Syllabus of Data Science Course in Tambaram

Module 1: Introduction to Python.

• What is Python?
• Who developed Python and when?
• How to install Python?
  • Download from the official
  • Use IDLE or install IDEs like VS Code, PyCharm, Jupyter
• Why choose or learn Python?
• Name some of the Real-world applications of Python?
• General & Salient Features of Python?
• Colour coding schemes in Python?
• Flavours in Python?

Module 2: Core Python Tokens & Syntax.

1. Naming Rules and Identifier
   • Private
   • Strong
   • Magical Method
   • Rules to create an
2. Literal Types and Their
3. Operators and Their Functional

o Arithmetic Operators.

• Relational or Comparison
• Assignment
• Shift
• Logical
• Membership
• Identity

4. Reserved Keywords and Their
5. Comments Practice and Quotation Comments:
   • Single Line
   • Multi-Line Quotations:
   • Single
   • Double
   • Triple

Module 3: String Operations and Handling Techniques.

1. Understanding Strings in Python?
2. Core String
   • Accessing Individual Characters (Indexing).
   • Extracting Substrings (Slicing).
   • Range-Based Substring Extraction (Ranging).
   • String Reversal Techniques (Reversing).
3. String Methods and Manipulation
   • String Concatenation or Merging
   • Repeating String
   • String Formatting Techniques
4. Built-in Functions for String

Module 4: Core Data Structures in Python.

1. Introduction to Python Data Types?
2. Working with Lists and Their
   • Compact List Creation using
   • Built-in Functions and methods for
   • Copying Lists: Deep vs
3. Working with Tuples and Built-in
4. Set Data Type and Its
5. Dictionaries and Mapping Structures in

Module 5: Conditional Statements.

1. What is a Conditional Statement?
2. Types of Conditional Statements?
   • Single Condition check / One-way
   • Binary Condition / Two-way
   • Multi-Way Branching / Conditional
   • Layered Condition / Hierarchical

Module 6: Iterative Statements.

1. What are Iterative Statements and related terms?
2. Types Of Iterative
   • Count-Controlled Loop / Fixed
   • Condition-Controlled Loop / Entry-Control
3. Loop Practice
4. Pattern Printing

Module 7: Statement Controllers.

1. What are Statement Controllers and related terms?
2. Types of Statement Controllers?
   • Null Operation / Placeholder Statement / Empty block
   • Loop Terminator / Exit Loop / Forced
   • Skip Iteration / Loop Skipper / Next Cycle / Loop
3. Structured Iteration
4. Decision-Based Pattern

Module 8: Functions.

1. What are Functions?
2. Components of functions?
3. Difference between a Method and a Function?
4. What is a Parameter?
5. What are Arguments?
6. Types of Functions?
   1. User-Defined
      • Types of arguments used in
        • Default
        • Positional

• Keyword
• Arbitrary

2. Built-in
3. Recursive
4. Lambda Functions (map, filter, reduce).
5. Math

Module 9: Object-Oriented Programming Structure.

1. What is OOPS?
2. Why OOPS?
3. How does Python support OOPS concepts?
4. Variables in OOPS?
   • Class
   • Global
   • Local
5. What are Classes and Objects?
6. .Properties or Principles of OOPS?
   • Data
   • Data
   • Single
   • Multiple
   • Multilevel
   • Hierarchical
   •  

7. How does the Constructor work?
8. Use of init  constructor?
9. Use of the Self keyword?

Module 10: Error and Exception Handling.

1. What Is an Error?
2. Types of Error?
   • Syntax
   • Runtime
   • Logical
3. What is an Exception?

4. Difference between Error and Exception?
5. Types of common Exceptions?
   • Zero Division
   • Value
   • Type
   • Index
   • Key
   • FileNotFound
   • Import
6. Exception handler components?
   • Try
   • Except
   • Finally

Module 11: Modules and Packages.

1. What are Libraries, Modules, and Packages?
2. How to use internal Modules of Python?
3. Importing Strategies or Module access techniques in Python?
4. Types of commonly used Modules?
   • OS
   • SYS
   • Math
   • Time
   • Datetime
   • Calendar

Module 12: File Handling Management (Data Storage Unit).

1. What is a file?
2. File handling access modes?
   • Read +.
   • Write +.
   • Append +.
   • Text +.
   • Read
   • Write
3. File handling Functions?

• Read a
• Read
• Write

3. How to store data in a CSV file format?

Module 13: Database Management.

1. Introduction to
   • What is data, information, and insight?
   • What is a Database?
   • Need for a
   • What is Database Manager?
   • What is a Database Management System?
   • Types of Databases:
     • Relational (RDBMS).
     • Non-relational (NoSQL).
   • Introduction to
   • MySQL Overview and

2.   Installation and setup of MySQL.

• Installing MySQL
• MySQL Workbench /
• Connecting to MySQL via Command

3. SQL Fundamentals.

• SQL Syntax &
• SQL Statement Types:

• DDL (Data Definition Language).
• DML (Data Manipulation Language).
• DCL (Data Control Language).
• TCL (Transaction Control Language).

4.   DDL (Data Definition Language).

• Create
• Create
• Create
• Alter
• Truncate

5.  DML (Data Manipulation Language).

• Inserting Data (INSERT).
• Updating Data (UPDATE).
• Deleting Data (DELETE).
• Selecting Data (SELECT).

6.  DCL (Data Control Language).

• Create
• Drop

7.  TCL (Transaction Control Language).

• Begin or start a
• Save
• Release Save
• Set auto

8.  Schema Design Concepts.

1. • Primary
   • Foreign
2. • Unique, Not Null,
   • Auto

9.  Functions.

1. Aggregate
   •  

2.  Datetime Functions.

• Date
• Cur

3.  String Functions.

4.  Math / Numeric Functions.

5.  Window Functions.

1. Window Partitioning and
   • Partition
   • Order inside
   • Row and range-based frame
2. Ranking
   • Row
   • Dense
   • Nt
3. Value
   • First
   • Last
4. Frame
   • Rows
   • Range
5. Aggregate window
   • Sum
   • Avg
   • Count
   • Min
   • Max

11. Common Table Expression (CTE).
    1. Introduction to
    2. Types of
    3. Recursive and Non-Recursive
    4. Multiple CTEs in one
    5. Using CTE with
12. 1. Introduction to
    2. Trigger
    3. Types of
    4. Managing
13. Stored
    1. Introduction to
    2. Creating
    3. Procedure
    4. Managing
14. 1. Working with
    2. Cursor
15.  

• Inner
• Left
• Right
• Full Join (Via Union).
• Joining Multiple

16. Subqueries and Nested

• Subquery in SELECT, FROM,
• Correlated

17. 1. Arithmetic
    2. Comparison
    3. Logical
    4. Bitwise
    5. Set
18. Views and

• Creating and Using
• Indexing for

19. Backup and

• Exporting a Database (MySQL dump).
• Importing a

20. MySQL and Python Integration (Optional Advanced).

• Using MySQL-connector-python.
• Connecting Python with

21. 1. Introduction to
    2. Data
    3. Normal forms:
       •  

MACHINE LEARNING

Module 1 — Introduction to Machine Learning

• What is ML?
• Types of ML

o Supervised

• Unsupervised
• Semi-supervised
• Reinforcement

• ML vs AI vs DL vs Data Science
• Traditional programming vs ML
• Real-world ML applications

Module 2 — Mathematics for ML

1. Linear Algebra
   • Scalars, Vectors, Matrices
   • Matrix operations
   • Eigenvalues & Eigenvectors
   • Dot product, Norms
   • Vector Spaces

2.  Calculus

• Derivatives
• Gradients
• Partial derivatives
• Gradient descent optimization

3.  Probability & Statistics

• Probability distributions
• Mean, Median, Variance
• Bayes theorem
• Hypothesis testing

Module 3 — Python for Machine Learning

• NumPy
• Pandas
• Matplotlib & Seaborn
• Scikit-learn basics
• Data preprocessing functions

Module 4: PANDAS.

Chapter 1: Introduction to Pandas.

1. What are Pandas and their importance in data analysis?
2. Comparison: Pandas vs Excel vs
3. How to Install
4. How to import
5. Uses of pandas in real-world
6. What is a data structure and an array?

Chapter 2: Data structures of pandas.

1. Data

Chapter 3: Series creation of pandas.

1. Series creation using a
2. Series creation using a
3. Series creation using a NumPy
4. Series creation using a
5. Accessing elements using:
   • Integer
6. Methods:
   • head ().
   • tail ().
   • unique ().
   • Nunique ().
   • value_counts ().
7. Series
   • Type and

8. Accessing elements of a
   • Slicing

Chapter 4: Data frame creation in pandas.

1. Data frame creation using a
2. Data frame creation using a
3. Data frame creation using a NumPy
4. Data frame creation using
5. Data frame creation using a data

Chapter 5: Indexing, Slicing, and Sub setting.

1. Selecting
2. Selecting rows using:
   • loc [] (label-based).
   • Iloc [] (position-based).
3. Slicing rows and

Chapter 6: Modifying and Updating Data

1. Adding new
2. Updating values in cells/columns.
3. Renaming columns and
4. Dropping columns and
5. Reindexing
6. Changing data

Chapter 7: Handling Missing Values and Sorting.

1. Detecting missing data:
   • Isnull ().
   • Notnull ().
2. Handling missing data:
   • Fillna () (forward/backward fill, mean/median).
   • Dropna () (rows or columns).
3. Replacing values using replace ().
4. Sorting:
   • sort_values (ascending/descending, multiple columns).
   • sort_index ().

Chapter 8: Aggregation, Grouping, and Statistical Functions.

1. Using groupby () for:
   • Single-column.
   • multi-column
2. Aggregation methods:
   • Mean ().
   • Sum ().
   • Count ().
   • Min ().
   • Max ().

Chapter 9: Data operations in pandas.

1. Joining.
2. Map and apply

Chapter 10: Date & Time Operations

1. Creating Date Time
2. Extracting parts of datetime:
3. Year.
4. month.
5. day.
6. Hour.
7. Filtering by date
8. Time-based

Chapter 11: File Input and Output (I/O).

1. Reading files:
   • read_csv ().
   • read_excel ().
   • read_json ().
   • read_html ().
2. Writing files:
   • to_csv ().
   • to_excel ().
   • to_json ().

Chapter 12: Data Visualization with Pandas.

1. Basic visualizations:

2. Customizing visualizations:

Module 5: NUMPY.

Chapter 1: Introduction to NumPy

1. What is NumPy, and why use it?
2. Applications and benefits of
3. How to Install
4. How to Import
5. Differences between Python lists and NumPy

Chapter 2: NumPy Arrays Basics.

1. What is an Array?
2. Types of Arrays?
   • One-dimensional
   • Two-dimensional
   • Three-dimensional array
3. Creating arrays:
   • list/tuple.
   • Multidimensional
4. Checking or NumPy array
   • Data
   • Number of
5. Perform arithmetic operations in an

Chapter 3: Array Creation Functions.

1. zeros ().
2. ones ().
3. Arrange (start, stop, step).
4. linspace (start, stop, Num).
5. eye (n) for identity matrix.

6. Random arrays:
   • random. Rand ().
   • random. Randn ().
   • random. Randint (low, high, size).
7. Algebraic
   • Inverse ().
   • Transpose ().
   • Trace ().

Chapter 5: Array Attributes and Properties

1. Changing shape or Shape Manipulation:
   • Ravel ().
   • Reshape ().
   • Resize ().
2. Copy vs View:
   • Shallow
   • deep
3. Concatenation:
   • concatenate ().
   • vstack ().
   • hstack ().
4. Splitting:
   • split ().
   • Hsplit ().
   • vsplit ().

Chapter 6: Mathematical and Statistical Operations.

1. Element-wise operations:

• +, -, *, /, **, sqrt (), log (), exp ().

2. Aggregate functions:
   • Sum (), min (), max (), mean (), median (), std (), var ().

Chapter 7: Linear Algebra with NumPy.

1. Dot product: dot (), @ operator.
2. Matrix multiplication: Matmul ().
3. Transpose:
4. Inverse: linalg.inv ().

Chapter 9: Random Module in NumPy.

1. random. seed () for reproducibility.
2. Uniform distribution: random. Rand().

3. Normal distribution: random. Randn ().
4. Random integers: random. Randint ().

Chapter 10: Universal Functions.

1. Arithmetic

o add, subtract, multiply, and divide.

2.      Trigonometric functions.

• sin, cos,

3.      Rounding functions.

• floor, ceil, round,

Module 6: MATPLOTLIB.

1. Introduction to Data Visualization
   • What is Data Visualization?
   • Why Matplotlib?
   • Comparison with Seaborn, Plotly

2.  Matplotlib Basics

• Installing Matplotlib
• Understanding pyplot
• figure(), plt.plot()
• Basic line plot
• Adding labels: xlabel, ylabel, title
• Adding legends
• Grid, ticks, limits
• Saving plots (savefig())

3.  Plot Customization

• Colors, line styles, linewidth
• Markers & marker styles
• Setting x and y axis limits
• Tick positions, tick labels
• Font sizes, font families
• Adding annotations (plt.annotate)
• Adding text (plt.text)

4.  Working with Figures & Subplots

• Creating multiple subplots (plt.subplot)
• subplots() (object-oriented method)

5.  Types of Plots

1. Line Plot
   • Multiple lines
   • Line color, width, style
2. Bar Plots
   • Vertical bar
   • Horizontal bar
   • Stacked bar
   • Grouped bar
   • Bar width & alignment
3. Histogram
   • Basic histogram
   • Multiple histograms
   • Bins, density parameter
4. Scatter Plot
   • Marker types
   • Color based on category
   • Bubble chart (size variation)
5. Pie Chart
   • explode
   • shadow
   • autopct
   • donut pie chart
6. Box Plot
   • Single box plot
   • Multiple box plots
   • Customizing whiskers/outliers
7. Violin Plot
   • Distribution visualization
   • Multiple violins
8. Area Plot
   • Filled area
   • Stacked area

9. Heatmap
   • Using imshow
   • Colorbars
10. Polar Plot
    • Wind-rose style
    • Radar/spider chart

Module 7: SEABORN.

1. Introduction to Seaborn
   • What is Seaborn?
   • Difference: Seaborn vs Matplotlib
   • Installing Seaborn
   • Importing Seaborn
2. CORE PLOT TYPES:

A.  RELATIONAL PLOTS

1. Scatterplot()
   • Hue, size, style
   • Categorical vs numerical
2. lineplot()
   • Multiple lines
   • Error bars
   • Time-series
3. relplot()
   • Scatter + Line combination
   • Facet grid with columns & rows

B.  DISTRIBUTION PLOTS

1. histplot()
   • KDE on/off
   • Bins, multiple histograms
2. kdeplot()
   • 1D & 2D KDE
   • Shaded density plot
3. distplot ()

C.  CATEGORICAL PLOTS

• stripplot()
• swarmplot()
• boxplot ()
• violinplot()
• boxenplot()
• countplot()
• barplot()
• pointplot()

D.  MATRIX PLOTS

1. heatmap ()
2. clustermap()
   • Hierarchical clustering
   • Row/column dendrogram

E.  REGRESSION PLOTS

1. regplot()
   • Linear regression
   • Scatter + line
2. lmplot()
   • Multi-feature regression
   • Faceting by hue, col, row
3. residplot()
   • Residual plot

F. MULTIVARIATE PLOTS

1. pairplot()
   • Multiple variable relationships
2. jointplot()
   • Scatter + histogram
   • Scatter + KDE
   • Hexbin
   • Regression + KDE
3. JointGrid(), PairGrid()
   • Highly customizable layouts

Module 8— Data Preprocessing & Cleaning

• Handling missing values
• Outlier detection & removal
• Feature engineering
• Feature scaling (StandardScaler, MinMaxScaler)
• Encoding (Label, One-Hot, Target Encoding)
• Data splitting
• Imbalanced data handling (SMOTE)

Module 9— Supervised Learning

1. Regression Algorithms
   • Linear Regression
   • Decision Tree Regression
   • Random Forest Regression
   • SVR (Support Vector Regression)
   • XGBoost Regression

2.  Classification Algorithms

• Logistic Regression
• K-Nearest Neighbors (KNN)
• Naive Bayes (Gaussian, Bernoulli, Multinomial)
• Decision Tree Classifier
• Random Forest Classifier
• Support Vector Machine (SVM)
• XGBoost Classifier

3. Model Evaluation

• Confusion Matrix
• Precision, Recall
• F1-Score
• AUC–ROC Curve
• Classification Report
• Regression metrics (MSE, RMSE, R²)

Module 10— Unsupervised Learning

1. Clustering

• • K-Means Clustering

2.  Dimensionality Reduction

• PCA (Principal Component Analysis)

Module 11 — Model Tuning & Optimization

• GridSearchCV
• RandomizedSearchCV
• Hyperparameter tuning
• Cross-Validation (K-Fold, Stratified)

Module12— Ensemble Techniques

• Bagging
• Boosting
• Stacking

Module 13— Time Series

• ARIMA
• SARIMA
• Prophet model
• LSTM introduction

DEEP LEARNING

Module 1 — Introduction to Deep Learning

• What is Deep Learning?
• ML vs DL vs AI
• Why Deep Learning works

Module 2 — Neural Network Basics

• Biological neuron vs Artificial neuron
• Activation Functions:
  • Sigmoid, Tanh

• ReLU, LeakyReLU
• ELU, GELU, Swish

• Loss functions:
  • MSE
  • Cross Entropy
  • Hinge loss

Module 3 — Deep Learning Frameworks

• TensorFlow
• Keras
• PyTorch

Module 4 — Regularization & Generalization

• Overfitting & Underfitting
• Dropout
• Batch Normalization
• Layer Normalization
• Data Augmentation
• Early Stopping

Module 5 — ARTIFICIAL NEURAL NETWORK (ANN)

A. ANN Basics

• • What is a perceptron?
  • Multi-layer perceptron
  • Forward pass
  • Backpropagation
  • Gradient descent

B.  Activation Functions

• Sigmoid
• Tanh
• ReLU, LeakyReLU
• Softmax
• GELU, Swish

C.  Architecture

• Input → Hidden Layers → Output
• Weight initialization
• Bias
• Learning rate

D.  ANN Regularization

• Dropout
• Batch Normalization
• Early stopping
• L1/L2 regularization

E.  ANN Applications

• Classification
• Regression

Module 6— CONVOLUTIONAL NEURAL NETWORK (CNN)

A. CNN Concepts

• • Convolution operations
  • Kernels, filters
  • Feature maps
  • Padding, stride
  • Pooling (Max/Average)

B.  CNN Layers

• Conv layer
• Pooling layer
• Flatten layer
• Fully connected (Dense) layer

C.  Advanced CNN Topics

• Dropout for CNN
• BatchNorm
• Data Augmentation (ImageDataGenerator)

Module 7 — RECURRENT NEURAL NETWORK (RNN)

1. RNN Basics
   • Sequential data
   • RNN architecture
   • Hidden state
   • Backpropagation Through Time (BPTT)
   • Vanishing gradient problem

B.  LSTM (Long Short-Term Memory)

• LSTM gates
  • Forget gate
  • Input gate
  • Output gate
• Cell state
• Bidirectional LSTM

Module 8: Computer Vision (OpenCV).

Chapter 1: Hands-on with CV2

1. What is computer vision?
2. How to install computer vision?
3. How to import computer vision?
4. How many versions of computer vision?
5. Real-time applications of computer vision?

Chapter 2: Digital Image Processing (DIP).

1. What is digital image processing?
2. Details of Image Structure and Representation?
   • What is a pixel?
   • Image Dimensions (Width * Height * Channel).
   • What is RGB?
3. Digital Image Processing Techniques:
   • Read the
   • Display the read
   • Display the image with colour, grayscale, and
   • Getting the dimensions of an

• Edge
• Concatenation (vertical and horizontal).
• Tile
• Flip an
• Blend
• Cropping an
• Downscale with
• upscale with
• Resize (height and width).
• Reading the transparency
• Image
• Image
• Rotating
• Image
• Image to Pencil
• Image to
• Image to Oil
• Image to QR
• Background

Module 9: Face Recognition.

Chapter 1: Introduction to Face Recognition.

1. What are face detection and facial recognition?
2. Real World
3. Current

Chapter 2: Face Detection Techniques.

1. Haar cascade using face
2. Media pipe using face

Chapter 3: Face Detection (Image & Video).

1. Face Detection in
2. Face Detection in video (Real-Time/Webcam).

Chapter 4: Facial Landmarks & Alignments.

1. Detecting Eye, Nose,

Module 10: YOLO Object Detection. (Real-time object tracking).

Chapter 1: Introduction to Object Detection.

1. What is object Detection?
2. Difference between object Classification, detection, and
3. Real-world
4. List of popular object detection

Chapter 2: You Only Look Once (YOLO).

1. What is YOLO, and why is it fast?
2. Yolo Architecture Overview.
3. One-stage vs Two-stage
4. Anchor boxes and Bounding box
5. Confidence Score and Non-Max Suppression (NMS).

Chapter 3: YOLO Pre-trained Model Inference.

🖼 Image-based Object Detection.

1. Run YOLO on
2. Draw labels and bounding
3. Show class

-.m   Video/Webcam Object Detection.

1. YOLO on real-time webcam
2. Drawing FPS on live

Module 11: Natural Language Processing (NLP).

1. What is NLP?
2. Goal of NLP?
3. Real-time applications of NLP?
4. Current challenges of NLP?
5. Structural components of NLP?
6. Libraries or Engines of NLP?
7. What is NLTK?
8. Install and import NLTK?
9. Data Collection and
   • Data Crawling without
   • Data
   • Counting
10. Stop Words and

• Stop
• Remove stop

11. Lexical
    • Synonyms
    •  
12. • Tokenizing the
13. Word
    •  
    • Lemmatizing.

Module 12: Speech Recognition.

Chapter 1: Introduction to Speech and Audio Processing.

1. What is Speech Recognition?
   • Definition and real-time
   • Speech Voice vs. Speaker Recognition.
   • Types.
2. • Voice Assistants (Siri, Alexa, Google Assistant).
   • Subtitles & Closed
   • Voice Typing &
   • Accessibility (Speech to Text for the hearing impaired).
3. Audio
   • Analog vs Digital
   • Sampling rate, Bit depth,
   • Audio file formats: WAV, MP3, FLAC,
   • PCM

Chapter 2: Python for Audio Handling.

1. Audio Handling
   • wav, pydub, Pyaudio, sound
2. Read, Play, and Save Audio
   • Convert formats (e.g., MP3 → WAV).
   • Slice and trim
   • Merge and export

• Play sound using system

3. Recording from the
   • Stream the microphone using
   • Save to .wav files in real-

Chapter 3: Audio Feature Extraction.

1. Digital Signal Processing (DSP)
   • Noise reduction and
   • Framing and
   • Fourier Transform,
2. Speech
   • MFCC (Mel Frequency Cepstral Coefficients).
   • Mel-
   • Chroma
   • Zero Crossing
   • Root Mean Square
   • Spectral Centroid &

Module 13: Speech-to-Text (STT).

Chapter 1: Introduction to STT.

• What is Speech-to-Text?
• Real-world
• Types: Real-time vs Batch
•  

Chapter 2: Audio Fundamentals.

• What is audio? (Sampling rate, bit depth, frequency).
• File formats: WAV, MP3, FLAC,
• Visualization: waveform,

Chapter 3: Python Basics for Audio.

• Record from the
• Convert audio
• Split, merge, and slice audio

Chapter 4: Preprocessing for STT.

• Voice Activity Detection (VAD).
• Noise
• Normalization, trimming
• Feature extraction (MFCC, MelSpectrogram).

Module 14: Text-to-Speech (TTS).

Chapter 1: Introduction to TTS

• What is Text-to-Speech?
• Use
• Speech synthesis vs
• Monotone vs natural-sounding

Chapter 2: Python TTS Tools.

• Basic TTS using:
  • pyttsx3 (offline).
  • gTTS (Google TTS).
• Convert text file →
• Save speech as an audio

Chapter 3: Audio Output Management.

• Format conversion (WAV → MP3).
• Audio playback in
• Batch generation of speech from

Chapter 4: Custom Voice and Language.

• Fine-tune your own
• Use Indian English, Tamil, and Hindi
• Multi-lingual
• Adjust speed, pitch, and emotion.

Module 15: Named Entity Recognition (NER).

Chapter 1: Introduction to NER.

• What is Named Entity Recognition?
• Importance and applications:
• Examples of Entities:
• NER vs POS tagging vs

Chapter 2: Fundamentals of NLP for NER.

• Text Cleaning and
• Tokenization (word-level and sentence-level).
• Stopword
• Lemmatization vs
• POS

Chapter 3: Rule-based NER.

• Using Regular
• Rule-based NER with ne_chunk.

• Chunking using POS
• Limitations of rule-based

Chapter 4: Pre-trained NER with NLP Libraries.

• Using Stanza (Stanford NLP).
• Using Flair for contextual
• Using transformers for

Module 16: Optical Character Recognition (OCR).

Chapter 1: Introduction to OCR.

1. What is OCR?
2. Real-world applications:
3. Challenges in

Chapter 2: Text Detection in Images.

1. Region of Interest (ROI)
2. Image denoising and
3. Skew correction and
4. Noise removal from scanned

Chapter 3: Basic OCR with Tesseract.

1. Introduction to Tesseract OCR
2. Installing and setting up
3. Reading printed text from
4. OCR from image files (JPG, PNG).
5. OCR from PDF

Chapter 4: Language and Customization in Tesseract.

1. Changing language models (English, Tamil, Hindi, ).
2. Tesseract configuration
3. Reading only digits, alphanumeric, or specific
4. Bounding box and confidence score

Chapter 5: OCR for Structured Documents.

1. Table
2. Invoice
3. Form data

4. ID card recognition (PAN card, Aadhar, ).
5. Key-value pair

Chapter 6: OCR in Videos and Real-time Applications.

1. Real-time OCR from webcam or
2. Frame extraction and
3. Text tracking in
4. License plate recognition (ALPR).

Module 17: Chatbot Creation.

Chapter 1: Introduction to Chatbots.

1. What is a Chatbot?
2. Types of Chatbots:
   • Rule-based.
   • Retrieval-based.
   • Generative (AI-based).
   • Customer
   • Personal
3. Chatbot architecture

Chapter 2: Text Preprocessing for Chatbots.

1. Normalize user input:
2. Removing

Chapter 3: Intent Recognition.

1. Define intents using patterns and responses (JSON format or Python dictionaries).
2. Use nltk for pattern matching with
3. Matching user input to intents using:
   • Keyword
   • Pattern
   • Bag-of-words (BoW)

Chapter 4: Rule-Based Chatbot with NLTK.

1. Basic chatbot logic using if-else
2. Pattern-response
3. Matching intents with regex
4. Creating a Q&A-style

Module 18:  SCAMP (Music composition & Music generation).

Chapter 1: Introduction to SCAMP

1. What is SCAMP?
2. History and
3. Use cases of SCAMP:
   • Algorithmic
   • Music theory
   • Real-time sound
   • AI + Music
4. Installing SCAMP: pip install
5. Setting up MIDI /

Chapter 2: SCAMP Basics.

1. Starting a session:
2. Creating
3. Basic note
   • Play note (Pitch, Volume, Duration).
   • Playing Melodies, Chords, and

Chapter 3: Music Theory with SCAMP.

1. Working with:
   • MIDI
   • Frequencies (Hz).
   • Note names (e.g., “C4”).
2. Intervals and scales:
   • Major, minor,
3. Chords: major, minor, 7th,

4. Rhythm patterns: durations and

Chapter 4: Time and Tempo Control.

1. Session clock: wait (), now ().
2. Metronome
3. Playing notes in sequence and
4. Sleep-based vs event-scheduled
5. Using a call after for

Chapter 5: Loops, Motifs & Patterns.

1. Define musical motifs as
2. Repeat patterns in a
3. Introduce randomness with:
   • choice ().
   • randint ().
4. Play variations: transpose, invert, and

Chapter 6: Multiple Instruments & Layers.

1. Adding multiple instruments in a
2. Playing instruments together or in
3. Assign different roles (melody, bass, harmony).

Chapter 7: Harmony and Counterpoint.

1. Understanding
2. Creating counterpoint
3. Using consonant and dissonant
4. Canon and fugue-style

Chapter 8: Real-Time Composition.

1. Live performance
2. Modify melody or rhythm in real-
3. Build responsive music
4. Capture external triggers (keyboard input, sensors).

Chapter 9: Data-Driven Music.

1. Map data to pitch, duration, and
2. Use external data: CSV, JSON,
3. Real-world applications:

• Stock data →
• Weather data →
• Emotion →

Chapter 10: SCAMP + Text / NLP Integration.

1. Input text → generate
2. Use sentiment to influence
3. Word frequency → pitch/duration
4. Lyric-based melody

Chapter 11: SCAMP + Image / Video Integration.

1. Use OpenCV to extract dominant
2. Map colour or pixel data to pitch/rhythm.
3. Live camera input for ambient
4. Scene-to-sound