Skip to content

Commit cc48b60

Browse files
author
adamp
committed
aktualizace todo
1 parent b16ba19 commit cc48b60

File tree

3 files changed

+38
-14
lines changed

3 files changed

+38
-14
lines changed

kod/preprocessing.py

Lines changed: 14 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -1217,24 +1217,24 @@ def split_measurements(mereni_dir, prohlidky_dir, diesel_dir, verbosity):
12171217
STATIONS_SUBDIR = 'stanice'
12181218

12191219

1220-
explain_verbosity(VERBOSITY)
1220+
# explain_verbosity(VERBOSITY)
12211221

1222-
print('——————————————————————————————————PROHLÍDKY VOZIDEL STK A SME:——————————————————————————————————\n')
1223-
downloaded_inspection_dates = downloaded_dates([INSPECTIONS_DIR / 'gz', INSPECTIONS_DIR / 'xml', INSPECTIONS_DIR / 'parquet' / INSPECTIONS_SUBDIR])
1224-
download_files(SPARQL_ENDPOINT, INSPECTIONS_DIR / 'gz', PARENT_DATASET_INSPECTIONS, START_DATE, END_DATE, downloaded_inspection_dates, NO_DOWNLOAD_THREADS, MAX_DOWNLOAD_ATTEMPTS, verbosity=VERBOSITY)
1225-
extract_files(INSPECTIONS_DIR / 'gz', INSPECTIONS_DIR / 'xml', NO_EXTRACT_THREADS, verbosity=VERBOSITY)
1226-
parse_inspections_to_parquet(INSPECTIONS_DIR, INSPECTIONS_SUBDIR, DEFECTS_SUBDIR, ACTIONS_SUBDIR, ADR_TYPE_SUBDIR, NO_PARSE_PROCESSES, VERBOSITY, False)
1222+
# print('——————————————————————————————————PROHLÍDKY VOZIDEL STK A SME:——————————————————————————————————\n')
1223+
# downloaded_inspection_dates = downloaded_dates([INSPECTIONS_DIR / 'gz', INSPECTIONS_DIR / 'xml', INSPECTIONS_DIR / 'parquet' / INSPECTIONS_SUBDIR])
1224+
# download_files(SPARQL_ENDPOINT, INSPECTIONS_DIR / 'gz', PARENT_DATASET_INSPECTIONS, START_DATE, END_DATE, downloaded_inspection_dates, NO_DOWNLOAD_THREADS, MAX_DOWNLOAD_ATTEMPTS, verbosity=VERBOSITY)
1225+
# extract_files(INSPECTIONS_DIR / 'gz', INSPECTIONS_DIR / 'xml', NO_EXTRACT_THREADS, verbosity=VERBOSITY)
1226+
# parse_inspections_to_parquet(INSPECTIONS_DIR, INSPECTIONS_SUBDIR, DEFECTS_SUBDIR, ACTIONS_SUBDIR, ADR_TYPE_SUBDIR, NO_PARSE_PROCESSES, VERBOSITY, False)
12271227

12281228
print('\n————————————————————————————————DATA Z MĚŘÍCÍCH PŘÍSTROJŮ:————————————————————————————————————\n')
12291229
downloaded_measurement_dates = downloaded_dates([MEASUREMENTS_DIR / 'gz', MEASUREMENTS_DIR / 'xml', MEASUREMENTS_DIR / 'parquet' / MEASUREMENTS_ALL_SUBDIR])
12301230
download_files(SPARQL_ENDPOINT, MEASUREMENTS_DIR / 'gz', PARENT_DATASET_MEASUREMENTS, START_DATE, END_DATE, downloaded_measurement_dates, NO_DOWNLOAD_THREADS, MAX_DOWNLOAD_ATTEMPTS, verbosity=VERBOSITY)
12311231
extract_files(MEASUREMENTS_DIR / 'gz', MEASUREMENTS_DIR / 'xml', NO_EXTRACT_THREADS, verbosity=VERBOSITY)
1232-
parse_measurements_to_parquet(MEASUREMENTS_DIR, MEASUREMENTS_ALL_SUBDIR, NO_PARSE_PROCESSES, VERBOSITY, False)
1233-
split_measurements(MEASUREMENTS_DIR / 'parquet' / MEASUREMENTS_ALL_SUBDIR, INSPECTIONS_DIR / 'parquet' / INSPECTIONS_SUBDIR, MEASUREMENTS_DIR / 'parquet' / DIESEL_SUBDIR, VERBOSITY)
1232+
# parse_measurements_to_parquet(MEASUREMENTS_DIR, MEASUREMENTS_ALL_SUBDIR, NO_PARSE_PROCESSES, VERBOSITY, False)
1233+
# split_measurements(MEASUREMENTS_DIR / 'parquet' / MEASUREMENTS_ALL_SUBDIR, INSPECTIONS_DIR / 'parquet' / INSPECTIONS_SUBDIR, MEASUREMENTS_DIR / 'parquet' / DIESEL_SUBDIR, VERBOSITY)
12341234

1235-
print('—————————————————————————————————Stanice STK a SME:—————————————————————————————————————————————\n')
1236-
# Seznam stanic prochází denní aktualizací
1237-
clear_folder(STATIONS_DIR, VERBOSITY)
1238-
download_stations(SPARQL_ENDPOINT, STATIONS_DIR / 'gz', DATASET_STATIONS, VERBOSITY)
1239-
extract_files(STATIONS_DIR / 'gz', STATIONS_DIR / 'xml', 1, verbosity=VERBOSITY)
1240-
parse_stations_to_parquet(STATIONS_DIR, STATIONS_SUBDIR, VERBOSITY, delete=False)
1235+
# print('—————————————————————————————————Stanice STK a SME:—————————————————————————————————————————————\n')
1236+
# # Seznam stanic prochází denní aktualizací
1237+
# clear_folder(STATIONS_DIR, VERBOSITY)
1238+
# download_stations(SPARQL_ENDPOINT, STATIONS_DIR / 'gz', DATASET_STATIONS, VERBOSITY)
1239+
# extract_files(STATIONS_DIR / 'gz', STATIONS_DIR / 'xml', 1, verbosity=VERBOSITY)
1240+
# parse_stations_to_parquet(STATIONS_DIR, STATIONS_SUBDIR, VERBOSITY, delete=False)

poznamky/TODO

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,12 @@ feature engineering - delka misto konce - zacatek zda svatek, rocni obdobi, cas
1212
; lepe oddelit uzitkova vozidla - hodne traktoru
1313
sjednotit jazyk pro pojmenovani souboru a promennych
1414
pripojit prohlidky mereni, ktera maji oddelenou prohlidku
15+
pridat wwh-obd
16+
odstranit prebytecne zkratky a doplnit zkratky, ktere chybi
17+
xml, zip, xsd, lpg, cng, nm, ba, adr, orp, adr, tsk
18+
prepsat, kdy co bylo citovano
19+
citace 20 % z nemecka primarni zdroj
20+
1521

1622
TODO MOZNA
1723
neosobni vozidla
@@ -30,6 +36,12 @@ dlouhe doby akcelerace, kdy vozidlo proslo
3036
pruchodnost na stanicich
3137
dukazy emulatoru shodnymi hodnotami akceleraci
3238

39+
uspesnost prohlidky x delka akceleraci
40+
technici kteri akceleruji pomalu
41+
lze nekde najit detailni protokoly
42+
dopocotat lambdu
43+
vuce nez 100 procemt kysliku
44+
3345

3446

3547

@@ -93,5 +105,13 @@ analyzovat vsechny stanice nebo pouze nezanikle
93105
zahodit extremni hodnoty, nebo je nahradit null
94106

95107

108+
109+
UDElANO
110+
psana prace
111+
analyzovan predchozi reseni
112+
96113
ZEPTAT SE
97114
mel bych kontaktovat petra novaka
115+
pridat wwh-obd
116+
muzu dat do prace jmeno, kdyz je to verejne dostupne
117+

poznamky/obhajoba.txt

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -104,3 +104,7 @@ beamer sablona
104104
- neni vetsinou prohlizecu podporovane
105105
- nepovinny parametr dokumentu, ktery umoznuje tisknout jenom nektere slidy - napr. handout
106106
- u slidu potom <handout>
107+
108+
109+
NAPADY:
110+
rict, ze kontrola funkci statu skrze analyzu otevrenych dat vnimam jako krok k moderni demokracii a transparentnosti

0 commit comments

Comments
 (0)