Calories burnt prediction using machine learning with Python

By Abdul Muthallib

using body temperature, heartbeat, time duration we will predict the number of calories burnt with xgboost regressor.

Generally when we do exercise or when we run or walk we will get sweat this sweat comes from the number of calories burnt so that we will be training based on the parameters like time duration, body temparature, heart beat with which our ml model will be predicting the output.

Data set link: - https://www.kaggle.com/datasets/fmendes/fmendesdat263xdemos?resource=download

FIRST WE HAVE TO INCLUDE ALL THE HEADER FILES

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from xgboost import XGBRegressor
from sklearn import metrics

Data preprocessing

calories = pd.read_csv('calories.csv')
calories.head()
exercise_data = pd.read_csv('exercise.csv')

Combing two data frames

calories_data = pd.concat([exercise_data, calories['Calories']], axis=1) 
calories_data.head() 
calories_data.shape 
calories_data.info() 
calories_data.isnull().sum()

 

Data analytics

calories_data.describe()

 data visuvalization

sns.set()
sns.countplot(calories_data['Gender'])
sns.distplot(calories_data['Age'])
sns.distplot(calories_data['Height'])
sns.distplot(calories_data['Weight'])

 

Finding the Correlation in the dataset

correlation = calories_data.corr()
plt.figure(figsize=(10,10))
sns.heatmap(correlation, cbar=True, square=True, fmt='.1f', annot=True, annot_kws={'size':8}, cmap='Blues')

converting the data into text values

calories_data.replace({"Gender":{'male':0,'female':1}}, inplace=True)
calories_data.head()

separating feautures and the target

X = calories_data.drop(columns=['User_ID','Calories'], axis=1)
Y = calories_data['Calories']
print(X)
print(Y)

separating training data set and the testing data set 

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=2)
print(X.shape, X_train.shape, X_test.shape)

model training

model = XGBRegressor()
model.fit(X_train, Y_train)

Evalution of the data & prediction

test_data_prediction = model.predict(X_test)
print(test_data_prediction)
mae = metrics.mean_absolute_error(Y_test, test_data_prediction)
print("Mean Absolute Error = ", mae)