-: Course Module :-

Module-1: Text and Image Data Analysis: An Introduction

1.         Basics of Python

1.1.           Python Basics:

      1.1.1.  Variables

      1.1.2.  Comments Output

      1.1.3.  Inputs

      1.1.4.  Libraries and Modules : Importing

1.2.            Control and Looping

      1.2.1.  “if”  statement

      1.2.2.  “if .. else” statement

      1.2.3.  “for” Loop

      1.2.4.  “While” Loop

      1.2.5.  Functions

1.3.            Data Structures

      1.3.1.  Array

      1.3.2.  List

      1.3.3.  Tuple

      1.3.4.  Dictionary

1.4.            Basic Functions for Text Data

      1.4.1.  Creating Text Data

      1.4.2.  Accessing Text Data

      1.4.3.  Case Conversion Functions

      1.4.4.  Alignment and Indentation Functions

      1.4.5.  Special Functions

      1.4.6.  Regular Expressions Functions

1.5.            Data Management

      1.5.1.  Importing Data

      1.5.2.  DataFrame Basics

      1.5.3.  Functions for DataFrame

      1.5.4.  Data Extraction

      1.5.5.  Data Grouping

      1.5.6.  Tables

      1.5.7.  Handling Duplicate and Missing Values

      1.5.8.  Data Transformation

      1.5.9.  Data Type Transformation

1.6.            Data Visualization

      1.6.1.  Line Chart

      1.6.2.  Pie Chart

      1.6.3.  Violin Chart

      1.6.4.  Scatter Chart

      1.6.5.  Bar Chart

2.         Pre-Processing : Text and Image Data

2.1.            Using “nltk” Library Text Data Pre-Processing

      2.1.1.  Data Cleaning

      2.1.2.  Tokenization

      2.1.3.  Stop Words Removal

      2.1.4.  Vectorizer and Bag of Words

      2.1.5.  Shallow Parsing

      2.1.6.  Stemming and Lemmatization

      2.1.7.  Frequency Distribution

      2.1.8.  Word Cloud

2.2.            Using “spacy” Library Text Data Pre-Processing

     2.2.1.  Text Data Representation

     2.2.2.  Data Cleaning

     2.2.3.  Named Entity Recognition

     2.2.4.  Tokenization

     2.2.5.  Stop Words Removal

     2.2.6.  Shallow Parsing

     2.2.7.  Lemmatization

     2.2.8.  Frequency Distribution

     2.2.9.  Word Cloud

2.3.            Image Data Pre-Processing

     2.3.1.  Image Data Representation

     2.3.2.  Resizing and Rescaling : Image

     2.3.3.  Image Rotation and Flipping

     2.3.4.  Image Intensity

     2.3.5.  Image Cropping

     2.3.6.  Edge Extraction Using Sobel Filter

     2.3.7.  Edge Extraction Using Prewitt Filter

Module-2: Text and Image Data Analysis: Using Unsupervised Machine Learning

3.         Sentiment Analysis and Topic Modeling

3.1.            Introduction

      3.1.1.  Sentiment Analysis

      3.1.2.  Topic Modeling

3.2.            Sentiment Analysis Using Lexicon-Based Approach

      3.2.1.  Sentiment Analysis with TextBlob

      3.2.2.  Sentiment Analysis with "nrc" Lexicon

      3.2.3.  Sentiment Analysis with "afinn" Lexicon

      3.2.4.  Sentiment Analysis with VADER  Lexicon

3.3.            Topic Modeling Using "Gensim" Library

      3.3.1.  Text Pre-Processing

      3.3.2.  Document Matrix and Bag of Words

      3.3.3.  LDA Model Development and Evaluation

      3.3.4.  Assigning Topics of Data

4.         Content-Based Recommendation System

4.1.            Introduction

      4.1.1.  Cosine Similarity

      4.1.2.  Cosine Distance

      4.1.3.  Euclidean Distance

      4.1.4.  Manhattan Distance

4.2.            Content-Based Recommendation System for Text Data

      4.2.1.  Cosine Similarity for Text Data Analysis

      4.2.2.  Cosine Distance for Text Data Analysis

      4.2.3.  Euclidean Distance for Text Data Analysis

      4.2.4.  Manhattan Distance for Text Data Analysis

4.3.            Content-Based Recommendation System for Image Data

      4.3.1.  Cosine Similarity for Image Data Analysis

      4.3.2.  Cosine Distance for Image Data Analysis

      4.3.3.  Euclidean Distance for Image Data Analysis

      4.3.4.  Manhattan Distance for Image Data Analysis

5.         Collaborative Filtering Recommendation System

5.1.            Introduction

      5.1.1.  Recommender Models

      5.1.2.  Item Popularity Based Recommender Models

      5.1.3.  Item Similarity Based Recommender Models

5.2.            Collaborative Filtering Recommendation System for Text Data

      5.2.1.  Recommender Models for Text Data

      5.2.2.  Item Popularity Based Recommender Models for Text Data

      5.2.3.  Item Similarity Based Recommender Models for Text Data

5.3.            Collaborative Filtering Recommendation System for Image Data

      5.3.1.  Recommender Models for Image Data

      5.3.2.  Item Popularity Based Recommender Models for Image Data

      5.3.3.  Item Similarity Based Recommender Models for Image Data

6.         Association Rule Mining

6.1.            Introduction

      6.1.1.  Apriori Algorithm

      6.1.2.  Association Rules

6.2.            Association Rule Mining for Text Data

      6.2.1.  Apriori Algorithm for Text Data Analysis

      6.2.2.  Association Rules for Text Data Analysis

6.3.            Association Rule Mining for Image Data

      6.3.1.  Apriori Algorithm for Image Data Analysis

      6.3.2.  Association Rules for Image Data Analysis

7.         Cluster Analysis

7.1.            Introduction

      7.1.1.  k-Means Clustering

      7.1.2.  Hierarchical Clustering

7.2.            Cluster Analysis for Text Data

      7.2.1.  k-Means Clustering for Text Data Analysis

      7.2.2.  Hierarchical Clustering for Text Data Analysis

7.3.            Cluster Analysis for Image Data Image Data Analysis

      7.3.1.  k-Means Clustering for Image Data Analysis

      7.3.2.  Hierarchical Clustering for Image Data Analysis

Module-3: Text and Image Data Analysis: Using Supervised Machine Learning

8.         Supervised Machine Learning Problems

8.1.            Introduction

      8.1.1.  Understanding The Data

      8.1.2.  Data Preparation

      8.1.3.  Model Selection

      8.1.4.  Model Development

      8.1.5.  Prediction Using Model

      8.1.6.  Model Evaluation

      8.1.7.  Creating Better Model

8.2.            Supervised Machine Learning Algorithms for Text Data Analysis

      8.2.1.  Linear Regression for Text Data Analysis

      8.2.2.  Logistic Regression for text Data Analysis

8.3.            Supervised Machine Learning Algorithms for Image Data Analysis

      8.3.1.  Linear Regression for Image Data Analysis

      8.3.2.  Logistic Regression for Image Data Analysis

9.         Supervised Machine Learning Regression Techniques

9.1.            Introduction

      9.1.1.  k-Nearest Neighbors(k-NN)

      9.1.2.  Support Vector Machine(SVM)

      9.1.3.  Decision Tree

      9.1.4.  Bagging

      9.1.5.  Random Forest

      9.1.6.  Extra Trees

      9.1.7.  Ada Boosting

      9.1.8.  Gradient Boosting

9.2.            Supervised Machine Learning Regression Algorithms for Text Data Analysis

       9.2.1.  k-NN Regressor for Text Data Analysis

       9.2.2.  Support Vector Machine(SVM) Regressor for Text Data Analysis

       9.2.3.  Decision Tree Regressor for Text Data Analysis

       9.2.4.  Bagging Regressor for Text Data Analysis

       9.2.5.  Random Forest Regressor for Text Data Analysis

       9.2.6.  Extra Tree Regressor for Text Data Analysis

       9.2.7.  Ada Boost Regressor for Text Data Analysis

       9.2.8.  Gradient Boosting Regressor for Text Data Analysis

9.3.            Supervised Machine Learning Regression Algorithms for Image Data Analysis

       9.3.1.  k-NN Regressor for Image Data Analysis

       9.3.2.  Support Vector Machine(SVM) Regressor for Image Data Analysis

       9.3.3.  Decision Tree Regressor for Image Data Analysis

       9.3.4.  Bagging Regressor for Image Data Analysis

       9.3.5.  Random Forest Regressor for Image Data Analysis

       9.3.6.  Extra Tree Regressor for Image Data Analysis

       9.3.7.  Ada Boost Regressor for Image Data Analysis

       9.3.8.  Gradient Boosting Regressor for Image Data Analysis

10. Supervised Machine Learning  Classification Techniques

10.1.        Introduction

       10.1.1.  Naïve Bayes Classifier

       10.1.2.  k-NN Classifier

       10.1.3.  Support Vector Machine(SVM) Classifier

       10.1.4.  Decision Tree Classifier for Image Data Analysis

       10.1.5.  Bagging Classifier

       10.1.6.  Random Forest Classifier

       10.1.7.  Extra Tree Classifier

       10.1.8.  Ada Boost Classifier

       10.1.9.  Gradient Boosting Classifier

10.2.        Supervised Machine Learning Classification Algorithms for Text Data Analysis

       10.2.1.  Naïve Bayes Classifier for Text Data Analysis

       10.2.2.  k-NN Classifier for Text Data Analysis

       10.2.3.  Support Vector Machine(SVM) Classifier for Text Data Analysis

       10.2.4.  Decision Tree Classifier for Text Data Analysis

       10.2.5.  Bagging Classifier for Text Data Analysis

       10.2.6.  Random Forest Classifier for Text Data Analysis

       10.2.7.  Extra Tree Classifier for Text Data Analysis

       10.2.8.  Ada Boost Classifier for Text Data Analysis

       10.2.9.  Gradient Boosting Classifier for Text Data Analysis

10.3.        Supervised Machine Learning Classification Algorithms for Image Data       Analysis

       10.3.1.  Naïve Bayes Classifier for Image Data Analysis

       10.3.2.  k-NN Classifier for Image Data Analysis

       10.3.3.  Support Vector Machine(SVM) Classifier for Image Data Analysis

       10.3.4.  Decision Tree Classifier for Image Data Analysis

       10.3.5.  Bagging Classifier for Image Data Analysis

       10.3.6.  Random Forest Classifier for Image Data Analysis

       10.3.7.  Extra Tree Classifier for Image Data Analysis

       10.3.8.  Ada Boost Classifier for Image Data Analysis

       10.3.9.  Gradient Boosting Classifier for Image Data Analysis

Module-4: Text and Image Data Analysis: Using Deep Learning

11.     Neural Network Models (Deep Learning)

11.1.        Introduction

       11.1.1.  Data Preparation

       11.1.2.  Building the Basic Sequential Model and Adding Layers

       11.1.3.  Compiling the Model

       11.1.4.  Fitting the Model on Training Dataset

       11.1.5.  Evaluating the Model

       11.1.6.  Creating Better Model with Increased Accuracy

11.2.        Neural Network Models for Text Data Analysis

       11.2.1.  Basic Neural Model for Text Data

       11.2.2.  Model with Different Units, Dropouts, Epochs, and Batch_size

       11.2.3.  Model with Different Activation, Loss and Optimizer

       11.2.4.  Model with Different Activation and Optimizer

       11.2.5.  Model with Grid-Based Approach for Best Value of Epoch and Batch_size

       11.2.6.  Model with LSTM Layers

       11.2.7.  Model with Different Activation and LSTM Layer

       11.2.8.  Model with Dropout Layer in LSTM Model

       11.2.9.  Model with Recurrent Dropout in LSTM Model

       11.2.10.       Model with Conv 1D Layer for Sequence Classification

11.3.        Neural Network Models for Image Data Analysis

       11.3.1.  Basic Neural Model for Image Data

       11.3.2.  Model with One-Hot Encoding

       11.3.3.  Model with ModelCheckPoint API

       11.3.4.  Model with Adding Hidden Layers

       11.3.5.  Model of Increased Depth

       11.3.6.  Model with Early Stopping API

       11.3.7.  Model with Grid-Based Approach

       11.3.8.  Model with CNN Layers

       11.3.9.  Model with Regularization

       11.3.10. Model with Autoencoder as Classifier

       11.3.11.  Model with Data augmentation

12. Transfer Learning for Text Data Analysis

12.1.        Introduction

       12.1.1.  Untrained Models

       12.1.2.  BERT Algorithm

       12.1.3.  GPT2 Algorithm

       12.1.4.  ROBERTIA Algorithm

       12.1.5.  XLM Algorithm

       12.1.6.  DistilBERT Algorithm

12.2.        Recommendation System Using Transfer Learning for Text Data

       12.2.1.  Recommendation System without Pre-Trained Model

       12.2.2.  Recommendation System Using BERT Algorithm

       12.2.3.  Recommendation System Using GPT2 Algorithm

       12.2.4.  Recommendation System Using ROBERTA Algorithm

       12.2.5.  Recommendation System Using XLM Algorithm

       12.2.6.  Recommendation System Using DistilBERT Algorithm

12.3.        Cluster Analysis Using Transfer Learning for Text Data

       12.3.1.  Cluster Analysis without Pre-Trained Model

       12.3.2.  Cluster Analysis Using BERT Algorithm

       12.3.3.  Cluster Analysis Using GPT2 Algorithm

       12.3.4.  Cluster Analysis Using ROBERTA Algorithm

       12.3.5.  Cluster Analysis Using XLM Algorithm

       12.3.6.  Cluster Analysis Using DistilBERT Algorithm

12.4.        Supervised Machine Learning Using Transfer Learning for Text Data Analysis

       12.4.1.  Supervised Machine Learning without Pre-Trained Model

       12.4.2.  Supervised Machine Learning Using BERT Algorithm

       12.4.3.  Supervised Machine Learning Using GPT2 Algorithm

       12.4.4.  Supervised Machine Learning Using ROBERTA Algorithm

       12.4.5.  Supervised Machine Learning Using XLM Algorithm

       12.4.6.  Supervised Machine Learning Using DistilBERT Algorithm

12.5.        User-Defined Trained Deep Learning Model

       12.5.1.  User-Defined Model Using BERT Algorithm

       12.5.2.  User-Defined Model Using Using GPT2 Algorithm

       12.5.3.  User-Defined Model Using Using ROBERTA Algorithm

       12.5.4.  User-Defined Model Using Using XLM Algorithm

       12.5.5.  User-Defined Model Using Using DistilBERT Algorithm

12.6.        Text Data Extraction Using Transfer Learning for Text Data

       12.6.1.  Text Data Extraction Using BERT Algorithm from PyTorch

       12.6.2.  Text Data Extraction Using BERT Algorithm from DeepPavlov

       12.6.3.  Text Data Extraction Using Ru_bert Algorithm from DeepPavlov

       12.6.4.  Text Data Extraction Using Ru_rubert Algorithm from DeepPavlov

13. Transfer Learning for Image Data Analysis

13.1.        Introduction

       13.1.1.  Untrained Model

       13.1.2.  MobileNet Model

       13.1.3.  MobileNetV2 Model

       13.1.4.  ResNet50 Model

       13.1.5.  VGG16 Model

       13.1.6.  VGG19 Model

13.2.        Recommendation System Using Transfer Learning for Image Data

       13.2.1.  Recommendation System without Pre-trained Model

       13.2.2.  Recommendation System Using MobileNet Model

       13.2.3.  Recommendation System Using MobileNetV2 Model

       13.2.4.  Recommendation System Using ResNet50 Model

       13.2.5.  Recommendation System Using VGG16 Model

       13.2.6.  Recommendation System Using VGG19 Model

13.3.        Cluster Analysis Using Transfer Learning for Image Data

       13.3.1.  Cluster Analysis without Pre-trained Model

       13.3.2.  Cluster Analysis Using MobileNet Model

       13.3.3.  Cluster Analysis Using MobileNetV2 Model

       13.3.4.  Cluster Analysis Using ResNet50 Model

       13.3.5.  Cluster Analysis Using VGG16 Model

       13.3.6.  Cluster Analysis Using VGG19 Model

13.4.        Supervised Machine Learning Using Transfer Learning for Image Data Analysis

       13.4.1.  Supervised Machine Learning without Pre-trained Model

       13.4.2.  Supervised Machine Learning Using MobileNet Model

       13.4.3.  Supervised Machine Learning Using MobileNetV2 Model

       13.4.4.  Supervised Machine Learning Using ResNet50 Model

       13.4.5.  Supervised Machine Learning VGG16 Model

       13.4.6.  Supervised Machine Learning VGG19 Model

13.5.        Facial Recognition Using Transfer Learning for Image Data Analysis

       13.5.1.  Single Image

       13.5.2.  Multiple Image

13.6.        Gender and Age Determination Using Transfer Learning for Image Data Analysis

       13.6.1.  Loading the Pre-Trained Model

       13.6.2.  Reading and Cropping the Face Image

       13.6.3.  Predicting Results

13.7.        Creating, Saving and Loading User-Defined Model for Feature Extraction

       13.7.1.  Creating and Saving the Model for Feature Extraction

       13.7.2.  Evaluating the Model on Existing Dataset

       13.7.3.  Loading the Model and Determining Emotions of Existing Image

       13.7.4.  Determining Emotions fro Cropped Facial Image

       13.7.5.  Determining Emotions of Image from Webcam

14. Chatbots with Rasa

14.1.        Understanding Rasa Environment and Executing Default Chatbot

       14.1.1.  Data Folder

       14.1.2.  domain.yml

       14.2.        Basic Chatbot

       14.2.1.  nlu.md File

       14.2.2.  stories.md File

       14.2.3.  domain.yml File

14.3.        Chatbot with Entities and Actions

       14.3.1.  Single Entity

       14.3.2.  Synonyms for Entities

       14.3.3.  Multiple Entities

       14.3.4.  Multiple Values of Entity in Same Intent

       14.3.5.  Numerous Values of Entity

       14.3.6.  nlu.md File

       14.3.7.  stories.md File

       14.3.8.  domain.yml File

       14.3.9.  actions.py File

14.4.        Chatbot with Slots

       14.4.1.  nlu.md Files

       14.4.2.  stories.md Files

       14.4.3.  domain.yml File

       14.4.4.  actions.py File

14.5.        Creating Chatbot with Database

       14.5.1.  nlu.md Files

       14.5.2.  stories.md Files

       14.5.3.  domain.yml File

       14.5.4.  actions.py File

14.6.        Chatbot with forms

       14.6.1.  nlu.md Files

       14.6.2.  stories.md Files

       14.6.3.  domain.yml File

       14.6.4.  actions.py File

14.7.        Creating Effective Chatbot

       14.7.1.  Providing Huge Training Data

       14.7.2.  Including out-of-Vocabulary Words

       14.7.3.  Managing Similar Intents

       14.7.4.  Balanced and Secured Data

15. Future Ahead:

       15.1.  Reinforcement Learning

       15.2.  Federated Learning

       15.3.  Graph Neural Networks

       15.4.  Generative Adversial Network