9

39

9
PSG Institute of Technology and Applied Research
03

03

03
0
3

43

43

43
24

32

2
23

23

23
2
Name: Rahul A Scan to verify results
55

55

55

55
71

71

71

71
Email: 23d101@[Link]
Roll no: 715523243039
Phone: 9677304434
Branch: PSG iTech
Department: AI&DS
Batch: 2027
Degree: [Link] AI&DS
39

39

39
3
30

30

30

30
24

24

24

24
2027_IV_AI&DS_Data Science Analytics Lab
23

23

23
52
55

55

55
5
71

71

71

71
NeoColab_PSGiTech_2027_Data Science Analytics_Week 7_COD

Attempt : 1
Total Mark : 40
Marks Obtained : 40

Section 1 : Coding

1. Problem Statement
9

39

9
03

03

03
0
43

43

43

43
Dr. Sophia, a medical researcher, is conducting a study to compare the
32

32

32

2
23
2

effectiveness of two medications, A and B, in reducing patient symptoms.

55

55

55

55
Given a CSV file containing the medication type and the corresponding
71

71

71

71

reduction in symptoms, write a program to perform a two-sample Z-test at

a 1% significance level. The program should compute the mean reduction
for each medication, Z-score, and critical value, then determine whether
there is a statistically significant difference in the effectiveness of the two
medications.

Answer
[Link]
39

39

9
03

03
30

30

import pandas as pd
24

24

24

24
23

23

23

23

import [Link] as stats

55

55

55

55
71

71

71

71
 9

39

9
from [Link] import norm
03

03

03
0
3

43

43

43
import numpy as np
24

32

2
import math as m
23

23

23
2
55

55

55

55
import os
71

71

71

71
import sys

# Prompt the user to enter the filename

file_name = input()

# Get the current directory of the script

current_directory = [Link][0]

# Construct the full path to the CSV file

39

39

39
file_path = [Link](current_directory, file_name)
3
30

30

30

30
24

24

24

24
# Read CSV file into a DataFrame
23

23

23
52
55

55

55
df = pd.read_csv(file_path)

5
71

71

71

71
# Separate Medication A and B
reduction_a=df[df['Medication']=='A']['Reduction']
reduction_b=df[df['Medication']=='B']['Reduction']

# Given data
a=reduction_a.mean()
b=reduction_b.mean()
9

39

9
# Step 2: Calculate the Z-score
03

03

03
0
43

43

43

43
z_sc_n=a-b
32

32

32

2
z_sc_d=[Link]((reduction_a.std(ddof=0)**2/
23
2

2
55

55

55

55
len(reduction_a))+(reduction_b.std(ddof=0)**2/len(reduction_b)))
71

71

71

71

z=z_sc_n/z_sc_d

# Print results
alpha=0.01
c=[Link](1-alpha/2)
print(f"Mean Reduction A: {a}")
print(f"Mean Reduction B:{b}")
print(f"Z-score: {z}")
print(f"Critical Value: ±{c}")
39

39

9
03

03
30

30

3
24

24

24

24

if abs(z)>c:
23

23

23

23
55

55

55

55
71

71

71

71
 9

39

9
print("Conclusion: There is a significant difference between the effectiveness
03

03

03
0
3

43

43

43
of the two medications.")
24

32

2
else:
23

23

23
2
55

55

55

55
print("Conclusion: There is no significant difference between the effectiveness
71

71

71

71
of the two medications.")

# Compare Z-score with critical value

[Link]
Medication,Reduction
A,15.2
39

39

39
A,14.8
3
30

30

30

30
A,16.0
24

24

24

24
A,15.1
23

23

23
52
55

55

55
A,14.5

5
71

71

71

71
A,15.7
A,14.3
A,15.4
A,16.3
A,15.9
A,15.0
A,14.7
A,14.9
A,16.1
9

39

9
A,15.8
03

03

03
0
43

43

43

43
A,15.3
32

32

32

2
A,15.5
23
2

2
55

55

55

55
A,14.6
71

71

71

71

A,14.4
A,15.6
B,12.5
B,13.2
B,12.7
B,13.5
B,12.9
B,13.8
B,12.6
39

39

B,14.0
03

03
30

30

B,13.1
24

24

24

24

B,12.8
23

23

23

23
55

55

55

55
71

71

71

71
 9

39

9
B,13.2
03

03

03
0
3

43

43

43
B,12.5
24

32

2
B,13.6
23

23

23
2
55

55

55

55
B,12.8
71

71

71

71
B,13.3
B,12.4
B,13.5
B,13.1
B,12.9
B,13.0
B,12.7
B,13.4
B,13.2
39

39

39
B,12.6
3
30

30

30

30
B,13.7
24

24

24

24
B,12.9
23

23

23
52
55

55

55
B,13.5

5
71

71

71

71
B,12.8
B,13.1
B,12.7
B,13.3
B,13.0
B,12.9
B,12.6
B,13.8
B,12.5
9

39

9
B,13.6
03

03

03
0
43

43

43

43
B,12.4
32

32

32

2
B,13.4
23
2

2
55

55

55

55
B,12.9
71

71

71

71

B,13.2
B,12.8

Status : Correct Marks : 10/10

2. Problem Statement

Emma, a university researcher, wants to analyze the effectiveness of online

39

39

9
03

03

and offline teaching methods by comparing their mean scores. Given a

30

30

3
24

24

24

24

CSV file containing sample size, mean, and standard deviation for both
23

23

23

23

teaching methods, write a program to perform a two-sample Z-test

55

55

55

55
71

71

71

71
 9

39

9
assuming equal variance. The program should compute the Z-score,
03

03

03
0
3

43

43

43
critical Z-score, and P-value, then determine whether there is a statistically
24

32

2
23

23

23
significant difference between the two teaching methods.

2
55

55

55

55
71

71

71

71
Answer
[Link]
import numpy as np
import [Link] as stats
import pandas as pd
import os
import sys
39

39

39
3
# Prompt the user to enter the filename
30

30

30

30
24

24

24

24
file_name = input()
23

23

23
52
55

55

55
5
# Get the current directory of the script
71

71

71

71
current_directory = [Link][0]

# Construct the full path to the CSV file

file_path = [Link](current_directory, file_name)

# Read CSV file into a DataFrame

df = pd.read_csv(file_path)

# Assuming the first row is Offline and the second row is Online
9

39

9
03

03

03
f=[Link][0,:].values
0
43

43

43

43
l=[Link][1,:].values
32

32

32

2
23
2

2
55

55

55

55
# Convert values to integers/floats
71

71

71

71

z_n=l[1]-f[1]
z_d=((f[2]**2/f[0])+(l[2]**2/l[0]))**0.5
z=z_n/z_d
from [Link] import norm
p = 2 * (1 - [Link](abs(z)))
cz=1.959963984540054
print(f"Z-Score: {z}")
print(f"Critical Z-Score: {1.959963984540054}")
# Null Hypothesis = mu_1 - mu_2 = 0
39

39

9
03

03

if abs(z)>cz:
30

30

3
24

24

24

24

print("Reject the null hypothesis.\nThere is a significant difference between

23

23

23

23

the online and offline classes.")

55

55

55

55
71

71

71

71
 9

39

9
# Calculate the test statistic (z-score)
03

03

03
0
3

43

43

43
print(f"P-Value: {p}")
24

32

2
print("Reject the null hypothesis.\nThere is a significant difference between
23

23

23
2
55

55

55

55
the online and offline classes.")
71

71

71

71
# Calculate the critical value
else:
print("Fail to reject the null hypothesis.\nThere is no significant difference
between the online and offline classes.")
print(f"P-Value: {p}")
print("Fail to reject the null hypothesis.\nThere is no significant difference
between the online and offline classes.")
39

39

39
# Print Z-score and critical Z-score
3
30

30

30

30
24

24

24

24
# Compare the test statistic with the critical value
23

23

23
52
55

55

55
5
71

71

71

71
# Approach 2: Using P-value
[Link]
Sample_Size,Mean,Std_Dev
50,75,10
60,80,12
[Link]
Sample_Size,Mean,Std_Dev
9

39

9
10,65,8
03

03

03
0
43

43

43

43
20,70,9
32

32

32

2
23
2

[Link]
55

55

55

55
71

71

71

71

Sample_Size,Mean,Std_Dev
20,85,11
30,88,13
[Link]
Sample_Size,Mean,Std_Dev
30,95,15
40,100,17
[Link]
39

39

9
03

03
30

30

Sample_Size,Mean,Std_Dev
24

24

24

24

40,55,7
23

23

23

23
55

55

55

55
71

71

71

71
 9

39

9
50,60,8
03

03

03
0
3

43

43

43
24
[Link]

32

2
23

23

23
2
55

55

55

55
Sample_Size,Mean,Std_Dev
71

71

71

71
60,78,10
70,82,11
[Link]
Sample_Size,Mean,Std_Dev
80,90,12
90,95,13
[Link]
39

39

39
Sample_Size,Mean,Std_Dev
3
30

30

30

30
100,85,14
24

24

24

24
110,88,15
23

23

23
52
55

55

55
5
71

71

71

71
Status : Correct Marks : 10/10

3. Problem Statement

Olivia, a quality control analyst at a tech company, is testing whether the

company’s claim that their device battery lasts an average of 12 hours is
statistically valid. Given a CSV file containing battery life measurements
from sample devices and a known population standard deviation of 0.5
9

39

9
03

03

03
hours, write a program to conduct a one-sample Z-test. The program
0
43

43

43

43
should compute the sample mean, Z-score, and critical Z-value for a two-
32

32

32

2
23
2

tailed test at a 5% significance level, then determine whether there is

55

55

55

55
71

71

71

71

sufficient evidence to refute the company’s claim.

Answer
[Link]
import pandas as pd
import [Link] as stats
import numpy as np
import os
39

39

import sys
03

03
30

30

3
24

24

24

24

# Prompt the user to enter the filename

23

23

23

23
55

55

55

55
71

71

71

71
 9

39

9
file_name = input()
03

03

03
0
3

43

43

43
24

32

2
# Get the current directory of the script
23

23

23
2
55

55

55

55
current_directory = [Link][0]
71

71

71

71
# Construct the full path to the CSV file
file_path = [Link](current_directory, file_name)

# Read CSV file into a DataFrame

df = pd.read_csv(file_path)

# Given company claim and known population standard deviation

btl=df['Battery Life'].mean()
39

39

39
print(f'Sample Mean: {btl}')
3
30

30

30

30
# Compute sample statistics from the dataset
24

24

24

24
n=len(df['Battery Life'])
23

23

23
52
55

55

55
print(f'Sample Size: {n}')

5
71

71

71

71
# Calculate the Z-score
s=df['Battery Life'].std()
z=(btl-12)/(0.5/(n**0.5))
print(f"Z-score: {z}")
c=1.959963984540054
print(f"Critical Value: ±{c}")
# Print results
if z<0:
if z<-1*c:
9

39

9
print("Conclusion: There is sufficient evidence to refute the company's claim
03

03

03
0
43

43

43

43
about battery life.")
32

32

32

2
else:
23
2

2
55

55

55

55
print("Conclusion: There is no sufficient evidence to refute the company's
71

71

71

71

claim about battery life.")

else:
if z>c:
print("Conclusion: There is sufficient evidence to refute the company's claim
about battery life.")
else:
print("Conclusion: There is no sufficient evidence to refute the company's
claim about battery life.")
39

39

9
03

03
30

30

# Compare Z-score with critical value to determine significance

24

24

24

24
23

23

23

23

[Link]
55

55

55

55
71

71

71

71
 9

39

9
4. Problem Statement
03

03

03
0
3

43

43

43
24

32

2
23

23

23
Michael, a statistics professor, wants to determine whether his class's

2
55

55

55

55
average test score significantly differs from the department's historical
71

71

71

71
average of 75. Given a CSV file containing student IDs and their scores,
write a program to compute the sample mean, standard deviation, Z-score,
and P-value. Based on the significance level of 0.05, determine whether
there is a statistically significant difference between the class average and
the department’s historical average.

Answer
[Link]
39

39

39
3
30

30

30

30
import pandas as pd
24

24

24

24
import [Link] as stats
23

23

23
52
from [Link] import norm
55

55

55
5
71

71

71

71
import numpy as np
import os
import sys

# Prompt the user to enter the filename

file_name = input()

# Get the current directory of the script

current_directory = [Link][0]
9

39

9
03

03

03
0

# Construct the full path to the CSV file

43

43

43

43
32

32

32

2
file_path = [Link](current_directory, file_name)
23
2

2
55

55

55

55
71

71

71

71

# Read CSV file into a DataFrame

df = pd.read_csv(file_path)
feat=df['Score']
m=[Link]()
sstd=[Link]()
z=(m-75)/(sstd/(len(feat)**0.5))
p = 2 * ([Link](abs(z)))
alpha = 0.05
c = [Link](1 - alpha / 2)
39

39

# Given historical department mean

03

03
30

30

print(f"Sample Mean: {m}")

3

3
24

24

24

24

print(f"Sample Standard Deviation: {sstd}")

23

23

23

23
55

55

55

55
71

71

71

71
 9

39

9
print(f"Z-score: {z}")
03

03

03
0
3

43

43

43
print(f"P-value: {p}")
24

32

2
if abs(z)>c:
23

23

23
2
55

55

55

55
print("Conclusion: There is a significant difference between the class average
71

71

71

71
and the department's historical average.")
else:
print("Conclusion: There is no significant difference between the class average
and the department's historical average.")

# Perform Z-test (assuming population std is unknown, we use t-test as an

approximation)
# Print results
# Significance Level (alpha)
39

39

39
3

[Link]
30

30

30

30
24

24

24

24
Student_ID,Score
23

23

23
52
55

55

55
1,80

5
71

71

71

71
2,70
3,75
4,78
5,74
[Link]
Student_ID,Score
19,81
20,79
9

39

9
21,74
03

03

03
0
43

43

43

43
22,75
32

32

32

2
23,76
23
2

2
55

55

55

55
24,77
71

71

71

71

25,78
26,73
27,72
28,80
29,81
30,79
31,74
32,75
33,76
39

39

34,77
03

03
30

30

35,78
24

24

24

24

36,73
23

23

23

23
55

55

55

55
71

71

71

71
71 71 71 71
55 55 55 55
23 2 32 23 23
24 43 24 24
30 30 3

99,81
98,80
97,72
96,73
95,78
94,77
93,76
92,75
91,74
90,79
89,81
88,80
87,72
86,73
85,78
84,77
83,76
82,75
81,74
80,79
79,81
78,80
77,72
76,73
75,78
74,77
73,76
03 03

100,79
39 9 39 9

Status : Correct
71 71 71 71
55 55 55 55
23 2 32 23 2 32
24 43 24 43
30 0 30 0
39 39 3 9 39

71 71 71 71
55 55 5 55
23 2 32
52
3 23
24 24 2
303
43
03 30 43
03
9 9 39 9

71 71 71 71
55 55 55 55
23 23
Marks : 10/10 23 23
24 2 24 2
3 03
43
03 30 43
03
9 9 39 9