snowscriptwinterofcode/ml-models

Drop in the links to predictive ML models and tell us about it in detail

ml-models's Issues

Text based emotion classifier

Objective: Build a model that can classify the emotions (e.g., happy, sad, angry) expressed in a given text input.

Workflow:

• Data Collection: Gather a dataset with text samples labeled with emotions.

• Data Preprocessing: Clean and preprocess the text data. This includes tasks like tokenization, removing stopwords, and converting text to numerical representations (e.g., word embeddings).

• Model Selection and Training: Train a machine learning or deep learning model for text classification (e.g., LSTM, Naive Bayes, or SVM).

• Evaluation: Evaluate the model's performance using metrics

Psychosocial Balance of Student Analysis

This project aims to uncover correlations between depression levels, academic performance, and various lifestyle factors of a student life.
Psychosocial Dimensions of Student Life Dataset will be used . Focus on finding key patterns and training a accurate model for predicting depression level of a student.
This project not only addresses crucial mental health concerns but also contributes to enhancing student support systems and fostering a positive learning environment.

Training more models on Flora Classification

• Random Forest
• XG Boost
• SVC
• Naive Bayes
• Decision Tree
• KNN
  Visualizing evaluation metrics
  Extension of #33

Bank Churn Dataset Analysis

The dataset for this problem was generated from a deep learning model trained on the [Bank Customer Churn Prediction] dataset. Feature distributions are close to, but not exactly the same, as the original.

Files
train.csv - the training dataset; Exited is the binary target

Goal is to analyze this data

Android Malware Detector using dataset from Kaggle

House Price predictor

• Use different machine learning models to predict house prices
• EDA
• Apply evaluation metrics
• Report the results
• Serialize and store the output

Git clone issue in Windows OS due to special character in file names

In the source code folder, there is a file named Dataset->Movie Recommender which creates problem during cloning the Git repo into local Windows OS.

In a GitHub repository, a file with a name containing "->" typically indicates the use of a symbolic link or symlink. Symbolic links are references to another file or directory, essentially creating a shortcut or alias. The "->" arrow is often used to visually represent the link between the original file/directory and the symlink.

For example, if you have a file named file1.txt and a symlink with the name file2.txt -> file1.txt, it means that accessing file2.txt will lead you to the contents of file1.txt. This can be useful for creating references to common files or directories without duplicating the actual data.

However, it's essential to note that symbolic links may not work as expected on all systems, and they might behave differently on Windows, macOS, and Linux. So, file names should not contain the special character "->", unless we are creating symlinks

The File name in the source code should not contain special characters, especially "->" character. It is misinterpreted by git as a Branch path. This issue is automatically handled in Linux or Mac OS.

Restructure Issue #2

Issue #2 - time series forecasting

Different folders are created - datasets, images, model
I want to put them inside one folder to make them organized.

Flora Classification

• Normalized data
• EDA
• Model Training
• Evaluation metrics

SMS Spam Classifier

Using a Kaggle dataset to perform EDA and finding out if a message is Spam or not

ShipWreck Prediction

use machine learning to create a model that predicts which passengers survived the Titanic shipwreck

Brain tumor prediction

the model would predict if tumor is present or not in brain using VGG-16

Stock Market Prediction Model

Develop a stock market prediction model using machine learning. Utilize historical stock data and relevant features for training various algorithms like Linear Regression or Random Forest. Evaluate the model's performance, fine-tune parameters, and continuously update with new data for enhanced accuracy in forecasting future stock prices.

Diabetes Prediction

Please assign this to me. Using kaggle dataset, I performed Exploratory data analysis and linear regression to predict diabetes among patients

Topic modelling in text data

• using nlp techniques

Covid19 Prediction

Predicting the daily number of confirmed COVID19 cases in various locations across the world

• Perform data analysis to identify the factors that impact the transmission rate of COVID-19.
• Analyze the the effect of COVID-19 in India.
• Use XGBoost and Random Forest regressor as ensemble learning models as well as to predict the daily # of confirmed cases

Credit Card Approval system using dataset from Kaggle

Please assign the issue to me

Image Captioning model

• Using LSTM and CNN

NLP Text Summarizer Project

NLP Text Summarizer Project

Problem Statement - Train and test a machine learning model to produce text summary using dataset from HuggingFace

Movie Recommender System(Content Based)

Building a content based Movie Recommender System using dataset from Kaggle

Time Series Forecasting

Time Series Forecasting

Problem Statement: Use a dataset with 2 months of data on One Drive user activities to predict 5 years of storage capacity.
Steps :

• Generate dataset with prompt engineering and use of OpenAI API
• Train conventional time series models - ARIMA, SARIMA etc.
• Get Predictions
• Introduce exogenous variables to the dataset and train model like ARIMAX and FB-PROPHET on it.
• Compare predictions of exogenous and standard feature utilizing models
• Get results
• Improve upon the results with ensemble methods.