3. AGENDA
TO PREDICT THE MENTAL FITNESS ON THE BASIS OF ‘SCHIZOPHRENIA', ‘BIPOLAR
DISORDER', ‘EATING DISORDER',’ANXIETY’,’DRUG USAGE’,’DEPRESSION’,’ALCHOHOL’
USING MACHINE LEARNING REGRESSION MODEL.
4. PROJECT OVERVIEW
Mental health includes our emotional, psychological, and social well-being. It affects how we think, feel, and
act. It also helps determine how we handle stress, relate to others, and make healthy choices.
Mental health is important at every stage of life, from childhood and adolescence through adulthood.
Here, In this project the Individual's well being Is being predicted by using the past data.
By, knowing one’s daily routines and life style and by choosing the right paramenters and comparing It against
the past data can help us predict the
5. WHO ARE THE END USERS OF THIS PROJECT?
The, End users can be Hospitals and other medical centres who wants to predict the mental well being of an
Individual.
Might be developers who wants to Integrate this Machine Learning model In their project If needed.
This ML model might also be used by researchers etc.
6. YOUR SOLUTION AND ITS VALUE PROPOSITION
As, the output of the dataset Is a numerical value.Regression, models can be used to Implement such tasks.
I used, a Random Forest Regressor provided by SK LEARN which fits perfectly with our problem statement.
Only, the Input columns which add sense to our data has been chosen to train our model.
As, a regression model Is good at dealing with the numerical values. The, regressor predicts the Index of
mental fitness of the patient.
7. HOW DID YOU CUSTOMIZE THE PROJECT AND MAKE IT YOUR OWN
This, entire project has been Implemented from scratch.
The datasets were downloaded from the Internet.
Pandas was used to read and preprocess the data and the library seaborn was used to find the correlation
between the different parameters.
The, Values has been scaled using Standard Scaler provided by SK Learn.
And Train Test Split was used to obtain Train and Test datasets.
The, Random Forest Regressor provided by the SK Learn tool kit was used to Implement the ML Algorithm.
And the training has been fit to the ML Model.
Finally the test data set were used to make predictions. And the Mean Squared Error was used as the Metrics to
evaluate the performance.
8. MODELLING
Random forest regression is a supervised learning algorithm that uses ensemble learning to create a more
accurate and robust regression model than a single decision tree. It does this by training multiple decision
trees on different subsets of the data and then averaging the predictions of the trees to get the final prediction.
• Bootstrapping: This is the process of randomly sampling the data with replacement. This means that some
data points may be sampled multiple times, while others may not be sampled at all.
• Random feature selection: This is the process of randomly selecting a subset of features to consider when
making a split at each node in the decision tree.
Here, In this Project SK Learn’s Random Forest Regressor ML Model Instance was used to solve the
problem.
9. RESULTS
Here, Mean Squared Error was used as a metric to measure the
error function of the ML Model and Our Model did pretty well.
Here, In the plot shown predicted values were plotted against
the real value.