sj.kim
/
siggen
1
1
Fork 0
Code Issues 0 Pull Requests 0 Projects 0 Releases 0 Wiki Activity
156 Commits
1 Branch
3.1 GiB
Tree: 02523ae37d
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '02523ae37d'
${ noResults }
Commit Graph

43 Commits (02523ae37dd67f0f5add1a7664a9f28aebcd0a3a)

Author SHA1 Message Date
  김선중 fd0beb9a56 decided that the creation and modification of the intermediates table 'matching' need not be corrected. 1 year ago
  김선중 333d61a5ac generate_signals.py : introduce self.sim_timespan, add parser (not tested), preprocess_signal.py : fix a specific date. 1 year ago
  김선중 ba087e50a8 preprocess.py and generate_signals.py now works anyway, under either config_name='draft' or 'revised'. But how 'matching' works? and how can I load movement_number for each 5 seconds? Moreover, the codes need cleaning, really. 1 year ago
  김선중 270e202149 revising codes (friday) until process_daily - 1 1 year ago
  김선중 99878f2cdf revising load_table section, but vs code linting is too slow 1 year ago
  김선중 7d0ebd2468 finished making raw tables and initialized 'revise_code.ipynb' 1 year ago
  김선중 31dfa38706 finished testing fetch_tables.ipynb 1 year ago
  김선중 036988f49f something is modified for table definition 1 year ago
  김선중 c253ddd4fb table definition : turn_Type / analysis : green_right_urn_arrow (still working) / network : set all the types of the traffic_light into traffic_light_right_on_red / preprocess_daily : (still working) 1 year ago
  김선중 6970c5b155 last modification 1 year ago
  김선중 97d7aad52f last modificatoins 1 year ago
  김선중 9e97e80d92 In make_match5, simplify the way to calculate cosine similarity. It should be equivalent to the former. 1 year ago
  김선중 601f2f147c modified the uturn-related csv files 1 year ago
  김선중 b44ef17106 modified newly defined tables : for example, angle_new.csv. Confer to table definition v0.8.5 1 year ago
  김선중 d6c11120e6 tested scenarios for all days and all nodes 1 year ago
  김선중 1c3ca4153b tested for new yellow-red code. I'll apply to the generate_signals.py soon 1 year ago
  김선중 2f1825ed46 last modifications 1 year ago
  김선중 a704feb703 unit test completed 1 year ago
  김선중 616b9c6ae4 unit test unsucessfully being done 1 year ago
  김선중 4591cf0e6a explanation 1 year ago
  김선중 3f7a4b01c7 last modifications 1 year ago
  김선중 8d5f71e175 revised generate_signal.py for speed issue 1 year ago
  김선중 428a843557 added a pdf file 1 year ago
  김선중 85e49830ae revised the ppt file again 1 year ago
  김선중 511ba2511e revised the ppt file 1 year ago
  김선중 0a289fe4ea removed unnecessary movements.csv and get_movements. It is duplicated by match1. And finished the unit test for preprocess_daily.py 1 year ago
  김선중 142b9f51dd make generate_signals.py 1 year ago
  김선중 40d1c6824e produces get_intermediates.py 1 year ago
  김선중 39c9428fb5 last modifications 1 year ago
  김선중 56a3b34a19 change the folder structure done right 1 year ago
  김선중 d65e9287e1 je pense que c'est fait, peut-etre 1 year ago
  김선중 e322f13d61 modified logic for missing values and outliers 1 year ago
  김선중 bfe9715c2f last modificatoin 1 year ago
  김선중 1f1d42fbea last modifications 1 year ago
  김선중 26dddda0b4 uturn and coordinated intersections 1 year ago
  김선중 b1b5bf8a9c last modifications 1 year ago
  김선중 8016b79ebc outliers and missing value test completed. history of inter_no=211 where cycle is equivalent to 5 modulo 10 is invalid. 1 year ago
  김선중 d190fe6bbf logic for missing value completed 1 year ago
  김선중 ad520b053a No, 결측이상치처리 should be inside the 이력+이동류. So the order is as before, except that processing of outlier and missing value should be taken place on rhistory, not hrhistory or so. 1 year ago
  김선중 490edf38e1 just made the 0111_preprocess_6.ipynb. version 5 is slightly wrong since '결측이상치처리' should precede '이력 + 이동류'. version 6 is for this change, but not having made any modification yet. 1 year ago
  김선중 7d603b2558 finished 이력+이동류, making new version named 0111_preprocess_5.ipynb 1 year ago
  김선중 b72b6c88bb corrected an error on flow_angle.csv 1 year ago
  김선중 0c2d22a925 thinking almost finished for '2. 이력+이동류' but something is going wrong. need to review from the beginning. 1 year ago