src/delta_barth/analysis/forecast.py

@@ -208,7 +208,17 @@ def _process_sales(
     df_cust["jahr"] = df_cust[DATE_FEAT].dt.year
     df_cust["monat"] = df_cust[DATE_FEAT].dt.month
 
-    monthly_sum = df_cust.groupby(["jahr", "monat"])[SALES_FEAT].sum().reset_index()
+    current_year = datetime.now().year
+    current_month = datetime.now().month
+    years = range(df_cust["jahr"].min(), current_year + 1)
+
+    old_monthly_sum = df_cust.groupby(["jahr", "monat"])[SALES_FEAT].sum().reset_index()
+
+    all_month_year_combinations = pd.DataFrame(
+        [(year, month) for year in years for month in range(1, 13) if (year < current_year or (year == current_year and month <= current_month))], columns=["jahr", "monat"]
+    )
+
+    monthly_sum = pd.merge(all_month_year_combinations, old_monthly_sum, on=["jahr", "monat"], how='left')
     monthly_sum[DATE_FEAT] = (
         monthly_sum["monat"].astype(str) + "." + monthly_sum["jahr"].astype(str)
     )
@@ -228,7 +238,7 @@ def _process_sales(
     # Randomized Search
     kfold = KFold(n_splits=5, shuffle=True)
     params: ParamSearchXGBRegressor = {
-        "n_estimators": scipy.stats.poisson(mu=1000),
+        "n_estimators": scipy.stats.poisson(mu=100),
         "learning_rate": [0.03, 0.04, 0.05],
         "max_depth": range(2, 9),
         "min_child_weight": range(1, 5),
@@ -245,35 +255,29 @@ def _process_sales(
     best_score_r2: float | None = None
     best_start_year: int | None = None
     too_few_month_points: bool = True
-    # forecast: pd.DataFrame | None = None
-    # TODO: write routine to pad missing values in datetime row
-    # TODO problem: continuous timeline expected, but values can be empty for multiple months
-    # TODO: therefore, stepping with fixed value n does not result in timedelta of n episodes
-    # Option A: pad data frame with zero values --> could impede forecast algorithm
-    # Option B: calculate next index based on timedelta
+
     dates = cast(pd.DatetimeIndex, monthly_sum.index)
     # print("dates: ", dates)
-    # ?? --- new: use monthly basis for time windows
     # baseline: 3 years - 36 months
     starting_date = datetime.datetime.now() - relativedelta(months=36)
-    # starting_date = dates.max() - relativedelta(months=36)
-    start_index = next(
-        (i for i, date in enumerate(dates) if date >= starting_date), len(dates) - 1
+
+    target_index, succ = next(
+        ((i, True) for i, date in enumerate(dates) if date >= starting_date), (len(dates) - 1, False)
     )
-    print("start idx: ", start_index, "length dates: ", len(dates))
+    # print("start idx: ", target_index, "length dates: ", len(dates))
 
     for add_year, date_idx in enumerate(range(start_index, -1, -12)):
-        print("date_idx: ", date_idx)
+        # print("date_idx: ", date_idx)
         first_date = dates[date_idx]
-        print("first date: ", first_date)
+        # print("first date: ", first_date)
         split_date = dates[-6]
 
         train = cast(
             pd.DataFrame,
             monthly_sum.loc[first_date:split_date].copy(),  # type: ignore
         )
-        print(train)
-        print("Length train: ", len(train))
+        # print(train)
+        # print("Length train: ", len(train))
         test = cast(
             pd.DataFrame,
             monthly_sum.loc[split_date:].copy(),  # type: ignore
@@ -284,7 +288,7 @@ def _process_sales(
         # ?? --- new: adapted condition to fit new for-loop
         # test set size fixed at 6 --> first iteration: baseline - 6 entries
         # for each new year 10 new data points needed
-        if len(train) >= 30 + 10 * add_year:
+        if len(train[train[SALES_FEAT] > 0]) >= 30 + 10 * add_year:
             too_few_month_points = False
 
             rand = RandomizedSearchCV(