height_prediction_From_age_using_decisiontree

import pandas as pd #to load dataset
import numpy as np #for the array ops
import matplotlib.pyplot as plt  # for visualization 
dataset = pd.read_csv('dataset.csv') # load the dataset
print(dataset.shape) #summarize the dataset
print(dataset.head(71))
# segregationg the dataset
X= dataset.iloc[:,:-1].values
X
Y = dataset.iloc[:,-1].values
Y
# splitting dataset for the training 
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(X,Y,test_size =0.20,random_state=0)
# algorithm --> decision tree
from sklearn.tree import DecisionTreeRegressor
model = DecisionTreeRegressor()
model.fit(x_train,y_train)
#Visualization of graph
X_val = np.arange(min(x_train),max(x_train),0.01)
X_val = X_val.reshape((len(X_val),1))
plt.scatter(x_train,y_train,color = 'blue')
plt.plot(X_val,model.predict(X_val),color= 'red') #datapoint fitting
plt.title('Height classification using DecisionTree')
plt.xlabel('Age (in years')
plt.ylabel('Height (in cm)')
plt.figure()
plt.show()

#prediction & validation
ypred = model.predict(x_test)
from sklearn.metrics import r2_score,mean_squared_error
mse = mean_squared_error(y_test,ypred)
rmse = np.sqrt(mse)
print("Root mean square error :",rmse)
r2score= r2_score(y_test,ypred)
print("R^2 Score:",r2score*100)