using your age and duration of workout finding how much calories you burned!

dataset: https://www.kaggle.com/fmendes/fmendesdat263xdemos/download

.........................................................................................................................................................

import pandas as  pd

import matplotlib.pyplot as plt

import numpy as np

import pickle 

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LinearRegression

df_calories=pd.read_csv("ineuron/calories.csv")

df_exercise=pd.read_csv("ineuron/exercise.csv")

data=df_exercise.merge(df_calories, on='User_ID')

#print(data.head())

#[:,0:-1] all rows and all expect last column (independent  variable) also feature column

#data_x = data.iloc[:,:-1].values

data_x= df.loc[:,[ 'Weight','Age','Duration']]

data_y=df.iloc[:,-1]

#[:,-1]all rows and only last column (dependent variable) also target column

#data_y = data.iloc[:,-1].values

x_train,x_test,y_train,y_test = train_test_split(data_x,data_y,test_size=0.3, random_state=0)

reg = LinearRegression()

reg.fit(x_train,y_train)

print("train_score=" ,reg.score(x_train,y_train))

print("train_score=" ,reg.score(x_test,y_test))

''''

pickle.dump(reg,open("taxi.pkl",'wb'))

model=pickle.load(open('taxi.pkl','rb'))

print(model.predict([[60,20,14]]))

'''

print(reg.predict([[60,20,14]]))

%matplotlib inline

plt.xlabel("Age")

plt.ylabel("Calories")

plt.scatter(df['Duration'],df["Calories"],cmap= None, marker="+")

.....................................................................................................................................................

soon i ll be deploying the whole project on heroku.

 stay tuned and be focused