Add new, update existing and remove unneeded tests

tests/lottery_predictor/test_analyze.py

@@ -1,19 +1,52 @@
 from datetime import datetime
 import pytest
 
+import numpy as np
+
 import lottery_predictor.analyze as analyze
 
 
-def test_load_dataframe() -> None:
+def test_load_dataframe_by_date() -> None:
     pb_start = datetime(2015, 10, 4)
     mm_start = datetime(2025, 4, 5)
     date_end = datetime(2026, 3, 8)
-    assert int(analyze.load_dataframe(
-        table_name='PowerballDraw', start_date=pb_start, end_date=date_end).count()['draw_date']) >= 1324
-    assert int(analyze.load_dataframe(
-        table_name='MegaMillionsDraw', start_date=mm_start, end_date=date_end).count()['draw_date']) >= 96
+    assert int(analyze.load_dataframe_by_dates(
+        game='Powerball', start_date=pb_start, end_date=date_end).count()['draw_date']) >= 1324
+    assert int(analyze.load_dataframe_by_dates(
+        game='MegaMillions', start_date=mm_start, end_date=date_end).count()['draw_date']) >= 96
+    with pytest.raises(KeyError):
+        analyze.load_dataframe_by_dates(game='SomeNonExistentGameName')
+
+
+def test_load_dataframe_most_recent() -> None:
+    assert len(analyze.load_dataframe_most_recent(game='Powerball')) == 10
+    assert len(analyze.load_dataframe_most_recent(game='MegaMillions')) == 10
+    assert len(analyze.load_dataframe_most_recent(game='Powerball', limit=105)) == 105
+    assert len(analyze.load_dataframe_most_recent(game='MegaMillions', limit=45)) == 45
     with pytest.raises(ValueError):
-        analyze.load_dataframe(table_name='SomNonExistentTableName')
+        analyze.load_dataframe_most_recent(game='Powerball', limit=-1)
+        analyze.load_dataframe_most_recent(game='DoesntExist')
+
+
+def test_prepare_split_data() -> None:
+    mm_start = datetime(2025, 4, 5)
+    date_end = datetime(2026, 3, 8)
+    mega = analyze.load_dataframe_by_dates(game='MegaMillions', start_date=mm_start, end_date=date_end)
+
+    x, y1, y2 = analyze.prepare_split_data(data=mega.values, window_size=len(mega) - 1)
+    assert isinstance(x, np.ndarray)
+    assert isinstance(y1, np.ndarray)
+    assert isinstance(y2, np.ndarray)
+
+
+def test_make_prediction() -> None:
+    pb_start = datetime(2015, 10, 4)
+    date_end = datetime(2026, 3, 8)
+    power = analyze.load_dataframe_by_dates(game='Powerball', start_date=pb_start, end_date=date_end)
+
+    main, game = analyze.make_prediction(data_frame=power, window_size=10)
+    assert isinstance(main, np.ndarray)
+    assert isinstance(game, np.int64)
 
 
 def test_least_and_most_common_number() -> None:
@@ -21,20 +54,20 @@ def test_least_and_most_common_number() -> None:
     mm_start = datetime(2025, 4, 5)
     date_end = datetime(2026, 3, 8)
 
-    pb_df = analyze.load_dataframe(
-        table_name='PowerballDraw', start_date=pb_start, end_date=date_end)
-    mm_df = analyze.load_dataframe(
-        table_name='MegaMillionsDraw', start_date=mm_start, end_date=date_end)
+    pb_df = analyze.load_dataframe_by_dates(
+        game='Powerball', start_date=pb_start, end_date=date_end)
+    mm_df = analyze.load_dataframe_by_dates(
+        game='MegaMillions', start_date=mm_start, end_date=date_end)
 
-    assert analyze.get_most_common_number(pb_df, top=5) == [61, 21, 28, 23, 33]
-    assert analyze.get_least_common_number(pb_df, bottom=5) == [13, 49, 46, 26, 34]
-    assert analyze.get_most_common_number(mm_df, top=5) == [42, 40, 18, 10, 49]
-    assert analyze.get_least_common_number(mm_df, bottom=5) == [35, 51, 3, 1, 20]
+    assert analyze.get_most_common_number(pb_df, top=5) == [61, 21, 23, 28, 33]
+    assert analyze.get_least_common_number(pb_df, bottom=5) == [13, 49, 26, 46, 34]
+    assert analyze.get_most_common_number(mm_df, top=5) == [42, 18, 40, 49, 10]
+    assert analyze.get_least_common_number(mm_df, bottom=5) == [35, 51, 61, 1, 20]
 
     assert analyze.get_most_common_number(pb_df, columns=['powerball'], top=1) == [4]
     assert analyze.get_least_common_number(pb_df, columns=['powerball'], bottom=1) == [16]
-    assert analyze.get_most_common_number(mm_df, columns=['mega_ball'], top=1) == [1]
-    assert analyze.get_least_common_number(mm_df, columns=['mega_ball'], bottom=1) == [3]
+    assert analyze.get_most_common_number(mm_df, columns=['mega_ball'], top=1) == [24]
+    assert analyze.get_least_common_number(mm_df, columns=['mega_ball'], bottom=1) == [20]
 
 
 def test_calculate_probabilities() -> None:
@@ -43,12 +76,12 @@ def test_calculate_probabilities() -> None:
     mm_start = datetime(2025, 4, 5)
     date_end = datetime(2026, 3, 8)
 
-    pb_df = analyze.load_dataframe(
-        table_name='PowerballDraw', start_date=pb_start, end_date=date_end)
+    pb_df = analyze.load_dataframe_by_dates(
+        game='Powerball', start_date=pb_start, end_date=date_end)
     pb_probabilities = analyze.calculate_probabilities(data_frame=pb_df, max_number=69)
 
-    mm_df = analyze.load_dataframe(
-        table_name='MegaMillionsDraw', start_date=mm_start, end_date=date_end)
+    mm_df = analyze.load_dataframe_by_dates(
+        game='MegaMillions', start_date=mm_start, end_date=date_end)
     mm_probabilities = analyze.calculate_probabilities(data_frame=mm_df, max_number=70)
 
     assert pb_probabilities[1] == 0.3142857142857143
@@ -61,11 +94,11 @@ def test_hot_cold_numbers() -> None:
     mm_start = datetime(2025, 4, 5)
     date_end = datetime(2026, 3, 8)
 
-    pb_df = analyze.load_dataframe(
-        table_name='PowerballDraw', start_date=pb_start, end_date=date_end)
+    pb_df = analyze.load_dataframe_by_dates(
+        game='Powerball', start_date=pb_start, end_date=date_end)
     pb_probs = analyze.calculate_probabilities(data_frame=pb_df, max_number=69)
-    mm_df = analyze.load_dataframe(
-        table_name='MegaMillionsDraw', start_date=mm_start, end_date=date_end)
+    mm_df = analyze.load_dataframe_by_dates(
+        game='MegaMillions', start_date=mm_start, end_date=date_end)
     mm_probs = analyze.calculate_probabilities(data_frame=mm_df, max_number=70)
 
     assert (analyze.get_hot_numbers(probabilities=pb_probs) ==

tests/lottery_predictor/test_collect.py

@@ -5,21 +5,21 @@ import lottery_predictor.collect as collect
 
 
 def test_get_record_count() -> None:
-    assert isinstance(collect.get_record_count(table_name='PowerballDraw'), int)
-    assert isinstance(collect.get_record_count(table_name='MegaMillionsDraw'), int)
-    with pytest.raises(ValueError):
-        collect.get_record_count(table_name='SomeNonExistentTable')
+    assert isinstance(collect.get_record_count(game='Powerball'), int)
+    assert isinstance(collect.get_record_count(game='MegaMillions'), int)
+    with pytest.raises(KeyError):
+        collect.get_record_count(game='SomeNonExistentTable')
 
 
 def test_get_recent_draw_date() -> None:
-    assert isinstance(collect.get_recent_draw_date(table_name='PowerballDraw'), datetime.date)
-    assert isinstance(collect.get_recent_draw_date(table_name='MegaMillionsDraw'), datetime.date)
-    with pytest.raises(ValueError):
-        collect.get_recent_draw_date(table_name='SomeNonExistentTable')
+    assert isinstance(collect.get_recent_draw_date(game='Powerball'), datetime.date)
+    assert isinstance(collect.get_recent_draw_date(game='MegaMillions'), datetime.date)
+    with pytest.raises(KeyError):
+        collect.get_recent_draw_date(game='SomeNonExistentTable')
 
 
 def test_get_missing_records() -> None:
-    assert isinstance(collect.get_missing_records(table_name='PowerballDraw'), int)
-    assert isinstance(collect.get_missing_records(table_name='MegaMillionsDraw'), int)
-    with pytest.raises(ValueError):
-        collect.get_missing_records(table_name='SomeNonExistentTable')
+    assert isinstance(collect.get_missing_records(game='Powerball'), int)
+    assert isinstance(collect.get_missing_records(game='MegaMillions'), int)
+    with pytest.raises(KeyError):
+        collect.get_missing_records(game='SomeNonExistentTable')