2.1 Python Language Overview

• History of Python and its growing ecosystem
• Comparison with other languages (Java, C++)
• Syntax overview and use cases in data science and AI

2.2 Introduction to Python Programming

• Writing a complete program from scratch
• print(), input(), basic variables and logic
• Emphasis on code structure and readability

2.3 Basics of Python Programming

• If-else conditions
• Nested statements
• While and For loops
• Logic and comparison operators

2.4 Python Programming – Part 1

• Lists: creation, access, loop through
• Tuples: immutability and usage
• Dictionary: keys and values, looping
• List comprehensions and nested structures

2.5 Python Programming – Part 2

• Functions: def, arguments, return values
• Modules: creating and importing (math, random)
• File I/O: reading and writing text files
• Try-except blocks for error handling

3.1 Introduction to Matplotlib

• Purpose: Visualizing trends and comparisons
• Introduction to pyplot, figure, axes

3.2 Matplotlib Plots

• Line, scatter, bar, histogram, pie charts
• Understanding x and y axes, legends, and grid

3.3 Matplotlib Styles – Part 1

• Customizing:
  • Title, x/y axis labels
  • Font size, type, color
  • Line styles (--, -, :)

3.4 Matplotlib Styles – Part 2

• Themes: seaborn styles, ggplot, bmh
• Using plt.style.use()
• Saving plots as new_images (.png, .svg)

3.5 Matplotlib Plot Variants

• Subplots: multiple plots in one figure
• Plotting from Pandas DataFrames
• Adding annotations, text, and markers

4.1 Introduction to NumPy

• Why use NumPy over regular Python lists
• Efficiency and memory handling

4.2 NumPy Data Types and Operations

• Types: int32, float64, bool
• Element-wise operations
• Comparisons and logical operations

4.3 NumPy Arrays

• Creating arrays: np.array, np.zeros, np.arange, np.linspace
• Reshaping: .reshape(), .flatten()
• Indexing and slicing multidimensional arrays

4.4 Array Attributes

• .shape, .ndim, .dtype, .size
• Transpose: .T
• Copy vs View behavior

4.5 NumPy Math

• Basic: sum, mean, std, min, max
• Linear algebra: dot product, matrix multiplication
• Random number generation: np.random

5.1 Introduction to Pandas

• Understanding Series and DataFrames
• Structure of tabular data

5.2 Reading Data

• read_csv(), read_excel(), read_json()
• Handling missing values: NaN, fillna(), dropna()

5.3 Data Manipulation – Part 1

• Selecting rows/columns using loc and iloc
• Adding/removing columns
• Filtering data using conditions

5.4 Data Manipulation – Part 2

• groupby(), aggregation
• Sorting by values or index
• Pivot tables and reshaping

5.5 Data Manipulation – Part 3

• Merging and joining DataFrames
• concat(), merge(), join()
• Time series basics (resample, rolling)

6.1 Introduction to Machine Learning

• What is ML, and its use in real-world applications
  • Healthcare
  • Finance
  • Retail & E-commerce
  • Transportation
  • Natural Language Processing (NLP)
  • Manufacturing
• Types of learning
  • Supervised
  • Unsupervised
  • Reinforcement
• Algorithms
  • Clustering
  • Classification
  • Regression

6.2 Unsupervised Learning Techniques

• Clustering
  • Visualizing clusters using PCA or t-SNE
  • K-Means
  • Hierarchical
  • DBSCAN
• Dimensionality Reduction
  • PCA
  • LDA
• Feature selection and extraction

7.0 Getting Started with TensorFlow

• Installing TensorFlow
  • Install using pip install tensorflow.
  • It supports CPU and GPU versions.
• Tensors
  • Core data structure in TensorFlow — multi-dimensional arrays used in computations.
• Architecture
  • TensorFlow uses a computation graph.
  • In v2.x, eager execution allows real-time operation.
• Basic Operations
  • Tensor creation
  • Arithmetic (add, multiply)
  • Reshaping
  • Reduction (sum, mean)

7.1 Introduction to Keras

• Keras Overview
  • High-level API within TensorFlow for building neural networks easily.
• Building Models
  • Use Sequential or functional API to define layers.
  • Compile with optimizer, loss, and metrics.
• Training & Evaluation
  • Use fit() to train.
  • Use evaluate() for test performance.
  • Use predict() for outputs.

7.2 Clustering

• Model Building
  • Use Scikit-learn for classic clustering (K-Means, DBSCAN).
  • Or use Keras with autoencoders for advanced clustering approaches.
• Visualization
  • Use PCA or t-SNE with matplotlib to plot clustered data in 2D.
• Evaluation
  • Silhouette Score measures how well data points fit within clusters (closer to 1 is better).

7.3 Deep Learning Basics

• Understanding
  • Perceptrons, hidden layers, weights, biases
  • Activation functions (ReLU, Sigmoid, Softmax)
  • Backpropagation and gradient descent

7.4 Natural Language Processing (NLP)

• Text cleaning
  • Lowercase
  • Punctuation removal
• Tokenization, stemming, lemmatization
• Word embeddings
  • Word2Vec
  • TF-IDF
• Simple NLP tasks
  • Sentiment Analysis
  • Spam Detection

7.5 Reinforcement Learning

• Concepts
  • Agent
  • Environment
  • Reward
  • Policy
• Introduction to Q-Learning and Markov Decision Processes
• Real-life examples
  • Games
  • Robotics
  • Recommendation systems