AI PathShala on

Python for Data Science

By AI-Shala Technologies Pvt Ltd

SCHEDULE

Date Da Lecture Modules Resources

y No.
Sat 1a - Welcome to the Summer Slides:
Training Program Lecture-1 A Career in ML
- A Career in Machine
Learning
21-July-23

1b Setup and installation Slides: Lecture-1c

(Instructor: Dr Anil Sharma)
- Dual boot linux with windows
(suggested)
•Win10 and Ubuntu:
https://itsfoss.com/install-
ubuntu-1404-dual-boot-mode-
windows-8-81-uefi/
•Win11 and Ubuntu:
https://www.youtube.com/wat
ch?v=T78rCJ_i1no

W 2 Introduction to python , Lecture :

E 24-July-23 Mon conditional statement , loop Python_basic_+_Programmin
E control g_concept.pdf
K (Instructor : Ayushi Pandey) Lab : Lab day 1

1 25-July-23 Tue 3 Function , OOPs Lab : Lab Day 2

(Instructor : Ayushi Pandey)

26-July-23 Wed 4 Data type Python Lab: Lab day 3

(Instructor : Ayushi Pandey)

4b Introduction to NumPy for Numpy.ipynb

numerical computing and array
manipulation.

27-July-23 Thu 5b Working with Pandas library for

data manipulation and analysis.
 28-July-23 Fri 6a Data cleaning, handling missing
values, and transforming data.

6b Exploratory data analysis (EDA)

techniques.

W 31-July-23 Mon 7a Visualizing data using Matplotlib

E for basic plots
E
7b Creating more advanced and
K interactive visualizations with
Seaborn and Plotly
2
1-Aug-23 Tue 8a Customizing plots, adding labels,
titles, and annotations.

8b Visualizing relationships and

patterns in data

2-Aug-23 Wed 9 Introduction to machine learning

concepts .
Supervised learning algorithms
(linear regression, logistic
regression, decision trees, random
forests, support vector machines)

3-Aug-23 Thu 10 Unsupervised learning algorithms

(clustering, dimensionality
reduction)
Model evaluation and validation
techniques
Data Preparation and Feature
Engineering

4-Aug-23 Fri 11 Regression analysis: Linear

regression, polynomial regression

7-Aug-23 Mon 12 Classification algorithms: Logistic

W regression, decision trees, random
E forests
E Classification algorithms: support
8-Aug-23 Tue 13 a
K vector machines, and naive Bayes.

3 13 b Model evaluation, performance

metrics, and cross-validation.

9-Aug-23 Wed 14 Clustering techniques: K-means,

hierarchical clustering, and
DBSCAN.

10-Aug-23 Thu 15 Dimensionality reduction

techniques: Principal Component
Analysis (PCA), tSNE.
 11-Aug-23 Fri 16 Anomaly detection using
unsupervised methods.

14-Aug-23 Mon 17 Basics of neural networks

W
E Introduction to Tensorflow/Pytorch
E Building and training neural
15-Aug-23 Tue 18
K networks using TensorFlow or
PyTorch
4
16-Aug-23 Wed 19 Deep learning applications (image
classification, natural language
processing)

17-Aug-23 Thu 20 a Basics of NLP and text

preprocessing techniques

20 b Building text classification models

using NLP libraries such as NLTK
or spaCy.

18-Aug-23 Fri 21 Privacy and data protection

Bias and fairness in algorithms

Ethical responsibilities in data

collection and analysis

WEEK-WISE TIMINGS:
Mon - Fri (9am - 1pm)

Pre-requisites:
Basic knowledge of programming

Post-requisites:
By the end of the module, students should be able to:

1. Formulate real-world problems using machine learning

2. Understand a wide variety of machine learning algorithms (like classification, regression,
deep learning, RL, etc.)
3. Understand how to evaluate models generated from data
4. Using ML and DL libraries like Scikit learn and Pytorch/Tensorflow

Assessment methodology:
The program follows regular assessment of the student through quizzes, assignments, and exams.
Certificate will be awarded to students who score at least 30% from the following weightage and end
exam score is greater than 10/25.
Tentative evaluation weightage:
Quizzes: 25%
Exam: 30%
Assignments / projects : 40%
Class interaction: 5%

Individual modules of the program:

1. Introduction to Python for Data Science

a. Introduction to Python programming language
b. Setting up the development environment
c. Installation and setup of essential Python libraries

2. Data Manipulation and Analysis

a. Introduction to NumPy for numerical computing and array manipulation.
b. Working with Pandas library for data manipulation and analysis.
c. Data cleaning, handling missing values, and transforming data.
d. Exploratory data analysis (EDA) techniques.

3. Data Visualization
a. Visualizing data using Matplotlib for basic plots.
b. Creating more advanced and interactive visualizations with Seaborn and Plotly.
c. Customizing plots, adding labels, titles, and annotations.
d. Visualizing relationships and patterns in data

4. Machine Learning with Scikit-Learn

a. Introduction to machine learning concepts
b. Supervised learning algorithms (linear regression, logistic regression, decision
trees, random forests, support vector machines)
c. Unsupervised learning algorithms (clustering, dimensionality reduction)
d. Model evaluation and validation techniques
e. Data Preparation and Feature Engineering

5. Supervised learning
a. Regression analysis: Linear regression, polynomial regression.
b. Classification algorithms: Logistic regression, decision trees, random forests,
support vector machines, and naive Bayes.
c. Model evaluation, performance metrics, and cross-validation.

6. Unsupervised learning
a. Clustering techniques: K-means, hierarchical clustering, and DBSCAN.
b. Dimensionality reduction techniques: Principal Component Analysis (PCA), t-
SNE.
c. Anomaly detection using unsupervised methods.
 7. Introduction to Deep Learning with TensorFlow or PyTorch
a. Basics of neural networks
b. Introduction to Tensorflow/Pytorch
c. Building and training neural networks using TensorFlow or PyTorch
d. Deep learning applications (image classification, natural language processing)

8. Introduction to Natural Language Processing (NLP)

a. Basics of NLP and text preprocessing techniques.
b. Building text classification models using NLP libraries such as NLTK or spaCy.

9. Real-world Data Science Projects

a. Practical hands-on project where students apply their knowledge to solve a real-
world data problem using Python.

10. Ethical Considerations in Data Science

a. Privacy and data protection
b. Bias and fairness in algorithms
c. Ethical responsibilities in data collection and analysis

Resources:

1. Basics (this Quora post should say all things https://qr.ae/pGbPyG )

a. Probability
i. https://www.wileyindia.com/mathematics-statistics-
textbooks/probability-and-stochastic-processes-3ed-an-indian-
adaptation.html
b. Linear algebra
i. Course by Gilbert Strang
ii. Essence of linear algebra course
2. Books
a. By Christopher Bishop (for ML) http://www.amazon.in/Pattern-Recognition-
Learning-Information-Statistics/dp/0387310738
b. By Stephen Marsland (for ML) http://www.amazon.in/Machine-Learning-
Algorithmic-Perspective-Recognition/dp/1420067184
c. By Ian Goodfellow and Yoshua Bengio (for DL)
https://www.deeplearningbook.org/
d. By Michael Nielson (for neural networks)
http://neuralnetworksanddeeplearning.com/
e. http://www.d2l.ai/
 f. RL Book by Sutton and Barto:
https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2nd
Ed.pdf

3. Good tutorials/talks/videos
a. Deep Learning: Theoretical Motivations by Yoshua Bengio, DLSS 2015.
b. A Beginners Guide to Deep Neural Networks by Natalie Hammel and
Lorraine Yurshansky, Google Research Blog 2015.
c. Deep Learning RNNaissance with Dr. Juergen Schmidhuber at NYC ML
Meetup 2014
d. The Unreasonable Effectiveness of Deep Learning by Yann LeCun Johns
Hopkins University, Center for Language and Speech Processing, 2014.
e. Deep Learning for Vision: Tricks of the trade Facebook, Bay Area Vision
Meeting 2013.
f. Deep Learning, Self-Taught Learning and Unsupervised Feature Learning by
Andrew Ng, Graduate Summer School: Deep Learning, Feature Learning
2013.
g. Deep Learning of Representations by Yoshua Bengio at GoogleTechTalks
2012.
h. Deep Residual Learning for Image Recognition, K He, X Zhang, S Ren, J Sun
- arXiv preprint arXiv:1512.03385, 2015.
i. Understanding Deep Image Representations by Inverting Them, A
Mahendran, A Vedaldi, CVPR 2015.
j. Visualizing and Understanding Convolutional Networks, MD Zeiler, R Fergus,
ECCV 2014.
k. Visualizing and Understanding Recurrent Networks, A Karpathy, J Johnson,
FF Li - arXiv preprint arXiv:1506.02078, 2015.
l. Deep Learning Summer School, Montreal 2015.
m. Gan Zoo, curated list of all GANs.
n. Awesome Deep Vision - a curated list of deep learning resources for
computer vision.
o. Awesome Deep Learning - a curated list of deep learning resources for deep
learning.

4. Good papers
a. Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for
Visual Question Answering, H Xu, K Saenko - arXiv preprint
arXiv:1511.05234, 2015.
b. VQA : Visual Question Answering, Antol S, Agrawal A, Lu J, Mitchell M, Batra
D, Lawrence Zitnick C, Parikh D, ICCV 2105.
c. Sequence to Sequence – Video to Text, Venugopalan S, Rohrbach M,
Donahue J, Mooney R, Darrell T, Saenko K, ICCV 2015.
d. Batch Normalization: Accelerating Deep Network Training by Reducing
Internal Covariate Shift, S Ioffe, C Szegedy - arXiv preprint arXiv:1502.03167,
2015.
e. Dropout: A Simple Way to Prevent Neural Networks from Overfitting,
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R, JMLR
2014.
f. Spatial Transformer Networks, Jaderberg M, Simonyan K, Zisserman A, NIPS
2015.