Artificial Intelligence in Health Care

Learn how to run Python code in an online Colaboratory notebook, execute cells with control enter, use the print function, and work with variables, data types, and comments.

Explore Python fundamentals for health care AI by mastering variables, data types (int, float, string, boolean), print and type checks, assignment, and basic operations.

Learn Python basics in this segment, covering input handling, typecasting to integers, arithmetic operations, and if-else logic to determine even or odd numbers, with hands-on examples.

Explore Python basics through hands-on coding, an assessment, and setup for use case datasets, visualizations, and AI and machine learning in health care.

Learn how to implement while and for loops in Python, using range to control iterations, updating a variable with increments or decrements, and printing values to observe loop behavior.

Learn how Python libraries extend functionality, from time library and aliasing to numpy, pandas, matplotlib, and sklearn, with next session focusing on pandas and sklearn.

Explore core Python data types such as lists, tuples, dictionaries, sets, and booleans. Learn to work with numpy arrays, sort them, and generate random numbers using numpy and random.

Explore numpy basics, including random values and seed control, then visualize data with matplotlib to plot x versus y, using arrays, sorting, and labeling for clarity.

Learn to download and install Tableau for data visualization and analysis, compare Tableau Public and Tableau Desktop, and verify system requirements (64-bit vs 32-bit) on Windows.

Learn how to install Tableau, accept terms, choose licensing, and prepare structured data for analysis using examples like COVID-19 India CSV and common data formats.

Analyze a simple nine-column state-level COVID-19 dataset in Tableau Public Desktop, tracing daily totals and patterns up to April 16, 2020, highlighting statewise infections.

Learn to import text and csv data into Tableau, identify dimensions and measures, build charts of confirmed cases by state, customize aggregation, color, and labels, and publish to Tableau Public.

Build interactive Tableau dashboards to visualize India's covid-19 data, including a pie chart of confirmed cases by state, annotate states, and compare cured versus confirmed with country and state filters.

Master building an interactive covid-19 dashboard in Tableau by selecting states to update confirmed and cured graphs, mapping data with state labels and tooltips, and delivering a clean, publication-ready visualization.

Learn to build a map-based visualization of confirmed cases by Indian states, edit locations, apply color, and customize tooltips and labels in a dynamic dashboard.

Create a Tableau Public pie chart from a state wise confirmed cases table. Filter to the last date, set a single color, show percent of total, and annotate top states.

Build a week-by-week health care data dashboard in Tableau Public, using date filters, text tables, and calculated fields to visualize confirmed, cured, and deaths with a dual-axis chart.

Learn to build a Covid analysis dashboard in Tableau, add charts from sheets (map, pie chart), apply date filters to worksheets, and synchronize dual axes for weekly trends.

Learn to build and refine a Tableau Public dashboard for covid India analysis by combining sheets, configuring layout, removing redundant visuals, using floating objects, and enabling interactive state-level insights.

Learn how a machine learning algorithm builds a predictive model from training data using features and labels. Compare supervised and unsupervised learning, including regression, classification, and clustering, with traditional programming.

Apply euclidean distance to kNN classification using coordinate points. Learn to implement the distance in Excel with cell references, sqrt, and locking for scalable health care data analysis.

Learn to lock and anchor spreadsheet references with F4 to fix x and y values while dragging formulas for a reliable knn weight dataset.

Demonstrates implementing KNN in Excel for health care data: compute Euclidean distances, rank neighbors, and use VLOOKUP to classify weights as underweight, normal, or overweight, with guidance on selecting k.

Learn to implement machine learning steps in Python, from creating a data frame and pre-processing to handling missing values, data visualization, and training and testing using input and output splits.

Learn the machine learning workflow with the KNN classifier: train the model on data, split test values, assess accuracy, and understand how data size and normalization influence predictions.

Open and rename a Google Colab notebook and upload the CSV dataset. Import pandas, numpy, and matplotlib, read the CSV with pd.read_csv, and create a data frame.

Learn to import a csv into a pandas data frame by copying the file path and using pd.read_csv assigned to df, then inspect the data frame.

Learn to prepare data for a k-nearest neighbors classifier using pandas iloc to split inputs and outputs, train with five neighbors using Euclidean distance, and make predictions.

Learn to split a data frame into three data frames for normal, underweight, and overweight classes, then plot a combined matplotlib scatter graph with colored points.

Label and color a weight-height scatter plot with axes, a title, and a legend for normal, underweight, and overweight. Show a KNN-based analysis and visualization using Python and pandas.

Apply machine learning to predict breast cancer malignancy using a Kaggle data set of features from digitized cell nuclei; prepare in a data frame and train-test split in Google Colab.

Explore how to preprocess structured cancer data, designate diagnosis as the output and other columns as inputs, and apply train-test split with random state to evaluate model accuracy.

Build a cancer prediction model with k nearest neighbors on split training and test data, fit on x train, predict x test, and evaluate accuracy for malignant versus benign.

Learn to build a simple web app using Streamlit in Google Colab, install dependencies with pip, and expose it with Ngrok for a temporary shareable url.

Explore how port numbers act as gates and how ngrok exposes a streamlit app on 8501. Set up and run app.py, manage runtime, and upload images for dna sequence visualization.

Build a Streamlit web app to count the nucleotide composition of a DNA sequence, displaying counts for adenine, cytosine, guanine, and thymine, with notes on RNA uracil.

Develop a streamlit web app to count DNA bases (A, T, G, C) from user input or uploads, convert to uppercase, and display results in a pandas data frame.