Add AI code in comment form for review

lottery_predictor/analyze.py

@@ -1,16 +1,15 @@
-from datetime import datetime
 from collections import Counter
+from datetime import datetime
+from itertools import combinations
 
 import numpy as np
 import pandas as pd
-from sklearn.ensemble import RandomForestClassifier
+from sklearn.ensemble import RandomForestRegressor
 from sqlalchemy import select
 
-from data.database import Base, dal, project_variables
+from data.database import Base, dal
 import util.drawing as drawutil
 
-RANDOM_SEED = 42
-
 
 def load_dataframe(
         table_name: str, start_date: datetime | None = None, end_date: datetime | None = None
@@ -125,3 +124,78 @@ def get_cold_numbers(probabilities: dict[int, float], bottom: int = 5) -> list[t
     :returns list of tuples: A list of the hot numbers and their raw score
     """
     return sorted(probabilities.items(), key=lambda item: item[1])[:bottom]
+
+
+"""
+def extract_features(row):
+    balls = [row['main_ball1'], row['main_ball2'], row['main_ball3'], row['main_ball4'], row['main_ball5']]
+    pd.Series({
+        'sum': sum(balls),
+        'mean': np.mean(balls),
+        'std': np.std(balls),
+        'even_count': len([b for b in balls if b % 2 == 0]),
+        'range': max(balls) - min(balls)
+    })
+
+# Melt the 5 ball columns into one long column of numbers
+melted = df.melt(id_vars=['draw_date'], value_vars=['ball1', 'ball2', 'ball3', 'ball4', 'ball5'], value_name='number')
+
+# Find the most recent date each number appeared
+last_seen = melted.groupby('number')['draw_date'].max()
+
+# calculate days overdue relative to today
+current_date = datetime.now()
+overdue_days = (current_date - last_seen).dt.days
+
+# sort to find the "most overdue" at the top
+most_overdue = overdue_days.sort_values(ascending=False)
+
+# print the 10 most overdue
+print(most_overdue.head(10))
+
+game_ball_last_seen = df.groupby('powerball')['draw_date'].max() # or 'mega-ball'
+game_ball_overdue = (current_date - game_ball_last_seen).dt.days.soft_values(ascending=False)
+
+features = np.apply(extract_features, axis=1)
+y = np.ones(len(data_frame))
+# train a model to recognize what a "winning" set looks like
+model = RandomForestRegressor(n_estimators=100)
+model.fit(features, y)
+
+# Sample: Generate combinations from the top 15 most frequent/overdue numbers
+target_numbers = most_overdue.head(15).index.tolist()
+candidate_sets = list(combinations(target_numbers, 2))
+
+results = []
+for s in candidate_sets:
+    # Create features for this hypothetical set
+    s_feat = extract_features({'main_ball1': s[0], 'main_ball2': s[1], 'main_ball3': s[2], 'main_ball4': s[3],
+        'main_ball5': s[4]})
+
+    # Model predicts how closely this matches historical 'winning' patterns
+    score = model.predict(s_feat.values.reshape(1, -1))[0]
+    results.append({'set': s, 'score': score})
+
+# Rank by score
+ranked_sets = pd.DataFrame(results).sort_values(by='score', ascending=False)
+
+# Get frequency counts
+counts = melted['number'].value_counts(normalize=True)
+
+def calc_prob(s):
+    return np.prod([counts.get(num, 0) for num in s])
+
+ranked_sets['statistical_prob'] = ranked_sets['set'].apply(calc_prob)
+
+game_counts = df['game_ball'].value_counts(normalize=True)
+
+def calc_total_prob(row):
+    # calculate prob for the 5 main balls
+    five_ball_prob = np.prod([counts.get(num, 0) for num in row['set']])
+    # multiply the prob of the specific game ball
+    game_prob = game_counts.get(row['game_ball'], 0)
+    return five_ball_prob * game_prob
+
+ranked_sets['total_prob'] = ranked_sets.apply(calc_total_prob, axis=1)
+
+"""

lottery_predictor/draw.py

@@ -11,6 +11,6 @@ def generate_random_ticket(max_main: int, max_game: int, num_main: int = 5) -> t
 
     :returns: A tuple of (main_balls, game_ball)
     """
-    main_balls = random.sample(range(1, max_main + 1), num_main)
+    main_balls = random.sample(range(1, max_main), num_main)
-    game_ball = random.randint(1, max_game + 1)
+    game_ball = random.randint(1, max_game)
     return sorted(main_balls), game_ball

tests/lottery_predictor/test_analyze.py

@@ -9,9 +9,9 @@ def test_load_dataframe() -> None:
     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
+        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
+        table_name='MegaMillionsDraw', start_date=mm_start, end_date=date_end).count()['draw_date']) == 96
     with pytest.raises(ValueError):
         analyze.load_dataframe(table_name='SomNonExistentTableName')
 

tests/util/test_util.py

@@ -144,4 +144,4 @@ def test_load_environment_variables() -> None:
     """test loading environment variables for script use"""
     env_vars = ue.load_environment_variables()
     assert type(env_vars) == dict
-    assert len(env_vars) == 25
+    assert len(env_vars) == 24

util/scrape.py

@@ -1,7 +1,7 @@
 """
     util/scrape.py
 
-    Utility functions for scraping web data relative to selected games
+    Utility functions for scaping web data relative to selected games
 """
 import httpx
 from dateutil import parser, utils