Python with AI Course

Data Analysis and Visualization using Pandas.

• Read data from Excel File using Pandas More Plotting, Date Time Indexing and writing to les

• How to get record specic records Using Pandas Adding & Resetting Columns, Mapping with function

• Using the Excel File class to read multiple sheets More Mapping, Filling Nonvalue’s

• Exploring the Data Plotting, Correlations, and Histograms

• Getting statistical information about the data Analysis Concepts, Handle the None Values

• Reading les with no header and skipping records Cumulative Sums and Value Counts, Ranking etc

• Reading a subset of columns Data Maintenance, Adding/Removing Cols and Rows

• Applying formulas on the columns Basic Grouping, Concepts of Aggre gate Function

• Complete Understanding of Pivot Table Data Slicing using iLoc and Loc property (Setting Indices)

• Under sting the Properties of Pivot Table in Pandas Advanced Reading CSVs/HTML, Binning, Categorical Data

• Exporting the results to Excel Joins

• Python | Pandas Data Frame Inner Join

• Under sting the properties of Data Frame Left Join (Left Outer Join)

• Indexing and Selecting Data with Pandas Right Join (Right Outer Join)

• Pandas | Merging, Joining and Concatenating Full Join (Full Outer Join)

• Pandas | Find Missing Data and Fill and Drop NA Appending Data Frame and Data

• Pandas | How to Group Data How to apply Lambda / Function on Data Frame

• Other Very Useful concepts of Pandas in Python Data Time Property in Pandas (More and More)

Data Analysis and Visualization using NumPy

• Introduction to NumPy Numerical Python

• Importing NumPy and Its Properties

• NumPy Arrays

• Creating an Array from a CSV

• Operations an Array from a CSV

• Operations with NumPy Arrays

• Two-Dimensional Array

• Selecting Elements from 1-D Array

• Selecting Elements from 2-D Array

• Logical Operation with Arrays

• Indexing NumPy elements using conditionals

• NumPy’s Mean and Axis

• NumPy’s Mode, Median and Sum Function

• NumPy’s Sort Function and More

Data Analysis and Visualization using MatPlotLib

• Bar Chart using Python MatPlotLib

• Column Chart using Python MatPlotLib

• Pie Chart using Python MatPlotLib

• Area Chart using Python MatPlotLib

• Scatter Plot Chart using Python MatPlotLib

• Play with Charts Properties Using MatPlotLib

• Export the Chart as Image

• Understanding plt. subplots () notation

• Legend Alignment of Chart using MatPlotLib

• Create Charts as Image

• Other Useful Properties of Charts.

• Complete Understanding of Histograms

• Plotting Different Charts, Labels, and Labels Alignment etc.

Introduction to Data Visualization with Seaborn

• Introduction to Seaborn

• Making a scatter plot with lists

• Making a count plot with a list

• Using Pandas with seaborn

• Tidy vs Untidy data

• Making a count plot with a Dataframe

• Adding a third variable with hue

• Hue and scattera plots

• Hue and count plots

• Visualizing Two Quantitative Variables
• Introduction to relational plots and subplots
• Creating subplots with col and row
• Customizing scatters plots
• Changing the size of scatter plot points
• Changing the style of scatter plot points
• Introduction to line plots
• Interpreting line plots
• Visualizing standard deviation with line plots
• Plotting subgroups in line plots

• Visualizing a Categorical and a Quantitative Variable
• Current plots and bar plots
• Count plots
• Bar plot with percentages
• Customizing bar plots
• Box plots
• Create and interpret a box plot
• Omitting outliers
• Adjusting the whisk
• Point plots
• Customizing points plots
• Point plot with subgroups

• Customizing Seaborn Plots
• Changing plot style and colour
• Changing style and palette
• Changing the scale
• Using a custom palette
• Adding titles and labels Part 1
• Face Grids vs. Axes Subplots
• Adding a title to a face Grid object
• Adding title and labels Part 2
• Adding a title and axis labels
• Rotating x-tics labels
• Putting it all together
• Box plot with subgroups
• Bar plot with subgroups and subplots
• Well done! What’s next

Foundation for AI: Learn traditional ML models, evaluation, and workflows.

• Introduction to ML, AI, and Deep Learning

• Types of ML (Supervised, Unsupervised, Reinforcement)

• ML Pipeline: Data Cleaning, Feature Engineering

• Common ML Algorithms: Linear, Logistic, DT, RF, SVM, KNN

• Model Evaluation: Accuracy, Precision, Recall, F1, ROC-AUC

• Overfitting, Underfitting, Cross-Validation

• Hands-on Project: Titanic Dataset (or similar)

Understand the inner workings of neural networks and train them with Keras.

• Introduction to Neural Networks & Deep Learning

• Activation Functions (ReLU, Sigmoid, Tanh)

• Feedforward Neural Network

• Backpropagation & Gradient Descent

• Learning Rate, Schedulers & Optimizers (SGD, Adam, RMSProp)

• Softmax, Cross-Entropy Loss

• Keras Basics: Sequential API & Functional API

• Fully Connected Layer – Forward/Backward Pass

• Regularization – Dropout, Batch Normalization

• Data Preprocessing & Data Augmentation

• Weight Initialization Strategies

• Babysitting Learning: Overfit detection, TensorBoard Monitoring

• Hands-on: MLP on MNIST / Tabular data (e.g. HR Analytics)

Master CNNs, object detection, segmentation, and deployment.

• Basics of Images, Image Preprocessing

• Convolution: 2D Conv, Forward & Backward

• Pooling, Padding, Stride, Transposed Conv

• CNN Architectures: LeNet, AlexNet, VGG, ResNet

• GPU vs CPU for DL

• Transfer Learning: Inception, MobileNet, fine-tuning

• Semantic Segmentation using UNet

• Object Detection – YOLO, SSD, Region Proposal

• Bounding Box Regressor

• Siamese Networks for Similarity Search

• Hands-on:
• Image Classification with CNN
• Object Detection with YOLOv8
• Visual Search with Embeddings