Reformat code to pythonic standards

lottery_predictor/analyze.py

@@ -1,5 +1,6 @@
-from datetime import datetime
+import random
 from collections import Counter
+from datetime import datetime
 
 import numpy as np
 import pandas as pd
@@ -7,11 +8,12 @@ from sklearn.ensemble import RandomForestRegressor
 from sqlalchemy import select
 
 from data.database import Base, dal
-from lottery_predictor.config import RANDOM_SEED, GAME_INFO
+from lottery_predictor.config import GAME_INFO
 
 
 def load_dataframe_by_dates(
-        game: str, start_date: datetime | None = None, end_date: datetime | None = None
+        game: str, start_date: datetime | None = None,
+        end_date: datetime | None = None,
 ) -> pd.DataFrame:
     """
         :param game: the name of the game to get data for
@@ -29,12 +31,16 @@ def load_dataframe_by_dates(
         target_table = Base.metadata.tables.get(game_dict['db_table_name'])
         if start_date is not None and end_date is not None:
             sql_statement = (select(target_table)
-                .where(target_table.columns.draw_date >= start_date)
+                             .where(
+                target_table.columns.draw_date >= start_date,
+            )
                              .where(target_table.columns.draw_date <= end_date)
                              .order_by(target_table.columns.draw_date.desc()))
         elif start_date is not None and end_date is None:
             sql_statement = (select(target_table)
-                .where(target_table.columns.draw_date >= start_date)
+                             .where(
+                target_table.columns.draw_date >= start_date,
+            )
                              .order_by(target_table.columns.draw_date.desc()))
         elif start_date is None and end_date is not None:
             sql_statement = (select(target_table)
@@ -68,12 +74,15 @@ def load_dataframe_most_recent(game: str, limit: int = 10) -> pd.DataFrame:
                              .limit(limit))
             return pd.read_sql(sql_statement, session.bind)
         else:
-            raise ValueError('Limit must be a positive integer greater than zero.')
+            raise ValueError(
+                'Limit must be a positive integer greater than zero.',
+            )
     else:
         raise ValueError('An invalid table name was provided.')
 
 
-def prepare_split_data(data: np.ndarray, window_size: int = 10) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
+def prepare_split_data(data: np.ndarray, window_size: int = 10) -> tuple[
+    np.ndarray, np.ndarray, np.ndarray]:
     # Clean the data by removing the draw_date and multiplier columns
     clean_data = data[:, 1:7]
 
@@ -81,7 +90,7 @@ def prepare_split_data(data: np.ndarray, window_size: int = 10) -> tuple[np.ndar
     if len(clean_data) <= window_size:
         raise ValueError(
             f"Not enough data! Dataset has {len(clean_data)} rows, "
-            f"but window_size requires at least {window_size + 1} rows."
+            f"but window_size requires at least {window_size + 1} rows.",
         )
 
     # Calculate the indices for all windows at once
@@ -99,7 +108,11 @@ def prepare_split_data(data: np.ndarray, window_size: int = 10) -> tuple[np.ndar
     return x, y_field, y_game
 
 
-def make_prediction(data_frame: pd.DataFrame, window_size: int = 10) -> tuple[np.ndarray, np.ndarray]:
+def make_prediction(data_frame: pd.DataFrame, window_size: int = 10) -> tuple[
+    np.ndarray, np.ndarray]:
+    # Get a random number
+    state = random.randint(1000, 300_000)
+
     # Convert the data_frame to a numpy array for slicing
     data = data_frame.values
 
@@ -107,25 +120,27 @@ def make_prediction(data_frame: pd.DataFrame, window_size: int = 10) -> tuple[np
     x, y_field, y_game = prepare_split_data(data, window_size=window_size)
 
     # Train the model for the field balls
-    field_model = RandomForestRegressor(n_estimators=200, random_state=RANDOM_SEED)
+    field_model = RandomForestRegressor(n_estimators=200, random_state=state)
     field_model.fit(x, y_field)
 
     # Train the model for the game ball
-    game_model = RandomForestRegressor(n_estimators=200, random_state=RANDOM_SEED)
+    game_model = RandomForestRegressor(n_estimators=200, random_state=state)
     game_model.fit(x, y_game)
 
     # Predict the next draw
     clean_data = data[:, 1:7]
     current_window = clean_data[-window_size:].flatten().reshape(1, -1)
     # Get predictions and round to the nearest whole number
-    predicted_field = np.sort(np.round(field_model.predict(current_window)).astype(int))
+    predicted_field = np.sort(
+        np.round(field_model.predict(current_window)).astype(int),
+    )
     predicted_game = np.round(game_model.predict(current_window)).astype(int)
 
     return predicted_field[0], predicted_game[0]
 
 
 def get_most_common_number(
-        data_frame: pd.DataFrame, columns: list | None = None, top: int = 1
+        data_frame: pd.DataFrame, columns: list | None = None, top: int = 1,
 ) -> list[int]:
     """
     :param data_frame: a pandas DataFrame containing the data
@@ -135,14 +150,16 @@ def get_most_common_number(
     :returns: a list of the most common numbers
     """
     if columns is None:
-        columns = ['main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5']
+        columns = [
+            'main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5',
+        ]
     flat_numbers = data_frame[columns].values.flatten()
     counts = Counter(flat_numbers)
     return [int(num) for num, _ in counts.most_common(top)]
 
 
 def get_least_common_number(
-        data_frame: pd.DataFrame, columns: list | None = None, bottom: int = 1
+        data_frame: pd.DataFrame, columns: list | None = None, bottom: int = 1,
 ) -> list[int]:
     """
     :param data_frame: a pandas DataFrame containing the data
@@ -152,23 +169,30 @@ def get_least_common_number(
     :returns: a list of the least common numbers
     """
     if columns is None:
-        columns = ['main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5']
+        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([int(num) for num, _ in counts.most_common()[-bottom:]]))
+    return list(
+        reversed([int(num) for num, _ in counts.most_common()[-bottom:]]),
+    )
 
 
 def calculate_probabilities(
-        data_frame: pd.DataFrame, max_number: int, columns: list | None = None
+        data_frame: pd.DataFrame, max_number: int, columns: list | None = None,
 ) -> dict[int, float]:
     """
-    :param data_frame: A pandas DataFrame containing the data to calculate probabilities for
+    :param data_frame: A pandas DataFrame containing the data to calculate
+    probabilities for
     :param max_number: The maximum number possible in the data_frame
     :param columns: The list of column names to use from the data_frame
     :returns dict: A dictionary containing the probabilities
     """
     if columns is None:
-        columns = ['main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5']
+        columns = [
+            'main_ball1', 'main_ball2', 'main_ball3', 'main_ball4', 'main_ball5',
+        ]
     if data_frame.empty:
         return dict()
 
@@ -177,9 +201,11 @@ def calculate_probabilities(
     # count all the occurrences of each number
     counts = Counter(all_numbers)
     # calculate the basic probability of each number occurring again
-    probabilities = {num: counts.get(num, 0) / (max_number + 1) for num in range(1, max_number + 1)}
+    probabilities = {num: counts.get(num, 0) / (max_number + 1) for num in
+                     range(1, max_number + 1)}
 
-    # if any calculation is greater than one, use what is to the right of the decimal point as the value
+    # if any calculation is greater than one, use what is to the right of the
+    # decimal point as the value
     for key, value in probabilities.items():
         if value > 1:
             probabilities[key] = value - int(str(value).split('.')[0])
@@ -188,16 +214,20 @@ def calculate_probabilities(
     return probabilities
 
 
-def get_hot_numbers(probabilities: dict[int, float], top: int = 5) -> list[tuple[int, float]]:
+def get_hot_numbers(probabilities: dict[int, float], top: int = 5) -> list[
+    tuple[int, float]]:
     """
     :param probabilities: A dictionary containing the probabilities
     :param top: The count of hottest items to return, defaults to 5
     :returns list of tuples: A list of the hot numbers and their raw score
     """
-    return sorted(probabilities.items(), key=lambda item: item[1], reverse=True)[:top]
+    return sorted(
+        probabilities.items(), key=lambda item: item[1], reverse=True,
+    )[:top]
 
 
-def get_cold_numbers(probabilities: dict[int, float], bottom: int = 5) -> list[tuple[int, float]]:
+def get_cold_numbers(probabilities: dict[int, float], bottom: int = 5) -> list[
+    tuple[int, float]]:
     """
     :param probabilities: A dictionary containing the probabilities
     :param bottom: The count of coldest items to return, defaults to 5

lottery_predictor/collect.py

@@ -1,7 +1,8 @@
 """
     collect.py
 
-    Functions for collecting data for insertion into the databse or pulling data from the database for analysis
+    Functions for collecting data for insertion into the databse or pulling
+    data from the database for analysis
 """
 from datetime import datetime, timedelta
 from time import sleep
@@ -9,10 +10,10 @@ from time import sleep
 from sqlalchemy import func
 from sqlalchemy.exc import IntegrityError
 
-from data.database import Base, dal
-from lottery_predictor.config import GAME_INFO, PROJECT_VARIABLES
 import util.drawing as drawutil
 import util.scrape as scrapeutil
+from data.database import Base, dal
+from lottery_predictor.config import GAME_INFO, PROJECT_VARIABLES
 
 
 def get_record_count(game: str) -> int | None:
@@ -26,7 +27,8 @@ def get_record_count(game: str) -> int | None:
         dal.connect()
         session = dal.Session()
         target_table = Base.metadata.tables.get(game_dict['db_table_name'])
-        return session.query(func.count(target_table.columns.draw_date)).first()[0]
+        return \
+        session.query(func.count(target_table.columns.draw_date)).first()[0]
     else:
         raise ValueError('An invalid table name was specified.')
 
@@ -42,7 +44,8 @@ def get_recent_draw_date(game: str) -> datetime | None:
         dal.connect()
         session = dal.Session()
         target_table = Base.metadata.tables.get(game_dict['db_table_name'])
-        return session.query(func.max(target_table.columns.draw_date)).first()[0]
+        return session.query(func.max(target_table.columns.draw_date)).first()[
+            0]
     else:
         raise ValueError('An invalid table name was specified.')
 
@@ -67,20 +70,39 @@ def get_missing_records(game: str) -> int:
         record_count = get_record_count(game=game)
         target_game = game_dict['game_name']
         end_year = datetime.today().year + 1
-        recent_draw_date = (get_recent_draw_date(game=game) + timedelta(days=1)).strftime(date_format)
-        following_draw_date = datetime.strptime(drawutil.get_next_draw_date(game=target_game,
-            from_date=recent_draw_date), date_format)
-        start_year = game_dict['inception_year'] if record_count == 0 else following_draw_date.year
-        check_date = datetime.strptime(drawutil.get_previous_draw_date(game=target_game, from_date=
-             drawutil.get_next_draw_date(game=target_game)), date_format).date()
+        recent_draw_date = (get_recent_draw_date(game=game) + timedelta(
+            days=1,
+        )).strftime(
+            date_format,
+        )
+        following_draw_date = datetime.strptime(
+            drawutil.get_next_draw_date(
+                game=target_game,
+                from_date=recent_draw_date,
+            ), date_format,
+        )
+        start_year = game_dict[
+            'inception_year'] if record_count == 0 else following_draw_date.year
+        check_date = datetime.strptime(
+            drawutil.get_previous_draw_date(
+                game=target_game, from_date=
+                drawutil.get_next_draw_date(game=target_game),
+            ), date_format,
+        ).date()
 
-        if session.query(target_table).filter_by(draw_date=check_date).first() is None:
+        if session.query(target_table).filter_by(
+                draw_date=check_date,
+        ).first() is None:
             # loop over the range of years and insert missing records
             for year in range(start_year, end_year):
-                scrape_data = scrapeutil.scrape_game_history(game=target_game, year=year)
+                scrape_data = scrapeutil.scrape_game_history(
+                    game=target_game, year=year,
+                )
                 # convert and insert records, discarding duplicate dates
                 for draw_date, draw_info in scrape_data.items():
-                    record = game_dict['record_type'](draw_date=draw_date, draw_result=draw_info)
+                    record = game_dict['record_type'](
+                        draw_date=draw_date, draw_result=draw_info,
+                    )
                     try:
                         session.add(record)
                         session.commit()
@@ -88,7 +110,10 @@ def get_missing_records(game: str) -> int:
                     except IntegrityError:
                         session.rollback()
                 if year != end_year - 1:
-                    sleep(30) # sleep between calls to the site for data to avoid being blocked
+                    sleep(
+                        30,
+                    )  # sleep between calls to the site for data to
+                    # avoid being blocked
 
         return insert_count
     else:

lottery_predictor/config.py

@@ -1,8 +1,9 @@
 from data.database import MegaMillionsDraw, PowerballDraw
-from util.drawing import get_powerball_object, get_mega_millions_object
+from util.drawing import get_mega_millions_object, get_powerball_object
 from util.environment import load_environment_variables
 from util.scrape import project_variables
 
+
 PROJECT_VARIABLES = load_environment_variables()
 
 RANDOM_SEED = 42
@@ -13,10 +14,16 @@ GAME_INFO = {
         'db_table_name': 'mega_millions_draws',
         'inception_year': int(project_variables["LP_MEGA_MILLIONS_INCEPTION"]),
         'rule_change': project_variables["LP_MEGA_MILLIONS_RULE_CHANGE_DATE"],
-        'max_game_ball': int(project_variables["LP_MEGA_MILLIONS_MAX_MEGA_BALL"]),
-        'max_main_ball': int(project_variables["LP_MEGA_MILLIONS_MAX_MAIN_BALL"]),
+        'max_game_ball': int(
+            project_variables["LP_MEGA_MILLIONS_MAX_MEGA_BALL"],
+        ),
+        'max_main_ball': int(
+            project_variables["LP_MEGA_MILLIONS_MAX_MAIN_BALL"],
+        ),
+        'main_count': 5,
+        'game_ball_name': 'Mega Ball',
         'scrape_name': 'mega-millions',
-        'object_function': get_mega_millions_object
+        'object_function': get_mega_millions_object,
     },
     'Powerball': {
         'game_name': 'powerball',
@@ -26,7 +33,9 @@ GAME_INFO = {
         'rule_change': project_variables["LP_POWERBALL_RULE_CHANGE_DATE"],
         'max_game_ball': int(project_variables["LP_POWERBALL_MAX_MAIN_BALL"]),
         'max_main_ball': int(project_variables["LP_POWERBALL_MAX_POWERBALL"]),
+        'main_count': 5,
+        'game_ball_name': 'Powerball',
         'scrape_name': 'powerball',
-        'object_function': get_powerball_object
-    }
+        'object_function': get_powerball_object,
+    },
 }

lottery_predictor/draw.py

@@ -1,12 +1,15 @@
 import random
 
 
-def generate_random_ticket(max_main: int, max_game: int, num_main: int = 5) -> tuple[list[int], int]:
+def generate_random_ticket(max_main: int, max_game: int, num_main: int = 5) -> \
+tuple[list[int], int]:
     """
     Generate a random lottery ticket.
 
-    :param max_main: The maximum number in the range to choose from for main game balls
-    :param max_game: The maximum number in the range to choose from for the game ball
+    :param max_main: The maximum number in the range to choose from for main
+    game balls
+    :param max_game: The maximum number in the range to choose from for the
+    game ball
     :param num_main: The number of numbers that can be chosen in the main field
 
     :returns: A tuple of (main_balls, game_ball)