Umbreit/umbreit-py
1
0
Fork 0
generated from dopt-python/py311
Code Issues 1 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

negligible changes

Browse Source
This commit is contained in:
Florian Förster 2026-03-03 09:01:27 +01:00
parent 5653e3fbcd
commit 97cd74d230
1 changed files with 44 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
data_analysis/02-3_oracle_workflow_test.py
View File

@ -270,7 +270,7 @@ temp.filter(pl.col.BEDP_MENGE_BEDARF_VM < 0)
# // NO LIVE DATA NEEDED # // NO LIVE DATA NEEDED
# SAVING/LOADING # SAVING/LOADING
# p_save = Path.cwd() / "raw_data_from_sql_query_20260115-altered_query.arrow" # p_save = Path.cwd() / "raw_data_from_sql_query_20260115-altered_query.arrow"
p_save = Path.cwd() / "raw_data_from_sql_query_20260116-1.arrow" p_save = Path.cwd() / "raw_data_from_sql_query_20260303-1.arrow"
# df.write_ipc(p_save) # df.write_ipc(p_save)
df = pl.read_ipc(p_save) df = pl.read_ipc(p_save)
# %% # %%
@ -897,7 +897,7 @@ def _wf100_sub1_umbreit(
) )
if SAVE_TMP_FILES: if SAVE_TMP_FILES:
save_tmp_file(relevant_titles, TMPFILE_WF200_SUB1) save_tmp_file(relevant_titles, TMPFILE_WF100_SUB1_UMBREIT)
relevant_titles = relevant_titles.filter(pl.col.CUSTOMER_COUNT >= 3) relevant_titles = relevant_titles.filter(pl.col.CUSTOMER_COUNT >= 3)
entries_to_show = pipe_result.open.filter( entries_to_show = pipe_result.open.filter(
@ -1236,7 +1236,7 @@ def _wf200_sub1(
# SAVING/LOADING # SAVING/LOADING
READ_DATABASE = False READ_DATABASE = False
OVERWRITE = True OVERWRITE = True
FILENAME = "raw_data_from_sql_query_20260202-1.arrow" FILENAME = "raw_data_from_sql_query_20260303-2.arrow"
p_save = Path.cwd() / FILENAME p_save = Path.cwd() / FILENAME
if READ_DATABASE: if READ_DATABASE:
df = get_raw_data() df = get_raw_data()
@ -1308,30 +1308,42 @@ pipe_res.results.height
all_tmps = load_all_tmp_files() all_tmps = load_all_tmp_files()
print(len(all_tmps)) print(len(all_tmps))
# %%
all_tmps
# %% # %%
def prepare_tmp_data() -> list[pl.DataFrame]: def prepare_tmp_data() -> list[pl.DataFrame]:
all_tmps = load_all_tmp_files() all_tmps = load_all_tmp_files()
WF_100_TMP_RENAME = {"COUNT": "WF-100_WDB_Anz-Best-Petersen_verg_6_Monate"} WF_100_TMP_WDB_RENAME = {"COUNT": "WF-100_WDB_Anz-Best-Petersen_verg_6_Monate"}
WF_100_TMP_UMBREIT_RENAME = {
"COUNT": "WF-100_Umbreit_Anz-Best-Kunde_verg_3_Monate",
"CUSTOMER_COUNT": "WF-100_Umbreit_Anz-Kunden_verg_3_Monate",
}
WF_200_TMP_RENAME = { WF_200_TMP_RENAME = {
"COUNT": "WF-200_Anz-Best-Kunde_verg_3_Monate", "COUNT": "WF-200_Anz-Best-Kunde_verg_3_Monate",
"CUSTOMER_COUNT": "WF-200_Anz-Kunden_verg_3_Monate", "CUSTOMER_COUNT": "WF-200_Anz-Kunden_verg_3_Monate",
} }
WF_100: list[pl.DataFrame] = [] WF_100_UMBREIT: list[pl.DataFrame] = []
WF_100_WDB: list[pl.DataFrame] = []
WF_200: list[pl.DataFrame] = [] WF_200: list[pl.DataFrame] = []
for name, df in all_tmps.items(): for name, df in all_tmps.items():
if TMPFILE_WF100_SUB1_WDB in name: if TMPFILE_WF100_SUB1_UMBREIT in name:
rename_schema = WF_100_TMP_RENAME rename_schema = WF_100_TMP_UMBREIT_RENAME
df = df.rename(rename_schema) df = df.rename(rename_schema)
WF_100.append(df) WF_100_UMBREIT.append(df)
elif TMPFILE_WF100_SUB1_WDB in name:
rename_schema = WF_100_TMP_WDB_RENAME
df = df.rename(rename_schema)
WF_100_WDB.append(df)
elif TMPFILE_WF200_SUB1 in name: elif TMPFILE_WF200_SUB1 in name:
rename_schema = WF_200_TMP_RENAME rename_schema = WF_200_TMP_RENAME
df = df.rename(rename_schema) df = df.rename(rename_schema)
WF_200.append(df) WF_200.append(df)
tmp_WF_collects = (WF_100, WF_200) tmp_WF_collects = (WF_100_UMBREIT, WF_100_WDB, WF_200)
all_tmps_preproc: list[pl.DataFrame] = [] all_tmps_preproc: list[pl.DataFrame] = []
for collect in tmp_WF_collects: for collect in tmp_WF_collects:
@ -1394,6 +1406,29 @@ def generate_test_result_data(
# %% # %%
test_results = generate_test_result_data(raw_data, pipe_res) test_results = generate_test_result_data(raw_data, pipe_res)
test_results.head() test_results.head()
# %%
col = "WF-100_Umbreit_Anz-Best-Kunde_verg_3_Monate"
# col = "WF-100_Umbreit_Anz-Kunden_verg_3_Monate"
# test_results.filter(pl.col(col) >= 3)
# %%
# RELEVANT_DATE = get_starting_date(60)
#
# title_no = 7753822
# title_no = 5383912
# filter_ = sql.and_(
# db.EXT_AUFPAUF.c.TITELNR == title_no,
# db.EXT_AUFPAUF.c.AUFTRAGS_DATUM >= RELEVANT_DATE,
# db.EXT_AUFPAUF.c.AUFP_VORMERKUNG == "J",
# )
# stmt = sql.select(
# db.EXT_AUFPAUF,
# ).where(filter_)
# relevant_titles = pl.read_database(
# stmt,
# engine,
# )
# relevant_titles
# %% # %%