add preprocessing steps

src/delta_barth/analysis/forecast.py

@@ -1,19 +1,34 @@
 from __future__ import annotations
 
 import dataclasses as dc
+from collections.abc import Mapping, Set
 from typing import TYPE_CHECKING
 
 import pandas as pd
 from sklearn.metrics import mean_squared_error
 from xgboost import XGBRegressor
 
+from delta_barth.analysis import parse
+from delta_barth.constants import COL_MAP_SALES_PROGNOSIS, FEATURES_SALES_PROGNOSIS
 from delta_barth.types import CustomerDataSalesForecast, FcErrorCodes
 
 if TYPE_CHECKING:
+    from delta_barth.api.common import SalesPrognosisResponse
     from delta_barth.types import FcResult
 
 # TODO check pandera for DataFrame validation
 
+
+def parse_api_resp_to_df(
+    resp: SalesPrognosisResponse,
+) -> pd.DataFrame:
+    if resp.error is not None:
+        raise ValueError("Response contains error code. Parsing aborted.")
+    data = resp.model_dump()["daten"]
+
+    return pd.DataFrame(data)
+
+
 # ------------------------------------------------------------------------------
 # Input:
 #   DataFrame df mit Columns f_umsatz_fakt, firmen, art, v_warengrp
@@ -28,8 +43,22 @@ if TYPE_CHECKING:
 
 # Prognose Umsatz je Firma
 
+
 # TODO: check usage of separate exception and handle it in API function
 # TODO set min number of data points as constant, not parameter
+def preprocess_sales_per_customer(
+    resp: SalesPrognosisResponse,
+    feature_map: Mapping[str, str],
+    target_features: Set[str],
+) -> pd.DataFrame:
+    df = parse_api_resp_to_df(resp)
+    df = parse.preprocess_features(
+        df,
+        feature_map=feature_map,
+        target_features=target_features,
+    )
+
+    return df
 
 
 def sales_per_customer(

src/delta_barth/analysis/parse.py

@@ -9,9 +9,9 @@ if TYPE_CHECKING:
     import pandas as pd
 
 
-def check_needed_features(
+def _check_needed_features(
     data: pd.DataFrame,
-    features: Set,
+    features: Set[str],
 ) -> None:
     data_feats = set(data.columns)
     missing_features = features - data_feats
@@ -23,10 +23,11 @@ def check_needed_features(
         )
 
 
-def map_features_to_targets(
+def _map_features_to_targets(
     data: pd.DataFrame,
     feature_map: Mapping[str, str],
 ) -> pd.DataFrame:
+    data = data.copy()
     data_feats = data.columns
     mapped_feats: list[str] = []
 
@@ -39,3 +40,14 @@ def map_features_to_targets(
     data.columns = mapped_feats
 
     return data
+
+
+def preprocess_features(
+    data: pd.DataFrame,
+    feature_map: Mapping[str, str],
+    target_features: Set[str],
+) -> pd.DataFrame:
+    data = _map_features_to_targets(data, feature_map)
+    _check_needed_features(data, target_features)
+
+    return data