fix: program name can be null when margin is not enough (#247)

dataforgoodfr · Sep 26, 2024 · ff9f5bb · ff9f5bb · github-actions · Sep 26, 2024
1 parent 9cd8967
commit ff9f5bb
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/quotaclimat/data_processing/mediatree/channel_program.py b/quotaclimat/data_processing/mediatree/channel_program.py
@@ -3,7 +3,7 @@
 import os
 from datetime import datetime
 import json
-from quotaclimat.data_processing.mediatree.utils import get_epoch_from_datetime, EPOCH__5MIN_MARGIN
+from quotaclimat.data_processing.mediatree.utils import get_epoch_from_datetime, EPOCH__5MIN_MARGIN, EPOCH__1MIN_MARGIN
 
 def format_hour_minute(time: str) -> pd.Timestamp:
     date_str = "1970-01-01"
@@ -81,8 +81,8 @@ def get_day_of_week(time: pd.Timestamp) -> int:
 def get_matching_program_hour(df_program: pd.DataFrame, start_time: pd.Timestamp):
     start_time = get_hour_minute(start_time)
     matching_rows = df_program[
-                         (df_program['start'] <= (start_time + pd.Timedelta(seconds=EPOCH__5MIN_MARGIN))) &
-                         (df_program['end'] > (start_time - pd.Timedelta(seconds=EPOCH__5MIN_MARGIN))) # stricly > to avoid overlapping programs
+                         (df_program['start'] <= (start_time + pd.Timedelta(seconds=EPOCH__5MIN_MARGIN + EPOCH__1MIN_MARGIN))) &
+                         (df_program['end'] > (start_time - pd.Timedelta(seconds=EPOCH__5MIN_MARGIN + EPOCH__1MIN_MARGIN)))
                     ]
     if(len(matching_rows) > 1): # no margin necessary because programs are next to each others
         return df_program[

diff --git a/quotaclimat/data_processing/mediatree/utils.py b/quotaclimat/data_processing/mediatree/utils.py
@@ -9,6 +9,7 @@
 
 timezone='Europe/Paris'
 EPOCH__5MIN_MARGIN = 300
+EPOCH__1MIN_MARGIN = 60 # to add margin for program
 
 def get_keyword_time_separation_ms(duration_seconds: int = 15):
     return duration_seconds * 1000
File	Stmts	Miss	Cover	Missing
postgres
insert_data.py	43	7	84%	36–38, 56–58, 63
insert_existing_data_example.py	19	3	84%	25–27
postgres/schemas
models.py	150	10	93%	124–131, 143–144, 202–203, 217–218
quotaclimat/data_ingestion
scrap_sitemap.py	134	17	87%	27–28, 33–34, 66–71, 95–97, 138–140, 202, 223–228
quotaclimat/data_ingestion/ingest_db
ingest_sitemap_in_db.py	55	37	33%	21–42, 45–58, 62–73
quotaclimat/data_ingestion/scrap_html
scrap_description_article.py	36	3	92%	19–20, 32
quotaclimat/data_processing/mediatree
api_import.py	214	135	37%	44–48, 53–72, 76–79, 85, 88–130, 136–151, 156, 169–181, 185–191, 204–216, 219–223, 229, 265–266, 269–305, 308–310
channel_program.py	162	58	64%	28–30, 41–43, 60–61, 64–66, 100, 112, 117–119, 164–205
config.py	15	2	87%	7, 16
detect_keywords.py	209	8	96%	220, 278–285
update_pg_keywords.py	62	45	27%	14–107, 130, 137–141, 164–190, 197
utils.py	71	22	69%	29–53, 56, 65, 86–87
quotaclimat/utils
healthcheck_config.py	29	14	52%	22–24, 27–38
logger.py	24	11	54%	22–24, 28–37
sentry.py	11	2	82%	22–23
TOTAL	1260	374	70%