Iconographic Visualization Inside Computational Notebooks
-
Updated
Oct 16, 2023 - Jupyter Notebook
Iconographic Visualization Inside Computational Notebooks
SentimentArcs: a large ensemble of dozens of sentiment analysis models to analyze emotion in text over time
Interactive ML Toolset
Bag of Colors implementation in notebook form
Computer Vision: Vehicle Detection
Notebook for NLP feature engineering
This notebook demonstrates visualization and analysis of music and audio files using the Librosa python library.
It is end-to-end CNN Image Classification Model notebook which identifies the food in your image. In this project I was working with pre-trained classification model EfficientNetB1 and Food101 Dataset.
Extensive Collection of Jupyter Notebooks focused on Machine Learning covering different techniques includes Feature Engineering, Feature Selection, Feature Extraction, Model Training & Testing.
Computer Vision Course Notebooks, 2022
An image processing repository with Jupyter Notebooks
This notebook involves sentiment analysis on US airline tweets dataset.
A Jupyter notebook documentation of an ETL (extract -> transform -> load) data pipeline
This Jupyter notebook serves as a machine learning template to quickly make predictions and analyse feature importance in a dataset.
CNN Based Approach for Audio File Classification. Contains Notebooks Illustrating Data Preprocessing, Feature Extraction, Model Training, & Model Inference Workflows & Overall Pipeline
This notebook illustrates feature selection reverting many of the selection method results into pandas dataframes so that you get the appropriate column headings.
The notebook break down a problem of classification based on a weather in australia's data set. The idea of this work is to show different aproaches in how to visualize a data set, besides the idea is to develop different kind of Machine Learning Algorithms as Random Forest, SVM and Neural Networks.
This repository contains code for analyzing and predicting outcomes in the Indian Premier League (IPL) cricket matches from 2008 to 2022. It includes data analysis notebooks, a prediction model, and a Flask-based web application for interactive predictions. Explore historical match data, gain insights, and make predictions on upcoming matches .
The project is mostly concerned with feature engineering. To help the model grasp the data better, created additional features based on the disaster tweets. In the included notebook, each and every step is described in depth. In the supplied data set, I also dealt with the class imbalance. Final results: F1 Score 0.7031431897555296 Precision Sco…
Add a description, image, and links to the feature-extraction topic page so that developers can more easily learn about it.
To associate your repository with the feature-extraction topic, visit your repo's landing page and select "manage topics."