Add code for least/most common number and load_dataframe

lottery_predictor/analyze.py

@@ -0,0 +1,52 @@
+from collections import Counter
+
+import pandas as pd
+from sqlalchemy import select
+
+from data.database import Base, dal, project_variables
+import util.drawing as drawutil
+
+
+def load_dataframe(table_name: str, use_rule_change_date: bool = True) -> pd.DataFrame:
+    """connect to the database and load game data into a pandas dataframe"""
+
+    dal.connect()
+    session = dal.Session()
+
+    game_dict = drawutil.check_table_name(table_name=table_name)
+    if game_dict:
+        start_date = game_dict['rule_date'] if use_rule_change_date else None
+        target_table = Base.metadata.tables.get(game_dict['db_table_name'])
+        if start_date is not None:
+            sql_statement = select(target_table).where(target_table.columns.draw_date >= start_date)
+        else:
+            sql_statement = select(target_table)
+
+        return pd.read_sql(sql_statement, session.bind)
+    else:
+        raise ValueError('An invalid table name was provided')
+
+
+def get_most_common_number(
+        data_frame: pd.DataFrame,
+        columns: list | None = None,
+        top: int = 1
+    ) -> list[int]:
+    if columns is None:
+        columns = ['main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5']
+    flat_numbers = data_frame[columns].values.flatten()
+    counts = Counter(flat_numbers)
+    return [num for num, _ in counts.most_common(top)]
+
+
+def get_least_common_number(
+        data_frame: pd.DataFrame,
+        columns: list | None = None,
+        bottom: int = 1
+) -> list[int]:
+    if columns is None:
+        columns = ['main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5']
+    flat_numbers = data_frame[columns].values.flatten()
+    counts = Counter(flat_numbers)
+    return list(reversed([num for num, _ in counts.most_common()[-bottom:]]))
+