major overhaul of forecast pipeline (#21)

includes several aspects:

- harden forecast logic with additional error checks
- fix wrong behaviour
- ensure minimum data viability
- extrapolate for multiple data points into the future

fix #19

Co-authored-by: frasu
Reviewed-on: #21
Co-authored-by: foefl <f.foerster@d-opt.com>
Co-committed-by: foefl <f.foerster@d-opt.com>

tests/analysis/test_forecast.py

@@ -1,4 +1,6 @@
+import datetime
 from datetime import datetime as Datetime
+from pathlib import Path
 from unittest.mock import patch
 
 import numpy as np
@@ -255,6 +257,7 @@ def test_preprocess_sales_FailOnTargetFeature(
     assert pipe.results is None
 
 
+@pytest.mark.forecast
 def test_process_sales_Success(sales_data_real_preproc):
     data = sales_data_real_preproc.copy()
     pipe = PipeResult(data, STATUS_HANDLER.SUCCESS)
@@ -277,6 +280,7 @@ def test_process_sales_Success(sales_data_real_preproc):
     assert pipe.statistics.xgb_params is not None
 
 
+@pytest.mark.forecast
 def test_process_sales_FailTooFewPoints(sales_data_real_preproc):
     data = sales_data_real_preproc.copy()
     data = data.iloc[:20, :]
@@ -303,6 +307,7 @@ def test_process_sales_FailTooFewPoints(sales_data_real_preproc):
     assert pipe.statistics.xgb_params is None
 
 
+@pytest.mark.forecast
 def test_process_sales_FailTooFewMonthPoints(sales_data_real_preproc):
     data = sales_data_real_preproc.copy()
     pipe = PipeResult(data, STATUS_HANDLER.SUCCESS)
@@ -329,8 +334,19 @@ def test_process_sales_FailTooFewMonthPoints(sales_data_real_preproc):
     assert pipe.statistics.xgb_params is None
 
 
+@pytest.mark.forecast
 def test_process_sales_FailNoReliableForecast(sales_data_real_preproc):
-    data = sales_data_real_preproc.copy()
+    # prepare fake data
+    df = sales_data_real_preproc.copy()
+    f_dates = "buchungs_datum"
+    end = datetime.datetime.now()
+    start = df[f_dates].max()
+    fake_dates = pd.date_range(start, end, freq="MS")
+    fake_data = [(1234, 1014, 1024, 1000, 10, date) for date in fake_dates]
+    fake_df = pd.DataFrame(fake_data, columns=df.columns)
+    enhanced_df = pd.concat((df, fake_df), ignore_index=True)
+
+    data = enhanced_df.copy()
     data["betrag"] = 10000
     print(data["betrag"])
     data = data.iloc[:20000, :]
@@ -340,7 +356,7 @@ def test_process_sales_FailNoReliableForecast(sales_data_real_preproc):
         def __init__(self, *args, **kwargs) -> None:
             class Predictor:
                 def predict(self, *args, **kwargs):
-                    return np.array([1, 1, 1, 1])
+                    return np.array([1, 1, 1, 1], dtype=np.float64)
 
             self.best_estimator_ = Predictor()
 
@@ -354,7 +370,7 @@ def test_process_sales_FailNoReliableForecast(sales_data_real_preproc):
         pipe = fc._process_sales(
             pipe,
             min_num_data_points=1,
-            base_num_data_points_months=-100,
+            base_num_data_points_months=1,
         )
 
     assert pipe.status != STATUS_HANDLER.SUCCESS