prateekagr21 / Gender-Classification-with-BMI

Analysis and Classification of gender with the help of Body Mass Index using some Machine Learning Algorithms.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Gender Classification with BMI

Analysis and Classification of Gender with Body Mass Index using Machine Learning Algorithms :

hw3

The reported Height and weight-related behaviours and weight misperception were associated with depressive symptoms, and among girls, this relationship was becoming even stronger over the three decades examined in this study. The findings could possibly be part of the explanation for increases in adolescent depressive symptoms that have been observed in recent decades.

Children under two years of age can move up and down centiles as they do what is called catch-up or catch-down growth to reach their genetically determined growth centile. Around 80% of height is down to genetics. To estimate a child's predicted final height, your doctor would take the mid-parental height.
For boys, that is the father's height in centimetres plus (the mother's height plus 14) divided by two, and for girls it is (the father's height minus 14) plus the mother's height divided by two. If a child's projected height lies within 5cm of this range and their rate of growth is normal, then they will be as tall as you would expect from their genetics.

An increase in dieting among young people is concerning because experimental studies have found that dieting is generally ineffective in the long term at reducing body weight in adolescents, but can instead have greater impacts on mental health. We know, for instance, that dieting is a strong risk factor in the development of eating disorders.

One reason diets don't work is because they can encourage people to think of foods as "good" or "bad," when the truth is everything is OK in moderation. Diets also encourage people to "give up" certain foods, which can make us feel more deprived. And not only do we feel deprived, diets often deplete our bodies of important nutrients. Teens should eat a variety of foods, and there's nothing wrong with the occasional treat. A candy bar somehow tastes more special if we treat ourselves once in a while instead of every day.

The best way to stay at a healthy weight (or lose weight if you need to) is to make healthy food choices daily. For some of us, that means changing our mindset about food. Instead of thinking of food emotionally (for example, as a reward for doing well on a test or as a way to deal with stress), see it for what it is — a practical way to fuel our bodies.

hw4

For Solving this Usecase, What I have done is :

  • Collected the data and organized it to form a meaningful dataset.
  • Checked for null values and took care of it.
  • Observed the data to form meaningful insights!

  • Did Exploratory Data Analysis on the dataset.
  • Used correlations to form a heatmap.
  • Visualizations were made by using Matplotlib and Seaborn Libraries..!!

Did Data Pre-Processing :

  • Made Binary Classifications Using Label Encoder
    to fit and transform Numerical and Categorical Column values.

And then I made my model for the Prediction :

  • Independent and Dependent Features.
  • Did Train-Test split

Trained my Model using :

Random Forest Classifier

  • Predicted for the data
  • Finded Accuracy score
  • used cross validation
  • Plotted Confusion Matrix
  • And at last, Classification report.
  • And Analyzed the key factors responsible for prediction.

Using K Nearest Neighbors Classifier

  • Predicted for the data
  • Finded Accuracy score
  • used cross validation
  • Plotted Confusion Matrix
  • And at last, Classification report.

hw2

And for the conclusion -

From the above two trained Models, It can be seen that
With the Accuracy of around 92%,
the KNN model performed slightly better than the Random Forest Classifier model.

About

Analysis and Classification of gender with the help of Body Mass Index using some Machine Learning Algorithms.


Languages

Language:Jupyter Notebook 100.0%