Kyran Adams (Work Log) - Revision history

Kyranstar: /* Spring 2018 */

2018-05-18T20:47:45Z

Spring 2018

2018-05-17T03:06:30Z

Spring 2018

2018-05-17T02:36:23Z

Spring 2018

2018-05-17T01:55:21Z

Spring 2018

2018-05-13T01:02:27Z

Spring 2018

2018-05-11T05:55:41Z

Spring 2018

2018-05-06T23:30:11Z

Spring 2018

2018-05-06T22:54:48Z

Spring 2018

2018-05-05T05:33:53Z

Spring 2018

2018-05-05T05:25:31Z

Spring 2018

@@ Line 2: / Line 2: @@
 <onlyinclude>
 [[Kyran Adams]] [[Work Logs]] [[Kyran Adams (Work Log)|(log page)]]
 -05-16: Wrote a script (classify_all_accelerator.py) to pull all of the unclassified accelerators from the master variable list (if they are not already in the Cohort List page), and then classify them. This works best if the creation years are provided in the Master Variable List. Started the run on the whole dataset. This will definitely pull up a lot of duplicate results, so it might be valuable to run a program at the end to remove duplicates.

@@ Line 3: / Line 3: @@
 [[Kyran Adams]] [[Work Logs]] [[Kyran Adams (Work Log)|(log page)]]
--05-16: Wrote a script to pull all of the unclassified accelerators from the master variable list (if they are not already in the Cohort List page), and then classify them. This works best if the creation years are provided in the Master Variable List. Started the run on the whole dataset. This will definitely pull up a lot of duplicate results, so we might need to run a program at the end to remove duplicates.
+-05-16: Wrote a script (classify_all_accelerator.py) to pull all of the unclassified accelerators from the master variable list (if they are not already in the Cohort List page), and then classify them. This works best if the creation years are provided in the Master Variable List. Started the run on the whole dataset. This will definitely pull up a lot of duplicate results, so it might be valuable to run a program at the end to remove duplicates.
 -05-11/12: Ran on data, predicted html files are saved in positive directory. Also determined that the model extremely overfits, more data is probably the only fix.

@@ Line 3: / Line 3: @@
 [[Kyran Adams]] [[Work Logs]] [[Kyran Adams (Work Log)|(log page)]]
--05-16: Wrote a script to pull all of the unclassified accelerators from the master variable list (if they are not already in the Cohort List page), and then classify them. This works best if the creation years are provided in the Master Variable List.
+-05-16: Wrote a script to pull all of the unclassified accelerators from the master variable list (if they are not already in the Cohort List page), and then classify them. This works best if the creation years are provided in the Master Variable List. Started the run on the whole dataset. This will definitely pull up a lot of duplicate results, so we might need to run a program at the end to remove duplicates.
 -05-11/12: Ran on data, predicted html files are saved in positive directory. Also determined that the model extremely overfits, more data is probably the only fix.

@@ Line 2: / Line 2: @@
 <onlyinclude>
 [[Kyran Adams]] [[Work Logs]] [[Kyran Adams (Work Log)|(log page)]]
 -05-11/12: Ran on data, predicted html files are saved in positive directory. Also determined that the model extremely overfits, more data is probably the only fix.

@@ Line 2: / Line 2: @@
 <onlyinclude>
 [[Kyran Adams]] [[Work Logs]] [[Kyran Adams (Work Log)|(log page)]]
 -05-06: Changed crawl_and_classify so that the html pages are separated based on what they are predicted to be. Added support for individual year searching. Started running on actual data. Tuned hyperparameters too, should save to params.txt.

@@ Line 3: / Line 3: @@
 [[Kyran Adams]] [[Work Logs]] [[Kyran Adams (Work Log)|(log page)]]
--05-04: Same. Also cleaned up directory, wiki, and changed crawl_and_classify so that the html pages are separated based on what they are predicted to be. Model now achieves 0.80 (+/- 0.15) accuracy.
+-05-06: Changed crawl_and_classify so that the html pages are separated based on what they are predicted to be. Started running on actual data.
 -05-03: Played around with different features and increased dataset.