Mohamed Shaad's Projects
This project demonstrates the creation of a 3D surface prediction model using TensorFlow. The model is trained on a randomly generated dataset and visualizes the predicted surface in a 3D space.
500 AI Machine learning Deep learning Computer vision NLP Projects with code
This code performs an A/B testing analysis using control and test group data. It analyzes various metrics such as amount spent, number of impressions, reach, website clicks, searches received, content viewed, added to cart, and purchases. The analysis includes visualizations of the data using Plotly.
This repository contains a project that leverages AI agents using CrewAI and Google Gemini to research and write about the latest trends in AI technology, specifically focusing on healthcare.
The AI-powered Cover Letter Generator is a Streamlit web application that leverages the GooglePalm language model to generate cover letters based on user input. Users can input details such as job description, company name, job position, experience, and the maximum number of characters for the cover letter.
This is a Python application that uses the Streamlit library to perform algorithmic trading analysis based on stock momentum. It retrieves stock data from Yahoo Finance using the yfinance library and visualizes the momentum and buying/selling signals using Plotly.
This project sets up agentic automation for planning, writing, and editing articles using AI agents with crewAI.
This project demonstrates Aspect-Based Sentiment Analysis (ABSA) using PyABSA, a library for aspect-based sentiment analysis. The application allows users to input a sentence, and it extracts aspects, predicts sentiment, and displays the results in a tabular form.
This project involves the prediction of house prices in Boston using Lasso Regression in Jupyter Notebook. The dataset contains features such as average number of rooms per dwelling, crime rate, and more. Through this analysis, we aim to build a regression model that accurately predicts house prices based on the given input features.
This project involves detecting breast cancer using the Naive Bayes classifier in Jupyter Notebook. Breast cancer detection is a crucial task in healthcare, as it aids in the early diagnosis and treatment of the disease. Through this project, we aim to explore and understand how the Naive Bayes classifier can be used for breast cancer detection.
This project aims to extract structured data from business cards using a combination of OpenCV, PyTesseract, and spaCy.
This repository provides a cancer classification model using Support Vector Classifier (SVC). The model aims to classify cancer cases into benign or malignant based on various features obtained from medical examinations.
This project involves predicting used car prices using linear regression in Jupyter Notebook. Used car price prediction is an important task in the automotive industry, as it helps estimate the value of pre-owned vehicles based on various factors such as mileage, brand, age, etc.
This is a simple chatbot implemented using Python and Streamlit. The chatbot uses a logistic regression classifier with TF-IDF vectorization to classify user input and generate appropriate responses.
A simple chatbot implementation using JavaScript and integration with the OpenAI GPT-3.5 Turbo model.
S-Chatbot is a Streamlit-based chatbot powered by GooglePalm language model. It allows users to interact with the chatbot and receive responses from the model.
This is a sample application that demonstrates how to build a classification AutoML app using Streamlit, Pandas Profiling, and PyCaret.
This project provides a user-friendly Gradio interface that enables you to interact with the custom model based on CodeLlama model from Ollama, an open-source large language model platform. Simply enter your prompt in the textbox, and custom model will generate code based on your input.
This repository demonstrates the potential of using Google's CodeGemma-2B Large Language Model (LLM) to assist in generating code.
This project utilizes the LangChain and Groq to perform various analyses on loan recovery conversations. The primary functionalities include summarizing conversations, identifying key actions or next steps, and undertaking sentiment analysis of both the recovery agent and the borrower.
This project automates the process of monitoring market data, developing trading strategies, executing trades, and assessing risks using a team of specialized AI Agents from crewAI. Each agent is equipped with specific roles and goals, and they collaborate to optimize trading decisions and strategies.
This repository contains code and data for analyzing the USD - INR conversion rate over the years. The analysis includes data visualization, growth analysis, seasonal decomposition, and time series forecasting using SARIMA.
This repository demonstrates the use of CrewAI to enhance sales outreach and lead profiling using a combination of advanced AI agents and tools. The project leverages CrewAI agents and LangChain to identify high-value leads and craft personalized outreach campaigns.
This project involves segmenting customers using k-means clustering in Jupyter Notebook. Customer segmentation is a powerful technique used in marketing and business analytics to divide customers into distinct groups based on their behaviors, preferences, or demographics.
This code demonstrates how to load the Fashion MNIST dataset using TensorFlow's Keras API, preprocess the data, and store it in a SQLite database. The Fashion MNIST dataset consists of grayscale images of clothing items with corresponding labels.
This project contains a data preprocessing pipeline implemented in Python using the pandas and numpy libraries. The pipeline handles missing values, outliers, and normalizes numeric features in a dataset.
Resoruce to help you to prepare for your comming data science interviews
This repository contains a collection of classic and essential data structures and algorithms implemented in Python.
This project involves the prediction of diabetes progression using Ridge Regression in Jupyter Notebook. The dataset contains features such as glucose level, blood pressure, body mass index, and more. Through this analysis, we aim to build a regression model that accurately predicts the progression of diabetes based on the given input features.