ARTIFICIAL INTELLIGENCE
Lab Manual
[Fall/ Spring 20__]
Student Name: _______________
Student Id: _______________
Prepared By: Dr. Noman Islam
Instructor: Dr. Noman Islam
LIST OF EXPERIMENTS
S. No Date Experiment
1 __/__/__ To study and implement a chatbot using DialogFlow
2 __/__/__ To setup the environment and familiarize with Python
3 __/__/__ To study and implement algorithms in Python
4 __/__/__ To study and implement Graph search algorithms in Python
5 __/__/__ To study and understand numpy library
6 __/__/__ To study and implement pandas library
7 __/__/__ To study and implement Artificial Neural Network using Keras
8 __/__/__ To study and implement Convolutional Neural Network using
Keras
9 __/__/__ To study and implement LSTM using Keras
10 __/__/__ To study and implement a web application in Django
11 __/__/__ To study and implement generative models based on LSTM to
generate text in Keras
Lab 1: To study and implement a chatbot using DialogFlow
The objective of this lab is to develop an admission chatbot using DialogFlow. DalogFlow gives
users new ways to interact with your product by building engaging voice and text-based
conversational interfaces powered by AI. You can connect with users on the Google Assistant,
Amazon Alexa, Facebook Messenger, and other popular platforms and devices.
Lab Tasks:
1. Login to dialogflow.com by using your Gmail account.
2. Create an agent Admission that can answer questions related to admission.
3. Create an intent with name “Ask programs” such that user can ask for the admission
programs at Iqra University.
4. Provide example questions to train the agent on this intent.
5. Provide sample responses as answer to this question.
6. Test your intent by asking questions
7. Create an intent named “Program Details” with parameter “degree program” and “query”
8. Provide example questions to train the agent on this intent such as “What is the
percentage requirement for BS(CS)”
9. Provide sample responses as answer to this question.
10. Provide a default value for the degree program.
11. Test your intent by asking questions.
12. Now make degree program required and provide a default prompt.
13. Test your intent by asking questions.
14. Provide a speech response and then test your intent.
15. Add a question “How about another degree program (such as BBA)”
16. Set the “query” as context variable
17. Now publish your chatbot
Lab 2: To setup the environment and familiarize with Python
The objective of this lab is to set up the Python environment and get some familiarity with the
language.
To set up the environment, follow the steps below:
1. Download and install Anaconda. Anaconda is the leading open data science platform
powered by Python
2. Download and install PyCharm. PyCharm is an Integrated Development Environment
(IDE) used in computer programming, specifically for the Python language.
Lab Tasks:
1. Write a small program in Python to print your CV.
2. Write a program that takes the month (1…12) as input. Print whether the season is summer,
winter, spring or autumn depending upon the input month.
3. To determine whether a year is a leap year, follow these steps:
1. If the year is evenly divisible by 4, go to step 2. Otherwise, go to step 5.
2. If the year is evenly divisible by 100, go to step 3. Otherwise, go to step 4.
3. If the year is evenly divisible by 400, go to step 4. Otherwise, go to step 5.
4. The year is a leap year (it has 366 days).
5. The year is not a leap year (it has 365 days).
Write a program to input an year as integer. Using if…else, determines whether the
input is a leap year or not.
4. Write a program that takes a line as input and finds the number of letters and digits in the
input
5. Write a program that takes a sentence as input. Compute the frequency of each words and
prints them.
Lab 3: To study and implement basic algorithms in Python
In this lab, we will familiarize ourselves with functions, classes and other advanced constructs of
python.
Lab Tasks:
1. Write a program to generate a dictionary that contains (i,sqrt(i)), where i is an integer
between 1 and n. n is a number input by the user.
2. Write a simple calculator program using functions add, sub, mul and div. The program
should accepts two numbers and an operator and calls the corresponding function to
perform the operation.
3. Write a function that generates a list with values that are square of number between 1 and
20.
4. Define a class named Shape with static method printType. Define methods draw() and
area(). Now define two class Rectangle and Triangle. Rectangle has two attributes length
and width. The Triangle class has attributes a,b and c. Override the two methods of shape
class. Demonstrate the functionality of class by creating its objects.
5. Using recursion, write a program to calculate the reverse of a string.
Lab 4: To study and implement Graph search algorithms in Python
In this lab, we are going to implement searching algorithms in Python. There are two popular
searching algorithms i.e. Depth First Search (Fig. 3a) and Breadth First Search (Fig 3b).
DFS(G,v) ( v is the vertex where the search starts )
Stack S := {}; ( start with an empty stack )
for each vertex u, set visited[u] := false;
push S, v;
while (S is not empty) do
u := pop S;
if (not visited[u]) then
visited[u] := true;
for each unvisited neighbour w of u
push S, w;
end if
end while
END DFS()
3a: Pseudo-code for Depth First Search
BFS(Graph, root):
create empty set S
create empty queue Q
root.parent = NIL
add root to S
Q.enqueue(root)
while Q is not empty:
current = Q.dequeue()
if current is the goal:
return current
for each node n that is adjacent to current:
if n is not in S:
add n to S
n.parent = current
Q.enqueue(n)
3b: Pseudo-code for Breadth First Search
Fig 3: Pseudo-code for Graph Searching algorithms
Lab Task:
1. Provide the implementation of DFS and BFS algorithms in Python.
Lab 5: To study and understand numpy library
In this lab, we are going to explore numpy. NumPy is an acronym for "Numeric Python" or
"Numerical Python". It is an open source extension module for Python, which provides fast
precompiled functions for mathematical and numerical routines.
Lab Task:
Open the Python Notebook provided with this lab and perform the tasks.
a. Import the "numpy" library as "np".
In [ ]:
b. Create an array of shape (2, 3, 4) of zeros.
In [ ]:
c. Create an array of shape (2, 3, 4) of ones
In [ ]:
d. Create an array with values 0 to 999 using the "np.arange" function
In [ ]:
e. Create an array from the list [2, 3.2, 5.5, -6.4, -2.2, 2.4] and assign it to the variable "a"
In [ ]:
f. Do you know what a[1] will equal? Print it to see
In [ ]:
g. Try printing a[1:4] to see what that equals
In [ ]:
h. Create a 2-D array from the following list and assign it to the variable "a": [[2, 3.2, 5.5, -6.4, -2.2,
2.4], [1, 22, 4, 0.1, 5.3, -9], [3, 1, 2.1, 21, 1.1, -2]]
In [ ]:
i. Can you guess what the following slices are equal to? Print them to check your understanding. a[:,
3] a[1:4, 0:4] a[1:, 2]
In [ ]:
j. Create a 2-D array of shape (2, 4) containing two lists (range(4), range(10, 14)) and assign it to the
variable "arr".Print the shape of the array. Print the size of the array. Print the maximum and
minimum of the array
In [ ]:
In [ ]:
In [ ]:
k. Continue to use the array "arr" as defined above.Print the array re-shaped to (2, 2, 2).Print the
array transposed.Print the array flattened to a single dimension. Print the array converted to floats.
In [ ]:
l. Create an an array counting from 1 to 20 inclusive
In [ ]:
m. The array of multiples of 3 greater than 0 and less than 30
In [ ]:
n. The array of 8 equally spaced floats x where 0 ≤ x ≤ 1
In [ ]:
o. Use np.arange and reshape to create the array A = [[1 2 3 4] [5 6 7 8]]
In [ ]:
p. Use np.array to create the array B = [1 2]
In [ ]:
q. Use broadcasting to add B to A to create the final array A + B
In [ ]:
In [ ]:
In [ ]:
Lab 6: To study and implement pandas library
Pandas is a Python package providing fast, flexible, and expressive data structures designed to
make working with “relational” or “labeled” data both easy and intuitive. It aims to be the
fundamental high-level building block for doing practical, real world data analysis in Python.
Lab Task:
Open the Python Notebook provided with this lab and perform the tasks.
1. Create a data series with marks of students : 75, 80, 79, 60
In [ ]:
2. Create a data frame with name of students, id and marks
In [ ]:
3. Now read the file 'data.csv' in panda
In [ ]:
4. What are the columns in the dataframe?
In [ ]:
5. Sort the data based on Marks obtained. Fill all the 'na' cells with 0
In [ ]:
6. Display the top 10 rows
In [ ]:
7. Display the last 10 rows
In [ ]:
8. Display only the odd rows
In [ ]:
9. Display only those students who got failed in examination
In [ ]:
10. Find out the basic statistical info about data
In [ ]:
11. How many students got A, B, C, F?
In [ ]:
12. What are the mean scores for students who got A, B, C, F?
In [ ]:
Lab 7: To study and implement Artificial Neural Network using Keras
Keras is a powerful easy-to-use Python library for developing and evaluating deep learning
models. It wraps the efficient numerical computation libraries Theano and TensorFlow and
allows you to define and train neural network models in a few short lines of code. Install Keras
by using the following command:
> pip install keras
Lab Tasks:
1. Initialize the random number generator
from keras.models import Sequential
from keras.layers import Dense
import numpy
# fix random seed for reproducibility
numpy.random.seed(7)
2. Load the data
# load pima indians dataset
dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",")
# split into input (X) and output (Y) variables
X = dataset[:,0:8]
Y = dataset[:,8]
Now create a model:
# create model
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
3. Compile the model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
4. Fit the model
model.fit(X, Y, epochs=150, batch_size=10)
5. Evaluate the model
scores = model.evaluate(X, Y)
print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
6. Perform Predictions
predictions = model.predict(X)
# round predictions
rounded = [round(x[0]) for x in predictions]
print(rounded)
Lab 8: To study and implement Convolutional Neural Network using Keras
Convolutional Neural Networks (CNN) are biologically-inspired variants of MLPs. A
Convolutional Neural Network (CNN) is comprised of one or more convolutional layers (often
with a subsampling step) and then followed by one or more fully connected layers as in a standard
multilayer neural network. In this lab, you will discover how to develop and evaluate deep learning
models for object recognition in Keras.
Lab Tasks:
Load the CIFAR-10 dataset in Keras.
Create the following model:
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(3, 32, 32), padding='same', activation='relu',
kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same',
kernel_constraint=maxnorm(3)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(512, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
Fit and evaluate the above model. What is the accuracy of your model?
Lab 9: To study and implement LSTM using Keras
The Long Short-Term Memory network or LSTM network is a type of recurrent neural network
used in deep learning. In this lab, you will discover how to develop LSTM networks in Python
using the Keras deep learning library to address a demonstration time-series prediction problem.
Lab Tasks:
1. Download the dataset from https://datamarket.com/data/set/22u3/international-airline-
passengers-monthly-totals-in-thousands-jan-49-dec-60#!ds=22u3&display=line
2. Develop an LSTM network model and train it on the downloaded dataset.
3. Fit and evaluate the model. What is the accuracy of your model?
Lab 10: To study and implement a web application in Django
In this lab, we will study how can we implement a small web application in Django. Django is a
framework for the development of web-based applications in Python. Django was designed to help
developers take applications from concept to completion as quickly as possible. Django includes
dozens of extras you can use to handle common Web development tasks. Django takes care of user
authentication, content administration, site maps, RSS feeds, and many more tasks — right out of
the box. Django takes security seriously and helps developers avoid many common security
mistakes, such as SQL injection, cross-site scripting, cross-site request forgery and clickjacking.
Its user authentication system provides a secure way to manage user accounts and passwords.
Lab Tasks:
1. Install django by using the following command:
$ pip install Django
2. Create a small project in Django by typing the following commands:
$ django-admin startproject mysite
3. Create a small view and map it to the URL.
Lab 11: To study and implement generative models based on LSTM to generate text in
Keras
In this lab, we will use LSTM to build a generative model that can produce text similar to the
data it is trained on.
Step 1: Necessary imports
import numpy as np
import keras
import numpy as np
from keras import layers
import random
import sys
Step 2: Reweight distribution
def reweight_distribution(original_distribution, temperature=0.5):
distribution = np.log(original_distribution) / temperature
distribution = np.exp(distribution)
return distribution / np.sum(distribution)
Step 3: Training data
def loadFile():
text = open('cricket.txt').read().lower()
return text
text = loadFile()
Step 4: Vectorize the data
maxlen = 60
step = 3
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
sentences.append(text[i: i + maxlen])
next_chars.append(text[i + maxlen])
print('Number of sequences:', len(sentences))
chars = sorted(list(set(text)))
print('Unique characters:', len(chars))
char_indices = dict((char, chars.index(char)) for char in chars)
print('Vectorization...')
x = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):
for t, char in enumerate(sentence):
x[i, t, char_indices[char]] = 1
y[i, char_indices[next_chars[i]]] = 1
Step 5: Define a sample function
def sample(preds, temperature=1.0):
preds = np.asarray(preds).astype('float64')
preds = np.log(preds) / temperature
exp_preds = np.exp(preds)
preds = exp_preds / np.sum(exp_preds)
probas = np.random.multinomial(1, preds, 1)
return np.argmax(probas)
Step 6: Develop the model
model = keras.models.Sequential()
model.add(layers.LSTM(128, input_shape=(maxlen, len(chars))))
model.add(layers.Dense(len(chars), activation='softmax'))
optimizer = keras.optimizers.RMSprop(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)
model.fit(x, y, batch_size=128, epochs=10)
Step 7: Generate the text
start_index = random.randint(0, len(text) - maxlen - 1)
generated_text = text[start_index: start_index + maxlen]
print('--- Generating with seed: "' + generated_text + '"')
sys.stdout.write(generated_text)
for i in range(2000):
sampled = np.zeros((1, maxlen, len(chars)))
for t, char in enumerate(generated_text):
sampled[0, t, char_indices[char]] = 1.
preds = model.predict(sampled, verbose=0)[0]
next_index = sample(preds, 0.5)
next_char = chars[next_index]
generated_text += next_char
generated_text = generated_text[1:]
sys.stdout.write(next_char)
Lab Tasks:
1. Develop a desktop application based on above code to generate text similar to training
data.
2. Develop a web application based on above code.
