I want to use mahout with hive, i will get data from hive and use data model some thing like to populate data and use mahout for recommendation. is this possible. because i have seen mahout is working only for files. 1) how to load data to mahout using hive table? 2) is there any other way i can use mahout recommendation with hive or others?
here i am having hive jdbc result, i want to populate to DataModel in mahout. how to populate?
i want to use database result instead of reading from file for mahout recommendation. for example :
hive:
import java.sql.SQLException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;
import java.sql.DriverManager;
public class HiveJdbcClient {
private static String driverName = "org.apache.hive.jdbc.HiveDriver";
/**
* @param args
* @throws SQLException
*/
public static void main(String[] args) throws SQLException {
try {
Class.forName(driverName);
} catch (ClassNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
System.exit(1);
}
//replace "hive" here with the name of the user the queries should run as
Connection con = DriverManager.getConnection("jdbc:hive2://localhost:10000/default", "hive", "");
Statement stmt = con.createStatement();
String tableName = "testHiveDriverTable";
stmt.execute("drop table if exists " + tableName);
stmt.execute("create table " + tableName + " (key int, value string)");
// show tables
String sql = "show tables '" + tableName + "'";
System.out.println("Running: " + sql);
ResultSet res = stmt.executeQuery(sql);
if (res.next()) {
System.out.println(res.getString(1));
}
// describe table
sql = "describe " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(res.getString(1) + "\t" + res.getString(2));
}
// load data into table
// NOTE: filepath has to be local to the hive server
// NOTE: /tmp/a.txt is a ctrl-A separated file with two fields per line
String filepath = "/tmp/a.txt";
sql = "load data local inpath '" + filepath + "' into table " + tableName;
System.out.println("Running: " + sql);
stmt.execute(sql);
// select * query
sql = "select * from " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(String.valueOf(res.getInt(1)) + "\t" + res.getString(2));
}
// regular hive query
sql = "select count(1) from " + tableName;
System.out.println("Running: " + sql);
res = stmt.executeQuery(sql);
while (res.next()) {
System.out.println(res.getString(1));
}
}
}
mahout:
// Create a data source from the CSV file
File userPreferencesFile = new File("data/dataset1.csv");
DataModel dataModel = new FileDataModel(userPreferencesFile);
UserSimilarity userSimilarity = new PearsonCorrelationSimilarity(dataModel);
UserNeighborhood userNeighborhood = new NearestNUserNeighborhood(2, userSimilarity, dataModel);
// Create a generic user based recommender with the dataModel, the userNeighborhood and the userSimilarity
Recommender genericRecommender = new GenericUserBasedRecommender(dataModel, userNeighborhood, userSimilarity);
// Recommend 5 items for each user
for (LongPrimitiveIterator iterator = dataModel.getUserIDs(); iterator.hasNext();)
{
long userId = iterator.nextLong();
// Generate a list of 5 recommendations for the user
List<RecommendedItem> itemRecommendations = genericRecommender.recommend(userId, 5);
System.out.format("User Id: %d%n", userId);
if (itemRecommendations.isEmpty())
{`enter code here
System.out.println("No recommendations for this user.");
}
else
{
// Display the list of recommendations
for (RecommendedItem recommendedItem : itemRecommendations)
{
System.out.format("Recommened Item Id %d. Strength of the preference: %f%n", recommendedItem.getItemID(), recommendedItem.getValue());
}
}
}
