https://github.com/sadmansakib93/mental-resilience-analysis-using-machine-learning
Utilized supervised and unsupervised ML techniques to analyze mental health and resilience levels of medical students [Project completed on December, 2019]
https://github.com/sadmansakib93/mental-resilience-analysis-using-machine-learning
artificial-intelligence classification clustering correlation linear-regression machine-learning machine-learning-algorithms mental-health python regression resilience scikit-learn statistical-analysis
Last synced: 7 months ago
JSON representation
Utilized supervised and unsupervised ML techniques to analyze mental health and resilience levels of medical students [Project completed on December, 2019]
- Host: GitHub
- URL: https://github.com/sadmansakib93/mental-resilience-analysis-using-machine-learning
- Owner: SadmanSakib93
- Created: 2021-06-16T21:35:22.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-06-16T21:45:47.000Z (over 4 years ago)
- Last Synced: 2025-01-12T01:22:24.250Z (9 months ago)
- Topics: artificial-intelligence, classification, clustering, correlation, linear-regression, machine-learning, machine-learning-algorithms, mental-health, python, regression, resilience, scikit-learn, statistical-analysis
- Language: Jupyter Notebook
- Homepage:
- Size: 2.61 MB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Machine Learning (ML)-based and Statistical Analysis Mental Resilience of Students
# Descriptions of each python file:
• Regression & Correlation folder contains python code for finding out correlations and regression results.
• Outputs folder contains results of different programs generate.
• ageBinning.py: This code was used for making age categorical using binning.
• ClusteringResilienceK_1_10.py: This program uses find cluster on resilience score (cluster 2 to 10)
• ClusteringResilienceK_Fixed_GenerateLevels.py: This program generates resilience levels based on input value and save two csv files.
• CrossValidation.py: For classification of 6 classes with SMOTE.
• featureImportance_Correlation.py: Find the feature importance and correlation saves in CSV file in outputs folder.
• FindCorrelHeatmap.ipynb: This file should be run in Jupyter Notebook to find the correlation heatmap.
• hypterparameterTuning.py: This program generates the hyper-parameter tuning results on validation set and test set also. Generates the bar charts of hyper-parameter tuning results.
• oneHotEncoding.py: Performs one hot encoding on categorical variables. This code was used to encode the categorical variables having more than 2 possible values.
# File Names for different variations of our dataset: (Change the file names in the code to generate different results)
• 2 Class (Age categorized) file name = datasetOneHotEncoded_AgeCategorized_2.csv
• 2 Class (Age numeric) file name = datasetOneHotEncoded_AgeNumeric_2.csv
• 3 Class (Age categorized) file name = datasetOneHotEncoded_AgeCategorized_3.csv
• 3 Class (Age numeric) file name = datasetOneHotEncoded_AgeNumeric_3.csv
• Raw dataset = dataset.csv
• 6 Class (Age categorized) file name = datasetOneHotEncoded_AgeCategorized.csv
• 6 Class (Age numeric) file name = datasetOneHotEncoded_AgeNumeric.csv