Finished refactoring and adding docstrings functions.

Added module-level docstrings to modules and cleaned up imports

builder_utils.py

@@ -1,49 +1,48 @@
-from typing import Dict, List, Tuple, Optional, Any, Callable, TypeVar, Union, cast
+"""Utility module for MTG deck building operations.
-import pandas as pd
+
-from price_check import PriceChecker
+This module provides utility functions for various deck building operations including:
-from input_handler import InputHandler
+- DataFrame validation and processing
-import logging
+- Card type counting and validation
+- Land selection and management
+- Theme processing and weighting
+- Price checking integration
+- Mana pip analysis
+
+The module serves as a central collection of helper functions used throughout the
+deck building process, handling data validation, card selection, and various
+deck composition calculations.
+
+Key Features:
+- DataFrame validation with timeout handling
+- Card type counting and categorization
+- Land type validation and selection (basic, fetch, dual, etc.)
+- Theme tag processing and weighting calculations
+- Mana pip counting and color distribution analysis
+
+Typical usage example:
+    >>> df = load_commander_data()
+    >>> validate_dataframe(df, DATAFRAME_VALIDATION_RULES)
+    >>> process_dataframe_batch(df)
+    >>> count_cards_by_type(df, ['Creature', 'Instant', 'Sorcery'])
+"""
+
+# Standard library imports
 import functools
+import logging
 import time
+from typing import Any, Callable, Dict, List, Optional, Tuple, TypeVar, Union, cast
+
+# Third-party imports
 import pandas as pd
 from fuzzywuzzy import process
-from settings import (
+
-    COMMANDER_CSV_PATH,
+# Local application imports
-    FUZZY_MATCH_THRESHOLD,
-    MAX_FUZZY_CHOICES,
-    COMMANDER_CONVERTERS,
-    DATAFRAME_VALIDATION_RULES,
-    DATAFRAME_VALIDATION_TIMEOUT,
-    DATAFRAME_BATCH_SIZE,
-    DATAFRAME_TRANSFORM_TIMEOUT,
-    DATAFRAME_REQUIRED_COLUMNS,
-    WEIGHT_ADJUSTMENT_FACTORS,
-    DEFAULT_MAX_DECK_PRICE,
-    DEFAULT_MAX_CARD_PRICE,
-    DECK_COMPOSITION_PROMPTS,
-    DEFAULT_RAMP_COUNT,
-    DEFAULT_LAND_COUNT,
-    DEFAULT_BASIC_LAND_COUNT,
-    DEFAULT_CREATURE_COUNT,
-    DEFAULT_REMOVAL_COUNT,
-    DEFAULT_CARD_ADVANTAGE_COUNT,
-    DEFAULT_PROTECTION_COUNT,
-    DEFAULT_WIPES_COUNT,
-    CARD_TYPE_SORT_ORDER,
-    DUPLICATE_CARD_FORMAT,
-    COLOR_TO_BASIC_LAND,
-    SNOW_BASIC_LAND_MAPPING,
-    KINDRED_STAPLE_LANDS,
-    DUAL_LAND_TYPE_MAP,
-    MANA_COLORS,
-    MANA_PIP_PATTERNS
-)
 from exceptions import (
+    CSVValidationError,
+    DataFrameTimeoutError,
+    DataFrameValidationError,
     DeckBuilderError,
     DuplicateCardError,
-    CSVValidationError,
-    DataFrameValidationError,
-    DataFrameTimeoutError,
     EmptyDataFrameError,
     FetchLandSelectionError,
     FetchLandValidationError,
@@ -54,6 +53,24 @@ from exceptions import (
     ThemeWeightError,
     CardTypeCountError
 )
+from input_handler import InputHandler
+from price_check import PriceChecker
+from settings import (
+    CARD_TYPE_SORT_ORDER, COLOR_TO_BASIC_LAND, COMMANDER_CONVERTERS,
+    COMMANDER_CSV_PATH, DATAFRAME_BATCH_SIZE,
+    DATAFRAME_REQUIRED_COLUMNS, DATAFRAME_TRANSFORM_TIMEOUT,
+    DATAFRAME_VALIDATION_RULES, DATAFRAME_VALIDATION_TIMEOUT,
+    DECK_COMPOSITION_PROMPTS, DEFAULT_BASIC_LAND_COUNT,
+    DEFAULT_CARD_ADVANTAGE_COUNT, DEFAULT_CREATURE_COUNT,
+    DEFAULT_LAND_COUNT, DEFAULT_MAX_CARD_PRICE, DEFAULT_MAX_DECK_PRICE,
+    DEFAULT_PROTECTION_COUNT, DEFAULT_RAMP_COUNT,
+    DEFAULT_REMOVAL_COUNT, DEFAULT_WIPES_COUNT, DUAL_LAND_TYPE_MAP,
+    DUPLICATE_CARD_FORMAT, FUZZY_MATCH_THRESHOLD, KINDRED_STAPLE_LANDS,
+    MANA_COLORS, MANA_PIP_PATTERNS, MAX_FUZZY_CHOICES,
+    SNOW_BASIC_LAND_MAPPING, THEME_POOL_SIZE_MULTIPLIER,
+    WEIGHT_ADJUSTMENT_FACTORS
+)
+from type_definitions import CardLibraryDF, CommanderDF, LandDF
 
 logging.basicConfig(
     level=logging.INFO,
@@ -61,7 +78,6 @@ logging.basicConfig(
 )
 
 logger = logging.getLogger(__name__)
-
 # Type variables for generic functions
 T = TypeVar('T')
 DataFrame = TypeVar('DataFrame', bound=pd.DataFrame)
@@ -431,7 +447,6 @@ def adjust_theme_weights(primary_theme: str,
         if total_weight > 0:
             adjusted_weights = {k: round(v/total_weight, 2) for k, v in adjusted_weights.items()}
 
-        print(adjusted_weights)
         return adjusted_weights
 
     except Exception as e:
@@ -1404,6 +1419,162 @@ def select_land_for_removal(filtered_lands: pd.DataFrame) -> Tuple[int, str]:
         logger.error(f"Error selecting land for removal: {e}")
         raise
     
+def get_card_theme_overlap(card_tags: List[str], deck_themes: List[str]) -> int:
+    """Count how many deck themes a given card matches.
+
+    Args:
+        card_tags: List of tags associated with the card
+        deck_themes: List of themes in the deck
+
+    Returns:
+        Number of deck themes that match the card's tags
+
+    Example:
+        >>> card_tags = ['Artifacts Matter', 'Token Creation', 'Sacrifice']
+        >>> deck_themes = ['Artifacts Matter', 'Sacrifice Matters']
+        >>> get_card_theme_overlap(card_tags, deck_themes)
+        2
+    """
+    if not card_tags or not deck_themes:
+        return 0
+
+    # Convert to sets for efficient intersection
+    card_tag_set = set(card_tags)
+    deck_theme_set = set(deck_themes)
+
+    # Count overlapping themes
+    return len(card_tag_set.intersection(deck_theme_set))
+
+def calculate_theme_priority(card_tags: List[str], deck_themes: List[str], THEME_PRIORITY_BONUS: float) -> float:
+    """Calculate priority score for a card based on theme overlap.
+
+    Args:
+        card_tags: List of tags associated with the card
+        deck_themes: List of themes in the deck
+        THEME_PRIORITY_BONUS: Bonus multiplier for each additional theme match
+
+    Returns:
+        Priority score for the card (higher means more theme overlap)
+
+    Example:
+        >>> card_tags = ['Artifacts Matter', 'Token Creation', 'Sacrifice']
+        >>> deck_themes = ['Artifacts Matter', 'Sacrifice Matters']
+        >>> calculate_theme_priority(card_tags, deck_themes, 1.2)
+        1.44  # Base score of 1.0 * (1.2 ^ 2) for two theme matches
+    """
+    overlap_count = get_card_theme_overlap(card_tags, deck_themes)
+    if overlap_count == 0:
+        return 0.0
+
+    # Calculate priority score with exponential bonus for multiple matches
+    return pow(THEME_PRIORITY_BONUS, overlap_count)
+
+def calculate_weighted_pool_size(ideal_count: int, weight: float, multiplier: float = THEME_POOL_SIZE_MULTIPLIER) -> int:
+    """Calculate the size of the initial card pool based on ideal count and weight.
+
+    Args:
+        ideal_count: Target number of cards to select
+        weight: Theme weight factor (0.0-1.0)
+        multiplier: Pool size multiplier (default from settings)
+
+    Returns:
+        Calculated pool size
+
+    Example:
+        >>> calculate_weighted_pool_size(10, 0.8, 2.0)
+        16
+    """
+    return int(ideal_count * weight * multiplier)
+
+def filter_theme_cards(df: pd.DataFrame, themes: List[str], pool_size: int) -> pd.DataFrame:
+    """Filter cards by theme and return top cards by EDHREC rank.
+
+    Args:
+        df: Source DataFrame to filter
+        themes: List of theme tags to filter by
+        pool_size: Number of cards to return
+
+    Returns:
+        Filtered DataFrame with top cards
+
+    Raises:
+        ValueError: If themes is None or contains invalid values
+        TypeError: If themes is not a list
+
+    Example:
+        >>> filtered_df = filter_theme_cards(cards_df, ['Artifacts Matter', 'Token Creation'], 20)
+    """
+    # Input validation
+    if themes is None:
+        raise ValueError("themes parameter cannot be None")
+        
+    if not isinstance(themes, list):
+        raise TypeError("themes must be a list of strings")
+        
+    if not all(isinstance(theme, str) for theme in themes):
+        raise ValueError("all themes must be strings")
+        
+    if not themes:
+        return pd.DataFrame()  # Return empty DataFrame for empty themes list
+
+    # Create copy to avoid modifying original
+    filtered_df = df.copy()
+
+    # Filter by theme
+    filtered_df = filtered_df[filtered_df['themeTags'].apply(
+        lambda x: any(theme in x for theme in themes) if isinstance(x, list) else False
+    )]
+
+    # Sort by EDHREC rank and take top cards
+    filtered_df.sort_values('edhrecRank', inplace=True)
+    return filtered_df.head(pool_size)
+
+def select_weighted_cards(
+    card_pool: pd.DataFrame,
+    target_count: int,
+    price_checker: Optional[Any] = None,
+    max_price: Optional[float] = None
+) -> List[Dict[str, Any]]:
+    """Select cards from pool considering price constraints.
+
+    Args:
+        card_pool: DataFrame of candidate cards
+        target_count: Number of cards to select
+        price_checker: Optional price checker instance
+        max_price: Maximum allowed price per card
+
+    Returns:
+        List of selected card dictionaries
+
+    Example:
+        >>> selected = select_weighted_cards(pool_df, 5, price_checker, 10.0)
+    """
+    selected_cards = []
+
+    for _, card in card_pool.iterrows():
+        if len(selected_cards) >= target_count:
+            break
+
+        # Check price if enabled
+        if price_checker and max_price:
+            try:
+                price = price_checker.get_card_price(card['name'])
+                if price > max_price * 1.1:
+                    continue
+            except Exception as e:
+                logger.warning(f"Price check failed for {card['name']}: {e}")
+                continue
+
+        selected_cards.append({
+            'name': card['name'],
+            'type': card['type'],
+            'manaCost': card['manaCost'],
+            'manaValue': card['manaValue'],
+            'themeTags': card['themeTags']
+        })
+
+    return selected_cards
+
 def count_color_pips(mana_costs: pd.Series, color: str) -> int:
     """Count the number of colored mana pips of a specific color in mana costs.
 

deck_builder.py

@@ -20,16 +20,16 @@ from settings import (
     COMMANDER_CSV_PATH, FUZZY_MATCH_THRESHOLD, MAX_FUZZY_CHOICES, FETCH_LAND_DEFAULT_COUNT,
     COMMANDER_POWER_DEFAULT, COMMANDER_TOUGHNESS_DEFAULT, COMMANDER_MANA_COST_DEFAULT,
     COMMANDER_MANA_VALUE_DEFAULT, COMMANDER_TYPE_DEFAULT, COMMANDER_TEXT_DEFAULT, 
+    THEME_PRIORITY_BONUS, THEME_POOL_SIZE_MULTIPLIER,
     COMMANDER_COLOR_IDENTITY_DEFAULT, COMMANDER_COLORS_DEFAULT, COMMANDER_TAGS_DEFAULT, 
     COMMANDER_THEMES_DEFAULT, COMMANDER_CREATURE_TYPES_DEFAULT, DUAL_LAND_TYPE_MAP,
     CSV_READ_TIMEOUT, CSV_PROCESSING_BATCH_SIZE, CSV_VALIDATION_RULES, CSV_REQUIRED_COLUMNS,
     STAPLE_LAND_CONDITIONS, TRIPLE_LAND_TYPE_MAP, MISC_LAND_MAX_COUNT, MISC_LAND_MIN_COUNT,
     MISC_LAND_POOL_SIZE, LAND_REMOVAL_MAX_ATTEMPTS, PROTECTED_LANDS,
-    MANA_COLORS, MANA_PIP_PATTERNS
+    MANA_COLORS, MANA_PIP_PATTERNS, THEME_WEIGHT_MULTIPLIER
 )
 import builder_utils
 import setup_utils
-from setup import determine_commanders
 from input_handler import InputHandler
 from exceptions import (
     BasicLandCountError,
@@ -37,7 +37,6 @@ from exceptions import (
     CommanderMoveError,
     CardTypeCountError,
     CommanderColorError,
-    CommanderLoadError,
     CommanderSelectionError, 
     CommanderValidationError,
     CSVError,
@@ -48,16 +47,12 @@ from exceptions import (
     DuplicateCardError,
     DeckBuilderError,
     EmptyDataFrameError,
-    EmptyInputError,
     FetchLandSelectionError,
     FetchLandValidationError,
     IdealDeterminationError,
-    InvalidNumberError,
-    InvalidQuestionTypeError,
     LandRemovalError,
     LibraryOrganizationError,
     LibrarySortError,
-    MaxAttemptsError,
     PriceAPIError,
     PriceConfigurationError,
     PriceLimitError, 
@@ -66,18 +61,21 @@ from exceptions import (
     ThemeSelectionError,
     ThemeWeightError,
     StapleLandError,
-    StapleLandError,
+    ManaPipError,
-    ManaPipError
+    ThemeTagError,
+    ThemeWeightingError,
+    ThemePoolError
 )
 from type_definitions import (
-    CardDict,
     CommanderDict,
     CardLibraryDF,
     CommanderDF,
     LandDF,
     ArtifactDF,
     CreatureDF,
-    NonCreatureDF)
+    NonCreatureDF,
+    PlaneswalkerDF,
+    NonPlaneswalkerDF)
 
 # Try to import scrython and price_checker
 try:
@@ -102,19 +100,6 @@ pd.set_option('display.max_columns', None)
 pd.set_option('display.max_rows', None)
 pd.set_option('display.max_colwidth', 50)
 
-"""
-Basic deck builder, primarily intended for building Kindred decks.
-Logic for other themes (such as Spellslinger or Wheels), is added.
-I plan to also implement having it recommend a commander or themes.
-
-Currently, the script will ask questions to determine number of 
-creatures, lands, interaction, ramp, etc... then add cards and 
-adjust from there.
-
-Land spread will ideally be handled based on pips and some adjustment
-is planned based on mana curve and ramp added.
-"""
-
 def new_line(num_lines: int = 1) -> None:
     """Print specified number of newlines for formatting output.
 
@@ -149,9 +134,10 @@ class DeckBuilder:
         self.artifact_df: ArtifactDF = pd.DataFrame()
         self.creature_df: CreatureDF = pd.DataFrame()
         self.noncreature_df: NonCreatureDF = pd.DataFrame()
-        
+        self.nonplaneswalker_df: NonPlaneswalkerDF = pd.DataFrame()
         # Initialize other attributes with type hints
         self.commander_info: Dict = {}
+        self.max_card_price: Optional[float] = None
         self.commander_dict: CommanderDict = {}
         self.commander: str = ''
         self.commander_type: str = ''
@@ -764,7 +750,7 @@ class DeckBuilder:
             
             # Remove lands from main DataFrame
             df = df[~df['type'].str.contains('Land')]
-            df.to_csv(f'{CSV_DIRECTORY}/test_cards.csv')
+            df.to_csv(f'{CSV_DIRECTORY}/test_cards.csv', index=False)
             
             # Create specialized frames
             self.artifact_df = df[df['type'].str.contains('Artifact')].copy()
@@ -774,9 +760,10 @@ class DeckBuilder:
             self.enchantment_df = df[df['type'].str.contains('Enchantment')].copy()
             self.instant_df = df[df['type'].str.contains('Instant')].copy()
             self.planeswalker_df = df[df['type'].str.contains('Planeswalker')].copy()
+            self.nonplaneswalker_df = df[~df['type'].str.contains('Planeswalker')].copy()
             self.sorcery_df = df[df['type'].str.contains('Sorcery')].copy()
 
-            self.battle_df.to_csv(f'{CSV_DIRECTORY}/test_battle_cards.csv')
+            self.battle_df.to_csv(f'{CSV_DIRECTORY}/test_battle_cards.csv', index=False)
             
             # Sort all frames
             for frame in [self.artifact_df, self.battle_df, self.creature_df,
@@ -859,8 +846,9 @@ class DeckBuilder:
         try:
             # Load and combine data
             self.full_df = self._load_and_combine_data()
+            self.full_df = self.full_df[~self.full_df['name'].str.contains(self.commander)]
             self.full_df.sort_values(by='edhrecRank', inplace=True)
-            self.full_df.to_csv(f'{CSV_DIRECTORY}/test_full_cards.csv')
+            self.full_df.to_csv(f'{CSV_DIRECTORY}/test_full_cards.csv', index=False)
             
             # Split into specialized frames
             self._split_into_specialized_frames(self.full_df)
@@ -962,7 +950,6 @@ class DeckBuilder:
                         self.tertiary_theme,
                         self.weights
                     )
-                    print(self.weights)
                     self.primary_weight = self.weights['primary']
                     self.secondary_weight = self.weights['secondary']
                     self.tertiary_weight = self.weights['tertiary']
@@ -972,8 +959,7 @@ class DeckBuilder:
             if self.secondary_theme:
                 self.themes.append(self.secondary_theme)
             if self.tertiary_theme:
-                self.themes.append(self.tertiary_theme)
+                self.themes.append
-            print(self.weights)
             self.determine_hidden_themes()
 
         except (ThemeSelectionError, ThemeWeightError) as e:
@@ -1323,7 +1309,7 @@ class DeckBuilder:
         6. Add miscellaneous utility lands
         7. Adjust total land count to match ideal count
         """
-        MAX_ADJUSTMENT_ATTEMPTS = 10
+        MAX_ADJUSTMENT_ATTEMPTS = (self.ideal_land_count - self.min_basics) * 1.5
         self.total_basics = 0
         
         try:
@@ -2032,222 +2018,395 @@ class DeckBuilder:
             logger.error(f"Error calculating CMC: {e}")
             self.cmc = 0.0
     
-    def weight_by_theme(self, tag, ideal=1, weight=1, df=None):
+    def weight_by_theme(self, tag: str, ideal: int = 1, weight: float = 1.0, df: Optional[pd.DataFrame] = None) -> None:
-        # First grab the first 50/30/20 cards that match each theme
+        """Add cards with specific tag up to weighted ideal count.
-        """Add cards with specific tag up to ideal_value count"""
-        ideal_value = math.ceil(ideal * weight * 0.9)
-        print(f'Finding {ideal_value} cards with the "{tag}" tag...')
-        if 'Kindred' in tag:
-            tags = [tag, 'Kindred Support']
-        else:
-            tags = [tag]
-        # Filter cards with the given tag
-        tag_df = df.copy()
-        tag_df.sort_values(by='edhrecRank', inplace=True)
-        tag_df = tag_df[tag_df['themeTags'].apply(lambda x: any(tag in x for tag in tags))]
-        # Take top cards based on ideal value
-        pool_size = int(ideal_value * random.randint(15, 20) /10)
-        tag_df = tag_df.head(pool_size)
-        
-        # Convert to list of card dictionaries
-        card_pool = [
-            {
-                'name': row['name'],
-                'type': row['type'],
-                'manaCost': row['manaCost'],
-                'manaValue': row['manaValue'],
-                'creatureTypes': row['creatureTypes'],
-                'themeTags': row['themeTags']
-            }
-            for _, row in tag_df.iterrows()
-        ]
 
-        # Randomly select cards up to ideal value
+        Args:
-        cards_to_add = []
+            tag: Theme tag to filter cards by
-        while len(cards_to_add) < ideal_value and card_pool:
+            ideal: Target number of cards to add
-            card = random.choice(card_pool)
+            weight: Theme weight factor (0.0-1.0)
-            card_pool.remove(card)
+            df: Source DataFrame to filter cards from
+
+        Raises:
+            ThemeWeightingError: If weight calculation fails
+            ThemePoolError: If card pool is empty or insufficient
+        """
+        try:
+            # Calculate target card count using weight and safety multiplier
+            target_count = math.ceil(ideal * weight * THEME_WEIGHT_MULTIPLIER)
+            logger.info(f'Finding {target_count} cards with the "{tag}" tag...')
+
+            # Handle Kindred theme special case
+            tags = [tag, 'Kindred Support'] if 'Kindred' in tag else [tag]
+
+            # Calculate initial pool size
+            pool_size = builder_utils.calculate_weighted_pool_size(target_count, weight)
+
+            # Filter cards by theme
+            if df is None:
+                raise ThemePoolError(f"No source DataFrame provided for theme {tag}")
             
-            # Check price constraints if enabled
+            tag_df = builder_utils.filter_theme_cards(df, tags, pool_size)
-            if use_scrython and self.set_max_card_price:
+            if tag_df.empty:
-                price = self.price_checker.get_card_price(card['name'])
+                raise ThemePoolError(f"No cards found for theme {tag}")
-                if price > self.max_card_price * 1.1:
+
-                    continue
+            # Select cards considering price and duplicates
+            selected_cards = builder_utils.select_weighted_cards(
+                tag_df,
+                target_count,
+                self.price_checker if use_scrython else None,
+                self.max_card_price if hasattr(self, 'max_card_price') else None
+            )
+
+            # Process selected cards
+            cards_added = []
+            for card in selected_cards:
+                # Handle multiple copy cards
+                if card['name'] in multiple_copy_cards:
+                    copies = {
+                        'Nazgûl': 9,
+                        'Seven Dwarves': 7
+                    }.get(card['name'], target_count - len(cards_added))
                     
-            # Add card if not already in library
+                    for _ in range(copies):
-            
+                        cards_added.append(card)
-            if card['name'] in multiple_copy_cards:
+                        
-                if card['name'] == 'Nazgûl':
+                # Handle regular cards
-                    for _ in range(9):
+                elif card['name'] not in self.card_library['Card Name'].values:
-                        cards_to_add.append(card)
+                    cards_added.append(card)
-                elif card['name'] == 'Seven Dwarves':
-                    for _ in range(7):
-                        cards_to_add.append(card)
                 else:
-                    num_to_add = ideal_value - len(cards_to_add)
+                    logger.warning(f"{card['name']} already in Library, skipping it.")
-                    for _ in range(num_to_add):
+
-                        cards_to_add.append(card)
+            # Add selected cards to library
-            
+            for card in cards_added:
-            elif (card['name'] not in multiple_copy_cards
+                self.add_card(
-                  and card['name'] not in self.card_library['Card Name'].values):
+                    card['name'],
-                cards_to_add.append(card)
+                    card['type'],
-                
+                    card['manaCost'],
-            elif (card['name'] not in multiple_copy_cards
+                    card['manaValue'],
-                  and card['name'] in self.card_library['Card Name'].values):
+                    card.get('creatureTypes'),
-                logger.warning(f"{card['name']} already in Library, skipping it.")
+                    card['themeTags']
-                continue
+                )
-        
+
-        # Add selected cards to library
+            # Update DataFrames
-        for card in cards_to_add:
+            used_cards = {card['name'] for card in selected_cards}
-            self.add_card(card['name'], card['type'], 
+            self.noncreature_df = self.noncreature_df[~self.noncreature_df['name'].isin(used_cards)]
-                         card['manaCost'], card['manaValue'],
+
-                         card['creatureTypes'], card['themeTags'])
+            logger.info(f'Added {len(cards_added)} {tag} cards')
-        
+            for card in cards_added:
-        card_pool_names = [item['name'] for item in card_pool]
+                print(card['name'])
-        self.full_df = self.full_df[~self.full_df['name'].isin(card_pool_names)]
+
-        self.noncreature_df = self.noncreature_df[~self.noncreature_df['name'].isin(card_pool_names)]
+        except (ThemeWeightingError, ThemePoolError) as e:
-        logger.info(f'Added {len(cards_to_add)} {tag} cards')
+            logger.error(f"Error in weight_by_theme: {e}")
-        #tag_df.to_csv(f'{CSV_DIRECTORY}/test_{tag}.csv', index=False)
+            raise
+        except Exception as e:
+            logger.error(f"Unexpected error in weight_by_theme: {e}")
+            raise ThemeWeightingError(f"Failed to process theme {tag}: {str(e)}")
     
-    def add_by_tags(self, tag, ideal_value=1, df=None):
+    def add_by_tags(self, tag, ideal_value=1, df=None, ignore_existing=False):
-        """Add cards with specific tag up to ideal_value count"""
+        """Add cards with specific tag up to ideal_value count.
-        print(f'Finding {ideal_value} cards with the "{tag}" tag...')
+        Args:
+            tag: The theme tag to filter cards by
+            ideal_value: Target number of cards to add
+            df: DataFrame containing candidate cards
 
-        # Filter cards with the given tag
+        Raises:
-        skip_creatures = self.creature_cards > self.ideal_creature_count * 1.1
+            ThemeTagError: If there are issues with tag processing or card selection
-        tag_df = df.copy()
+        """
-        tag_df.sort_values(by='edhrecRank', inplace=True)
+        try:
-        tag_df = tag_df[tag_df['themeTags'].apply(lambda x: tag in x)]
+            # Count existing cards with target tag
-        # Take top cards based on ideal value
+            print()
-        pool_size = int(ideal_value * random.randint(2, 3))
+            if not ignore_existing:
-        tag_df = tag_df.head(pool_size)
+                existing_count = len(self.card_library[self.card_library['Themes'].apply(lambda x: x is not None and tag in x)])
-
+                remaining_slots = max(0, ideal_value - existing_count + 1)
-        # Convert to list of card dictionaries
-        card_pool = [
-            {
-                'name': row['name'],
-                'type': row['type'],
-                'manaCost': row['manaCost'],
-                'manaValue': row['manaValue'],
-                'creatureTypes': row['creatureTypes'],
-                'themeTags': row['themeTags']
-            }
-            for _, row in tag_df.iterrows()
-        ]
-
-        # Randomly select cards up to ideal value
-        cards_to_add = []
-        while len(cards_to_add) < ideal_value and card_pool:
-            card = random.choice(card_pool)
-            card_pool.remove(card)
-
-            # Check price constraints if enabled
-            if use_scrython and self.set_max_card_price:
-                price = self.price_checker.get_card_price(card['name'])
-                if price > self.max_card_price * 1.1:
-                    continue
-
-            # Add card if not already in library
-            if card['name'] not in self.card_library['Card Name'].values:
-                if 'Creature' in card['type'] and skip_creatures:
-                    continue
-                else:
-                    if 'Creature' in card['type']:
-                        self.creature_cards += 1
-                        skip_creatures = self.creature_cards > self.ideal_creature_count * 1.1
-                    cards_to_add.append(card)
-
-        # Add selected cards to library
-        for card in cards_to_add:
-            if len(self.card_library) < 100:
-                self.add_card(card['name'], card['type'],
-                              card['manaCost'], card['manaValue'],
-                              card['creatureTypes'], card['themeTags'])
             else:
-                continue
+                existing_count = 0
+                remaining_slots = max(0, ideal_value - existing_count + 1)
 
-        card_pool_names = [item['name'] for item in card_pool]
+            if remaining_slots == 0:
-        self.full_df = self.full_df[~self.full_df['name'].isin(card_pool_names)]
+                if not ignore_existing:
-        self.noncreature_df = self.noncreature_df[~self.noncreature_df['name'].isin(card_pool_names)]
+                    logger.info(f'Already have {existing_count} cards with tag "{tag}" - no additional cards needed')
-        logger.info(f'Added {len(cards_to_add)} {tag} cards')
+                    return
-        #tag_df.to_csv(f'{CSV_DIRECTORY}/test_{tag}.csv', index=False)
+                else:
+                    logger.info(f'Already have {ideal_value} cards with tag "{tag}" - no additional cards needed')
+                    return
+
+            logger.info(f'Finding {remaining_slots} additional cards with the "{tag}" tag...')
+
+            # Filter cards with the given tag
+            skip_creatures = self.creature_cards > self.ideal_creature_count * 1.1
+            tag_df = df.copy()
+            tag_df.sort_values(by='edhrecRank', inplace=True)
+            tag_df = tag_df[tag_df['themeTags'].apply(lambda x: x is not None and tag in x)]
+
+            # Calculate initial pool size using THEME_POOL_SIZE_MULTIPLIER
+            pool_size = int(remaining_slots * THEME_POOL_SIZE_MULTIPLIER)
+            tag_df = tag_df.head(pool_size)
+
+            # Convert to list of card dictionaries with priority scores
+            card_pool = []
+            for _, row in tag_df.iterrows():
+                theme_tags = row['themeTags'] if row['themeTags'] is not None else []
+                priority = builder_utils.calculate_theme_priority(theme_tags, self.themes, THEME_PRIORITY_BONUS)
+                card_pool.append({
+                    'name': row['name'],
+                    'type': row['type'],
+                    'manaCost': row['manaCost'],
+                    'manaValue': row['manaValue'],
+                    'creatureTypes': row['creatureTypes'],
+                    'themeTags': theme_tags,
+                    'priority': priority
+                })
+
+            # Sort card pool by priority score
+            card_pool.sort(key=lambda x: x['priority'], reverse=True)
+
+            # Select cards up to remaining slots
+            cards_to_add = []
+            for card in card_pool:
+                if len(cards_to_add) >= remaining_slots:
+                    break
+
+                # Check price constraints if enabled
+                if use_scrython and hasattr(self, 'max_card_price') and self.max_card_price:
+                    price = self.price_checker.get_card_price(card['name'])
+                    if price > self.max_card_price * 1.1:
+                        continue
+
+                # Handle multiple-copy cards
+                if card['name'] in multiple_copy_cards:
+                    existing_copies = len(self.card_library[self.card_library['Card Name'] == card['name']])
+                    if existing_copies < ideal_value:
+                        cards_to_add.append(card)
+                    continue
+
+                # Add new cards if not already in library
+                if card['name'] not in self.card_library['Card Name'].values:
+                    if 'Creature' in card['type'] and skip_creatures:
+                        continue
+                    else:
+                        if 'Creature' in card['type']:
+                            self.creature_cards += 1
+                            skip_creatures = self.creature_cards > self.ideal_creature_count * 1.1
+                        cards_to_add.append(card)
+
+            # Add selected cards to library
+            for card in cards_to_add:
+                if len(self.card_library) < 100:
+                    self.add_card(card['name'], card['type'],
+                                card['manaCost'], card['manaValue'],
+                                card['creatureTypes'], card['themeTags'])
+                else:
+                    break
+
+            # Update DataFrames
+            card_pool_names = [item['name'] for item in card_pool]
+            self.noncreature_df = self.noncreature_df[~self.noncreature_df['name'].isin(card_pool_names)]
+
+            logger.info(f'Added {len(cards_to_add)} {tag} cards (total with tag: {existing_count + len(cards_to_add)})')
+            for card in cards_to_add:
+                print(card['name'])
+
+        except Exception as e:
+            raise ThemeTagError(f"Error processing tag '{tag}'", {"error": str(e)})
         
     def add_creatures(self):
         """
-        Add creatures to the deck based on themes and self.weights.
+        Add creatures to the deck based on themes and weights.
         
         This method processes the primary, secondary, and tertiary themes to add
-        creatures proportionally according to their self.weights. The total number of
+        creatures proportionally according to their weights. The total number of
         creatures added will approximate the ideal_creature_count.
         
-        Themes are processed in order of importance (primary -> secondary -> tertiary)
+        The method follows this process:
-        with error handling to ensure the deck building process continues even if
+        1. Process hidden theme if present
-        a particular theme encounters issues.
+        2. Process primary theme
+        3. Process secondary theme if present
+        4. Process tertiary theme if present
+
+        Each theme is weighted according to its importance:
+        - Hidden theme: Highest priority if present
+        - Primary theme: Main focus
+        - Secondary theme: Supporting focus
+        - Tertiary theme: Minor focus
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        Raises:
+            ThemeWeightingError: If there are issues with theme weight calculations
+            ThemePoolError: If the card pool for a theme is insufficient
+            Exception: For any other unexpected errors during creature addition
+
+        Note:
+            The method uses error handling to ensure the deck building process
+            continues even if a particular theme encounters issues.
         """
-        print(f'Adding creatures to deck based on the ideal creature count of {self.ideal_creature_count}...')
+        print()
+        logger.info(f'Adding creatures to deck based on the ideal creature count of {self.ideal_creature_count}...')
         
         try:
             if self.hidden_theme:
-                print(f'Processing Hidden theme: {self.hidden_theme}')
+                print()
+                logger.info(f'Processing Hidden theme: {self.hidden_theme}')
                 self.weight_by_theme(self.hidden_theme, self.ideal_creature_count, self.hidden_weight, self.creature_df)
             
-            print(f'Processing primary theme: {self.primary_theme}')
+            logger.info(f'Processing primary theme: {self.primary_theme}')
             self.weight_by_theme(self.primary_theme, self.ideal_creature_count, self.primary_weight, self.creature_df)
             
             if self.secondary_theme:
-                print(f'Processing secondary theme: {self.secondary_theme}')
+                print()
+                logger.info(f'Processing secondary theme: {self.secondary_theme}')
                 self.weight_by_theme(self.secondary_theme, self.ideal_creature_count, self.secondary_weight, self.creature_df)
             
             if self.tertiary_theme:
-                print(f'Processing tertiary theme: {self.tertiary_theme}')
+                print()
+                logger.info(f'Processing tertiary theme: {self.tertiary_theme}')
                 self.weight_by_theme(self.tertiary_theme, self.ideal_creature_count, self.tertiary_weight, self.creature_df)
                 
         except Exception as e:
             logger.error(f"Error while adding creatures: {e}")
         finally:
             self.organize_library()
-            logger.info(f'Creature addition complete. Total creatures (including commander): {self.creature_cards}')
     
     def add_ramp(self):
+        """Add ramp cards to the deck based on ideal ramp count.
+
+        This method adds three categories of ramp cards:
+        1. Mana rocks (artifacts that produce mana) - ~1/3 of ideal ramp count
+        2. Mana dorks (creatures that produce mana) - ~1/4 of ideal ramp count
+        3. General ramp spells - remaining portion of ideal ramp count
+
+        The method uses the add_by_tags() helper to add cards from each category
+        while respecting the deck's themes and color identity.
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        Raises:
+            ThemeTagError: If there are issues adding cards with ramp-related tags
+        """
         try:
             self.add_by_tags('Mana Rock', math.ceil(self.ideal_ramp / 3), self.noncreature_df)
             self.add_by_tags('Mana Dork', math.ceil(self.ideal_ramp / 4), self.creature_df)
-            self.add_by_tags('Ramp', math.ceil(self.ideal_ramp / 2), self.noncreature_df)
+            self.add_by_tags('Ramp', self.ideal_ramp, self.noncreature_df)
         except Exception as e:
             logger.error(f"Error while adding Ramp: {e}")
-        finally:
+            
-            logger.info('Adding Ramp complete.')
-    
     def add_interaction(self):
+        """Add interaction cards to the deck for removal and protection.
+
+        This method adds two categories of interaction cards:
+        1. Removal spells based on ideal_removal count
+        2. Protection spells based on ideal_protection count
+
+        Cards are selected from non-planeswalker cards to ensure appropriate
+        interaction types are added.
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        Raises:
+            ThemeTagError: If there are issues adding cards with interaction-related tags
+        """
         try:
-            self.add_by_tags('Removal', self.ideal_removal, self.noncreature_nonplaneswaker_df)
+            self.add_by_tags('Removal', self.ideal_removal, self.nonplaneswalker_df)
-            self.add_by_tags('Protection', self.ideal_protection, self.noncreature_nonplaneswaker_df)
+            self.add_by_tags('Protection', self.ideal_protection, self.nonplaneswalker_df)
         except Exception as e:
             logger.error(f"Error while adding Interaction: {e}")
-        finally:
-            logger.info('Adding Interaction complete.')
         
     def add_board_wipes(self):
+        """Add board wipe cards to the deck.
+
+        This method adds board wipe cards based on the ideal_wipes count.
+        Board wipes are selected from the full card pool to include all possible
+        options across different card types.
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        Raises:
+            ThemeTagError: If there are issues adding cards with the 'Board Wipes' tag
+        """
         try:
             self.add_by_tags('Board Wipes', self.ideal_wipes, self.full_df)
         except Exception as e:
             logger.error(f"Error while adding Board Wipes: {e}")
-        finally:
-            logger.info('Adding Board Wipes complete.')
         
     def add_card_advantage(self):
+        """Add card advantage effects to the deck.
+
+        This method adds two categories of card draw effects:
+        1. Conditional draw effects (20% of ideal_card_advantage)
+           - Cards that draw based on specific conditions or triggers
+        2. Unconditional draw effects (80% of ideal_card_advantage)
+           - Cards that provide straightforward card draw
+
+        Cards are selected from appropriate pools while avoiding planeswalkers
+        for unconditional draw effects.
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        Raises:
+            ThemeTagError: If there are issues adding cards with draw-related tags
+        """
         try:
             self.add_by_tags('Conditional Draw', math.ceil(self.ideal_card_advantage * 0.2), self.full_df)
-            self.add_by_tags('Unconditional Draw', math.ceil(self.ideal_card_advantage * 0.8), self.noncreature_nonplaneswaker_df)
+            self.add_by_tags('Unconditional Draw', math.ceil(self.ideal_card_advantage * 0.8), self.nonplaneswalker_df)
         except Exception as e:
             logger.error(f"Error while adding Card Draw: {e}")
-        finally:
-            logger.info('Adding Card Draw complete.')
     
     def fill_out_deck(self):
-        """Fill out the deck to 100 cards with theme-appropriate cards."""
+        """Fill out the deck to 100 cards with theme-appropriate cards.
+
+        This method completes the deck by adding remaining cards up to the 100-card
+        requirement, prioritizing cards that match the deck's themes. The process
+        follows these steps:
+
+        1. Calculate how many cards are needed to reach 100
+        2. Add cards from each theme with weighted distribution:
+           - Hidden theme (if present)
+           - Tertiary theme (20% weight if present)
+           - Secondary theme (30% weight if present)
+           - Primary theme (50% weight)
+
+        The method includes safeguards:
+        - Maximum attempts limit to prevent infinite loops
+        - Timeout to prevent excessive runtime
+        - Progress tracking to break early if insufficient progress
+
+        Args:
+            None
+
+        Returns:
+            None
+
+        Raises:
+            ThemeTagError: If there are issues adding cards with specific theme tags
+            TimeoutError: If the process exceeds the maximum allowed time
+
+        Note:
+            If the deck cannot be filled to 100 cards, a warning message is logged
+            indicating manual additions may be needed.
+        """
+        print()
         logger.info('Filling out the Library to 100 with cards fitting the themes.')
-        
         cards_needed = 100 - len(self.card_library)
         if cards_needed <= 0:
             return
@@ -2274,38 +2433,57 @@ class DeckBuilder:
             
             try:
                 # Add cards from each theme with adjusted self.weights
-                if self.tertiary_theme:
+                if self.hidden_theme and remaining > 0:
+                    self.add_by_tags(self.hidden_theme, 
+                        math.ceil(weight_multiplier),
+                        self.full_df,
+                        True)
+                    
+                    # Adjust self.weights based on remaining cards needed
+                    remaining = 100 - len(self.card_library)
+                    weight_multiplier = remaining / cards_needed
+                if self.tertiary_theme and remaining > 0:
                     self.add_by_tags(self.tertiary_theme, 
-                        math.ceil(self.tertiary_weight * 10 * weight_multiplier),
+                        math.ceil(weight_multiplier * 0.2),
-                        self.noncreature_df)
+                        self.noncreature_df,
-                if self.secondary_theme:
+                        True)
+                    
+                if self.secondary_theme and remaining > 0:
                     self.add_by_tags(self.secondary_theme, 
-                        math.ceil(self.secondary_weight * 3 * weight_multiplier),
+                        math.ceil(weight_multiplier * 0.3),
-                        self.noncreature_df)
+                        self.noncreature_df,
-                self.add_by_tags(self.primary_theme, 
+                        True)
-                    math.ceil(self.primary_weight * 2 * weight_multiplier),
+                if remaining > 0:
-                    self.noncreature_df)
+                    self.add_by_tags(self.primary_theme, 
+                        math.ceil(weight_multiplier * 0.5),
+                        self.noncreature_df,
+                        True)
                 
                 # Check if we made progress
                 if len(self.card_library) == initial_count:
                     attempts += 1
                     if attempts % 5 == 0:
+                        print()
                         logger.warning(f"Made {attempts} attempts, still need {100 - len(self.card_library)} cards")
                         
                 # Break early if we're stuck
                 if attempts >= MAX_ATTEMPTS / 2 and len(self.card_library) < initial_count + (cards_needed / 4):
+                    print()
                     logger.warning("Insufficient progress being made, breaking early")
                     break
                     
             except Exception as e:
+                print()
                 logger.error(f"Error while adding cards: {e}")
                 attempts += 1
         
         final_count = len(self.card_library)
         if final_count < 100:
             message = f"\nWARNING: Deck is incomplete with {final_count} cards. Manual additions may be needed."
+            print()
             logger.warning(message)
         else:
+            print()
             logger.info(f"Successfully filled deck to {final_count} cards in {attempts} attempts")
 def main():
     """Main entry point for deck builder application."""

exceptions.py

@@ -1278,4 +1278,111 @@ class ManaPipError(DeckBuilderError):
             message,
             code="MANA_PIP_ERR",
             details=details
+        )
+
+class ThemeTagError(DeckBuilderError):
+    """Raised when there are issues processing theme tags.
+    
+    This exception is used when there are problems processing or validating theme tags,
+    such as invalid tag formats, missing required tags, or tag validation failures.
+    
+    Examples:
+        >>> raise ThemeTagError(
+        ...     "Invalid theme tag format",
+        ...     {"tag": "invalid#tag", "expected_format": "theme:subtheme"}
+        ... )
+        
+        >>> raise ThemeTagError(
+        ...     "Missing required theme tags",
+        ...     {"card_name": "Example Card", "required_tags": ["theme:tribal", "theme:synergy"]}
+        ... )
+    """
+    
+    def __init__(self, message: str, details: dict | None = None):
+        """Initialize theme tag error.
+        
+        Args:
+            message: Description of the theme tag processing failure
+            details: Additional context about the error
+        """
+        super().__init__(
+            message,
+            code="THEME_TAG_ERR",
+            details=details
+        )
+
+class ThemeWeightingError(DeckBuilderError):
+    """Raised when there are issues with theme-based card weighting.
+    
+    This exception is used when there are problems calculating or validating
+    theme weights, such as invalid weight values, calculation errors, or
+    inconsistencies in theme weight distribution.
+    
+    Examples:
+        >>> raise ThemeWeightingError(
+        ...     "Invalid theme weight value",
+        ...     {"theme": "tribal", "weight": -1, "valid_range": "0-100"}
+        ... )
+        
+        >>> raise ThemeWeightingError(
+        ...     "Theme weight calculation error",
+        ...     {"theme": "artifacts", "error": "Division by zero in weight normalization"}
+        ... )
+    """
+    
+    def __init__(self, message: str, details: dict | None = None):
+        """Initialize theme weighting error.
+        
+        Args:
+            message: Description of the theme weighting failure
+            details: Additional context about the error
+        """
+        super().__init__(
+            message,
+            code="THEME_WEIGHT_ERR",
+            details=details
+        )
+
+class ThemePoolError(DeckBuilderError):
+    """Raised when there are issues with the theme card pool.
+    
+    This exception is used when there are problems creating or managing the theme
+    card pool, such as empty pools, insufficient cards, or invalid pool configurations.
+    
+    Examples:
+        >>> raise ThemePoolError(
+        ...     "Empty theme card pool",
+        ...     {"theme": "spellslinger", "required_cards": 30}
+        ... )
+        
+        >>> raise ThemePoolError(
+        ...     "Insufficient cards in theme pool",
+        ...     {
+        ...         "theme": "artifacts",
+        ...         "available_cards": 15,
+        ...         "required_cards": 25
+        ...     }
+        ... )
+        
+        >>> raise ThemePoolError(
+        ...     "Invalid card pool configuration",
+        ...     {
+        ...         "theme": "tribal",
+        ...         "creature_type": "Dragon",
+        ...         "error": "No cards match creature type"
+        ...     }
+        ... )
+    """
+    
+    def __init__(self, message: str, details: dict | None = None):
+        """Initialize theme pool error.
+        
+        Args:
+            message: Description of the theme pool failure
+            details: Additional context about the error
+        """
+        super().__init__(
+            message,
+            code="THEME_POOL_ERR",
+            details=details
         )

settings.py

@@ -544,7 +544,7 @@ REMOVAL_TEXT_PATTERNS = [
     'returns target.*to.*hand'
 ]
 
-REMOVAL_SPECIFIC_CARDS = [] # type: list
+REMOVAL_SPECIFIC_CARDS = ['from.*graveyard.*hand'] # type: list
 
 REMOVAL_EXCLUSION_PATTERNS = [] # type: list
 
@@ -1032,7 +1032,17 @@ REQUIRED_COLUMNS: List[str] = [
     'power', 'toughness', 'keywords', 'themeTags', 'layout', 'side'
 ]
 
-# Constants for theme weight management
+# Constants for theme weight management and selection
+
+# Multiplier for initial card pool size during theme-based selection
+THEME_POOL_SIZE_MULTIPLIER: Final[float] = 2.0
+
+# Bonus multiplier for cards that match multiple deck themes
+THEME_PRIORITY_BONUS: Final[float] = 1.2
+
+# Safety multiplier to avoid overshooting target counts
+THEME_WEIGHT_MULTIPLIER: Final[float] = 0.9
+
 THEME_WEIGHTS_DEFAULT: Final[Dict[str, float]] = {
     'primary': 1.0,
     'secondary': 0.6,

setup.py

@@ -1,26 +1,53 @@
 from __future__ import annotations
 
+"""MTG Python Deckbuilder setup module.
+
+This module provides the main setup functionality for the MTG Python Deckbuilder
+application. It handles initial setup tasks such as downloading card data,
+creating color-filtered card lists, and generating commander-eligible card lists.
+
+Key Features:
+    - Initial setup and configuration
+    - Card data download and processing
+    - Color-based card filtering
+    - Commander card list generation
+    - CSV file management and validation
+
+The module works in conjunction with setup_utils.py for utility functions and
+exceptions.py for error handling.
+"""
+
 # Standard library imports
 import logging
 from enum import Enum
-from pathlib import Path
 import os
+from pathlib import Path
 from typing import Union, List, Dict, Any
 
 # Third-party imports
-import pandas as pd
 import inquirer
+import pandas as pd
 
 # Local application imports
 from settings import (
-    banned_cards, CSV_DIRECTORY, SETUP_COLORS, COLOR_ABRV, MTGJSON_API_URL
+    banned_cards,
+    COLOR_ABRV,
+    CSV_DIRECTORY,
+    MTGJSON_API_URL,
+    SETUP_COLORS
 )
 from setup_utils import (
-    download_cards_csv, filter_dataframe, process_legendary_cards, filter_by_color_identity
+    download_cards_csv,
+    filter_by_color_identity,
+    filter_dataframe,
+    process_legendary_cards
 )
 from exceptions import (
-    CSVFileNotFoundError, MTGJSONDownloadError, DataFrameProcessingError,
+    CSVFileNotFoundError,
-    ColorFilterError, CommanderValidationError
+    ColorFilterError,
+    CommanderValidationError,
+    DataFrameProcessingError,
+    MTGJSONDownloadError
 )
 # Create logs directory if it doesn't exist
 if not os.path.exists('logs'):

setup_utils.py

@@ -347,7 +347,7 @@ def process_legendary_cards(df: pd.DataFrame) -> pd.DataFrame:
         ) from e
 
 def process_card_dataframe(df: CardLibraryDF, batch_size: int = 1000, columns_to_keep: Optional[List[str]] = None,
-                         include_commander_cols: bool = False, skip_availability_checks: bool = False) -> pd.DataFrame:
+                         include_commander_cols: bool = False, skip_availability_checks: bool = False) -> CardLibraryDF:
     """Process DataFrame with common operations in batches.
 
     Args:

tagger.py

@@ -293,7 +293,7 @@ def create_theme_tags(df: pd.DataFrame, color: str) -> None:
         raise TypeError("df must be a pandas DataFrame")
     if not isinstance(color, str):
         raise TypeError("color must be a string")
-    if color not in settings.colors:
+    if color not in settings.COLORS:
         raise ValueError(f"Invalid color: {color}")
 
     try:
@@ -2633,6 +2633,24 @@ def create_token_modifier_mask(df: pd.DataFrame) -> pd.Series:
 
     return has_modifier & has_effect & ~name_exclusions
 
+def create_tokens_matter_mask(df: pd.DataFrame) -> pd.Series:
+    """Create a boolean mask for cards that care about tokens.
+
+    Args:
+        df: DataFrame to search
+
+    Returns:
+        Boolean Series indicating which cards care about tokens
+    """
+    # Create patterns for token matters
+    text_patterns = [
+        'tokens.*you.*control',
+        'that\'s a token',
+    ]
+    text_mask = tag_utils.create_text_mask(df, text_patterns)
+
+    return text_mask
+
 def tag_for_tokens(df: pd.DataFrame, color: str) -> None:
     """Tag cards that create or modify tokens using vectorized operations.
 
@@ -2670,6 +2688,13 @@ def tag_for_tokens(df: pd.DataFrame, color: str) -> None:
             tag_utils.apply_tag_vectorized(df, modifier_mask,
                 ['Token Modification', 'Token Creation', 'Tokens Matter'])
             logger.info('Tagged %d cards that modify token creation', modifier_mask.sum())
+            
+        # Create tokens matter mask
+        matters_mask = create_tokens_matter_mask(df)
+        if matters_mask.any():
+            tag_utils.apply_tag_vectorized(df, matters_mask,
+                ['Tokens Matter'])
+            logger.info('Tagged %d cards that care about tokens', modifier_mask.sum())
 
         duration = (pd.Timestamp.now() - start_time).total_seconds()
         logger.info('Completed token tagging in %.2fs', duration)
@@ -3638,7 +3663,7 @@ def tag_for_cantrips(df: pd.DataFrame, color: str) -> None:
         logger.error('Error tagging Cantrips in %s_cards.csv: %s', color, str(e))
         raise
 
-
+## Magecraft
 def create_magecraft_mask(df: pd.DataFrame) -> pd.Series:
     """Create a boolean mask for cards with magecraft effects.
 
@@ -6369,6 +6394,18 @@ def create_removal_text_mask(df: pd.DataFrame) -> pd.Series:
     """
     return tag_utils.create_text_mask(df, settings.REMOVAL_TEXT_PATTERNS)
 
+def create_removal_exclusion_mask(df: pd.DataFrame) -> pd.Series:
+    """Create a boolean mask for cards that should be excluded from removal effects.
+
+    Args:
+        df: DataFrame to search
+
+    Returns:
+        Boolean Series indicating which cards should be excluded
+    """
+    return tag_utils.create_text_mask(df, settings.REMOVAL_EXCLUSION_PATTERNS)
+
+
 def tag_for_removal(df: pd.DataFrame, color: str) -> None:
     """Tag cards that provide spot removal using vectorized operations.
 
@@ -6422,7 +6459,8 @@ def tag_for_removal(df: pd.DataFrame, color: str) -> None:
 
 def run_tagging():
     start_time = pd.Timestamp.now()
-    for color in settings.colors:
+    for color in settings.COLORS:
         load_dataframe(color)
     duration = (pd.Timestamp.now() - start_time).total_seconds()
-    logger.info(f'Tagged cards in {duration:.2f}s')
+    logger.info(f'Tagged cards in {duration:.2f}s')
+

type_definitions.py

@@ -46,4 +46,5 @@ NonCreatureDF = pd.DataFrame
 EnchantmentDF = pd.DataFrame
 InstantDF = pd.DataFrame
 PlaneswalkerDF = pd.DataFrame
+NonPlaneswalkerDF = pd.DataFrame
 SorceryDF = pd.DataFrame