Added codes, datasets and Jupyter notebooks directory.

2025-06-11 13:48:53 +05:30
parent b3a22e9b79
commit 76dc1de8db
32 changed files with 8930 additions and 0 deletions
@@ -0,0 +1,72 @@
+import java.io.IOException;
+import java.util.StringTokenizer;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.Text;
+
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.Mapper;
+import org.apache.hadoop.mapreduce.Reducer;
+
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+
+public class WordCount {
+
+    // Mapper Class
+    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
+        private final static IntWritable one = new IntWritable(1);
+        private Text word = new Text();
+
+        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
+            StringTokenizer itr = new StringTokenizer(value.toString());
+            while (itr.hasMoreTokens()) {
+                word.set(itr.nextToken().toLowerCase().replaceAll("[^a-zA-Z0-9]", ""));
+                if (!word.toString().isEmpty()) {
+                    context.write(word, one);
+                }
+            }
+        }
+    }
+
+    // Reducer Class
+    public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
+        private IntWritable result = new IntWritable();
+
+        public void reduce(Text key, Iterable<IntWritable> values, Context context)
+                throws IOException, InterruptedException {
+            int sum = 0;
+            for (IntWritable val : values) {
+                sum += val.get();
+            }
+            result.set(sum);
+            context.write(key, result);
+        }
+    }
+
+
+    public static void main(String[] args) throws Exception {
+        if (args.length != 2) {
+            System.err.println("Usage: WordCount <input path> <output path>");
+            System.exit(-1);
+        }
+
+        Configuration conf = new Configuration();
+        Job job = Job.getInstance(conf, "word count");
+
+        job.setJarByClass(WordCount.class);
+        job.setMapperClass(TokenizerMapper.class);
+        job.setCombinerClass(IntSumReducer.class); // optional
+        job.setReducerClass(IntSumReducer.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);
+    }
+}