Data Science and Artificial Intelligence Boot camp

Flat No #3, V R K H Building, Vivekananda Layout, Opposite to Home town, Beside Biriyani Zone, Marathahalli, Bangalore,Karnataka– 560037

INTRODUCTION TO STATISTICS

Basic business statistics

• How businesses use statistics
• The basic vocabulary of statistics
• The types of data used in business

Organizing and Visualizing Data

• The sources of data used in business
• To construct tables and charts for numerical data
• To construct tables and charts for categorical data
• The principles of properly presenting graphs

Numerical Descriptive Measures

• To describe the properties of central tendency, variation, and shape in numerical data
• To construct and interpret a boxplot
• To compute descriptive summary measures for a population
• To compute the covariance and the coefficient of correlation

Basic Probability and Terms

• Basic probability concepts
• Conditional probability
• To use Bayes’ Theorem to revise probabilities
• Various counting rules

Probability Distributions

• Types of Distributions like Discrete and Continuous
• Functions of Random Variables
• Probability Distribution Graphs

Sampling and Sampling Distributions

• To distinguish between different sampling methods
• The concept of the sampling distribution
• To compute probabilities related to the sample mean and the sample proportion
• The importance of the Central Limit Theorem

Confidence Interval Estimation

• To construct and interpret confidence interval estimates for the mean and the proportion
• How to determine the sample size necessary to develop a confidence interval estimate for the mean or proportion
• How to use confidence interval estimates in auditing

Fundamentals of Hypothesis Testing

• Null and Alternate hypothesis
• One sample Tests
• Test statistic and critical values
• Possible errors in testing
• p- value approach | t and z-tests | Testing on proportions

DATA TRANSFORMATION AND VISUALIZATION

Data Transformations

Merge, Rollup, Transpose and Append | Smoothing |
Aggregation | Normalization | Attribute construction

Feature Engineering

Missing value Imputation | Outlier Analysis and Treatment |
Binning | Creating dummy variables | feature scaling |
Extracting Date | Log Transformation | Feature split | Label
Encoding | One-Hot Encoding

Exploratory Data Analysis

Summarizing and Visualizing the Important Characteristics
of Data | Visualization techniques – Box plot | Histogram |
Multi-variate chart | Pareto chart | Scatter plot | Stem-
and-leaf plot.

PYTHON PROGRAMMING

Introduction to Python

Installation | Python Basics | Spyder IDE | Jupyter Notebook
| Floats and Strings Simple Input & Output | Variables |
Operators | Single and Multiline Comments |
Taking input from user

Data Structures

List | Strings | Tuple | Dictionary | Sets and their examples

Conditional Statements

If | if-else | if-elif-else | nested if else

Loops

For | while | nested loops| loop control statements

Functions

Creating user defined Functions | Function arguments like-
Required, Keyword, Default and variable-length | Scope of
variables in creating functions | Anonymous Functions –
Lambda

Exception and File handling

Exception Handling | Raising Exceptions | Assertions | Files
I/O

INTRODUCTION TO MACHINE LEARNING

Introduction

What is Machine Learning? | End-to-end Process of
Investigating Data Through a Machine Learning Lens |
Evolution and Trends | Application of Machine Learning |
Best Practices of Machine Learning

Machine Learning Methods

Supervised | Unsupervised

Machine Learning Algorithms

Classification | Regression | Time Series | Collaborative
Filtering | Clustering | Principal Component Analysis

 

MACHINE LEARNING WITH PYTHON

Numpy module

Basics of numpy | creating arrays | Numpy functions

Pandas

Introduction to Pandas | IO Tools | Pandas – Series and Dataframe and their functions

Matplotlib and Seaborn

Graphical representation of data using various plots

Scikit learn

Introduction to SciKit Learn | Load Data into Scikit Learn |
Run Machine Learning Algorithms Both for Unsupervised and
Supervised Data | Supervised Methods: Classification &
Regression | Unsupervised Methods: Clustering, Gaussian
Mixture Models | Decide What’s the Best Model for Every
Scenario

MACHINE LEARNING APPLICATIONS

Linear Regression

Implementing Simple & Multiple Linear Regression |
Making Sense of Result Parameters | Model Validation |
Handling Other Issues/Assumptions in Linear Regression:
Handling Outliers, Categorical Variables, Autocorrelation,
Multicollinearity, Heteroskedasticity | Prediction and
Confidence Intervals | Use Cases

Logistic Regression

Implementing Logistic Regression| Making Sense of Result
Parameters: Wald Test, Likelihood Ratio Test Statistic, Chi-
Square Test | Goodness of Fit Measures | Model
Validation: Cross Validation, ROC Curve, Confusion Matrix |
Use Cases

Decision Tree

Implementing Decision Trees | Homogeneity | Entropy
Information Gain | Gini Index | Standard Deviation
Reduction | Vizualizing & Prunning a Tree | Implementing
Random Forests using Python | Random Forest Algorithm
| Important hyper-parameters of Random Forest for tuning
the model | Variable Importance | Out of Bag Errors

Naïve Bayes

Bayes Theorem | Gaussian Naïve Bayes & its
implementation | Multinomial Naïve Bayes, Count
vectorizer, TF-IDF Vectorizer and its use cases on Text
Classification

K-Nearest Neighbors

Concept of nearest neighbors | Euclidean Distance | Use
Cases of KNN Classifier & Regressor

Support Vector Machine

Introduction to support vectors | Concept of hard & soft
margins | slack variable | Lagrangian Primal & Dual | Kernel
Trick | Use Cases

Time Series

Introduction | Components of Time Series | Stationarity |
ACF | PACF | ARIMA model for forecasting | Use Cases

K-Means Clustering

Clustering concept | Finding optimal number of clusters |
Use Cases

Hierarchical Clustering

Agglomerative & Divisive Clustering | Dendrograms |
Linkage Matrix like Single, Complete & Average | Use Cases

Ensemble Techniques

Bagging | Boosting | Stacking | Regularization | Different
cross-validation techniques used to treat Over fitting and
Under fitting in machine learning models

Principal Component Analysis

Concept of Dimensionality reduction | Eigen values | Eigen
Vectors | Use Cases.

Can Machine Learning Teach Us anything?

PROJECTS

PROJECT 1
Title: Real Estate Price Prediction using Linear Regression
Industry: Real Estate
Description: The goal of this Use-case is to make property
price predictions using Real Estate data. The dataset
contains the of the price of apartments and various
characteristics of the property. Based on this data, decide
on the price of new properties.

PROJECT 2
Title: Loan Prediction using Logistic Regression & Decision
Tree
Industry: Finance
Description: The goal is to build a classification model to
predict if a loan is approved or not. Dataset contains
demographic information like age, income etc. of various
customers. Based on this, predict for a new customer
whether loan will be approved or not

PROJECT 3
Title: Student’s Performance Prediction using KNN & Naïve
Bayes
Industry: Education
Description: The goal is to build a classification model to
predict student’s performance from various characteristics
associated with student’s academics

PROJECT 4
Title: Handwritten digit recognition using Decision Tree
&Random forest
Description: Dataset contains various pixel values of
handwritten digits between 0 to 9. The goal is to build a
classification model to predict the digit from its pixel
values.

PROJECT 5
Title: Amazon fine food review-Sentiment Analysis
Industry: Amazon
Description: The analysis is to study Amazon food review
from customers and try to predict whether a review is
positive or negative. The dataset contains more than 500k
reviews with number of upvotes and total votes to those
comments

DEEP LEARNING APPLICATIONS

Neural Networks
Understanding Neural Networks | The Biological
Inspiration | Perceptron Learning & Binary Classification |
Backpropagation Learning | Learning Feature Vectors for
Words | Object Recognition

Keras
Keras for Classification and Regression in Typical Data
Science Problems | Setting up KERAS | Di erent Layers
in KERAS | Creating a Neural Network Training Models
and Monitoring | Artificial Neural Networks

Tensorflow
Introducing Tensorflow | Neural Networks using
Tensorflow | Debugging and Monitoring | Convolutional
Neural Networks

Recurrent Neural Networks
Introduction to RNN | RNN long & short term dependencies
| Vanishing gradient problem | Basic LSTM | Step by step
walk through LSTM | Use cases

PROJECT 1
ANN ON KERAS

Title: Credit Default using ANN on Keras
Industry: Finance
Description: This research aimed at the case of customers’
default payments in Taiwan. From the perspective of risk
management, the result of predictive accuracy of the
estimated probability of default will be more valuable than
the binary result of classification – credible or not credible
clients.

PROJECT 2
CNN ON KERAS & TENSORFLOW

Title: Handwriting/Facial recognition using CNN on
TensorFlow & Keras

Industry: Pattern Recognition
Description: This project will help build a model using

Convolutional Neural Network to recognize
handwriting/faces

PROJECT 3
LSTM
Title: Google stock price prediction
Industry: Finance
Description: Dataset contains dates, volume, open, close, high and low prices of stocks. Based on this build a LSTM model to predict current and future stock price