From 4ea9d35a913517b1edbeabe4bb3550fb47003bf1 Mon Sep 17 00:00:00 2001 From: foefl Date: Thu, 15 Jan 2026 17:09:21 +0100 Subject: [PATCH] new tests --- data_analysis/02-3_oracle_workflow_test.py | 18 +++++++- data_analysis/queries.sql | 48 +++++++++++----------- src/umbreit/db.py | 2 +- 3 files changed, 42 insertions(+), 26 deletions(-) diff --git a/data_analysis/02-3_oracle_workflow_test.py b/data_analysis/02-3_oracle_workflow_test.py index 11f2093..895a89f 100644 --- a/data_analysis/02-3_oracle_workflow_test.py +++ b/data_analysis/02-3_oracle_workflow_test.py @@ -201,6 +201,7 @@ stmt = sql.select( db.ext_bedpbed.c.BEDP_SEQUENZ, db.ext_bedpbed.c.BEDP_TITELNR, db.ext_bedpbed.c.BEDP_MAN, + db.ext_bedpbed.c.BEDP_MENGE_BEDARF_VM, sql.case( (db.ext_bedpbed.c.BEDP_MENGE_BEDARF_VM <= -1, sql.null()), else_=db.ext_bedpbed.c.BEDP_MENGE_BEDARF_VM, @@ -229,14 +230,27 @@ df.head() # %% # // NO LIVE DATA NEEDED # SAVING/LOADING -p_save = Path.cwd() / "raw_data_from_sql_query_20260114-1.arrow" +p_save = Path.cwd() / "raw_data_from_sql_query_20260115-altered_query.arrow" +# p_save = Path.cwd() / "raw_data_from_sql_query_20251203-2.arrow" # df.write_ipc(p_save) df = pl.read_ipc(p_save) # %% print(len(df)) df.head() # %% -df.head() +temp = df.fill_null(0) +mask = df.select(pl.exclude("BEDARFNR", "BEDP_SEQUENZ")).is_duplicated() +temp.filter(mask).sort("BEDP_TITELNR") +# %% +temp = df.filter(pl.col.BEDP_MAN.is_in((1, 90))).with_columns( + pl.col.BEDP_MENGE_BEDARF_VM.fill_null(0), +) +temp = df.with_columns( + pl.col.BEDP_MENGE_BEDARF_VM.fill_null(0), +) +temp.filter(pl.col.BEDP_MENGE_BEDARF_VM < 0) +# %% +df.filter(pl.col.BEDP_MENGE_BEDARF_VM < 0) # %% # ** CHECK: duplicates temp = df.fill_null(0) diff --git a/data_analysis/queries.sql b/data_analysis/queries.sql index 08feafd..a1af327 100644 --- a/data_analysis/queries.sql +++ b/data_analysis/queries.sql @@ -105,19 +105,19 @@ WHERE besp.BESP_TITELNR IN ( besp.BES_DATUM > TO_DATE('2025-06-01', 'YYYY-MM-DD') ORDER BY besp.BES_DATUM ASC; --- SELECT --- bedp.BEDARFNR, --- bedp.BEDP_SEQUENZ, --- bedp.BEDP_TITELNR, --- bedp.BEDP_MAN, --- bedp.BEDP_MENGE_BEDARF_VM, --- t_info.MELDENUMMER, --- t_info.VERLAGSNR, --- t_info.MENGE_VORMERKER, --- t_info.MANDFUEHR --- FROM EXT_BEDPBED bedp --- LEFT JOIN EXT_TITEL_INFO_NEU t_info --- ON bedp.BEDP_TITELNR = t_info.TI_NUMMER; +SELECT + bedp.BEDARFNR, + bedp.BEDP_SEQUENZ, + bedp.BEDP_TITELNR, + bedp.BEDP_MAN, + bedp.BEDP_MENGE_BEDARF_VM, + t_info.MELDENUMMER, + t_info.VERLAGSNR, + t_info.MENGE_VORMERKER, + t_info.MANDFUEHR +FROM EXT_BEDPBED bedp +LEFT JOIN EXT_TITEL_INFO t_info + ON bedp.BEDP_TITELNR = t_info.TI_NUMMER; SELECT COUNT(*) FROM (SELECT @@ -240,21 +240,23 @@ bedp.BEDP_MENGE_BEDARF_VM = 0); -- WHERE auf.AUFTRAGS_DATUM > TO_DATE('2025-11-18', 'YYYY-MM-DD'); -- system queries --- SELECT owner, table_name --- FROM all_tables --- ORDER BY owner, table_name; +SELECT owner, table_name +FROM all_tables +ORDER BY owner, table_name; -- SELECT table_name -- FROM user_tables -- ORDER BY table_name; --- SELECT view_name --- FROM user_views --- ORDER BY view_name; --- SELECT owner, view_name --- FROM all_views +SELECT view_name +FROM user_views +ORDER BY view_name; +SELECT owner, view_name +FROM all_views +-- WHERE VIEW_NAME LIKE 'EXT_' -- WHERE owner = 'UMB' --- ORDER BY view_name; +ORDER BY view_name; -- DESC all_views; -DESC EXT_AUFPAUF; \ No newline at end of file +DESC EXT_DOPT_ERGEBNIS; +SELECT * FROM v$version;d-opt \ No newline at end of file diff --git a/src/umbreit/db.py b/src/umbreit/db.py index a160e23..946e96e 100644 --- a/src/umbreit/db.py +++ b/src/umbreit/db.py @@ -51,7 +51,7 @@ ext_bedpbed_null_values: PolarsNullValues = { } ext_titel_info = Table( - "ext_titel_info_neu", + "ext_titel_info", metadata, Column("TI_NUMMER", sql.Integer, primary_key=True, autoincrement=False, nullable=False), Column("MANDFUEHR", sql.Integer, primary_key=True, autoincrement=False, nullable=False),