From 2d81b6dd50868b8bf95dc43c11a0dfdd1bfa9a3e Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sat, 12 Oct 2024 23:14:29 +0530 Subject: [PATCH 1/7] Create README.md --- .../README.md | 92 +++++++++++++++++++ 1 file changed, 92 insertions(+) create mode 100644 Prediction Models/Advanced House Price Predictions/README.md diff --git a/Prediction Models/Advanced House Price Predictions/README.md b/Prediction Models/Advanced House Price Predictions/README.md new file mode 100644 index 000000000..0957f1281 --- /dev/null +++ b/Prediction Models/Advanced House Price Predictions/README.md @@ -0,0 +1,92 @@ + +### Advanced House Price Prediction + +This project utilizes the California housing dataset to predict housing prices based on various features using machine learning techniques. The primary goal is to explore the relationships between different features of the dataset and the median house value, then build a model that can accurately predict house prices. + +### Table of Contents + +- Dataset +- Installation +- Usage +- Data Exploration +- Model Training +- Results +- Contributions +- License + + +### Dataset: + +The dataset used in this project is the California housing dataset, which includes the following features: + +- **MedInc:** Median income in block group +- **HouseAge:** Median house age in the block +- **AveRooms:** Average number of rooms per household +- **AveBedrms:** Average number of bedrooms per household +- **Population**: Block group population +- **AveOccup:** Average house occupancy +- **Latitude:** Geographical latitude +- **Longitude:** Geographical longitude +- **MedHouseVal:** Median house value (target variable) +- The dataset can be fetched directly using fetch_california_housing() from sklearn.datasets. + +### **Installation** +To run this project, ensure you have Python installed on your machine. You will also need the following packages: + +- pandas +- numpy +- matplotlib +- seaborn +- scikit-learn + +You can install the required packages using pip: + + ```bash + pip install pandas numpy matplotlib seaborn scikit-learn + ``` + +Clone this repository: + + ```bash + git clone https://github.com/yourusername/california-housing-price-prediction.git + cd california-housing-price-prediction + ``` +Run the Jupyter Notebook or Python script: + +```bash +jupyter notebook California_Housing_Price_Prediction.ipynb +``` + +### Data Exploration +The data exploration process includes: + +- Displaying the first few rows of the dataset. +- Summary statistics of the features. +- Checking for missing values. +- Visualizing relationships between features using pair plots and scatter plots. +- Analyzing the distribution of the target variable (Median House Value). + +### Model Training +The project utilizes a Random Forest Regressor to predict the median house value based on the input features. The workflow includes: + + 1. Data Preprocessing: + + - Splitting the dataset into training and testing sets. + - Standardizing the features using StandardScaler. + + 2. Model Training: + + - Training the Random Forest model with 100 estimators. + + 3. Evaluation: + + - Evaluating the model's performance using Mean Squared Error (MSE) and R-squared metrics. + + +### Results +The model's performance metrics are as follows: + +- Training MSE: 0.04 +- Testing MSE: 0.26 +- Training R²: 0.97 +- Testing R²: 0.81 From c6f2d3b8f37b2a7d711b3788731d82ea1d1020fd Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sat, 12 Oct 2024 23:27:38 +0530 Subject: [PATCH 2/7] Create README.md --- .../Models/README.md | 56 +++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 Prediction Models/Alzheimer's Disease Prediction/Models/README.md diff --git a/Prediction Models/Alzheimer's Disease Prediction/Models/README.md b/Prediction Models/Alzheimer's Disease Prediction/Models/README.md new file mode 100644 index 000000000..74a055120 --- /dev/null +++ b/Prediction Models/Alzheimer's Disease Prediction/Models/README.md @@ -0,0 +1,56 @@ +# Alzheimer's Disease Classification Using CNN + +## Project Overview + +This project aims to classify images of individuals into different categories of Alzheimer's disease using Convolutional Neural Networks (CNN). The dataset used includes images from four classes: Non-Demented, Very Mild Demented, Mild Demented, and Moderate Demented. The model is trained to recognize features that distinguish these classes, providing a tool for early diagnosis and research. + +## Table of Contents + +- [Installation](#installation) +- [Dataset](#dataset) +- [Model Architecture](#model-architecture) +- [Training](#training) +- [Results](#results) +- [Acknowledgements](#acknowledgements) + +## Installation + +To run this project, you'll need to have Python 3.x and the following packages installed: + +```bash +pip install pandas numpy opencv-python matplotlib tensorflow imbalanced-learn +``` + +You can clone the repository and navigate to the project directory: + +```bash +git clone +cd +``` + +### Dataset +The dataset used in this project is the Alzheimer’s Dataset, which contains images categorized into four classes: + +- Non-Demented +- Very Mild Demented +- Mild Demented +- Moderate Demented +The dataset can be downloaded from the following link: Alzheimer's Dataset. + +### Model Architecture +The model is built using the Keras Sequential API. The architecture consists of: + +- Input Layer: Input shape of (176, 176, 3) +- Flatten Layer: Converts the 2D image into a 1D array. +- Dense Layers: Five hidden layers with ReLU activation functions. +- Output Layer: Softmax activation function to predict class probabilities. + +### Training +The model is trained using: + +- Optimizer: Adam +- Loss Function: Categorical Crossentropy +- Metrics: AUC (Area Under Curve) + + + From 9747dafde0c3fc5ba400df9d92bd7753a2f3123c Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sat, 12 Oct 2024 23:32:54 +0530 Subject: [PATCH 3/7] Create README.md --- .../Blood Donation Prediction/README.md | 52 +++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 Prediction Models/Blood Donation Prediction/README.md diff --git a/Prediction Models/Blood Donation Prediction/README.md b/Prediction Models/Blood Donation Prediction/README.md new file mode 100644 index 000000000..b54986dc5 --- /dev/null +++ b/Prediction Models/Blood Donation Prediction/README.md @@ -0,0 +1,52 @@ +# Blood Glucose Level Prediction + +## Overview + +This project aims to predict blood glucose levels using machine learning techniques, specifically focusing on the relationship between glucose levels, insulin doses, and carbohydrate intake over time. The dataset includes timestamps, glucose levels, insulin doses, and carbohydrate intake. + +## Table of Contents + +- [Technologies Used](#technologies-used) +- [Dataset](#dataset) +- [Installation](#installation) +- [Model Training and Evaluation](#model-training-and-evaluation) +- [Results](#results) + +## Technologies Used + +- Python +- Pandas +- NumPy +- Matplotlib +- Scikit-learn + +## Dataset + +The dataset used for this project is `blood_glucose_data.csv`, which contains the following columns: + +- `timestamp`: The date and time of the recorded glucose level. +- `glucose_level`: The level of glucose in mg/dL. +- `insulin_dose`: The dose of insulin administered in units. +- `carb_intake`: The amount of carbohydrate intake in grams. + +## Installation + +To run this project, make sure you have the following libraries installed. You can install them using pip: + +```bash +pip install pandas numpy matplotlib scikit-learn +``` + +### Model Training and Evaluation +The model is trained using a linear regression approach with the following features: + +- Hour of the day. +- Day of the week. +- Insulin dose. +- Carbohydrate intake. + +### Model Evaluation Metrics +- Mean Absolute Error (MAE): 15.43 +- Root Mean Squared Error (RMSE): 19.20 +Results +The results of the model training can be visualized to compare actual glucose levels with predicted values. From a5b7ef1dce45beec21fef274a89aed313a3b3efa Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sat, 12 Oct 2024 23:33:41 +0530 Subject: [PATCH 4/7] Update README.md --- .../Alzheimer's Disease Prediction/Models/README.md | 2 -- 1 file changed, 2 deletions(-) diff --git a/Prediction Models/Alzheimer's Disease Prediction/Models/README.md b/Prediction Models/Alzheimer's Disease Prediction/Models/README.md index 74a055120..bc7b0dbc8 100644 --- a/Prediction Models/Alzheimer's Disease Prediction/Models/README.md +++ b/Prediction Models/Alzheimer's Disease Prediction/Models/README.md @@ -10,8 +10,6 @@ This project aims to classify images of individuals into different categories of - [Dataset](#dataset) - [Model Architecture](#model-architecture) - [Training](#training) -- [Results](#results) -- [Acknowledgements](#acknowledgements) ## Installation From cfbaf5aa65124ae1e9362cb617b53910f60c92cc Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sat, 12 Oct 2024 23:34:18 +0530 Subject: [PATCH 5/7] Update README.md --- .../Advanced House Price Predictions/README.md | 6 ------ 1 file changed, 6 deletions(-) diff --git a/Prediction Models/Advanced House Price Predictions/README.md b/Prediction Models/Advanced House Price Predictions/README.md index 0957f1281..fe902636a 100644 --- a/Prediction Models/Advanced House Price Predictions/README.md +++ b/Prediction Models/Advanced House Price Predictions/README.md @@ -10,9 +10,6 @@ This project utilizes the California housing dataset to predict housing prices b - Usage - Data Exploration - Model Training -- Results -- Contributions -- License ### Dataset: @@ -83,9 +80,6 @@ The project utilizes a Random Forest Regressor to predict the median house value - Evaluating the model's performance using Mean Squared Error (MSE) and R-squared metrics. -### Results -The model's performance metrics are as follows: - - Training MSE: 0.04 - Testing MSE: 0.26 - Training R²: 0.97 From a71edfb194c4f855b8a4f39835c9f429d54a9210 Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sat, 12 Oct 2024 23:36:20 +0530 Subject: [PATCH 6/7] Create README.md --- .../README.md | 52 +++++++++++++++++++ 1 file changed, 52 insertions(+) create mode 100644 Prediction Models/Blood Glucose Level Prediction (Machine Learning)/README.md diff --git a/Prediction Models/Blood Glucose Level Prediction (Machine Learning)/README.md b/Prediction Models/Blood Glucose Level Prediction (Machine Learning)/README.md new file mode 100644 index 000000000..25ac1cf61 --- /dev/null +++ b/Prediction Models/Blood Glucose Level Prediction (Machine Learning)/README.md @@ -0,0 +1,52 @@ +# Blood Glucose Level Prediction + +## Overview + +This project aims to predict blood glucose levels using machine learning techniques, specifically focusing on the relationship between glucose levels, insulin doses, and carbohydrate intake over time. The dataset includes timestamps, glucose levels, insulin doses, and carbohydrate intake. + +## Table of Contents + +- [Technologies Used](#technologies-used) +- [Dataset](#dataset) +- [Installation](#installation) +- [Model Training and Evaluation](#model-training-and-evaluation) + + +## Technologies Used + +- Python +- Pandas +- NumPy +- Matplotlib +- Scikit-learn + +## Dataset + +The dataset used for this project is `blood_glucose_data.csv`, which contains the following columns: + +- `timestamp`: The date and time of the recorded glucose level. +- `glucose_level`: The level of glucose in mg/dL. +- `insulin_dose`: The dose of insulin administered in units. +- `carb_intake`: The amount of carbohydrate intake in grams. + +## Installation + +To run this project, make sure you have the following libraries installed. You can install them using pip: + +```bash +pip install pandas numpy matplotlib scikit-learn +``` + +### Model Training and Evaluation +The model is trained using a linear regression approach with the following features: + +- Hour of the day. +- Day of the week. +- Insulin dose. +- Carbohydrate intake. + +### Model Evaluation Metrics +- Mean Absolute Error (MAE): 15.43 +- Root Mean Squared Error (RMSE): 19.20 +Results +The results of the model training can be visualized to compare actual glucose levels with predicted values. From dbaf1a21efce9455f4860feef489eff91e026647 Mon Sep 17 00:00:00 2001 From: DEEPANSHU BAGHEL <92099428+deepanshubaghel@users.noreply.github.com> Date: Sun, 13 Oct 2024 01:04:45 +0530 Subject: [PATCH 7/7] Create README.md --- .../Calories Burnt Prediction/README.md | 41 +++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 Prediction Models/Calories Burnt Prediction/README.md diff --git a/Prediction Models/Calories Burnt Prediction/README.md b/Prediction Models/Calories Burnt Prediction/README.md new file mode 100644 index 000000000..2162eef0e --- /dev/null +++ b/Prediction Models/Calories Burnt Prediction/README.md @@ -0,0 +1,41 @@ +## Calories Burn Prediction + +### Project Overview +The "Calories Fat Burn" project aims to predict the number of calories burned based on various features such as user demographics, exercise duration, and physiological parameters. Utilizing the XGBoost regression algorithm, the model helps in understanding the relationship between exercise and calorie expenditure, enabling users to optimize their workouts for better fat burning. + +### Table of Contents +- Installation +- Data Collection +- Data Processing +- Data Analysis +- Model Training +- Evaluation + +### Installation +To run this project, you will need to install the following libraries: + +```bash +pip install numpy pandas matplotlib seaborn scikit-learn xgboost +``` + +### Data Collection +The data is collected from two CSV files: + +1. calories.csv: Contains user IDs and calories burned. +2. exercise.csv: Contains user demographics and exercise details. + +### Data Processing +The data is processed to create a combined DataFrame containing user demographics and calories burned. The categorical variable "Gender" is encoded into numerical values for model training. + +### Data Analysis +Statistical analysis and visualization techniques are employed to understand the data distribution and correlations among features. + +- Gender Distribution +- Age Distribution +- Correlation Heatmap + +### Model Training +The XGBoost regressor is trained on the training dataset to predict calorie burn. + +### Evaluation +The model's performance is evaluated using the Mean Absolute Error (MAE).