add demo link

Author: qiaoliuhub

README.md

@@ -1,6 +1,8 @@
 # Autotagging Overflow
 The objective of this pipeline is to enable autotagging of stack overflow questions and answers. The model will be trained with TF-IDF with Spark MLlib in batch processing. Then the model would be used to autotag the new coming questions from Kafka (latency?). Finally the data will be persisted in Cassandra to support the front end.
 
+<a href = https://youtu.be/WYg8NzZs4Us > DEMO </a>
+
 # Sample datasets
 
 <p align="center">

autotagOverflow/index.js

@@ -83,27 +83,27 @@ app.get('/home/:post_id', function(req, res){
 var post_id = req.params.post_id;
 var tag;
  console.log('Retriving data for post_id %s', post_id);
-// cassandraClient.execute("SELECT tag FROM "+table +" WHERE id = '" + post_id + "'", function(err, result){
-// if (!err){
-// if ( result.rows.length > 0 ) {
- //  var user = result.rows[0];
- //  var tag=user.tag;
- //  res.send({tag: tag});
- //  } else {
- //  console.log("No results");
- //  }
-// }
-// });
- redis_client.hmget(post_id, 'tags', function(err, result){
- if (!err){
- if ( result.length > 0 ) {
- var tag = result[0];
- res.send({tag: tag});
- } else {
- console.log("No results");
- }
- }
- });
+cassandraClient.execute("SELECT tag FROM "+table +" WHERE id = '" + post_id + "'", function(err, result){
+if (!err){
+if ( result.rows.length > 0 ) {
+ var user = result.rows[0];
+ var tag=user.tag;
+ res.send({tag: tag});
+ } else {
+ console.log("No results");
+ }
+}
+});
+ // redis_client.hmget(post_id, 'tags', function(err, result){
+ //  if (!err){
+ //  if ( result.length > 0 ) {
+ //  var tag = result[0];
+ //  res.send({tag: tag});
+ //  } else {
+ //  console.log("No results");
+ //  }
+ //  }
+ // });
 })
 
 app.post('/home', function(req, res){

autotagOverflow/public/js/get_tag.js

@@ -10,7 +10,7 @@ $(function(){
  success:function(data,status){
  if(status == 'success'){
  var after_time = new Date().getTime();
- alert((after_time - start_time) + 'ms')
+ // alert('It takes '+(after_time - start_time) + 'ms to get the tag!')
  var tag = data.tag;
  $('#predicted_tag').text(tag);
  $('#predicted_tag').val(tag);

kafka_producer.py

@@ -100,7 +100,7 @@ def generate_data():
 while True:
 for line in posts:
 send_to_broker(kafka_producer, line,)
-time.sleep(5)
+time.sleep(2)
 
 if __name__ == '__main__':