data_rangers_iit_dharwad_ai_cure_experiment.py

# -*- coding: utf-8 -*-
"""Data Rangers_IIT Dharwad AI Cure_Experiment

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1AlD5Vcep054MiUWVJaZi4KH6eSpV-Qci
"""

# Import libraries
import pandas as pd
import numpy as np

# Load files
train = pd.read_csv("./train_data.csv")
test = pd.read_csv("./sample_test_data.csv")
Sample_Output = pd.read_csv("./sample_output_generated.csv")

train

test

Sample_Output

train.drop(['uuid'], axis=1, inplace=True)
test.drop(['uuid'], axis=1, inplace=True)

from sklearn.preprocessing import LabelEncoder
label_encoder = LabelEncoder()

train['condition'] = label_encoder.fit_transform(train['condition'])
test['condition'] = label_encoder.transform(test['condition'])

columns = train.columns
columns =  [col for col in columns if col not in ['HR']]
features = columns
target = 'HR'

X = train[columns]
y = train[target]

from sklearn.model_selection import train_test_split
X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.1, random_state=40)

import lightgbm as lgb
import xgboost as xgb
model = lgb.LGBMRegressor()
model.fit(X, y)

y_pred_val =model.predict(test)

import sklearn.metrics
mse = sklearn.metrics.mean_squared_error(Sample_Output['HR'], y_pred_val)
import math
rmse = math.sqrt(mse)
print("The difference between actual and predicted values(MSE)", mse)
print("The difference between actual and predicted values(RMSE)", rmse)

test.to_csv("./result.csv",index=False)