R

PGP-
DATA SCIENCE
Course Module
Foundations
Introduction to programming using Python (3 weeks)
Introduction Data Structures
Ø Introduction to Python Ø List
Ø Basic Programming syntax Ø Tuple
Ø Variables Ø Dictionary
Ø Basic Arithmetic & logical operators Ø Array
(int, float) Ø List Comprehension
Ø Data Types

Conditional Statement in Python Iteration (loops)

Ø If Ø While Loop
Ø If-else Ø For Loop
Ø elif

Advance Python Python as OOP Language

Ø Functions Ø OOPS Concept- Class, objects,
Ø Methods Detailed Introduction
Ø Map Function Ø Inheritance-Multi level Inheritance,
Ø Reduce Single level Inheritance
Ø Filter Ø Encapsulation
Ø Lambda Ø Polymorphism
Ø Generators
Ø Iterators

Exploring Data Analysis ( 1 Week)

Ø Reading the Data

Ø Cleaning the Data

Ø Data Visualization in Python

Ø Summary statistics (mean, median, mode, variance, standard deviation)

Ø Seaborn

Ø Matplotlib

Ø Population VS sample

Ø Univariate and Multivariate statistics

Ø Types of variables – Categorical and Continuous

Ø Coefficient of correlations, Skewness and kurtosis

Statistical Methods for Decision Making (1 week)
Ø Brief Introduction To Statistics

Ø Probability distribution

Ø Normal distribution

Ø Poisson's distribution

Ø Bayes' theorem

Ø Central limit theorem

Ø Hypothesis testing

Ø One Sample T-Test

Ø Two Sample T-Test

Ø Anova and Chi-Square

Ø Pearson Co-relation

Ø Co-Variance

Ø Chebyshiv-Inequality Formula
Database Management System using My SQL Workbench (2 weeks)

Introduction
Introduction to DBMS
An Introduction to Relational Database
Concepts and SQL Accessing

Working on My SQL work bench

Data Servers MYSQL/RDBMS Concepts
Extraction, Transformation and Loading (“ETL”) Processes
Retrieve data from Single Tables-(use of SELECT Statement) and the
power of WHERE and ORDER by Clause. Retrieve and Transform data
from multiple Tables using JOINS and Unions
Introduction to Views Working with Aggregate functions, grouping and
summarizing Records Writing Sub queries
 Machine Learning Techniques
(Supervised Learning+ Unsupervised Learning)- (6 Weeks)

Regression
Linear
Introduction
Regression

Introduction to Regression Introduction to Linear Regression

Looking at regression through the Accuracy scores as a metric of model
perspective of machine learning performance
Brief Introduction to Regression
Techniques Measuring the importance of
individual variables in a regression
Brief Introduction to Best Fit line in model
Regression
Review - testing for individual
significance vs joint significance
Logistic
Regression Using the adjusted R^2 to compare
model with different number of
Introduction to Logistic Regression independent variables
Log transformation of dependent
Approaches to feature selection
and independent variables
Dealing with categorical independent Forward and backward selection
variables
Parameter tuning and Model
One hot encoding vs dummy variable evaluation
Modelling probabilistic dependent
Extending linear regression
variables
The sigmoid function and odds ratio Data transformations and
normalization
The concept of logit
The failure of OLS in estimating L1 & L2(LASSO AND RIDGE)
parameters for a logistic regression
Introduction to the concept of
Maximum likelihood estimation
Case Study
Advantages of the maximum
likelihood approach sigmoid function Case study on Linear Regression
Modelling a logistic regression
Case study on Logistic Regression
problem with a case study
Making predictions and evaluating
parameters
Featurization

Featurization, Model Selection & amp; Tuning

Feature engineering

Model selection and tuning

Model performance measures

Regularising Linear models

ML pipeline

Bootstrap sampling

Grid search CV
Randomized search CV
K fold cross-validation
 Classification
Decision
Introduction
Trees

Introduction to Classification Entropy and Ginny

Looking at Classification through Information Gain
the perspective of machine learning
Decision trees – Simple decision
Brief Introduction to Classification trees. Visualizing decision trees and
Techniques nodes and splits.
Balancing Data set
Working of the Decision tree
Binary classification vs Multi class algorithm.
classification
Importance and usage of Entropy
and Gini index.
Classification Manually calculating entropy using
Techniques gini formula and working out how to
split decision nodes
CART - Extending decision trees to
Evaluating decision tree models.
regressing problems.
Advantages of using CART. Accuracy metrics – precision, recall
and confusion matrix
The Bayes theorem. Prior probability.
Interpretation for accuracy metric.
KNN CLASSIFIER
The Gaussian NAÏVE'S BAYES Building a a robust decision tree
Classifier. model. k-fold cross validation -
Advantages against simple train
Assumptions of the Naive Bayes
test split.
Classifier.
Functioning of the Naïve's Bayes
algorithm.
Evaluating the model - Precision, Case Study
Recall, Accuracy metrics and k-fold
cross validation Case study on Classification Data Set
Random Forest
Voting Classifier
ROC Curve and AUC for binary
classification for Naive Bayes.
Extending Bayesian Classification for
Multiclass Classification
Support Vector Machine
KNN
Ensemble Techniques (1 week)

Bagging
Boosting( GRADIENT BOOSTING,ADA BOOSTING,XG BOOSTING)

Unsupervised Learning
K-Means
Introduction
Algorithm

What is Unsupervised Learning? The K-means algorithm.

The two major Unsupervised Measures of distance – Euclidean,
Learning problems - Dimensionality Manhattan and Minowski distance.
reduction and clustering.
The concept of within cluster sums
of squares.
Clustering
Using the elbow plot to select
Algorithms
optimum number of cluster's.

The different approaches to Case study on k-means clustering.

clustering – Heirarchical and K means
Comparison of k means and
clustering.
agglomerative approaches to
Heirarchical clustering - The concept clustering.
of agglomerative and divisive clustering.
Agglomerative Clustering – Working
PCA (Principal
of the basic algorithms.
Component Analysis)
Distance matrix - Interpreting
dendograms. Noise in the data and dimensional
Choosing the threshold to determine reduction.
the optimum number of clusters. Capturing Variance - The concept of
a principal components.
Assumptions in using PCA.
Case Study
The working of the PCA algorithm.
Eigen vectors and orthogonality of
The relationship between
principal components.
unsupervised and supervised
learning. What is complexity curve?
Case study on Dimensionality Advantages of using PCA.
reduction followed by a supervised Bulid a model using Principal
learning model. components and comparing with
Case study on Clustering followed normal model. What is the difference?
by classification model. Putting it all together.
Data Visualization Using Tableau (2 week)

Introduction
Ø Introduction to Visualization, Rules of Visualization

Ø How to Import The Data In Tableau?

Ø Blending the Data

Visualization in Tableau
Ø Data Types, Sources, Connections, Loading, Reshaping

Ø Data Aggregation

Ø Working with Continuous and Discrete Data

Ø Using Filters

Ø Using Calculated Fields and parameters

Ø Creating Tables and Charts

Ø Building Dash Boards and story boards

Ø Sharing Your Work and Publishing for wider audience

 R

Internship
Module
Module 1: Natural Language Processing and Speech Recognition
Introduction to Natural Language Processing
Lesson 1 - Feature Engineering on Text Data Lesson
Lesson 2 - Natural Language Understanding Techniques
Lesson 3 - Natural Language Generation
Lesson 4 - Natural Language Processing Libraries
Lesson 5 - Natural Language Processing with Machine Learning and Deep Learning
Introduction of Speech Recognition
Lesson 1 - Signal Processing and Speech Recognition Models
Lesson 2 - Speech to Text
Lesson 3 - Text to Speech
Lesson 4 - Voice Assistant Devices
Module 2 : Text Mining And Sentimental Analysis
Lesson 1 - Text cleaning, regular expressions, Stemming, Lemmatization
Lesson 2 - Word cloud, Principal Component Analysis, Bigrams & Trigrams
Lesson 3 - Web scrapping, Text summarization, Lex Rank algorithm
Lesson 4 - Latent Dirichlet Allocation (LDA) Technique
Lesson 5 - Word2vec Architecture (Skip Grams vs CBOW)
Lesson 6 - ext classification, Document vectors, Text classification using Doc2vec

Module 3: Reinforcement Learning

Lesson 1 - Introduction to Reinforcement Learning
Lesson 2 - Reinforcement Learning Framework and Elements
Lesson 3 - Multi-Arm Bandit
Lesson 4 - Markov Decision Process
Lesson 5 - Solution Methods
Lesson 6 - Q-value and Advantage Based Algorithms
Module 4: Time Series Forecasting
Lesson 1 - What is Time Series?
Lesson 2 - Regression vs Time Series
Lesson 3 - Examples of Time Series data
Lesson 4 - Trend, Seasonality, Noise and Stationarity
Lesson 5 - Time Series Operations
Lesson 6 - Detrending
Lesson 7 - Successive Differences
Lesson 8 - Moving Average and Smoothing
Lesson 9 - Exponentially weighted forecasting model
Lesson 10 - Lagging
Lesson 11 - Correlation and Auto-correlation
Lesson 12 - Holt Winters Methods
Lesson 13 - Single Exponential smoothing
Lesson 14 - Holt's linear trend method
Lesson 15 - Holt's Winter seasonal method
Lesson 16 - ARIMA and SARIMA
Module 5
Introduction to AI And Deep Learning
Ÿ What is Deep Learning ?

Ÿ Universal Function Approximator

Ÿ Neural Network

Ÿ Difference between ML and DL

Ÿ Major Types of NN-ANN,CNN and RNN

Ÿ Perceptron In Neural Network

Ÿ Solving the INPUT

Ÿ Bias

Ÿ Epoch

Ÿ Batch size

Ÿ Front Propagation

Ÿ Back Propagation

Ÿ Weight Updation in Back Propagation Formula

Ø Introduction Activation Function

Ÿ Types of Activation Function

Ÿ Vanishing Gradient Descent

Ÿ Exploding Gradient Descent

Ÿ Under Fitting and Over Fitting

Ø Introduction of Regularization Technique

Ÿ Regularization- L1 and L2 (Lasso and Rigid)

Ÿ Regulization - Drop Out

Ø Introduction of Weight Initialization Technique.

Ÿ Different Weight Initialization Technique

Ø Introduction of Grdient Decent

Ÿ TYPES OF GRADIENT DESCENT

Ÿ Convex and Non Convex Function

Ÿ Saddle Point
Ÿ Artificial Neural Network Lesson

Ÿ Deep Neural Network and Tools Lesson

Ÿ Deep Neural Net Optimization, Tuning, and Interpretability

Ÿ Convolutional Neural Net(CNN)

Ÿ Recurrent Neural Networks

Module 6: Advanced Deep Learning and Computer Vision

Introduction to Computer Vision
Lesson 1 - Prerequisites for the course
Lesson 2 - RBM and DBNs
Introduction to Image processing in CNN
Ÿ Introduction to Convolutional Neural Networks

Ÿ Famous CNN architectures

Ÿ Transfer Learning

Ÿ Classification model in image processing

Ÿ Semantic segmentation

Ÿ Instance Segmentation

Ÿ Other variants of convolution

Ÿ Metric Learning

Introduction to sequence Data Processing in RNN

Ÿ Introduction to RNN

Ÿ Advantages of RNN

Ÿ Disadvantages of RNN

Introduction of LSTM and GRU

Ÿ Long-short term memory (LSTM)

Ÿ Model of LSTM

Ÿ Advantages of LSTM

Ÿ LSTM v/s GRU (Gate Recurrent Unit)

Ÿ Input gate, Output gate, forget gate

Ÿ Bidirectional Recurrent Neural Networks (BRNN)

(USA)
2-Industrial Park Drive, E-Waldorf, MD, 20602,
United States

CONTACT US
(INDIA)
B-44, Sector-59, Noida Uttar Pradesh 201301

(USA)
+1-844-889-4054

(INDIA)
+91-92-5000-4000

info@careerera.com

www.careerera.com