The Symptom Matcher project utilizes a dataset containing symptoms and disease labels to build a predictive model using the Random Forest Classifier. This model helps predict the disease based on the provided symptoms.
-
Data Loading: Load the dataset containing symptoms and disease labels.
-
Exploratory Data Analysis (EDA): Perform basic data exploration to understand the dataset's structure and characteristics.
-
Random Forest Classifier: Build a predictive model using the Random Forest Classifier algorithm to predict diseases based on symptoms.
-
User Interaction: Allow users to input their symptoms and use the model to predict potential diseases.
The dataset used in this project contains the following columns:
- Symptoms: Various symptoms represented as Boolean values (0 or 1).
- Diseases: Labels representing different diseases.
The exploratory data analysis (EDA) phase includes examining basic statistics of the dataset and understanding the distribution of symptoms and diseases.
A Random Forest Classifier is employed to create a predictive model. The model is trained on the dataset, and its performance is evaluated using metrics such as F1-score, precision, recall, and accuracy.
To use the Symptom Matcher:
- Load the dataset containing symptoms and disease labels.
- Perform EDA to understand the dataset.
- Train a Random Forest Classifier on the dataset.
- Allow users to input their symptoms.
- Use the trained model to predict potential diseases based on the provided symptoms.
The Symptom Matcher project provides a tool for predicting diseases based on symptoms using a Random Forest Classifier. Users can interact with the model by entering their symptoms to get potential disease predictions