A=mean(y)-
calculate y intercept byx*mean(x) 66.11417323

dependent
variable=y=A+byx*x 166.192913

16
Introduction to Data Science Lab REVA University

2. Using the data file DISPOSABLE INCOME AND VEHICLE SALES, perform the following:
vi) Plot a scatter diagram.
vii) Determine the regression equation.
viii) Plot the regression line (hint: use MS Excel's Add Trendline feature).
ix) Compute the predicted vehicle sales for disposable income of $16,500 and of $17,900.
Compute the coefficient of determination and the coefficient of correlation

Solution: Sales data have been taken from dataset.

disposable vehicle
income sales
15000 200
28000 300
18000 180
19000 190
22000 220
25000 250
10000 100
29000 285

a)

Scatter diagram is as follows:

15000 Residual Plot

20
10
Residuals

0
0 10000 20000 30000 40000
-10
-20
15000

b) Regression equation is as follows:

y=A+Bx

17
Introduction to Data Science Lab REVA University

c)Regression line:

15000 Residual Plot

20
15
10
Residuals

5
0
0 5000 10000 15000 20000 25000 30000 35000
-5
-10
-15
15000

d)

Step 1: Enter the data for Independent Variable x and dependent variable y as shown above 8 values

18
Introduction to Data Science Lab REVA University

Step 2: Then click on the Data Analysis button

Step 4: Then click on the Regression button

19
Introduction to Data Science Lab REVA University

Step 4: Then select the range of dependent variable as shown above

Step 6: After selecting both ranges click on ok button

20
Introduction to Data Science Lab REVA University

Step 7: We will get the output as shown with residual plot graph

21
Introduction to Data Science Lab REVA University

The value of sales when sales is 16500 and 17900 is

22
Introduction to Data Science Lab REVA University

e) coefficient of determination and the coefficient of correlation

r=∑(xi−¯x)(yi−¯y ) / √ ∑(xi−¯x)2∑(yi−¯y)2

SSR=∑(y^−y¯)2
SSE=∑(yi−y^)2
SSTO=∑(y−y¯)2
r2=SSR/SSTO=1−SSE/SSTO

coefficient of correlation and coefficient of determination can be found out by:

disposable sales(y) x-mean(x) y- x- y- x-

income(x) mean(y) mean(x)^2 mean(y) mean(x)*y
^2 -mean(y)

244.140
15000 200 -5750 -15.625 33062500 6 89843.75
7119.14
28000 300 7250 84.375 52562500 1 611718.8
1269.14
18000 180 -2750 -35.625 7562500 1 97968.75
656.640
19000 190 -1750 -25.625 3062500 6 44843.75
19.1406
22000 220 1250 4.375 1562500 3 5468.75
1181.64
25000 250 4250 34.375 18062500 1 146093.8
13369.1
10000 100 -10750 -115.625 115562500 4 1242969
4812.89
29000 285 8250 69.375 68062500 1 572343.8

299500000. 28671.8
sum(x) sum(y) 0.00 0 00 8 2811250
166000 1725
mean(x) mean(y)
20750 215.625

((sum(x-
mean(x) *y-
coefficient of mean(y)) ) /
regressionbyx= (x- 0.01

23
Introduction to Data Science Lab REVA University

mean(x)^2)

A=mean(y)-
calculate y byx*mean(x 20.855592
intercept ) 65

dependent
variable=y=A+by 175.73247 when When Y=188.87
x*x 08 x=16500 x=17900 35

correlation 0.959341

determination=SS -20601.0189
R

SSTO= 28671.88

-0.71851
So the answer is

24
Introduction to Data Science Lab REVA University

3.Managers model costs in order to make predictions. The cost data in the data file INDIRECT
COSTS AND MACHINE HOURS show the indirect manufacturing costs of an ice-skate
manufacturer. Indirect manufacturing costs include maintenance costs and setup costs. Indirect
manufacturing costs depend on the number of hours the machines are used, called machine hours.
Based on the data for January to December, perform the following operations.

vi) Plot a scatter diagram.

vii) Determine the regression equation.
viii) Plot the regression line (hint: use MS Excel's Add Trendline feature).
ix) Compute the predicted indirect manufacturing costs for 300 machine hours and for 430
machine hours.
Compute the coefficient of determination and the coefficient of correlation

Solution:

Step 1:

no. of
hours
machine machine
month used cost
Jan 50 100
Feb 350 700
Mar 100 200
Apr 400 800
May 150 300
Jun 450 900
Jul 200 400
Aug 500 1000
Sept 250 500
Oct 550 1100
Nov 300 600
Dec 600 1200

25
Introduction to Data Science Lab REVA University

a) Scatter diagram is as follows:

X Variable 1 Residual Plot

1
Residuals

0.5

0
0 200 400 600 800
X Variable 1

b) Regression equation is as follows:

y=A+Bx

c)Regression line:

X Variable 1 Residual Plot

1
Residuals

0.5

0
0 200 400 600 800
X Variable 1

d)

26
Introduction to Data Science Lab REVA University

Step 1: Enter the data for Independent Variable x and dependent variable y as shown above 12 values

Step 2: Then click on the Data Analysis button

27
Introduction to Data Science Lab REVA University

Step 3: Then click on the Regression button

Step 4: Then select the range of dependent variable as shown above

28
Introduction to Data Science Lab REVA University

Step 5: After selecting both ranges click on ok button

Step 6: We will get the output as shown with residual plot graph

29
Introduction to Data Science Lab REVA University

The value of cost when the machine hours are 300 and 430 are:

Y300=0+300*2

=600

Y430=0+430*2

=860

e) coefficient of determination and the coefficient of correlation

r=∑(xi−¯x)(yi−¯y ) / √ ∑(xi−¯x)2∑(yi−¯y)2

SSR=∑(y^−y¯)2
SSE=∑(yi−y^)2
SSTO=∑(y−y¯)2
r2=SSR/SSTO=1−SSE/SSTO

Manual Calculation:

machine hours(x) cost(y) x- y- x- y- x-mean(x)*y-

mean(x) mean(y) mean(x)^2 mean(y)^2 mean(y)

50 100 -275 -550 75625 302500 151250

350 700 25 50 625 2500 1250
100 200 -225 -450 50625 202500 101250
400 800 75 150 5625 22500 11250
150 300 -175 -350 30625 122500 61250
450 900 125 250 15625 62500 31250
200 400 -125 -250 15625 62500 31250
500 1000 175 350 30625 122500 61250
250 500 -75 -150 5625 22500 11250
550 1100 225 450 50625 202500 101250
300 600 -25 -50 625 2500 1250
600 1200 275 550 75625 302500 151250

sum(x) sum(y) 0.00 0 357500.00 1430000 715000

3900 7800
mean(x) mean(y)

30
Introduction to Data Science Lab REVA University

325 650

((sum(x-
mean(x) *y-
mean(y)) ) /
coefficient of (x-
regressionbyx= mean(x)^2) 2.00

A=mean(y)-
byx*mean(x
calculate y intercept ) 0

dependent
variable=y=A+byx* when When
x 860 x=430 X=300 Y=600

correlation 1

determination=SSR 160

1430000

SSTO=

So the coeff of 0.0001119

determination is

31
Introduction to Data Science Lab REVA University

4. Apply multiple linear regression to predict the stock index price which is a dependent variable
of a fictitious economy based on two independent / input variablesinterest rateand unemployment
rate.

stock
mont interes unemploymen
year index
h t rate t rate
price
2020 10 2.75 5.3 1464

Solution:

stock
interest unemployment
year month index
rate rate
price
2020 10 2.75 5.3 1464
2020 1 2.5 5.1 1300
2020 2 2.4 5 1200
2020 3 2 4.5 1000
2020 4 3 5.5 1500
2020 6 3.5 5.7 1650
2020 8 2.9 5 1600
2020 9 2 5 1400

Step 2: Enter the data for Independent Variable x and dependent variable y as shown above 8 values

32
Introduction to Data Science Lab REVA University

Step 3: Then click on the Data Analysis button

Step 4: Then click on the Regression button

33
Introduction to Data Science Lab REVA University

Step 5: Then select the range of dependent variable as shown above

Step 6: After selecting both ranges click on ok button

34
Introduction to Data Science Lab REVA University

Step 7: We will get the output as shown with residual plot graph

The comparison of values can be done by the above graph

35
Introduction to Data Science Lab REVA University

5. Calculate the total interest paid on a car loan which has been availed from HDFC bank. For
example, Rs.10,00,000 has been borrowed from a bank with annual interest rate of 5.2% and
the customer needs to pay every month as shown in table below. Calculate the total interest
rate paid for a loan availed of Rs.10,00,000during 3 years.

Sl
A B
No.
1 Principal Rs.10,00,000
2 Annual interest rate 5.20%
3 Year of the loan 3
Starting payment
4 1
number
Ending payment
5 36
number
total interest paid during
6 ?
period

One of the easiest ways to calculate the EMI on your loan is by using Microsoft Excel. Excel provides a
simple formula for this purpose: PMT (rate, nper, pv, [fv], [type]).
PMT stands for Payment – and gives periodic loan payment or EMI value as an output. The arguments
required for this function are:

 rate - The interest rate for the loan.

 nper - The total number of payments for the loan.
 pv - The present value, or the total value of all loan payments now, i.e. the outstanding loan amount.
 fv - [optional] The future value, or a cash balance you want after the last payment is made. Defaults to 0,
i.e. the outstanding loan amount after all the payments are made.
 type - [optional] When payments are due. 0 = end of the period. 1 = beginning of the period. Default is 0.
When using this function, make sure that the units for rate and nper are the same. For example, if you are
looking to calculate monthly EMI, the rate should be the monthly interest rate and not the annual interest
rate. Let us look at an example to understand this:
Consider a loan of ₹10 lakh at 10% interest per annum for 20 years. If it is repaid in quarterly instalments:
Rate = 10%/4 per quarter
Npr = 20X4
EMI calculation in excel will be:
= PMT(10%/4, 20*4, 10,00,000)

36
Introduction to Data Science Lab REVA University

Sl
No. A B
1 Principal Rs.10,00,000
Annual interest
2 rate 5.20%
3 Year of the loan 3
Starting payment
4 number 1
Ending payment
5 number 36
total interest paid
6 during period ($90,541.68)

37
Introduction to Data Science Lab REVA University

6. Create a supplier database of 10 records with SUPPLIER_ID as primary key,

SUPPLIER_NAME, PRODUCTS, QUANTITY, ADDRESS, CITY,PHONE_NO and
PINCODE, Where SUPPLIER_NAME, PRODUCTS, QUANTITY and PHONE_NO,
should not be NULL.

Solution:

mysql> create table supplier(SUPPLIER_ID varchar(20) , SUPPLIER_NAME varchar(20) not null,

PRODUCTS varchar(20) not null, QUANTITY varchar(20) not null, ADDRESS varchar(20), CITY
varchar(20), PHONE_NO integer(20) not null, PINCODE varchar(20), primary key(SUPPLIER_ID));

Query OK, 0 rows affected

mysql> insert into supplier values("111","amar","pen","20","peenya","bangalore",12345678,560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into supplier values("222","akbar","pencil","20","peenya","bangalore",12345678,560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into supplier values("333" ,"anthnony" ,"pencil" ,"20" ,"peenya" ,"bangalore" ,12345688
,560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into supplier values("444","mahi","eraser","25","jharkand","bengal",12675688,650078);

Query OK, 1 row affected (0.01 sec)

mysql> insert into supplier values("555","manya","book","25","jharkand","bengal",12699988,650078);

Query OK, 1 row affected (0.01 sec)

mysql> insert into supplier values("666" ,"manyata" ,"sharpner" ,"25" ,"hebbal", "bangalore" ,99699988
,650078);

Query OK, 1 row affected (0.01 sec)

mysql> insert into supplier values("888" ,"jennifer" ,"sharpner" ,"25" ,"hebbal" ,"bangalore" ,89699988
,789098);

Query OK, 1 row affected (0.01 sec)

insert into supplier values("999","joyes","chart","25","agra","delhi",89688548,324098) ;

Query OK, 1 row affected (0.01 sec)

38
Introduction to Data Science Lab REVA University

insert into supplier values("000","suchitra","pen pencil","25","agra","delhi",89666548,324099);

Query OK, 1 row affected (0.01 sec)

insert into supplier values("1111","hemcheth","choclate","25","bidadi","mandya",9654321,234199);

Query OK, 1 row affected (0.01 sec)

mysql> select * from supplier;

+-------------+---------------+------------+----------+----------+-----------+----------+---------+

| SUPPLIER_ID | SUPPLIER_NAME | PRODUCTS | QUANTITY | ADDRESS | CITY |

PHONE_NO | PINCODE |

+-------------+---------------+------------+----------+----------+-----------+----------+---------+

| 000 | suchitra | pen pencil | 25 | agra | delhi | 89666548 | 324099 |

| 111 | amar | pen | 20 | peenya | bangalore | 12345678 | 560057 |

| 1111 | hemcheth | choclate | 25 | bidadi | mandya | 9654321 | 234199 |

| 222 | akbar | pencil | 20 | peenya | bangalore | 12345678 | 560057 |

| 333 | anthnony | pencil | 20 | peenya | bangalore | 12345688 | 560057 |

| 444 | mahi | eraser | 25 | jharkand | bengal | 12675688 | 650078 |

| 555 | manya | book | 25 | jharkand | bengal | 12699988 | 650078 |

| 666 | manyata | sharpner | 25 | hebbal | bangalore | 99699988 | 650078 |

| 888 | jennifer | sharpner | 25 | hebbal | bangalore | 89699988 | 789098 |

| 999 | joyes | chart | 25 | agra | delhi | 89688548 | 324098 |

+-------------+---------------+------------+----------+----------+-----------+----------+---------+

10 rows in set (0.00 sec)

39
Introduction to Data Science Lab REVA University

7. Create the customer database of a big Market with CUSTOMER_IDas primary

key,CUSTOMER_NAME, PHONE_NO, EMAIL_ID, ADDRESS, CITY and PIN_CODE.
Store at least twenty customers details where CUSTOMER_NAME and PHONE_NO are
mandatory and display the customer data in alphabetical order.

mysql> create table big_market(CUSTOMER_ID varchar(20), CUSTOMER_NAME varchar(20) not null,

PHONE_NO integer(30) not null, EMAIL varchar(20),ADDRESS varchar(20), CITY
varchar(20),PINCODE integer(20),primary key(CUSTOMER_ID));

Query OK, 0 rows affected(0.07 sec)

insert into big_market values("111","Geetha",7019231,"[email protected]","peenya", "bangalore"

,560057);

Query OK, 1 row affected (0.02 sec)

mysql> insert into big_market values("2","HEM",23719231,"[email protected]","khalli",

"bangalore",560035);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("3","nagesh",23719231,"[email protected]","khalli", "bangalore"

,560035);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("4","akki",23732731,"[email protected]","khalli","bangalore",

560035);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("5","vinay",87732731,"[email protected]","khalli","bangalore",

560035);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("6","shankar",87732731,"[email protected]","khalli",

"bangalore", 560035);

40
Introduction to Data Science Lab REVA University

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("7","kali",56732731,"[email protected]","dhalli",

"bangalore",560067);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("8","chetan",70982731,"[email protected]","dhalli",

"bangalore",560067);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("9","giri",90882731,"[email protected]","dhalli",

"bangalore",560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("10","lat",090882731,"[email protected]","dhalli",

"bangalore",560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("11","gowrish",99882731,"[email protected]","dhalli",

"bangalore",560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("12","suri",99882731,"[email protected]","dhalli",

"bangalore",560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("13","kat",99800831,"[email protected]","dhalli",

"bangalore",560057);

41
Introduction to Data Science Lab REVA University

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("14","shalini",99776831,"[email protected]","mhalli",

"bangalore",560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("15","thiru",900776831,"[email protected]","mhalli",

"bangalore",560057);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("16","archana",987776831,"[email protected]","hennu",

"bangalore",560407);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("17","anirudh",886776831,"[email protected]","hennu",

"bangalore",560407);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("18","aman",776776831,"[email protected]","kannur",

"bangalore",509907);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("19","akash",776776831,"[email protected]","kannur"

,"bangalore", 509907);

Query OK, 1 row affected (0.01 sec)

mysql> insert into big_market values("20","santosh",776776831,"[email protected]","kannur", "bangalore"

, 509907);

42
Introduction to Data Science Lab REVA University

Query OK, 1 row affected (0.01 sec)

mysql> select * from big_market;

+-------------+---------------+-----------+----------------------+---------+-----------+---------+

| CUSTOMER_ID | CUSTOMER_NAME | PHONE_NO | EMAIL | ADDRESS | CITY |

PINCODE |

+-------------+---------------+-----------+----------------------+---------+-----------+---------+

| 10 | lat | 90882731 | [email protected] | dhalli | bangalore | 560057 |

| 11 | gowrish | 99882731 | [email protected] | dhalli | bangalore | 560057 |

| 111 | Geetha | 7019231 | [email protected] | peenya | bangalore | 560057 |

| 12 | suri | 99882731 | [email protected] | dhalli | bangalore | 560057 |

| 13 | kat | 99800831 | [email protected] | dhalli | bangalore | 560057 |

| 14 | shalini | 99776831 | [email protected] | mhalli | bangalore | 560057 |

| 15 | thiru | 900776831 | [email protected] | mhalli | bangalore | 560057 |

| 16 | archana | 987776831 | [email protected] | hennu | bangalore | 560407 |

| 17 | anirudh | 886776831 | [email protected] | hennu | bangalore | 560407 |

| 18 | aman | 776776831 | [email protected] | kannur | bangalore | 509907 |

| 19 | akash | 776776831 | [email protected] | kannur | bangalore | 509907 |

|2 | HEM | 23719231 | [email protected] | khalli | bangalore | 560035 |

| 20 | santosh | 776776831 | [email protected] | kannur | bangalore | 509907 |

|3 | nagesh | 23719231 | [email protected] | khalli | bangalore | 560035 |

|4 | akki | 23732731 | [email protected] | khalli | bangalore | 560035 |

|5 | vinay | 87732731 | [email protected] | khalli | bangalore | 560035 |

|6 | shankar | 87732731 | [email protected] | khalli | bangalore | 560035 |

43
Introduction to Data Science Lab REVA University

|7 | kali | 56732731 | [email protected] | dhalli | bangalore | 560067 |

|8 | chetan | 70982731 | [email protected] | dhalli | bangalore | 560067 |

|9 | giri | 90882731 | [email protected] | dhalli | bangalore | 560057 |

+-------------+---------------+-----------+----------------------+---------+-----------+---------+

20 rows in set (0.00 sec)

To arrange in alphabetical order;

mysql> select * from big_market order by CUSTOMER_NAME;

+-------------+---------------+-----------+----------------------+---------+-----------+---------+

| CUSTOMER_ID | CUSTOMER_NAME | PHONE_NO | EMAIL | ADDRESS | CITY |

PINCODE |

+-------------+---------------+-----------+----------------------+---------+-----------+---------+

| 19 | akash | 776776831 | [email protected] | kannur | bangalore | 509907 |

|4 | akki | 23732731 | [email protected] | khalli | bangalore | 560035 |

| 18 | aman | 776776831 | [email protected] | kannur | bangalore | 509907 |

| 17 | anirudh | 886776831 | [email protected] | hennu | bangalore | 560407 |

| 16 | archana | 987776831 | [email protected] | hennu | bangalore | 560407 |

|8 | chetan | 70982731 | [email protected] | dhalli | bangalore | 560067 |

| 111 | Geetha | 7019231 | [email protected] | peenya | bangalore | 560057 |

|9 | giri | 90882731 | [email protected] | dhalli | bangalore | 560057 |

| 11 | gowrish | 99882731 | [email protected] | dhalli | bangalore | 560057 |

|2 | HEM | 23719231 | [email protected] | khalli | bangalore | 560035 |

|7 | kali | 56732731 | [email protected] | dhalli | bangalore | 560067 |

| 13 | kat | 99800831 | [email protected] | dhalli | bangalore | 560057 |

| 10 | lat | 90882731 | [email protected] | dhalli | bangalore | 560057 |

|3 | nagesh | 23719231 | [email protected] | khalli | bangalore | 560035 |

44
Introduction to Data Science Lab REVA University

| 20 | santosh | 776776831 | [email protected] | kannur | bangalore | 509907 |

| 14 | shalini | 99776831 | [email protected] | mhalli | bangalore | 560057 |

|6 | shankar | 87732731 | [email protected] | khalli | bangalore | 560035 |

| 12 | suri | 99882731 | [email protected] | dhalli | bangalore | 560057 |

| 15 | thiru | 900776831 | [email protected] | mhalli | bangalore | 560057 |

|5 | vinay | 87732731 | [email protected] | khalli | bangalore | 560035 |

+-------------+---------------+-----------+----------------------+---------+-----------+---------+

20 rows in set (0.01 sec)

45
Introduction to Data Science Lab REVA University

8. Apply linear regression to find the weather (temperature) of a city with the amount of rain
in centimeters. Create your own database with following details.
CITY Temperature Rain in
in Centigrade Centimeters

Solution:

Step 1: Height data have been taken from dataset.

Temperature Rain in
in centigrade centimeters
23 163
25 158
22 167
18 170
20 160
15 180
16 175
17 172

Step 2: Enter the data for Independent Variable x and dependent variable y as shown above 11 values

Step 3: Then click on the Data Analysis button

46
Introduction to Data Science Lab REVA University

Step 4: Then click on the Regression button

Step 5: Then select the range of dependent variable as shown above

47
Introduction to Data Science Lab REVA University

Step 6: After selecting both ranges click on ok button

Step 7: We will get the output as shown with residual plot graph

48
Introduction to Data Science Lab REVA University

The comparison of values can be done by the above graph.

49
Introduction to Data Science Lab REVA University

9. Use the linear regression technique to compare the age of humans with the amount of sleep in
hours.
Name Age in Years Sleep in hours
Create your own database with above details.

Solution:

Step 1: Height data have been taken from dataset.

Name Sleep in
Age in Years hours
Ashwini 50 5
Arthi 25 11
Afreen 29 9
Aman 18 10
Hem 10 13
Chetan 9 14
Gouri 60 4
Ameen 17 12

Step 2: Enter the data for Independent Variable x and dependent variable y as shown above 11 values

Step 3: Then click on the Data Analysis button

50
Introduction to Data Science Lab REVA University

Step 4: Then click on the Regression button

51
Introduction to Data Science Lab REVA University

Step 5: Then select the range of dependent variable as shown above

Step 6: After selecting both ranges click on ok button

Step 7: We will get the output as shown with residual plot graph

52
Introduction to Data Science Lab REVA University

The comparison of values can be done by the above graph.

53
Introduction to Data Science Lab REVA University

10. Apply the linear regression, compare the average salaries of batsman depending on the run rate
scored/ recorded in the matches. Assume your own database.

Solution:

Step 1: Salary data have been taken from dataset.

Name
Run scored Salary
Ashwini 2000 50000
Arthi 1000 25000
Afreen 500 12500
Aman 2500 65000
Hem 3000 80000
Chetan 3500 90000
Gouri 1500 30000
Ameen 100 10000

Step 2: Enter the data for Independent Variable x and dependent variable y as shown above 11 values

Step 3: Then click on the Data Analysis button

54
Introduction to Data Science Lab REVA University

Step 4: Then click on the Regression button

Step 5: Then select the range of dependent variable as shown above

55
Introduction to Data Science Lab REVA University

Step 6: After selecting both ranges click on ok button

Step 7: We will get the output as shown with residual plot graph

56
Introduction to Data Science Lab REVA University

The comparison of values can be done by the above graph.

57
Introduction to Data Science Lab REVA University

11. Design the ER diagram and create schema of the REVA library management system.

Staff
Name Staff_id

Readers
User_id Name Phone no Email Address

Books
ISBN Category AuthNo Title Edition Price

Authentication_System
Login_id Password

Publisher

58
Introduction to Data Science Lab REVA University

Publisher_id Name Year of publication

Reports
User_id Register_no Book_no Issue/Return

59
Introduction to Data Science Lab REVA University

12. Design the ER diagram and create schema for Hospital Management system.

Patient

Id Name Address Date_admitted Date_discharged

Doctor

Doc_id Doc_name

Record

Record_no Appointment Patient_bill

Assistant

Batch_no Ward_no
Test

Test_no Test_type

60
Introduction to Data Science Lab REVA University

Account

Acc_id Description

61
Introduction to Data Science Lab REVA University

PART-B
Mini-Project

62
Introduction to Data Science Lab REVA University

Big Mart Sales Forecasting

Data Science plays a huge role in forecasting sales and risks in the retail sector. Majority of the leading
retail stores implement Data Science to keep a track of their customer needs and make better business
decisions. Big Mart is one such retailer.

Problem Statement: To analyze the Big Mart Sales Data set in order to predict department-wise sales for
each of their stores.

Data Set Description: The data set used for this project contains historical training data, which covers
sales details from 2010-02-05 to 2012-11-01. For the analysis of this problem, the following predictor
variables are used:

1. Store – the store number

2. Dept – the department number
3. Date – the week
4. CPI – the consumer price index
5. Weekly_Sales – sales for the given department in the given store
6. IsHoliday – whether the week is a special holiday week

By studying the dependency of these predictor variables on the response variable, you can predict or
forecast sales for the upcoming months.

Logic:

1. Import the Data Set: The data set needed for this project can be downloaded from Kaggle.
2. Data Cleaning: In this stage, you must make sure to get rid of all inconsistencies, such as missing
values and any redundant variables.
3. Data Exploration: At this stage, you can plot boxplots and qplots to understand the significance of
each predictor variables.
4. Data Modelling: For this particular problem statement, since the outcome is a continuous variable
(Number of sales), it is reasonable to build a Regression model. The Linear Regression algorithm
can be used to solve such problems since it is specifically used to predict continuous dependent
variables.
5. Validate the model: At this stage, you should evaluate the efficiency of the data model by using
the testing data set

Solution:

1. Import the data model:

The Big Mart sales obtained from Kaggle website is as shown below:

Test .csv

63
Introduction to Data Science Lab REVA University

2. Data Cleaning:

After removing the redundant values, the dataset is as shown below:

project1.xlsx

3. Data Exploration:

The residual plot is as shown below

20.75 Residual Plot

150

100

50
Residuals

0
0 5 10 15 20 25
-50

-100
20.75

4. Data modeling and validation

Using the Regression tool of excel , the dataset obtained is analysed as shown below . The y intercept and
Coefficient of regression values are as shown in the below snapshot.

64
Introduction to Data Science Lab REVA University

65
Introduction to Data Science Lab REVA University

Bangalore Crime Analysis

With the increase in the number of crimes taking place in Bangalore, law enforcement agencies are trying
their best to understand the reason behind such actions. Analyses like these can not only help understand
the reasons behind these crimes, but they can also prevent further crimes.

Problem Statement: To analyze and explore the Bangalore Crime data set to understand trends and
patterns that will help predict any future occurrences of such felonies.

Data Set Description: The dataset used for this project consists of every reported instance of a crime in the
city of Bangalore from 01/01/2001

For this analysis, the data set contains many predictor variables such as:

1. ID – Identifier of the record

2. Case Number – The Bangalore Police Chain RD number
3. Date – Date of the incident
4. Description – Secondary description of the IUCR code
5. Location – Location of the occurred incident

Logic:

Like any other Data Science project, the below-described series of steps are followed:

1. Import the Data Set: The data set needed for this project can be downloaded from Kaggle.
2. Data Cleaning: In this stage, you must make sure to get rid of all inconsistencies, such as missing
values and any redundant variables.
3. Data Exploration: You can begin this stage by translating the occurrence of crimes into plots on a
geographical map of the city. Graphically studying each predictor variable will help you understand
which variables are essential for building the model.
4. Data Modelling: For this particular problem statement, since the nature of crimes varies, it is
reasonable to build a clustering model. K-means is the most suitable algorithm for this analysis
since it is easy to build clusters using k-means.
5. Analyzing patterns: Since this problem statement requires you to draw patterns and insights about
the crimes, this step mainly involves creating reports and drawing conclusions from the data model.
6. Validate the model: At this stage, you should evaluate the efficiency of the data model by using
the testing data set and finally calculate the accuracy of the model by using a confusion matrix.

Solution:

1. Import the data model:

The Bangalore Crime dataset obtained from Kaggle website is as shown below:

66
Introduction to Data Science Lab REVA University

p2.xlsx

2. Data Cleaning:

After removing the redundant values, the dataset is as shown below:

p2.xlsx

3. Data Exploration:

The residual plot is as shown below

X Variable 1 Residual Plot

40000000
20000000
Residuals

0
0 1000 2000 3000 4000
-20000000
-40000000
X Variable 1

4. Data modeling and validation

Using the Regression tool of excel , the dataset obtained is analysed as shown below . The y intercept and
Coefficient of regression values are as shown in the below snapshot.

67
Introduction to Data Science Lab REVA University

68
Introduction to Data Science Lab REVA University

Additional Projects
1. Walmarts Sales forcast
2. Movie Recommendation Engine
3. Text Mining
4. Chicago crime Analysis

5. Gender and age detection system

6. Emotion recognition software
7. Customer Segmentation system
8. Android chatbot
9. Movie recommendation system
10. Fraud app detection software

69
Introduction to Data Science Lab REVA University

Appendix
Installation Guide

70
Introduction to Data Science Lab REVA University

What is Microsoft Excel?

Microsoft Excel is a spreadsheet program that is used to record and analyse numerical data. Think of a
spreadsheet as a collection of columns and rows that form a table. Alphabetical letters are usually assigned
to columns and numbers are usually assigned to rows. The point where a column and a row meet is called a
cell. The address of a cell is given by the letter representing the column and the number representing a row.

How to Open Microsoft Excel?

Running Excel is not different from running any other Windows program. If you are running Windows
with a GUI like (Windows XP, Vista, and 7) follow the following steps.

 Click on start menu

 Point to all programs
 Point to Microsoft Excel
 Click on Microsoft Excel

Follow the following steps to run Excel on Windows 8.1

 Click on start menu

 Search for Excel N.B. even before you even typing, all programs starting with what you have typed
will be listed.
 Click on Microsoft Excel

71
Introduction to Data Science Lab REVA University

Lab setup to be done before starting the execution of lab programs

ADDING-IN THE DATA ANALYSIS TOOLPACK TO EXCEL

Statistical analysis such as descriptive statistics and regression requires the Excel Data Analysis add-in.
The default configuration of Excel does not automatically support descriptive statistics and regression
analysis.
You may need to add these to your computer (a once-only operation).

Excel 2007: The Data Analysis add-in should appear at right-end of Data menu as Data Analysis.
If not then

72
Introduction to Data Science Lab REVA University

9. Click the Microsoft Office Button, and then click Excel Options.

Click on Microsoft office

button

2. Click Add-Ins, and then in the Manage box, select Excel Add-ins.

73
Introduction to Data Science Lab REVA University

Click on Analysis tool pack

Click on Add on menu

10. Click Go.

11. In the Add-Ins available box, select the Analysis ToolPak check box, and then click OK.
Tip If Analysis ToolPak is not listed in the Add-Ins available box, click Browse to locate it.

74
Introduction to Data Science Lab REVA University

If you get prompted that the Analysis ToolPak is not currently installed on your computer,

12. click Yes to install it.

75
Introduction to Data Science Lab REVA University

13. After you load the Analysis ToolPak, the Data Analysis command is available in the Analysis
group on the Data tab.

In Data Menu - Data Analysis button will

be displayed as shown

This is one time procedure to be followed to add on the Data Analysis button to the Excel. After this
procedure is done.

76