dragon-ml-toolbox 4.0.0__tar.gz → 4.1.0__tar.gz

{dragon_ml_toolbox-4.0.0/dragon_ml_toolbox.egg-info → dragon_ml_toolbox-4.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 4.0.0
+Version: 4.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -12,6 +12,11 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: LICENSE-THIRD-PARTY.md
+Provides-Extra: base
+Requires-Dist: pandas; extra == "base"
+Requires-Dist: numpy; extra == "base"
+Requires-Dist: polars; extra == "base"
+Requires-Dist: joblib; extra == "base"
 Provides-Extra: ml
 Requires-Dist: numpy; extra == "ml"
 Requires-Dist: pandas; extra == "ml"
@@ -107,7 +112,6 @@ Install from the conda-forge channel:
 ```bash
 conda install -c conda-forge dragon-ml-toolbox
 ```
-**Note:** This version is outdated or broken due to dependency incompatibilities. Use PyPi instead.
 
 ## Modular Installation
 
@@ -142,6 +146,7 @@ ML_trainer
 ML_inference
 path_manager
 PSO_optimization
+SQL
 RNN_forecast
 utilities
 ```
@@ -220,6 +225,24 @@ ML_inference
 path_manager
 ```
 
+### 🎫 Base Tools [base]
+
+General purpose functions and classes.
+
+```Bash
+pip install "dragon-ml-toolbox[base]"
+```
+
+#### Modules:
+
+```bash
+ETL_Engineering
+custom_logger
+SQL
+utilities
+path_manager
+```
+
 ## Usage
 
 After installation, import modules like this:

{dragon_ml_toolbox-4.0.0 → dragon_ml_toolbox-4.1.0}/README.md

@@ -36,7 +36,6 @@ Install from the conda-forge channel:
 ```bash
 conda install -c conda-forge dragon-ml-toolbox
 ```
-**Note:** This version is outdated or broken due to dependency incompatibilities. Use PyPi instead.
 
 ## Modular Installation
 
@@ -71,6 +70,7 @@ ML_trainer
 ML_inference
 path_manager
 PSO_optimization
+SQL
 RNN_forecast
 utilities
 ```
@@ -149,6 +149,24 @@ ML_inference
 path_manager
 ```
 
+### 🎫 Base Tools [base]
+
+General purpose functions and classes.
+
+```Bash
+pip install "dragon-ml-toolbox[base]"
+```
+
+#### Modules:
+
+```bash
+ETL_Engineering
+custom_logger
+SQL
+utilities
+path_manager
+```
+
 ## Usage
 
 After installation, import modules like this:

{dragon_ml_toolbox-4.0.0 → dragon_ml_toolbox-4.1.0/dragon_ml_toolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 4.0.0
+Version: 4.1.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT
@@ -12,6 +12,11 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: LICENSE-THIRD-PARTY.md
+Provides-Extra: base
+Requires-Dist: pandas; extra == "base"
+Requires-Dist: numpy; extra == "base"
+Requires-Dist: polars; extra == "base"
+Requires-Dist: joblib; extra == "base"
 Provides-Extra: ml
 Requires-Dist: numpy; extra == "ml"
 Requires-Dist: pandas; extra == "ml"
@@ -107,7 +112,6 @@ Install from the conda-forge channel:
 ```bash
 conda install -c conda-forge dragon-ml-toolbox
 ```
-**Note:** This version is outdated or broken due to dependency incompatibilities. Use PyPi instead.
 
 ## Modular Installation
 
@@ -142,6 +146,7 @@ ML_trainer
 ML_inference
 path_manager
 PSO_optimization
+SQL
 RNN_forecast
 utilities
 ```
@@ -220,6 +225,24 @@ ML_inference
 path_manager
 ```
 
+### 🎫 Base Tools [base]
+
+General purpose functions and classes.
+
+```Bash
+pip install "dragon-ml-toolbox[base]"
+```
+
+#### Modules:
+
+```bash
+ETL_Engineering
+custom_logger
+SQL
+utilities
+path_manager
+```
+
 ## Usage
 
 After installation, import modules like this:

{dragon_ml_toolbox-4.0.0 → dragon_ml_toolbox-4.1.0}/dragon_ml_toolbox.egg-info/SOURCES.txt

@@ -16,6 +16,7 @@ ml_tools/ML_inference.py
 ml_tools/ML_trainer.py
 ml_tools/PSO_optimization.py
 ml_tools/RNN_forecast.py
+ml_tools/SQL.py
 ml_tools/VIF_factor.py
 ml_tools/__init__.py
 ml_tools/_logger.py

{dragon_ml_toolbox-4.0.0 → dragon_ml_toolbox-4.1.0}/dragon_ml_toolbox.egg-info/requires.txt

@@ -19,6 +19,12 @@ shap
 tqdm
 Pillow
 
+[base]
+pandas
+numpy
+polars
+joblib
+
 [excel]
 pandas
 openpyxl

{dragon_ml_toolbox-4.0.0 → dragon_ml_toolbox-4.1.0}/ml_tools/PSO_optimization.py

@@ -9,7 +9,6 @@ from .utilities import (
     threshold_binary_values, 
     threshold_binary_values_batch, 
     deserialize_object,
-    save_dataframe,
     yield_dataframes_from_dir)
 from .path_manager import sanitize_filename, make_fullpath, list_files_by_extension, list_csv_paths
 import torch
@@ -19,6 +18,8 @@ import seaborn as sns
 from ._logger import _LOGGER
 from .keys import ModelSaveKeys
 from ._script_info import _script_info
+from .SQL import DatabaseManager
+from contextlib import nullcontext
 
 
 __all__ = [
@@ -182,45 +183,73 @@ def _set_feature_names(size: int, names: Union[list[str], None]):
     else:
         assert len(names) == size, "List with feature names do not match the number of features"
         return names
-    
 
-def _save_results(*dicts, save_dir: Union[str,Path], target_name: str):
-    combined_dict = dict()
-    for single_dict in dicts:
-        combined_dict.update(single_dict)
+
+def _save_result(result_dict: dict,
+                 save_format: Literal['csv', 'sqlite', 'both'],
+                 csv_path: Path,
+                 db_manager: Optional[DatabaseManager] = None,
+                 db_table_name: Optional[str] = None):
+    """
+    Handles saving a single result to CSV, SQLite, or both.
+    """
+    # Save to CSV
+    if save_format in ['csv', 'both']:
+        _save_or_append_to_csv(result_dict, csv_path)
+
+    # Save to SQLite
+    if save_format in ['sqlite', 'both']:
+        if db_manager and db_table_name:
+            db_manager.insert_row(db_table_name, result_dict)
+        else:
+            _LOGGER.warning("SQLite saving requested but db_manager or table_name not provided.")
+
+
+def _save_or_append_to_csv(data_dict: dict, save_path: Path):
+    """
+    Saves or appends a dictionary of data as a single row to a CSV file.
+
+    If the file doesn't exist, it creates it and writes the header.
+    If the file exists, it appends the new data without the header.
+    """
+    df_row = pd.DataFrame([data_dict])
     
-    df = pd.DataFrame(combined_dict)
+    file_exists = save_path.exists()
     
-    save_dataframe(df=df, save_dir=save_dir, filename=f"Optimization_{target_name}")
+    df_row.to_csv(
+        save_path, 
+        mode='a',              # 'a' for append mode
+        index=False,           # Don't write the DataFrame index
+        header=not file_exists # Write header only if file does NOT exist
+    )
 
 
-def _run_single_pso(objective_function: ObjectiveFunction, pso_args: dict, feature_names: list[str], target_name: str, random_state: int):
-    """Helper for a single PSO run."""
+def _run_single_pso(objective_function: ObjectiveFunction, pso_args: dict, feature_names: list[str], target_name: str, random_state: int, save_format: Literal['csv', 'sqlite', 'both'], csv_path: Path, db_manager: Optional[DatabaseManager], db_table_name: str):
+    """Helper for a single PSO run that also handles saving."""
     pso_args.update({"seed": random_state})
     
     best_features, best_target, *_ = _pso(**pso_args)
     
-    # Flip best_target if maximization was used
     if objective_function.task == "maximization":
         best_target = -best_target
     
-    # Threshold binary features
     binary_number = objective_function.binary_features
     best_features_threshold = threshold_binary_values(best_features, binary_number)
     
-    # Name features and target
     best_features_named = {name: value for name, value in zip(feature_names, best_features_threshold)}
     best_target_named = {target_name: best_target}
     
+    # Save the result using the new helper
+    combined_dict = {**best_features_named, **best_target_named}
+    _save_result(combined_dict, save_format, csv_path, db_manager, db_table_name)
+    
     return best_features_named, best_target_named
 
 
-def _run_post_hoc_pso(objective_function: ObjectiveFunction, pso_args: dict, feature_names: list[str], target_name: str, repetitions: int):
-    """Helper for post-hoc PSO analysis."""
-    all_best_targets = []
-    all_best_features = [[] for _ in range(len(feature_names))]
-    
-    for _ in range(repetitions):
+def _run_post_hoc_pso(objective_function: ObjectiveFunction, pso_args: dict, feature_names: list[str], target_name: str, repetitions: int, save_format: Literal['csv', 'sqlite', 'both'], csv_path: Path, db_manager: Optional[DatabaseManager], db_table_name: str):
+    """Helper for post-hoc analysis that saves results incrementally."""
+    progress = trange(repetitions, desc="Post-Hoc PSO", unit="run")
+    for _ in progress:
         best_features, best_target, *_ = _pso(**pso_args)
         
         if objective_function.task == "maximization":
@@ -229,28 +258,25 @@ def _run_post_hoc_pso(objective_function: ObjectiveFunction, pso_args: dict, fea
         binary_number = objective_function.binary_features
         best_features_threshold = threshold_binary_values(best_features, binary_number)
         
-        for i, best_feature in enumerate(best_features_threshold):
-            all_best_features[i].append(best_feature)
-        all_best_targets.append(best_target)
-    
-    # Name features and target
-    all_best_features_named = {name: lst for name, lst in zip(feature_names, all_best_features)}
-    all_best_targets_named = {target_name: all_best_targets}
-    
-    return all_best_features_named, all_best_targets_named
+        result_dict = {name: value for name, value in zip(feature_names, best_features_threshold)}
+        result_dict[target_name] = best_target
+        
+        # Save each result incrementally
+        _save_result(result_dict, save_format, csv_path, db_manager, db_table_name)
 
 
 def run_pso(lower_boundaries: list[float], 
             upper_boundaries: list[float], 
             objective_function: ObjectiveFunction,
             save_results_dir: Union[str,Path],
+            save_format: Literal['csv', 'sqlite', 'both'] = 'csv',
             auto_binary_boundaries: bool=True,
             target_name: Union[str, None]=None, 
             feature_names: Union[list[str], None]=None,
             swarm_size: int=200, 
             max_iterations: int=3000,
             random_state: int=101,
-            post_hoc_analysis: Optional[int]=10) -> Tuple[Dict[str, float | list[float]], Dict[str, float | list[float]]]:
+            post_hoc_analysis: Optional[int]=10) -> Optional[Tuple[Dict[str, float], Dict[str, float]]]:
     """
     Executes Particle Swarm Optimization (PSO) to optimize a given objective function and saves the results as a CSV file.
 
@@ -264,6 +290,11 @@ def run_pso(lower_boundaries: list[float],
         A callable object encapsulating a tree-based regression model.
     save_results_dir : str | Path
         Directory path to save the results CSV file.
+    save_format : {'csv', 'sqlite', 'both'}, default 'csv'
+        The format for saving optimization results.
+        - 'csv': Saves results to a CSV file.
+        - 'sqlite': Saves results to an SQLite database file. ⚠️ If a database exists, new tables will be created using the target name.
+        - 'both': Saves results to both formats.
     auto_binary_boundaries : bool
         Use `ObjectiveFunction.binary_features` to append as many binary boundaries as needed to `lower_boundaries` and `upper_boundaries` automatically.
     target_name : str or None, optional
@@ -279,14 +310,11 @@ def run_pso(lower_boundaries: list[float],
 
     Returns
     -------
-    Tuple[Dict[str, float | list[float]], Dict[str, float | list[float]]]
-        If `post_hoc_analysis` is None, returns two dictionaries:
-            - feature_names: Feature values (after inverse scaling) that yield the best result.
-            - target_name: Best result obtained for the target variable.
-
-        If `post_hoc_analysis` is an integer, returns two dictionaries:
-            - feature_names: Lists of best feature values (after inverse scaling) for each repetition.
-            - target_name: List of best target values across repetitions.
+    Tuple[Dict[str, float], Dict[str, float]] or None
+        - If `post_hoc_analysis` is None, returns two dictionaries containing the
+          single best features and the corresponding target value.
+        - If `post_hoc_analysis` is active, results are streamed directly to a CSV file
+          and this function returns `None`.
 
     Notes
     -----
@@ -311,8 +339,9 @@ def run_pso(lower_boundaries: list[float],
     # Append binary boundaries
     binary_number = objective_function.binary_features
     if auto_binary_boundaries and binary_number > 0:
-        local_lower_boundaries.extend([0] * binary_number)
-        local_upper_boundaries.extend([1] * binary_number)
+        # simplify binary search by constraining range
+        local_lower_boundaries.extend([0.45] * binary_number)
+        local_upper_boundaries.extend([0.55] * binary_number)
         
     # Set the total length of features
     size_of_features = len(local_lower_boundaries)
@@ -328,7 +357,25 @@ def run_pso(lower_boundaries: list[float],
     if target_name is None and objective_function.target_name is not None:
         target_name = objective_function.target_name
     if target_name is None:
-        target_name = "Target"
+        raise ValueError(f"'target' name was not provided and was not found in the .joblib object.")
+    
+    # --- Setup: Saving Infrastructure ---
+    sanitized_target_name = sanitize_filename(target_name)
+    save_dir_path = make_fullpath(save_results_dir, make=True, enforce="directory")
+    base_filename = f"Optimization_{sanitized_target_name}"
+    csv_path = save_dir_path / f"{base_filename}.csv"
+    db_path = save_dir_path / "Optimization.db"
+    db_table_name = f"{sanitized_target_name}"
+    
+    if save_format in ['sqlite', 'both']:
+        # Dynamically create the schema for the database table
+        schema = {name: "REAL" for name in names}
+        schema[target_name] = "REAL"
+        schema = {"result_id": "INTEGER PRIMARY KEY AUTOINCREMENT", **schema}
+        
+        # Create table
+        with DatabaseManager(db_path) as db:
+            db.create_table(db_table_name, schema)
         
     pso_arguments = {
             "func":objective_function,
@@ -340,17 +387,29 @@ def run_pso(lower_boundaries: list[float],
             "particle_output": False,
     }
     
-    # Dispatcher
-    if post_hoc_analysis is None or post_hoc_analysis <= 1:
-        features, target = _run_single_pso(objective_function, pso_arguments, names, target_name, random_state)
-    else:
-        features, target = _run_post_hoc_pso(objective_function, pso_arguments, names, target_name, post_hoc_analysis)
-    
-    # --- Save Results ---
-    save_results_path = make_fullpath(save_results_dir, make=True)
-    _save_results(features, target, save_dir=save_results_path, target_name=target_name)
-    
-    return features, target # type: ignore
+    # --- Dispatcher ---
+    # Use a real or dummy context manager to handle the DB connection cleanly
+    db_context = DatabaseManager(db_path) if save_format in ['sqlite', 'both'] else nullcontext()
+
+    with db_context as db_manager:
+        if post_hoc_analysis is None or post_hoc_analysis <= 1:
+            # --- Single Run Logic ---
+            features_dict, target_dict = _run_single_pso(
+                objective_function, pso_arguments, names, target_name, random_state,
+                save_format, csv_path, db_manager, db_table_name
+            )
+            _LOGGER.info(f"✅ Single optimization complete.")
+            return features_dict, target_dict
+        
+        else:
+            # --- Post-Hoc Analysis Logic ---
+            _LOGGER.info(f"🏁 Starting post-hoc analysis with {post_hoc_analysis} repetitions...")
+            _run_post_hoc_pso(
+                objective_function, pso_arguments, names, target_name, post_hoc_analysis,
+                save_format, csv_path, db_manager, db_table_name
+            )
+            _LOGGER.info("✅ Post-hoc analysis complete. Results saved.")
+            return None
 
 
 def _pso(func: ObjectiveFunction,

dragon_ml_toolbox-4.1.0/ml_tools/SQL.py

@@ -0,0 +1,272 @@
+import sqlite3
+import pandas as pd
+from pathlib import Path
+from typing import Union, Dict, Any, Optional, List, Literal
+from ._logger import _LOGGER
+from ._script_info import _script_info
+from .path_manager import make_fullpath
+
+
+__all__ = [
+    "DatabaseManager",
+]
+
+
+class DatabaseManager:
+    """
+    A user-friendly context manager for handling SQLite database operations.
+
+    This class abstracts the underlying sqlite3 connection and cursor management,
+    providing simple methods to execute queries, create tables, and handle data
+    insertion and retrieval using pandas DataFrames.
+
+    Parameters
+    ----------
+    db_path : Union[str, Path]
+        The file path to the SQLite database. If the file does not exist,
+        it will be created upon connection.
+
+    Example
+    -------
+    >>> schema = {
+    ...     "id": "INTEGER PRIMARY KEY AUTOINCREMENT",
+    ...     "run_name": "TEXT NOT NULL",
+    ...     "feature_a": "REAL",
+    ...     "score": "REAL"
+    ... }
+    >>> with DatabaseManager("my_results.db") as db:
+    ...     db.create_table("experiments", schema)
+    ...     data = {"run_name": "first_run", "feature_a": 0.123, "score": 95.5}
+    ...     db.insert_row("experiments", data)
+    ...     df = db.query_to_dataframe("SELECT * FROM experiments")
+    ...     print(df)
+    """
+    def __init__(self, db_path: Union[str, Path]):
+        """Initializes the DatabaseManager with the path to the database file."""
+        if isinstance(db_path, str):
+            if not db_path.endswith(".db"):
+                db_path = db_path + ".db"
+        elif isinstance(db_path, Path):
+            if db_path.suffix != ".db":
+                db_path = db_path.with_suffix(".db")
+        
+        self.db_path = make_fullpath(db_path, make=True, enforce="file")
+        self.conn: Optional[sqlite3.Connection] = None
+        self.cursor: Optional[sqlite3.Cursor] = None
+
+    def __enter__(self):
+        """Establishes the database connection and returns the manager instance."""
+        try:
+            self.conn = sqlite3.connect(self.db_path)
+            self.cursor = self.conn.cursor()
+            _LOGGER.info(f"✅ Successfully connected to database: {self.db_path}")
+            return self
+        except sqlite3.Error as e:
+            _LOGGER.error(f"❌ Database connection failed: {e}")
+            raise  # Re-raise the exception after logging
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """Commits changes and closes the database connection."""
+        if self.conn:
+            if exc_type:  # If an exception occurred, rollback
+                self.conn.rollback()
+                _LOGGER.warning("⚠️ Rolling back transaction due to an error.")
+            else:  # Otherwise, commit the transaction
+                self.conn.commit()
+            self.conn.close()
+            _LOGGER.info(f"❇️ Database connection closed: {self.db_path.name}")
+
+    def create_table(self, table_name: str, schema: Dict[str, str], if_not_exists: bool = True):
+        """
+        Creates a new table in the database based on a provided schema.
+
+        Parameters
+        ----------
+        table_name : str
+            The name of the table to create.
+        schema : Dict[str, str]
+            A dictionary where keys are column names and values are their SQL data types
+            (e.g., {"id": "INTEGER PRIMARY KEY", "name": "TEXT NOT NULL"}).
+        if_not_exists : bool, default=True
+            If True, adds "IF NOT EXISTS" to the SQL statement to prevent errors
+            if the table already exists.
+        """
+        if not self.cursor:
+            raise sqlite3.Error("Database connection is not open.")
+
+        columns_def = ", ".join([f'"{col_name}" {col_type}' for col_name, col_type in schema.items()])
+        exists_clause = "IF NOT EXISTS" if if_not_exists else ""
+        
+        query = f"CREATE TABLE {exists_clause} {table_name} ({columns_def})"
+        
+        _LOGGER.info(f"🗂️ Executing: {query}")
+        self.cursor.execute(query)
+
+    def insert_row(self, table_name: str, data: Dict[str, Any]):
+        """
+        Inserts a single row of data into the specified table.
+
+        Parameters
+        ----------
+        table_name : str
+            The name of the target table.
+        data : Dict[str, Any]
+            A dictionary where keys correspond to column names and values are the
+            data to be inserted.
+        """
+        if not self.cursor:
+            raise sqlite3.Error("Database connection is not open.")
+
+        columns = ', '.join(f'"{k}"' for k in data.keys())
+        placeholders = ', '.join(['?'] * len(data))
+        values = list(data.values())
+        
+        query = f"INSERT INTO {table_name} ({columns}) VALUES ({placeholders})"
+        
+        self.cursor.execute(query, values)
+
+    def query_to_dataframe(self, query: str, params: Optional[tuple] = None) -> pd.DataFrame:
+        """
+        Executes a SELECT query and returns the results as a pandas DataFrame.
+
+        Parameters
+        ----------
+        query : str
+            The SQL SELECT statement to execute.
+        params : Optional[tuple], default=None
+            An optional tuple of parameters to pass to the query for safety
+            against SQL injection.
+
+        Returns
+        -------
+        pd.DataFrame
+            A DataFrame containing the query results.
+        """
+        if not self.conn:
+            raise sqlite3.Error("Database connection is not open.")
+            
+        return pd.read_sql_query(query, self.conn, params=params)
+
+    def execute_sql(self, query: str, params: Optional[tuple] = None):
+        """
+        Executes an arbitrary SQL command that does not return data (e.g., UPDATE, DELETE).
+
+        Parameters
+        ----------
+        query : str
+            The SQL statement to execute.
+        params : Optional[tuple], default=None
+            An optional tuple of parameters for the query.
+        """
+        if not self.cursor:
+            raise sqlite3.Error("Database connection is not open.")
+        
+        self.cursor.execute(query, params if params else ())
+
+    def insert_many(self, table_name: str, data: List[Dict[str, Any]]):
+        """
+        Inserts multiple rows into the specified table in a single, efficient transaction.
+
+        Parameters
+        ----------
+        table_name : str
+            The name of the target table.
+        data : List[Dict[str, Any]]
+            A list of dictionaries, where each dictionary represents a row to be inserted.
+            All dictionaries should have the same keys.
+        """
+        if not self.cursor:
+            raise sqlite3.Error("Database connection is not open.")
+        if not data:
+            _LOGGER.warning("⚠️ insert_many called with empty data list. No action taken.")
+            return
+
+        # Assume all dicts have the same keys as the first one
+        first_row = data[0]
+        columns = ', '.join(f'"{k}"' for k in first_row.keys())
+        placeholders = ', '.join(['?'] * len(first_row))
+        
+        # Create a list of tuples, where each tuple is a row of values
+        values_to_insert = [list(row.values()) for row in data]
+
+        query = f"INSERT INTO {table_name} ({columns}) VALUES ({placeholders})"
+        
+        self.cursor.executemany(query, values_to_insert)
+        _LOGGER.info(f"✅ Bulk inserted {len(values_to_insert)} rows into '{table_name}'.")
+        
+    def insert_from_dataframe(self, table_name: str, df: pd.DataFrame, if_exists: Literal['fail', 'replace', 'append'] = 'append'):
+        """
+        Writes records from a pandas DataFrame to the specified SQL table.
+
+        Parameters
+        ----------
+        table_name : str
+            The name of the target SQL table.
+        df : pd.DataFrame
+            The DataFrame to be written.
+        if_exists : str, default 'append'
+            How to behave if the table already exists.
+            - 'fail': Raise a ValueError.
+            - 'replace': Drop the table before inserting new values.
+            - 'append': Insert new values to the existing table.
+        """
+        if not self.conn:
+            raise sqlite3.Error("Database connection is not open.")
+
+        df.to_sql(
+            table_name,
+            self.conn,
+            if_exists=if_exists,
+            index=False  # Typically, we don't want to save the DataFrame index
+        )
+        _LOGGER.info(f"✅ Wrote {len(df)} rows from DataFrame to table '{table_name}' using mode '{if_exists}'.")
+        
+    def list_tables(self) -> List[str]:
+        """Returns a list of all table names in the database."""
+        if not self.cursor:
+            raise sqlite3.Error("Database connection is not open.")
+        
+        self.cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
+        # The result of the fetch is a list of tuples, e.g., [('table1',), ('table2',)]
+        return [table[0] for table in self.cursor.fetchall()]
+
+    def get_table_schema(self, table_name: str) -> pd.DataFrame:
+        """
+        Retrieves the schema of a specific table and returns it as a DataFrame.
+
+        Returns a DataFrame with columns: cid, name, type, notnull, dflt_value, pk
+        """
+        if not self.conn:
+            raise sqlite3.Error("Database connection is not open.")
+            
+        # PRAGMA is a special SQL command in SQLite for database metadata
+        return pd.read_sql_query(f'PRAGMA table_info("{table_name}");', self.conn)
+
+    def create_index(self, table_name: str, column_name: str, unique: bool = False):
+        """
+        Creates an index on a column of a specified table to speed up queries.
+
+        Parameters
+        ----------
+        table_name : str
+            The name of the table containing the column.
+        column_name : str
+            The name of the column to be indexed.
+        unique : bool, default=False
+            If True, creates a unique index, which ensures all values in the
+            column are unique.
+        """
+        if not self.cursor:
+            raise sqlite3.Error("Database connection is not open.")
+
+        index_name = f"idx_{table_name}_{column_name}"
+        unique_clause = "UNIQUE" if unique else ""
+        
+        query = f"CREATE {unique_clause} INDEX IF NOT EXISTS {index_name} ON {table_name} ({column_name})"
+        
+        _LOGGER.info(f"🗂️ Executing: {query}")
+        self.cursor.execute(query)
+
+
+def info():
+    _script_info(__all__)

{dragon_ml_toolbox-4.0.0 → dragon_ml_toolbox-4.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dragon-ml-toolbox"
-version = "4.0.0"
+version = "4.1.0"
 description = "A collection of tools for data science and machine learning projects."
 authors = [
     { name = "Karl Loza", email = "luigiloza@gmail.com" }
@@ -19,6 +19,14 @@ Homepage = "https://github.com/DrAg0n-BoRn/ML_tools"
 Changelog = "https://github.com/DrAg0n-BoRn/ML_tools/blob/master/CHANGELOG.md"
 
 [project.optional-dependencies]
+# Base all purpose tools
+base = [ 
+    "pandas", 
+    "numpy", 
+    "polars", 
+    "joblib"
+]
+
 # Machine Learning main toolbox. Additionally Requires PyTorch with CUDA / MPS support if pytorch models are used
 ML = [
     "numpy",