shashwatwork

        apiInterface=ApiClient.getApiClient().create(ApiInterface.class);
        Call<Pojo> call = apiInterface.getAPIResponse(vizdata);
        call.enqueue(new Callback<Pojo>() {
            @Override
            public void onResponse(@NonNull Call<Pojo> call, @NonNull Response<Pojo> response) {
                Pojo pojo=response.body();
                AlertDialog alertDialog = new AlertDialog.Builder(MainActivity.this).create();
                alertDialog.setTitle("Heart Prediction");
                alertDialog.setMessage("Predicted Result is "+pojo.getIsHeart());
                alertDialog.setButton(AlertDialog.BUTTON_NEUTRAL, "OK",

shashwatwork

package com.infinitemakerz.heartdiseaseprediction;

import com.google.gson.annotations.SerializedName;

public class Pojo {
    @SerializedName("isHeart")
    private String isHeart;
    @SerializedName("CHECK")
    private String CHECK;

shashwatwork

package com.infinitemakerz.heartdiseaseprediction;

import java.util.List;

import retrofit2.Call;
import retrofit2.http.GET;
import retrofit2.http.Query;

public interface ApiInterface
{

shashwatwork

package com.infinitemakerz.heartdiseaseprediction;


import retrofit2.Retrofit;
import retrofit2.converter.gson.GsonConverterFactory;
public class ApiClient
{
    private static final String BASE_URL="https://heart-prediction.herokuapp.com";
    private static Retrofit retrofit;
    public static Retrofit getApiClient()

shashwatwork

Retrofit retrofit = new Retrofit.Builder()
.baseUrl(“https://api.github.com/")
.build();
Demo service = retrofit.create(Demo.class);
Call<List<Movie>> movie = service.listMovie(“Gino Osahon”);

shashwatwork

public interface Demo {
@GET("users/{user}/repos")
Call<List<Movie>> listMovie(@Path("user") String user);
@GET("group/{id}/users")
Call<List<User>> groupList(@Path("id") int groupId);
}
// Query parameters can also be added to a method.
@GET(“group/{id}/users”)
Call<List<User>> groupList(@Path(“id”) int groupId, @Query(“sort”) String sort);

shashwatwork

recomendations = model.transform(single_user)
recomendations.orderBy('prediction',ascending=False).show()

shashwatwork

single_user = test.filter(test['userId']==11).select(['movieId','userId'])
# User had 10 ratings in the test data set 
# Realistically this should be some sort of hold out set!
single_user.show()

shashwatwork

from pyspark.ml.evaluation import RegressionEvaluator
evaluator = RegressionEvaluator(metricName="rmse", labelCol="rating",predictionCol="prediction")
rmse = evaluator.evaluate(predictions)
print("Root-mean-square error = " + str(rmse))

shashwatwork

predictions = model.transform(test)
predictions.show()