List of usage examples for org.apache.hadoop.fs Path Path
public Path(URI aUri)
From source file:Analysis.A2_Top_20_Most_Popular_Artists.Top_20_Most_Popular_Artist_Driver.java
/** * @param args the command line arguments *///from w w w . jav a 2 s . c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Top 20 most popular artist "); job.setJarByClass(Top_20_Most_Popular_Artist_Driver.class); job.setMapperClass(Top_20_Most_Popular_Artist_Mapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setNumReduceTasks(1); job.setCombinerClass(Top_20_Most_Popular_Artist_Combiner.class); job.setReducerClass(Top_20_Most_Popular_Artist_Reducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A3_Total_Users_By_Gender.User_Gender_Count_Driver.java
/** * @param args the command line arguments *///from w w w. j a v a 2 s. c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Genderwise Demography on Service"); job.setJarByClass(User_Gender_Count_Driver.class); job.setMapperClass(User_Gender_Count_Mapper.class); job.setCombinerClass(User_Gender_Count_Reducer.class); job.setReducerClass(User_Gender_Count_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A4_High_Traffic_Countries.Top_10_Countries_by_User_Traffic_Driver.java
/** * @param args the command line arguments *///w w w . j av a 2 s .c o m public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Top 10 Countries by User Traffic"); job.setJarByClass(Top_10_Countries_by_User_Traffic_Driver.class); job.setMapperClass(Top_10_Countries_by_User_Traffic_Mapper.class); job.setCombinerClass(Top_10_Countries_by_User_Traffic_Combiner.class); job.setReducerClass(Top_10_Countries_by_User_Traffic_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A5_Min_Max_Median_Age_Top_Countries.Min_Max_Age_By_Country_Driver.java
/** * @param args the command line arguments *///from w w w. ja v a2 s .c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Min, Max, Average, Median age of users by country"); job.setJarByClass(Min_Max_Age_By_Country_Driver.class); job.setMapperClass(Min_Max_Age_By_Country_Mapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setReducerClass(Min_Max_Age_By_Country_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setNumReduceTasks(1); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A6_User_Differentiation_By_Age.Partition_Users_By_Age_Driver.java
/** * @param args the command line arguments *//* w ww . j a va 2 s.c o m*/ public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Users by Age"); job.setJarByClass(Partition_Users_By_Age_Driver.class); job.setMapperClass(Partition_Users_By_Age_Mapper.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(Text.class); // partitioner class inclusion job.setPartitionerClass(Partition_Users_By_Age_Partitioner.class); // set multiple formats for custom naming partitioning MultipleOutputs.addNamedOutput(job, "ageBins", TextOutputFormat.class, Text.class, NullWritable.class); MultipleOutputs.setCountersEnabled(job, true); //11-17, 18-25, 26-35, 36-49,50-65,66-80, 81-99 // set num of reduce tasks based on partition we need (here we need 10 cos total no.of countries) job.setNumReduceTasks(8); job.setReducerClass(Partition_Users_By_Age_Reducer.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A7_Total_Signups_By_Year.Total_Signup_by_Year_Driver.java
/** * @param args the command line arguments *///from w ww. jav a2 s. c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Total Signups by Year"); job.setJarByClass(Total_Signup_by_Year_Driver.class); job.setMapperClass(Total_Signup_by_Year_Mapper.class); job.setCombinerClass(Total_Signup_by_Year_Reducer.class); job.setReducerClass(Total_Signup_by_Year_Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A8_Top_10_Most_Popular_Tracks.Top_10_Most_Popular_Tracks_Driver.java
/** * @param args the command line arguments *///from w w w . j av a2 s .c om public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Top 10 most popular tracks "); job.setJarByClass(Top_10_Most_Popular_Tracks_Driver.class); job.setMapperClass(Top_10_Most_Popular_Tracks_Mapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setNumReduceTasks(1); job.setReducerClass(Top_10_Most_Popular_Tracks_Reducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:Analysis.A9_Max_Activity_By_Time_of_Day.Most_Listens_By_Time_of_Day_Driver.java
/** * @param args the command line arguments */// ww w .j a va2s . c o m public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Most listens by Time of the Day"); job.setJarByClass(Most_Listens_By_Time_of_Day_Driver.class); job.setMapperClass(Most_Listens_By_Time_of_Day_Mapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(NullWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); int code = job.waitForCompletion(true) ? 0 : 1; if (code == 0) { for (Counter counter : job.getCounters() .getGroup(Most_Listens_By_Time_of_Day_Mapper.HOUR_COUNTER_GROUP)) { System.out.println(counter.getDisplayName() + "\t" + counter.getValue()); } } FileSystem.get(conf).delete(new Path(args[1]), true); System.exit(code); }
From source file:apex.benchmark.RedisHelper.java
License:Apache License
public void fillDB(String fileName) throws IOException { Path filePath = new Path(fileName); Configuration configuration = new Configuration(); FileSystem fs;//from w ww. j av a2 s . c om fs = FileSystem.newInstance(filePath.toUri(), configuration); FSDataInputStream inputStream = fs.open(filePath); BufferedReader bufferedReader; try { bufferedReader = new BufferedReader(new InputStreamReader(inputStream)); String line; while ((line = bufferedReader.readLine()) != null) { String[] mapping = line.split("\\s+"); if (mapping.length != 2) { continue; } jedis.sadd("campaigns", mapping[0]); jedis.set(mapping[1], mapping[0]); } } catch (Exception e) { throw e; } }
From source file:application.RecommenderEvaluator.java
License:Open Source License
/** * il metodo evaluate prende in ingresso una collezione di item e media e standard error ad esso associato, * una collezione di user che ha come valore una collezione delle medie degli item per i quali ha espresso un voto, * una stringa che contiene il path ad un file di testo (#user,#item,#vote) per effettuare i test. Il metodo fornisce in output la matrice di confusione cosi' formata * nella cella [0][0] ci sara' il numero di volte in cui il voto e' stato positivo e la previsione e' stata positiva (True Positive) * nella cella [0][1] ci sara' il numero di volte in cui il voto e' stato positivo e la previsione e' stata negativa (False Negative) * nella cella [1][0] ci sara' il numero di volte in cui il voto e' stato negativo e la previsione e' stata positiva (False Positive) * nella cella [1][1] ci sara' il numero di volte in cui il voto e' stato negativo e la previsione e' stata negativa (True Negative) * @param Stato_Item e' una collezione di item con media e standard error a ciascuno di esso associato * @param Stato_User e' una collezione di user con valore una collezione delle medie degli item per i quali l'user ha espresso un voto * @param s e' una stringa che contiene il path ad un file di testo per effettuare i test * @return una matrice di confusione con il numero di TruePositive, FalsePositive, FalseNegative, TrueNegative ottenuti. * @throws IOException// w w w . j a va 2s . c o m */ public void evaluate() { String test_file = GLOBALS.getTEST_FILE_NAME(); String split = GLOBALS.getSPLIT_TOKEN(); try { FileSystem fs = FileSystem.get(conf); BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(new Path(test_file)))); String line; while ((line = br.readLine()) != null) { StringTokenizer st = new StringTokenizer(line, split); int user = Integer.parseInt(st.nextToken()); int item = Integer.parseInt(st.nextToken()); int vote = Integer.parseInt(st.nextToken()); UserProfile UP = USER_STATE.get(user); ItemProfile IP = ITEM_STATE.get(item); if (UP == null || IP == null) { skipped_evaluation++; } else { Boolean prediction = estimatePreference(UP, IP); if (prediction == null) { skipped_evaluation++; continue; } // System.out.println("prediction:"+prediction+", vote:"+vote); if (prediction) { if (vote == 1) { CM[0][0] += 1; } //TP else if (vote == -1) { CM[1][0] += 1; } //FP } else { if (vote == -1) { CM[1][1] += 1; } //TN else if (vote == 1) { CM[0][1] += 1; } //FN } } } br.close(); //STAT // System.out.println("TP: "+CM[0][0]); // System.out.println("FN: "+CM[0][1]); // System.out.println("FP: "+CM[1][0]); // System.out.println("TN: "+CM[1][1]); // System.out.println("SKYPPED: "+skipped_evaluation); } catch (Exception e) { System.out.println("Exception " + e); e.printStackTrace(); System.exit(-1); } }