Full Stack

Data Science EXPERT

Build a portfolio, create a network,
and land your dream job.

www.trainingbasket.in
 Table of Contents

03 Welcome

04 Designed For Success

05 Our Mission

06 Units & Overview

18 Capstone Projects

19 Assessment

20 Career Statistics

21 Testimonials

22 Partnerships

Full Stack Data Science

2
 Welcome

The Job Ready curriculum from Training Basket is a structured, self-paced online instruction
that will give you complete knowledge of Data Science in just six months. As a Full Stack Data
Scientist, you'll construct attractive, interactive AI applications using Python and its libraries.
Our Data Science experts from the industry take you through from scratch to the advanced
level and give exposure to industry-level projects from the ground up and provide you with a
solid foundation in AI. You'll learn about Machine Learning, which is used to train models. This
course will culminate in the study of Python which is the most widely used programming
language on the planet.

AI enables technical systems to perceive their environment, deal with what they perceive, solve
problems and act to achieve a specific goal. This is a one-of-a-kind online learning
environment.

Bootcamp-style program that prepares you for

a high-paying career in tech
Each unit in the Training Basket curriculum teaches a core concept, skill, language component,
or framework. You learn by viewing videos, and you may reinforce your skills by doing
interactive programming quizzes and challenges. Mini-exercises will help you implement
everything you've learned, and then you'll apply all you've learned in an individually graded,
hard assignment with feedback. After completing more than 10+ projects in this training and
passing the final exam, you will receive a Training Basket Certificate of Achievement and have
the skills that will better prepare you for entry-level employment as a Data Scientist.

Full Stack Data Science

3
 Designed For
Success

Online learning may be difficult, and we

understand how difficult it can be to learn on
your own. Thankfully, We've created AWARD-
WINNING LMS to Learn through 24*7 interactive
LMS with PPTs, Videos, Assignments, Case
Studies & Quizzes along with a progress tracker
with flexibility to match your needs your hectic
way of life.

Key Benefits of this

Job-ready Training

Live support A professional

Study at your Study and
and an online and finished
own pace career guidance
community portfolio

Full Stack Data Science

4
 Our Mission

Training Basket works to make education more Training Basket’s mission

inclusive and accessible so that individuals may is to diversify the tech industry
accomplish their goals. We've taught over through online-learning
50,000 individuals how to code and design however, if you already have some experience
since 2017, and our objective is to achieve long- but want to advance, Training Basket offers
term, systemic change in the IT industry. current and relevant skills to help you reach
Competency-based learning is used in Training where you need to go. You'll additionally
Basket training programs to reinforce what benefit from the Training Basket Slack, a
students have learned. We've reinvented the thriving online community where you can ask
learning process and created a tried-and-true questions and network with other students,
approach to help you get the skills and regardless of your past experience level. You'll
information you need to achieve your have weekly office hours, and Training Basket
support professionals will be accessible for
objectives. Stay on track with our points system,
advice and encouragement.
badges, and weekly activity journal, which has
been scientifically proved to enhance We designed this program to be
motivation. You didn't merely view a video an accessible alternative to
when you finished a course; you learned, bootcamps
practiced, and internalized an idea. Plus, at the We concluded that in order to diversify the IT
end of each lesson, Training Basket walks you industry, we needed a curriculum that was fully
through an immersive project, so you'll have a beginner-friendly, didn't result in student debt
portfolio of work ready to present as soon as and didn't demand any repayment. Many
you're through. Our Job-Ready programs are bootcamps cost huge amounts of money, or
geared toward beginners worse, force graduates to take a share of their
salary when they obtain a job. At a fraction of
the cost of bootcamps, Training Basket provides
high-quality courses, comprehensive learning
assistance, and professional expertise.

Full Stack Data Science

5
Units & Overview

Unit-1 Python

Python Libraries
Database and Statistics Unit-2

Unit-3 Machine Learning

Deep Learning Unit-4

Unit-5 Natural Language Processing

MLOPS Unit-6

Full Stack Data Science

6
 Unit-1

Python
Week 1-5

Intro to data science and python

• Case study based discussion and problem solving thought process initiation
• Different Analytical Domain Industry mentors guest talk

Python
• Python , Anaconda and relevant packages installations
• Structure of python program (comments , indentations)
• Operators
• Data type , variable
• User input ,string methods

Data structure
• Mutable /Immutable
• List/tuple
• Sets / Dictionary
• List , sets and dictionary comprehension

Control Structures
• If,Else , Elif and Nested if else
• While and For loop
• Break and Continue
• Keywords in python
• Pattern making

Functions
• Basic functions
• Built-in
• User dened functions
• *args , **kwargs

Advanced Functions
• Maps , lter, reduce
• Iterators and iterables
• Closures / decorators
• Generators

Full Stack Data Science

7
 Unit-1

File Handling and Exception Handling

Raise error and Built in errors

Object Oriented Programming

• Class , Object
• Data abstraction , encapsulation , Inheritance, Dunder methods
• Customized modules

Flask

Multithreading and Multiprocessing

Assignments
Assignment with 15 questions
Assignment with 10 question

Full Stack Data Science

8
 Unit-2

Python Libraries
Database and Statistics
Week 6-10

Numpy
• Indexing/slicing
• Appending /Inserting on axis
• Mathematical and statistical operations
• Sort/Condition
• Transpose Operations
• Joining/splitting
• Linear Algebra

Pandas
• Data Extraction
• Series/Dataframe Creation
• Indexing and Slicing
• Conditions/Grouping/Imputations
• Append/concat/merge/join
• Datetime functionalities and resampling
• Excel functions

Data visualization with Matplotlib and Seaborn

• Customization of matplotlib and seaborn
• Scatterplots/barplot/histogram/density plots
• Box Plot and outlier detection
• Visualization Linear relationship
• Univariate , Bivariate and Multivariate analysis

Data base
• Mysql
• MongoDB

Full Stack Data Science

9
 Unit-2

Statistics
• Probability
• Conditional Probability
• Dependent and Independent events
• Bayes Theorem
• Descriptive / Inferential
• Variance / standard deviation
• Covariance And correlation(Pearson/Spearman)
• Central Limit theorem
• Pdf , cdf , pmf
• Types of distributions
• Condence Intervals
• Hypothesis testing
• Z Test,t test,chi-2 test
• F-test/Anova

Project 1 : Analysis on coivid-19 data(india)

Libraries used in Project :

statistics pandas matplotlib,seaborn and numpy

Full Stack Data Science

10
 Unit-3

Machine Learning
Week 11-18

Introduction to Machine Learning

• Difference Between AI, ML and DL
• Applications of Machine Learning
• Categorization of Machine Learning
• Supervised / Unsupervised / Semi Supervised
• Parametric vs NonParametric

Supervised (Regression/ Classication)

Regression
• Linear Regression
• Polynomial Regression
• Lasso Regression
• Ridge Regression
• Stepwise Regression
• Bayesian Regression

Classication
• Logistic Regression
• KNN
• SVM (Support Vector Machines)
• Decision Tree
• Naive Bayes
• LDA
• Classication for Imbalanced Dataset

Ensemble Learning
• Random forest
• Adaboost
• Gradient boosting
• Xgboost

Unsupervised Learning
• K-means
• PCA
• Hierarchical Clustering
• DBSCAN/ HDBSCAN

Scikit Learn
• Introduction to SciKit Learn (sklearn)
• Sample Dataset in SciKit Learn
• Articial Generation of Dataset

Full Stack Data Science

11
 Unit-3

EDA and Data Wrangling

• Null Values Imputation
• Outlier Detection
• Univariate/ Bivariate/ Multivariate Analysis
• Encoding
• Label Encoder
• Ordinal Encoding
• One Hot Encoding
• Scaling
• MinMaxScaling

Feature Selection and Dimensionality Reduction

• Feature Selection
• Filter Methods
• Wrapper Methods
• Embedding(Ridge /Lasso)
• Dimensional Reduction
• PCA
• AutoEncoders

Modeling
• Train/ Test Split
• Assumptions
• Basic Modeling
• Under tting, Over tting, Bias and Variance
• Loss Functions

Cross-Validation and HyperParameter Tuning

• Holdout Validation
• K-fold cross Validation
• Stratied Kfold
• Cross_val_score
• GridSearchCV
• RandomizedSearchCV

Evaluation Metrics and Improvement Techniques

• MSE/ MAE/ R2/Adjusted R2
• Accuracy measurement
• Confusion Matrix
• Precision/ Sensitivity/ Specicity/ F1 Score
• AUC/ ROC

Criteria to Select Models

• Bias vs Variance Trade offs

Full Stack Data Science

12
 Unit-3

Time Series:
• Stationarity
• AutoRegression/ AutoCorrelation
• ACF vs PACF Plots
• Smoothing Time Series
• Dicky Fuller Test
• Time Series Decomposition
• Modeling and Forecasting
• AR/ MA/ ARIMA/ SARIMA

Project 2: Advance House Price Prediction

Libraries used in project :

Sklearn , pandas, numpy,seaborn,scipy,matplotlib

Project 3. Water quality test

Libraries used In project:

Sklearn , pandas, numpy,seaborn,scipy,matplotlib

Project 4. Flight price prediction

Libraries used In project:

Sklearn , pandas, numpy,seaborn,scipy,matplotlib , ask

Project 5. Stock price prediction

Libraries used in project:

Sklearn , pandas, numpy,seaborn,scipy,matplotlib

Full Stack Data Science

13
 Unit-4

Deep Learning
Week 19-23

Deep Learning
• Articial Neural Networks In Python
• Perceptron and relate it with Logistic Regression
• Multiple layer Neural network
• Similarities and Differences with Basic ML
• Forward Propagation
• Back Propagation Algorithm
• Vanishing Gradient and Exploding Gradient
• Activation Functions:
• Non Linearity
• Sigmoid / Tanh Function
• Relu /Leaky Relu /Gelu
• Softmax Function
• Optimizers
• Gradient Descent
• Stochastic Gradient Descent

Momentum
• AdaGrad
• RMSProp
• NAG
• Adam/ Nadam

Tensorow:
• Tensors
• Session
• Placeholders and Variables
• Hands on with Tensorow
• Graphs

Keras:
• Purpose of Keras
• Sequential vs Functional
• Model Creating
• Using while Regression and Classication

Pytorch
• Tensors
• Autograd
• Graphs
• Pytorch.nn
• Control Flow and Weight Sharing

Full Stack Data Science

14
 Unit-4

OpenCV
• Read/ Write Images
• Gray to BGR
• Filter2D
• Scaling/ Rotation
• Laplace Transformation

Types of Networks
• Feed Forward Networks
• Fully Connected Networks
• Recurrent Neural Networks
• Convolutional Networks
• RBM
• Deep Belief Networks

CNN(Convolutional Neural Network)

• Convolution/ Filters/ Pooling
• Backpropagation in CNN
• Masking and RoI
• Types Of CNN
• RCNN, FastRCNN, YOLO

Architectures
• LeNet/ Alexnet
• VGG 16/ 19
• ResNet
• MobileNet

Project 6. Face recognition on custom dataset

Libraries used in Project:

Numpy , pandas,matplotlib, seaborn,tensorow , keras

Project 7. Image classication on custom dataset

Libraries used in Project:

Numpy , pandas,matplotlib, seaborn,tensorow , keras

Full Stack Data Science

15
 Unit-5

Natural Language Processing

Week 24-26

• Recurrent Neural Networks

• Classical RNN
• LSTM/GRU
• Vanishing Gradient
• Exploding Gradient
• Bidirectional RNN
• Transfer Learning
• ImageNet
• Need of Transfer Learning
• Freezing of Layers
• Reusing of Structure
• WordEmbedding
• Frequency vs Production based embedding
• Count Vector/ TFIDF/ Co Occurrence
• Bag of Words / Skip Gram
• Word2Vec /GloVe
• Syntactic and Semantic Analysis
• Tagging

Attention Mechanism
• Soft and Hard Attention
• Local and Global attention
• Monotonic Alignment and Predictive Alignment
• Multi headed Attention

Miscellaneous
• Semi Supervised Learning
• Transformers/Bert/GPT3
• Graphs and GNN

Project 8. Language translation

Libraries used in project :
Numpy,pandas,matplotlib,seaborn,tensorow,keras,numpy

Project 8. Spam classication

Libraries used in project :
Numpy,pandas,matplotlib,seaborn,tensorow,keras,numpy

Project 9. Text classication using Bert

Libraries used in project :
Numpy,pandas,matplotlib,seaborn,tensorow,keras,numpy

Full Stack Data Science

16
 Unit-6

MLOps
Week 26-30

Github
• Life Cycle
• Local Repository
• Add / Commit / Push / Pull
• Merge
• Stas

AWS
• AWS Servers
• AWS Sagemaker
• S3 Buckets
• Build Train Deploy

Docker
• Architectures
• Images
• Containers
• Container Linking
• Instruction Commands

Spark
• RDD
• Pyspark
• Broadcast and Accumulator
• Mlibb

Full Stack Data Science

17
 Capstone Projects

1 Fake News Detection Using Python

2 Medical Image Segmentation (Polyp segmentation)

3 Credit card fraud detection

4 Project on Sentiment Analysis

5 Project on Speech Recognition through the Emotions

Interview Preparation

Full Stack Data Science

18
 Assessment
Our lecturers are working
experts in the field of technology
who give useful and constructive
advice.
{./.}

</>

{./.}

This Job-Ready curriculum incorporates You'll have the chance to fix the problems
project-based learning, which allows you to and resubmit the project for further
apply the skills you're learning by working on assessment. As you go through the course,
projects of increasing complexity. Each you will show your developing skill set by
project you create will be evaluated completing quizzes and coding tasks,
separately using a thorough grading criteria culminating in a Final Exam. The Final Exam is
that is specific to that assignment. Aside from your opportunity to demonstrate what
an overall grade of Exceeds, You will receive you've learned during this Training. You must
individualised written feedback on your correctly answer at least 70% of the
project in the form of Expectations, Meets questions on the Final Exam in order to
Expectations, or Needs Work. Don't panic if succeed. If you don't meet that standard, you
your project is labelled as Needs Work. can study and repeat the exam the next day.

Full Stack Data Science

19
 Statistics on a Career

Day to Day Tasks as a

You'll be ready to start your new job in the
tech bus i nes s af ter you have your Data Scientist
Certificate! As an entry-level Data Scientist, Ÿ A data scientist's daily tasks revolve
these are some of the options available to around data
you. Ÿ Gathering data and looking at data
Ÿ Shaping data, but in many different ways
and for many different reasons

A typical entry-level Data Science job pays

₹60,000 higher per year than the National

₹11,00,000 Average Wage Index.

According to Glassdoor.com, the typical

base income in INDIA

With new technologies being invented

every day, the IT sector has been rising year
Levels after year and shows no signs of slowing
₹1700k down.

₹1500k

₹1300k

₹1100k

L1 L4 L7

Average Salary Growth

Full Stack Data Science

20
 Testimonials

Initially, I thought online training wouldn't work.

But After Joining the Training Basket, I realized
online training classes are more convenient. We can
learn study material at any time using LMS. Trainer
mainly focuses on real-life scenarios like how to
handle the complexity of the issue. Thank you so
much, Training Basket, for providing excellent
service.
- Nagaraju

I got placed after completing the course of

Data Science. It was excellent training; the
detailed course content and support system
were terrific. I will recommend the Training
Basket without any doubt.

- Vipin Kumar

The excellent learning experience with the

Training Basket. Great efforts from the
instructor and outstanding support assistance.
The guidance was very appreciable. I would
recommend Training Basket to my friends and
colleagues

- Priya Singh

Full Stack Data Science

21
 Partnerships
We collaborate with a number of IT
businesses to guarantee that our students
receive the most up-to-date and relevant
education possible.

Companies With
Which We Collaborate

Full Stack Data Science

22