generated from dopt-python/py311
add prototyping
This commit is contained in:
228
prototypes/01_first-look_20260603.py
Normal file
228
prototypes/01_first-look_20260603.py
Normal file
@@ -0,0 +1,228 @@
|
||||
# %%
|
||||
from pathlib import Path
|
||||
|
||||
import polars as pl
|
||||
|
||||
# %%
|
||||
PROJECT_BASE = Path(__file__).parents[1]
|
||||
DATA = PROJECT_BASE / "data"
|
||||
assert DATA.exists()
|
||||
# %%
|
||||
data_t1 = DATA / "PSM/20260507"
|
||||
assert data_t1.exists()
|
||||
# %%
|
||||
data_t1_jobs = data_t1 / "MIS-Auträge_22.csv"
|
||||
assert data_t1_jobs.exists()
|
||||
data_t1_PSM = data_t1 / "Produktionsstandsmeldungen.csv"
|
||||
assert data_t1_PSM.exists()
|
||||
# %%
|
||||
# // MIS-Aufträge
|
||||
pl.read_csv(data_t1_jobs, encoding="windows-1252", separator=";")
|
||||
|
||||
# %%
|
||||
# // PSM
|
||||
schema_PSM: dict[str, type[pl.DataType]] = {
|
||||
"VK Auftrag": pl.UInt32,
|
||||
"Artikelbez.": pl.String,
|
||||
"Auftragsmenge": pl.UInt32,
|
||||
"Kunde": pl.String,
|
||||
"PA": pl.UInt64,
|
||||
"PA Pos": pl.UInt32,
|
||||
"PSM gemeldet am": pl.Datetime,
|
||||
"Konfektionär": pl.String,
|
||||
"Artikelnr.": pl.String,
|
||||
"LT Kunde bestätigt": pl.Date,
|
||||
"Export Ist": pl.Date,
|
||||
"1.bestät. Import Konfektionär": pl.Date,
|
||||
"Import Ist": pl.Date,
|
||||
"Ablief.(Import Ist+Transport)": pl.Date,
|
||||
"Wareneingang am": pl.Date,
|
||||
"Wareneingang geprüft": pl.String,
|
||||
"Täglicher Ausstoss": pl.Int64,
|
||||
"Zuschnitt am": pl.Date,
|
||||
"Teile in Zuschnitt": pl.UInt64,
|
||||
"Teile im Nähband": pl.UInt64,
|
||||
"Fertigware aus Nähband": pl.UInt64,
|
||||
"Teile kontrolliert": pl.UInt64,
|
||||
"Teile verpackt in Karton": pl.UInt64,
|
||||
"Anzahl Bänder": pl.UInt16,
|
||||
"Anzahl Näher": pl.UInt16,
|
||||
"Arbeitsstunden pro Näher": pl.UInt8,
|
||||
"Anzahl Arbeitstage pro Woche": pl.UInt8,
|
||||
"Blockauftrag": pl.String,
|
||||
}
|
||||
|
||||
# psm = pl.read_csv(data_t1_PSM, encoding="windows-1252", separator=";")
|
||||
psm = pl.read_csv(
|
||||
data_t1_PSM,
|
||||
encoding="windows-1252",
|
||||
separator=";",
|
||||
schema_overrides=schema_PSM,
|
||||
null_values=["01.01.1111 00:00:00"],
|
||||
)
|
||||
# %%
|
||||
psm.filter(pl.col("Konfektionär").str.contains("MEMTEKS"))
|
||||
# %%
|
||||
|
||||
# %%
|
||||
psm.estimated_size("mb")
|
||||
|
||||
# %%
|
||||
regex_pattern = r"^[\s\-#+/$]+$"
|
||||
psm = psm.with_columns(
|
||||
pl.when(pl.col(pl.String).str.contains(regex_pattern))
|
||||
.then(None)
|
||||
.otherwise(pl.col(pl.String))
|
||||
.name.keep()
|
||||
)
|
||||
psm.filter((pl.col.PA == 17191) & (pl.col("PA Pos") == 10))
|
||||
|
||||
# %%
|
||||
psm.estimated_size("mb")
|
||||
|
||||
# %%
|
||||
psm.head()
|
||||
# %%
|
||||
psm.filter(pl.any_horizontal(pl.col("VK Auftrag").is_null()))
|
||||
|
||||
# %%
|
||||
psm.filter(pl.col("Wareneingang am") == "01.01.1111 00:00:00").group_by(
|
||||
pl.col.Konfektionär
|
||||
).agg(pl.len())
|
||||
|
||||
# %%
|
||||
dupl_filter = psm.select([pl.col.PA, pl.col("PA Pos")]).is_duplicated()
|
||||
# %%
|
||||
psm.group_by(["PA", "PA Pos"]).agg(pl.col("PA").n_unique().alias("unique")).sort(
|
||||
"unique", descending=True
|
||||
)
|
||||
# %%
|
||||
most_occurrences = (
|
||||
psm.group_by(["PA", "PA Pos", "Konfektionär"])
|
||||
.agg(pl.len().alias("count"))
|
||||
.sort("count", descending=True)
|
||||
)
|
||||
most_occurrences
|
||||
# %%
|
||||
most_occurrences.filter(~pl.col("Konfektionär").str.contains("May Tekstil Camcesme"))
|
||||
# %%
|
||||
psm.filter((pl.col.PA == 16003) & (pl.col("PA Pos") == 10)).sort(
|
||||
"PSM gemeldet am", descending=False
|
||||
)
|
||||
|
||||
|
||||
# %%
|
||||
psm.filter((pl.col.PA == 17085) & (pl.col("PA Pos") == 10)).sort(
|
||||
"PSM gemeldet am", descending=False
|
||||
)
|
||||
# %%
|
||||
tmp = psm.filter((pl.col.PA == 15372) & (pl.col("PA Pos") == 10)).sort(
|
||||
"PSM gemeldet am", descending=False
|
||||
)
|
||||
tmp
|
||||
# %%
|
||||
# // simulate time series
|
||||
series: list[pl.DataFrame] = []
|
||||
|
||||
for i in range(tmp.height):
|
||||
series.append(tmp[: (i + 1)])
|
||||
|
||||
assert len(series) == tmp.height
|
||||
|
||||
for idx, entry in enumerate(series, start=1):
|
||||
assert idx == entry.height
|
||||
# %%
|
||||
series[1]
|
||||
# %%
|
||||
tmp.columns
|
||||
# %%
|
||||
tmp = psm.filter((pl.col.PA == 16003) & (pl.col("PA Pos") == 10)).sort(
|
||||
"PSM gemeldet am", descending=False
|
||||
)
|
||||
# %%
|
||||
# // plausibility check
|
||||
# ** production quantities
|
||||
plausi_features_all = [
|
||||
"Teile in Zuschnitt",
|
||||
"Teile im Nähband",
|
||||
"Fertigware aus Nähband",
|
||||
"Teile kontrolliert",
|
||||
"Teile verpackt in Karton",
|
||||
]
|
||||
plausi_features_endpoint_only = [
|
||||
"Teile in Zuschnitt",
|
||||
"Fertigware aus Nähband",
|
||||
"Teile kontrolliert",
|
||||
"Teile verpackt in Karton",
|
||||
]
|
||||
plausi_features = plausi_features_all
|
||||
# plausi_features = plausi_features_endpoint_only
|
||||
# %%
|
||||
IDX = None
|
||||
if IDX is None:
|
||||
tmp_1 = tmp.select(plausi_features_all)
|
||||
else:
|
||||
tmp_1 = tmp[IDX].select(plausi_features_all)
|
||||
print(tmp_1)
|
||||
# %%
|
||||
# ** empty: default state
|
||||
tmp_1 = tmp_1.with_columns(
|
||||
pl.all_horizontal(pl.col("*").is_null() | (pl.col("*") == 0)).alias("is_empty")
|
||||
)
|
||||
# %%
|
||||
# tmp_1 = tmp_1.transpose()
|
||||
# %%
|
||||
# tmp_1.shift(1)
|
||||
|
||||
# %%
|
||||
conditions = [
|
||||
pl.col(plausi_features[i]) >= pl.col(plausi_features[i + 1])
|
||||
for i in range(len(plausi_features) - 1)
|
||||
]
|
||||
|
||||
# 4. Filter anwenden
|
||||
# pl.all_horizontal stellt sicher, dass die Bedingung für JEDES Paar in der Zeile stimmt
|
||||
df_markiert = tmp_1.with_columns(
|
||||
pl.when(pl.all_horizontal(conditions) | pl.col("is_empty"))
|
||||
.then(pl.lit(True))
|
||||
.otherwise(pl.lit(False))
|
||||
.alias("Produktionsstückzahlen_valide")
|
||||
)
|
||||
print(df_markiert)
|
||||
|
||||
# df_valide = tmp_1.filter(pl.all_horizontal(conditions))
|
||||
# df_invalide = tmp_1.filter(
|
||||
# ~pl.all_horizontal(conditions)
|
||||
# ) # Das Tilde-Zeichen ~ bedeutet "NOT"
|
||||
|
||||
# print("--- Valide Zeilen ---")
|
||||
# print(df_valide)
|
||||
|
||||
# print("\n--- Invalide Zeilen ---")
|
||||
# print(df_invalide)
|
||||
|
||||
|
||||
# %%
|
||||
# 1. Testdaten erstellen (Zeile 0-2 sind valide, Zeile 3 ist dein invalides Beispiel)
|
||||
df = pl.DataFrame({"EP-1": [0, 100, 100, 0], "EP-2": [0, 0, 100, 100], "EP-3": [0, 0, 0, 0]})
|
||||
|
||||
# 2. Liste der Erfassungspunkte in der richtigen (konsekutiven) Reihenfolge
|
||||
ep_spalten = ["EP-1", "EP-2", "EP-3"]
|
||||
|
||||
# 3. Dynamisch die Bedingungen für alle Paare erstellen
|
||||
# Wir prüfen für jedes Paar: Ist der vorherige Punkt (i) >= dem nächsten Punkt (i+1)?
|
||||
bedingungen = [
|
||||
pl.col(ep_spalten[i]) >= pl.col(ep_spalten[i + 1]) for i in range(len(ep_spalten) - 1)
|
||||
]
|
||||
|
||||
# 4. Filter anwenden
|
||||
# pl.all_horizontal stellt sicher, dass die Bedingung für JEDES Paar in der Zeile stimmt
|
||||
df_valide = df.filter(pl.all_horizontal(bedingungen))
|
||||
df_invalide = df.filter(~pl.all_horizontal(bedingungen)) # Das Tilde-Zeichen ~ bedeutet "NOT"
|
||||
|
||||
print("--- Valide Zeilen ---")
|
||||
print(df_valide)
|
||||
|
||||
print("\n--- Invalide Zeilen ---")
|
||||
print(df_invalide)
|
||||
# %%
|
||||
Reference in New Issue
Block a user