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

update WF-100 Petersen for special case

Browse Source
This commit is contained in:
Florian Förster 2026-01-15 08:36:49 +01:00
parent ab4eb1cbac
commit 3557ab0687
1 changed files with 29 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
data_analysis/02-3_oracle_workflow_test.py
View File

@ -39,10 +39,10 @@ USER_NAME = CFG["user"]["name"]
USER_PASS = CFG["user"]["pass"] USER_PASS = CFG["user"]["pass"]
# %% # %%
# !! init thick mode # !! init thick mode
p_oracle_client = Path(r"C:\Databases\Oracle\instantclient_19_29") # p_oracle_client = Path(r"C:\Databases\Oracle\instantclient_19_29")
assert p_oracle_client.exists() # assert p_oracle_client.exists()
assert p_oracle_client.is_dir() # assert p_oracle_client.is_dir()
oracledb.init_oracle_client(lib_dir=str(p_oracle_client)) # oracledb.init_oracle_client(lib_dir=str(p_oracle_client))
# %% # %%
conn_string = ( conn_string = (
f"oracle+oracledb://{USER_NAME}:{USER_PASS}@{HOST}:{PORT}?service_name={SERVICE}" f"oracle+oracledb://{USER_NAME}:{USER_PASS}@{HOST}:{PORT}?service_name={SERVICE}"
@ -264,19 +264,21 @@ df.with_columns(
) )
# %% # %%
# ** CHECK: distribution of MELDENUMMER # ** CHECK: distribution of MELDENUMMER
temp = df.filter(pl.col.BEDP_MAN.is_in((1, 90)))
sum_entries = len(temp)
temp = ( temp = (
df.group_by("MELDENUMMER") temp.group_by("MELDENUMMER")
.agg(pl.col("MELDENUMMER").len().alias("count")) .agg(pl.col("MELDENUMMER").len().alias("count"))
.sort("count", descending=True) .sort("count", descending=True)
) )
sum_entries = len(df)
temp = temp.with_columns((pl.col.count / sum_entries).alias("proportion")) temp = temp.with_columns((pl.col.count / sum_entries).alias("proportion"))
temp = temp.with_columns(pl.col.proportion.cum_sum().alias("cum")) temp = temp.with_columns(pl.col.proportion.cum_sum().alias("cum"))
temp temp
# df.filter(pl.col("MELDENUMMER").is_not_null() & pl.col("MELDENUMMER").is_in((17, 18))).select( # df.filter(pl.col("MELDENUMMER").is_not_null() & pl.col("MELDENUMMER").is_in((17, 18))).select(
# pl.len() # pl.len()
# ) # )
# p_save = Path.cwd() / "meldenummer_anteile_20260114-1.xlsx" # p_save = Path.cwd() / "meldenummer_anteile_20260114-2.xlsx"
# temp.write_excel(p_save) # temp.write_excel(p_save)
# %% # %%
# ** CHECK: differences MANDANT in BEDP and in TINFO # ** CHECK: differences MANDANT in BEDP and in TINFO
@ -703,7 +705,6 @@ def workflow_100_petersen(
filter_mandant = pl.col(MANDANT_CRITERION) == 90 filter_mandant = pl.col(MANDANT_CRITERION) == 90
filter_WDB = pl.col("VERLAGSNR").is_in((76008, 76070)) filter_WDB = pl.col("VERLAGSNR").is_in((76008, 76070))
filter_number_vm = pl.col(vm_criterion) == 0 filter_number_vm = pl.col(vm_criterion) == 0
res = _apply_several_filters( res = _apply_several_filters(
pipe_result.open, pipe_result.open,
( (
@ -742,10 +743,29 @@ def workflow_100_petersen(
pipe_result.merge_pipeline(wdb_sub_pipe) pipe_result.merge_pipeline(wdb_sub_pipe)
# // other branch # // other branch
# show always entries with #VM > 1
filter_meldenummer = pl.col("MELDENUMMER") == 18
filter_mandant = pl.col(MANDANT_CRITERION) == 90
filter_number_vm = pl.col(vm_criterion) > 1
res = _apply_several_filters(
pipe_result.open,
(
filter_meldenummer,
filter_mandant,
filter_number_vm,
),
)
pipe_result.write_results(
data=res.in_,
vorlage=True,
wf_id=100,
freigabe_auto=types.Freigabe.WF_100,
is_out=False,
)
filter_meldenummer = pl.col("MELDENUMMER") == 18 filter_meldenummer = pl.col("MELDENUMMER") == 18
filter_mandant = pl.col(MANDANT_CRITERION) == 90 filter_mandant = pl.col(MANDANT_CRITERION) == 90
filter_number_vm = pl.col(vm_criterion) > 0 filter_number_vm = pl.col(vm_criterion) > 0
res = _apply_several_filters( res = _apply_several_filters(
pipe_result.open, pipe_result.open,
( (