Build ML App (Streamlit Python) + Top Data Science projects

Ai apps evolve rapidly; data scientists must translate models into web-based visuals and tables for diverse end users in Asia, bridging gaps in JavaScript and HTML skills.

Explore how Strangelet enables ai web apps by handling back-end and requirements, while Streamliner simplifies ui creation and deployment with disease prediction and sales forecasting demos.

Set up the infrastructure for building a streamlined app by downloading Anakonda, using Notepad to write Python programs, and installing strangelet via the Anakonda command prompt.

Create your first web app using Streamliner, display hello world, customize font size and color, run from the Anaconda prompt, and preview locally with basic rerun and deployment options.

Create a Streamlit app with a header, subheader, and title, show success messages and handle errors or warnings, then run and preview ML results in a web interface.

Access and read a file stored in a folder, then display its data in a web app. Load CSV file from the streamed folder to create graphs and run algorithms.

Create and display a line, pie, and bar chart from data read into a data frame, in a web app, with view, download, and zoom options.

Display an external image in your ml app by reading a file and using mpl image to show a company logo, then save, refresh, and adjust its size and position.

Create a file upload button in a Streamlit app, upload and process files, read a file from a folder, browse files, understand size limits and paid options for larger uploads.

build a form with a selection box to choose machine learning or deep learning, a text input and submit button, plus role and knowledge level sliders.

Explore drop down options for single and multiple selections, using a select box to choose programming languages like Python, Java, C++, Go, and Google.

Explore how to switch themes in streamline, choosing light or dark modes and customizing colors via settings and the config file in the Anakonda folder.

Explore exploratory data analysis and missing values treatment to boost forecast accuracy in machine learning. Use univariate analysis and impute with mean/median for continuous data and mode for categorical data.

Explore exploratory data analysis with a Streamlit web app that uploads banking data, handles missing values (mean for numeric, mode for non-numeric), and visualizes histograms, correlations, and scatter plots.

learn to build a breast cancer prediction app with streamlit and logistic regression, using 32 tumor features, numeric encoding, a 75/25 train-test split, and evaluation via confusion matrix and accuracy.

Build a word cloud app using natural language processing to extract key terms from articles, remove stop words, count word frequencies, and visualize results with matplotlib and Beautiful Soup.

Build a time series forecasting app in Streamlit that uses ARIMA and Facebook's profit algorithm, decomposes data into seasonality, trend, and residuals, and visualizes future forecasts.

Explore CLV concepts and learn to compute it using sales and time value of money with discount rate, then segment customers by recency, frequency, and monetary value to drive campaigns.

Compute customer lifetime value using lifelines with BG/NBD and gamma-gamma models to predict order frequency and monetary value, then discount future revenue to present value for up to 60 months.

Explore market basket analysis to uncover relationships between items, including frequently bought together patterns, using apriori with support, confidence, and lift, via a Streamlit app.