Vansh 2822649

PANIPAT INSTITUTE OF
ENGINEERING AND TECHNOLOGY

Department of AI & ML

PYTHON LAB - II
(PC-CS-AIML - 220 A)

Submitted to: Submitted by:

Ms. JYOTI VANSH
Asst. Professor B. Tech CSE - AIML
4th Semester (2822649)

Affiliated to:

KURUKSHETRA UNIVERSITY, KURUKSHETRA, INDIA

1|Page
Vansh 2822649

INDEX

Serial Program Date Teacher’s

No. Signature
Write a program to implement of
1 Basic Python Libraries-numpy,
scipy.
Write a program to implement of
2 Basic Python Libraries-matplotlib,
pandas.
Write a program to create samples
3 from population.

Write a program to evaluate Mean,

4 Median, Mode of dataset.

Write a program to implement

5 Central Limit Theorem in dataset.

Write a program to implement

6 Measure of Spread in datset.
Write a program to implement
7 program to differentiate between
descriptive and inferential statistics.
Write a program to implement pmf,
8 pdf and cdf.

Write a program to implement

9 different visualization techniques on
sample
Write a program to implement
10 different hypothesis test on sample
dataset.

2|Page
Vansh 2822649

Program No. 1
Aim: Write a program to implement numpy and scipy library of python.

Program:-

# numpy Library

# one dimensional array

import numpy as np

# Creating a one-dimensional array

arr1 = np.array([1, 2, 3, 4, 5])
print("One-dimensional array (arr1):")
print(arr1)

# two dimensional array

# Creating a two-dimensional array

arr2 = np.array([[1, 2, 3], [4, 5, 6]])
print("\nTwo-dimensional array (arr2):")
print(arr2)

# three dimensional array

# Creating a three-dimensional array

arr3 = np.array([[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [1, 2, 3]]])
print("\nThree-dimensional array (arr3):")
print(arr3)

Output:

3|Page
Vansh 2822649

#The Basics

import numpy as np

# Create the numpy array

a = np.array([[[1, 2], [3, 4]], [[5, 6], [7, 8]]])

# Print the numpy array

print("Array 'a':")
print(a)

# Print the data type of the array

print("\nData type of 'a':")
print(a.dtype)

# Print the size of each element in the array (in bytes)

print("\nSize of each element in 'a' (itemsize):")
print(a.itemsize)

# Print the total number of bytes consumed by the elements of the array
print("\nTotal number of bytes (nbytes):")
print(a.nbytes)

# Print the initial memory location of the array

print("\nInitial memory location of 'a':")
print(a.data)

# Print the strides of the array

print("\nStrides of 'a':")
print(a.strides)

# Print the number of dimensions of the array

print("\nNumber of dimensions (ndim):")
print(a.ndim)

# Print the shape of the array

print("\nShape of 'a':")
print(a.shape)

Output:

4|Page
Vansh 2822649

#Append

import numpy as np

# Appending one-dimensional arrays

a1 = np.array([5, 8])
a2 = np.array([9, 2])
print("Appending one-dimensional arrays:")
print(np.append(a1, a2, axis=0))

# Appending two-dimensional arrays along axis 1

a1 = np.array([[5, 8, 3], [2, 6, 4]])
a2 = np.array([[9, 2, 8], [2, 4, 2]])
print("\nAppending two-dimensional arrays along axis 1:")
5|Page
Vansh 2822649
print(np.append(a1, a2, axis=1))

Output:

#Reshape

import numpy as np

# Original array
a = np.array([[1, 2, 3], [4, 5, 6]])

# Create a view of the array

c = a.view()

# Reshape the view to (3, 2)

c = c.reshape(3, 2)

# Print the original array

print("Original array 'a':")
print(a)

# Print the reshaped view 'c'

print("\nReshaped array 'c':")
print(c)

Output:

# Zeros, Ones, and Custom Values

import numpy as np

6|Page
Vansh 2822649
# Creating an array of zeros with shape (2, 3)
e = np.zeros([2, 3])
print("Array 'e' filled with zeros:")
print(e)

# Creating an array of ones with shape (2, 3)

f = np.ones([2, 3])
print("\nArray 'f' filled with ones:")
print(f)

# Creating an array filled with the value 5 with shape (2, 3)

g = np.full([2, 3], 5)
print("\nArray 'g' filled with fives:")
print(g)

Output:

#Arithmetic operations

import numpy as np
a = np.array([[1, 2, 2, 3], [1, 3, 4, 5], [1, 2, 3, 4], [1, 3, 4, 2]])
b = np.array([[2, 2, 2, 3], [2, 3, 4, 5], [2, 2, 3, 4], [2, 3, 4, 2]])

# Arithmetic Operators
add = a + b
sub = a - b
mul = a * b
div = a / b
exp = a ** 2
mod = a % 3

print("\nArithmetic Operators:")
7|Page
Vansh 2822649
print(f"Addition:\n{add}")
print(f"Subtraction:\n{sub}")
print(f"Multiplication:\n{mul}")
print(f"Division:\n{div}")
print(f"Exponentiation:\n{exp}")
print(f"Modulus:\n{mod}")

Output:

#Statistical operations
8|Page
Vansh 2822649

import numpy as np

# 1D Array
a1= np.array([1, 2, 3, 4, 5])

# Statistical measures for 1D Array

print("\n1D Array Statistical Functions:")
print("Mean:", np.mean(a1))

print("Median:", np.median(a1))
print("Minimum:", np.min(a1))
print("Maximum:", np.max(a1))
print("Standard Deviation:", np.std(a1))
print("Variance:", np.var(a1))
print("Sum:", np.sum(a1))
print("Product:", np.prod(a1))
print("Count Nonzero:", np.count_nonzero(a1))

Output:

# Statistical operations by axis for 3D Array

import numpy as np

# 3D Array
a3 = np.array([[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [10, 11, 12]], [[13, 14, 15], [16, 17, 18]]])
print("\n3D Array - Statistical Operations by Axis:")
print("Depth-wise Minimum:")
print(np.min(a3, axis=0))
print("Height-wise Minimum:")
print(np.min(a3, axis=1))
print("Width-wise Minimum:")
print(np.min(a3, axis=2))
9|Page
Vansh 2822649
print("Depth-wise Maximum:")
print(np.max(a3, axis=0))
print("Height-wise Maximum:")
print(np.max(a3, axis=1))
print("Width-wise Maximum:")
print(np.max(a3, axis=2))
print("Depth-wise Mean:")
print(np.mean(a3, axis=0))
print("Depth-wise Median:")

print(np.median(a3, axis=0))
print("Cumulative Sum along Depth:")
print(np.cumsum(a3, axis=0))

Output:

10 | P a g e
Vansh 2822649

#Comparison

import numpy as np

# Check if each element of array 'a' is less than 5

a = np.array([1, 2, 3, 4])

11 | P a g e
Vansh 2822649
print(a < 5)

# Check if each element of array 'b' is less than each element of array 'a'
a = np.array([1, 2, 3, 4])
b = np.array([5, 6, 7, 8])
print(b < a)

# Check if the arrays 'a' and 'b' are equal element-wise

print(np.array_equal(a, b))

Output:

#Bitwise

#bitwise operation(and)

import numpy as np

a1= np.array([1,3])
a2= np.array([4,5])
a3 = np.bitwise_and(a1, a2)
print ("Bitwise operation(and) =",a3)

#bitwise operation(or)

a1= np.array([5,8])
a2= np.array([9,2])
a3 = np.bitwise_and(a1, a2)

print ("Bitwise operation(or) =",a3)

#bitwise operation(XOR)

a1= np.array([5,6])

a2= np.array([9,3])
a3 = np.bitwise_xor(a1, a2)
print ("Bitwise operation(XOR) =" ,a3)

#bitwise operation(left shift)

12 | P a g e
Vansh 2822649
a1= np.array([5,8])
a2= np.array([9,2])
a3 = np.left_shift(a1, a2)
print ("Bitwise operation(left shift) =",a3)

Output:

#Copying

import numpy as np

c = np.array([[2, 5, 6, 3], [8, 3, 5, 5], [1, 2, 3, 4]])

# No copy: e is just another reference to c

e=c
print("No copy (e):")
print(e)

# Shallow copy: f is a new array object, but shares data with c

f = c.view()
print("Shallow copy (f):")
print(f)

# Reshape c to check if it affects f

c_reshaped =c.reshape(4,3) # Note: reshape doesn't modify the original array in
place
print("After reshaping c (does not affect f):")
print(f)

# Check if f is the same object as c

print("Is f the same object as c?", f is c)

# Deep copy: g is a new array object with a copy of the data from c
g = np.copy(c)

print("Deep copy (g):")

print(g)

# Modify an element in c to see if it affects g

c[2][3] = 9 # Change element at position (2, 3) to 9
13 | P a g e
Vansh 2822649
print("After modifying c:")

print("c:")
print(c)
print("g (should not be affected):")
print(g)

# Check if g is the same object as c

print("Is g the same object as c?", g is c)

Output:

#scipy Library

from scipy import constants

print(constants.kilo)

from scipy.sparse import csr_matrix

14 | P a g e
Vansh 2822649
import numpy as np

a=np.array([[0,1,1,0,0],[1,2,0,0,0]])

print(csr_matrix(a))
print (csr_matrix(a).data)
print (csr_matrix(a).count_nonzero)
print(csr_matrix(a).eliminate_zeros)
print(csr_matrix(a).sum_duplicates)

Output:

#Root

from scipy.optimize import root

from math import cos
import numpy as np

def eq(x):
return x+np.cos(x)
myroot=root (eq,0)
print(myroot.x)

Output:

#Linear Algebra

import numpy as np

15 | P a g e
Vansh 2822649

a1= np.array([[5,8,3],[2,6,4]])
print(np.transpose(a1))
print(np.trace(a1))

Output:

Program No. 2
Aim: Write a program to implement matplotlib and pandas library of python.

16 | P a g e
Vansh 2822649
Program:-

#Line Graph
import matplotlib.pyplot as plt
import numpy as np

xpoints = np.array([0, 6])

ypoints = np.array([0, 250])

plt.plot(xpoints, ypoints)
plt.show()

Output:

#Two line grapgh

import matplotlib.pyplot as plt

import numpy as np

x1= np.array([0,1,2,])
y1= np.array([3,4,5])
x2= np.array([6,7,8])
y2= np.array([9,10,11])

plt.plot(x1,y1)
plt.plot(x2,y2)
plt.plot(x1,y1,x2,y2)
plt.show()

Output:
17 | P a g e
Vansh 2822649

#zigzag line
xpoints = np.array([2, 4, 8, 10])
ypoints = np.array([2, 4, 2, 4])

plt.plot(xpoints, ypoints)
plt.show()

OUTPUT:

#markers
ypoints = np.array([3, 8, 1, 10])

plt.plot(ypoints, marker = 'o')

plt.show()

18 | P a g e
Vansh 2822649
OUTPUT:

#marker size, edge color and face color

ypoints = np.array([3, 8, 1, 10])

plt.plot(ypoints, marker = 'o', ms = 20, mec = 'g', mfc = 'y')

plt.show()

OUTPUT:

#label and title

x = np.array([80, 85, 90, 95, 100, 105, 110, 115, 120, 125])
y = np.array([50, 42, 40, 37, 30, 25, 20, 16, 9, 4])

plt.plot(x, y)
plt.title("alt./temp.")
plt.xlabel("Altitude")
19 | P a g e
Vansh 2822649
plt.ylabel("Temprature")
plt.show()

OUTPUT:

#subplots

#plot 1:
x = np.array([0, 1, 2, 3])
y = np.array([3, 8, 1, 10])

plt.subplot(1, 2, 1)
plt.plot(x,y)

#plot 2:

x = np.array([0, 1, 2, 3])
y = np.array([10, 20, 30, 40])

plt.subplot(1, 2, 2)
plt.plot(x,y)
plt.show()

OUTPUT:

20 | P a g e
Vansh 2822649

Program No. 3
21 | P a g e
Vansh 2822649

Aim: Write a program to create samples from population in python.

Program :-

import pandas as pd

#using dataset

df = pd.read_csv('data.csv')
print(df.sample(10))

Output:

#using series

a = [1, 7, 2, 8, 5, 12, 6, 18]

s = pd.Series(a)
print(s.sample(3))

Output:

#using dataframe

data = {
"student": ["Ram", "Shyam", "Geeta", "Seeta", "Kush", "Khushi", "Dhruv"],

"percentage": [58, 79, 45, 84, 67, 36, 97]

}

22 | P a g e
Vansh 2822649
df1 = pd.DataFrame(data)
print(df1.sample(3))

Output:

Program No. 4

23 | P a g e
Vansh 2822649
Aim: Write a program to evaluate mean, median and mode of a dataset in
python.

Program :-

import pandas as pd
a = [1, 6, 17, 23, 45, 23, 67, 84, 17, 96]
df = pd.Series(a)

mean = df.mean()
print(“Mean “,mean)

median = df.median()
print(“Median “,median)

mode = df.mode()
print(“Mode “,mode)

Output:

#Using datframes

import pandas as pd

data = {
'Name':['Vansh','Sujal','Sumit','Rounak','Ayush'],
'Age':[20,20,19,20,21],
'Class':['A','B','A','C','D'],
'Marks':[40,39,38,37,39]
}
c = pd.DataFrame(data)
print(c)

print("Mean of 'Marks' column:", c['Marks'].mean())

print("Minimum value in 'Marks' column:", c['Marks'].min())

print("Maximum value in 'Marks' column:", c['Marks'].max())
print("Variance of 'Marks' column:", c['Marks'].var())
24 | P a g e
Vansh 2822649
print("Median of 'Marks' column:", c['Marks'].median())

Output:

#CSV FILE

import pandas as pd

# Read the CSV file into a DataFrame

e = pd.read_csv(r'D:\4th SEMESTER\PYTHON LAB\FILE.csv')

# Print the DataFrame

print(e)

# Print descriptive statistics of the DataFrame

print(e.describe())

Output:

25 | P a g e
Vansh 2822649

Program No. 5

Aim: Write a program to implement Central Limit Theorem in dataset.

Program :-

import numpy as np
import matplotlib.pyplot as plt

num=[1,11,25,56,28,90,72,34]
means=[]
for j in num:
np.random.seed(1)
x=[np.mean(np.random.randint(-40,40,j)) for _i in range (1000)]
means.append(x)
k=0
fig,ax=plt.subplots(2,2,figsize=(8,8))

for i in range (0,2):

for j in range (0,2):
ax[i,j].hist(means[k],10,density=True)
ax[i,j].set_title(label=num[k])
k=k+1
plt.show()

Output:

26 | P a g e
Vansh 2822649

Program No. 6

Aim: Write a program to implement measures of spread in python.

Program :-

import numpy as np

# Creating a NumPy array

a = np.array([1, 2, 9, 23, 3, 32, 12, 11, 24, 12])

# Calculating and printing the standard deviation

std_dev = np.std(a)
print("Standard Deviation:", std_dev)

# Calculating and printing the variance

variance = np.var(a)
print("Variance:", variance)

Output:

27 | P a g e
Vansh 2822649

Program No. 7

Aim: Write a program to differentiate between descriptive and inferential

statistics.
Program:-
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

# Creating DataFrame with random normal distribution

data = pd.DataFrame({
'Height': np.random.normal(170, 5, 100),
'Weight': np.random.normal(65, 7, 100)
})

# Descriptive Statistics
print("Descriptive Statistics:")
print("Mean:")
print(data.mean())
print("\nStandard Deviation:")
print(data.std())
print("\nSummary Statistics:")
print(data.describe())

# Graphical Representation using Matplotlib

plt.figure(figsize=(14, 7))

# Histograms
plt.subplot(2, 2, 1)
plt.hist(data['Height'], bins=10, alpha=0.7, color='blue', edgecolor='black')
plt.title('Height Distribution')
plt.xlabel('Height (cm)')
plt.ylabel('Frequency')

plt.subplot(2, 2, 2)
plt.hist(data['Weight'], bins=10, alpha=0.7, color='green', edgecolor='black')
28 | P a g e
Vansh 2822649

plt.title('Weight Distribution')
plt.xlabel('Weight (kg)')
plt.ylabel('Frequency')

plt.xlabel('Height (cm)')
plt.ylabel('Weight (kg)')
plt.grid(True)
plt.show()

Output:

# Inferential Statistics (Example: T-test)

from scipy.stats import ttest_ind

sample1 = np.random.normal(170, 5, 30)

sample2 = np.random.normal(172, 5, 30)
29 | P a g e
Vansh 2822649

t_statistic, p_value = ttest_ind(sample1, sample2)

print("\nInferential Statistics (T-test):")
print("T-statistic:", t_statistic)
print("P-value:", p_value)
if p_value < 0.05:
print("The difference between the two samples is statistically significant.")
else:
print("The difference between the two samples is not statistically significant.")

Output:

30 | P a g e
Vansh 2822649

Program No. 8

Aim: Write a program to implement pmf, pdf and cdf.

Program :-

#PMF(probability mass function)

from scipy.stats import binom

n=20
p=0.5

r_values=list(range (n+1))
print(r_values)

mean,var=binom.stats(n,p)

print(mean)
print(var)

dist_1=[binom.pmf(r,n,p)for r in r_values]
print("r\tp(r)")

for i in range (n+1):

print(str(r_values[i])+"\t" +str(dist_1[i]))

print("mean ="+str(mean))
print("variance ="+str(var))

31 | P a g e
Vansh 2822649

Output:

#PDF(Probability Density Function)

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

N = 400

data = np.random.randn(N)
count,bins_count = np.histogram(data,density=True,bins=10)

print(count)
print(bins_count)

pdf=count/sum(count)
print(pdf)

plt.plot(bins_count[1:],pdf,label="PDF")
plt.legend()
plt.show()

32 | P a g e
Vansh 2822649

Output:

#CDF (Cumulative Distribution Function)

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

N = 400
data = np.random.randn(N)
count,bins_count = np.histogram(data,density=True,bins=10)

print(count)
print(bins_count)
pdf=count/sum(count)

cdf=np.cumsum(pdf)
print(cdf)

plt.plot(bins_count[1:],cdf,label="CDF")
plt.legend()
plt.show()

33 | P a g e
Vansh 2822649

Output:

34 | P a g e
Vansh 2822649

Program No. 9

Aim: Write a program to implement different visualization techniques on sample

dataset.
Program :-

#Bar Graph

import numpy as np
import matplotlib.pyplot as plt

# creating the dataset

data = {'C':20, 'C++':15, 'Java':30, 'Python':35}
courses = list(data.keys())
values = list(data.values())
fig = plt.figure(figsize = (10, 5))

# creating the bar plot

plt.bar(courses, values, color ='maroon', width = 0.4)
plt.xlabel("Courses offered")
plt.ylabel("No. of students enrolled")
plt.title("Students enrolled in different courses")
plt.show()

Output:

35 | P a g e
Vansh 2822649

# Histogram

import numpy as np
import matplotlib.pyplot as plt

# Creating the dataset for histogram

scores = [22, 45, 23, 67, 89, 90, 55, 47, 68, 90, 73, 87, 45, 58, 62, 71, 85, 42, 48, 60]
fig = plt.figure(figsize=(10, 5))

# Creating the histogram

plt.hist(scores, bins=10, color='blue', edgecolor='black')
plt.xlabel('Scores')
plt.ylabel('Number of Students')
plt.title('Distribution of Students\' Scores')
plt.show()

Output:

36 | P a g e
Vansh 2822649

#Pie Chart

import matplotlib.pyplot as plt

# Creating the dataset for pie chart

data = {'C': 20, 'C++': 15, 'Java': 30, 'Python': 35}
courses = list(data.keys())
values = list(data.values())

fig = plt.figure(figsize=(10, 5))

# Creating the pie chart

plt.pie(values, labels=courses, autopct='%1.1f%%', startangle=140)

plt.title('Distribution of Students in Different Courses')

plt.show()

Output:

37 | P a g e
Vansh 2822649

#Scatter Plot

import matplotlib.pyplot as plt

# Creating the dataset for scatter plot

math_scores = [22, 45, 23, 67, 89, 90, 55, 47, 68, 90]
science_scores = [20, 48, 21, 60, 85, 88, 50, 40, 65, 88]

fig = plt.figure(figsize=(10, 5))

# Creating the scatter plot

plt.scatter(math_scores, science_scores, color='green')

plt.xlabel('Math Scores')
plt.ylabel('Science Scores')
plt.title('Math vs Science Scores')
plt.show()

Output:

38 | P a g e
Vansh 2822649

#Line Plot

import matplotlib.pyplot as plt

# Creating the dataset for line plot

months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun']
students = [10, 15, 20, 30, 40, 55]

fig = plt.figure(figsize=(10, 5))

# Creating the line plot

plt.plot(months, students, marker='o', color='purple')

plt.xlabel('Months')
plt.ylabel('Number of Students')
plt.title('Growth in Number of Students Enrolled in Python Course')
plt.show()

Output:

39 | P a g e
Vansh 2822649

Program No. 10

Aim: Write a program to implement different hypothesis test on sample dataset.

Program :-

#T-Test (sample size <30)

#One Sample Test

from scipy.stats import ttest_1samp

import numpy as np

#we are having 10 ages and mean is 30 or not

ages=[32,34,29,29,22,39,38,37,36,30,26,22,22]
print(ages)

ages_mean=np.mean(ages)
print(ages_mean)
tset,pval=ttest_1samp(ages,30)
print("p-value =",pval)

if pval<0.05:
print("we are rejecting null hypothesis")
else:
print("we are accepting the null hypothesis")

Output:

40 | P a g e
Vansh 2822649

#Z-Test (sample size >30)

import scipy.stats as stats

import numpy as np

sample_mean=110
population_mean=100
population_std=15
population_size=50
alpha=0.05

z_score=(sample_mean-population_mean)/(population_std/np.sqrt(population_size))
print('z-score =',z_score)

p_value=1-stats.norm.cdf(z_score)
print('p-value',p_value)

if p_value<alpha:
print("we are rejecting null hypothesis")
else:
print("we are accepting the null hypothesis")

Output:

41 | P a g e