rgwfuncs 0.0.7__py3-none-any.whl → 0.0.9__py3-none-any.whl

rgwfuncs/__init__.py

@@ -1,4 +1,4 @@
 # This file is automatically generated
 # Dynamically importing functions from modules
 
-from .df_lib import append_columns, append_percentile_classification_column, append_ranged_classification_column, append_ranged_date_classification_column, append_rows, append_xgb_labels, append_xgb_logistic_regression_predictions, append_xgb_regression_predictions, bag_union_join, bottom_n_unique_values, cascade_sort, delete_rows, docs, drop_duplicates, drop_duplicates_retain_first, drop_duplicates_retain_last, filter_dataframe, filter_indian_mobiles, first_n_rows, from_raw_data, last_n_rows, left_join, limit_dataframe, load_data_from_path, load_data_from_query, load_data_from_sqlite_path, mask_against_dataframe, mask_against_dataframe_converse, numeric_clean, order_columns, print_correlation, print_dataframe, print_memory_usage, print_n_frequency_cascading, print_n_frequency_linear, rename_columns, retain_columns, right_join, send_data_to_email, send_data_to_slack, send_dataframe_via_telegram, top_n_unique_values, union_join, update_rows
+from .df_lib import append_columns, append_percentile_classification_column, append_ranged_classification_column, append_ranged_date_classification_column, append_rows, append_xgb_labels, append_xgb_logistic_regression_predictions, append_xgb_regression_predictions, bag_union_join, bottom_n_unique_values, cascade_sort, delete_rows, docs, drop_duplicates, drop_duplicates_retain_first, drop_duplicates_retain_last, filter_dataframe, filter_indian_mobiles, first_n_rows, from_raw_data, last_n_rows, left_join, limit_dataframe, load_data_from_path, load_data_from_query, load_data_from_sqlite_path, mask_against_dataframe, mask_against_dataframe_converse, numeric_clean, order_columns, print_correlation, print_dataframe, print_memory_usage, print_n_frequency_cascading, print_n_frequency_linear, rename_columns, retain_columns, right_join, send_data_to_email, send_data_to_slack, send_dataframe_via_telegram, sync_dataframe_to_sqlite_database, top_n_unique_values, union_join, update_rows

rgwfuncs/df_lib.py

@@ -27,10 +27,13 @@ from typing import Optional, Callable, Dict, List, Tuple, Any
 
 def docs(method_type_filter: Optional[str] = None) -> None:
     """
-    Print a list of function names in alphabetical order. If method_type_filter is specified, print the docstrings of the functions that match the filter. Using '*' as a filter will print the docstrings for all functions.
+    Print a list of function names in alphabetical order. If method_type_filter
+    is specified, print the docstrings of the functions that match the filter.
+    Using '*' as a filter will print the docstrings for all functions.
 
     Parameters:
-        method_type_filter: Optional filter string, comma-separated to select docstring types, or '*' for all.
+        method_type_filter: Optional filter string representing a function name,
+        or '*' to display docstrings for all functions.
     """
     # Get the current module's namespace
     current_module = __name__
@@ -41,7 +44,7 @@ def docs(method_type_filter: Optional[str] = None) -> None:
     }
 
     # List of function names sorted alphabetically
-    function_names: List[str] = sorted(local_functions.keys())
+    function_names = sorted(local_functions.keys())
 
     # Print function names
     print("Functions in alphabetical order:")
@@ -50,26 +53,13 @@ def docs(method_type_filter: Optional[str] = None) -> None:
 
     # If a filter is provided or '*', print the docstrings of functions
     if method_type_filter:
-        print("\nFiltered function documentation:")
+        # print("\nFiltered function documentation:")
         for name, func in local_functions.items():
             docstring: Optional[str] = func.__doc__
             if docstring:
-                if method_type_filter == '*':
-                    # Print the entire docstring for each function
+                if method_type_filter == '*' or method_type_filter == name:
+                    # Print the entire docstring for the matching function
                     print(f"\n{name}:\n{docstring}")
-                else:
-                    # Extract only the first line of the docstring
-                    first_line: str = docstring.split('\n')[0]
-                    if "::" in first_line:
-                        # Find the first occurrence of "::" and split there
-                        split_index: int = first_line.find("::")
-                        function_type: str = first_line[:split_index].strip()
-                        function_type_list: List[str] = [
-                            mt.strip() for mt in method_type_filter.split(',')]
-                        if function_type in function_type_list:
-                            # Print the entire docstring if the filter matches
-                            print(f"\n{name}:\n{docstring}")
-
 
 def numeric_clean(df: pd.DataFrame, column_names: str, column_type: str, irregular_value_treatment: str) -> pd.DataFrame:
     """
@@ -1696,3 +1686,60 @@ def right_join(df1: pd.DataFrame, df2: pd.DataFrame, left_on: str, right_on: str
         A new DataFrame as the result of a right join.
     """
     return df1.merge(df2, how='right', left_on=left_on, right_on=right_on)
+
+def sync_dataframe_to_sqlite_database(db_path: str, tablename: str, df: pd.DataFrame) -> None:
+    """
+    Processes and saves a DataFrame to an SQLite database, adding a timestamp column
+    and replacing the existing table if needed. Creates the table if it does not exist.
+
+    Parameters:
+    - db_path (str): Path to the SQLite database file.
+    - tablename (str): The name of the table in the database.
+    - df (pd.DataFrame): The DataFrame to be processed and saved.
+    """
+    # Step 1: Add a timestamp column to the dataframe
+    df['rgwfuncs_sync_timestamp'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+
+    # Define a simple mapping from pandas dtypes to SQLite types
+    dtype_mapping = {
+        'int64': 'INTEGER',
+        'float64': 'REAL',
+        'object': 'TEXT',
+        'datetime64[ns]': 'TEXT',  # Dates are stored as text in SQLite
+        'bool': 'INTEGER',  # SQLite does not have a separate Boolean storage class
+    }
+
+    # Helper function to map pandas dtype to SQLite type
+    def map_dtype(dtype):
+        return dtype_mapping.get(str(dtype), 'TEXT')
+
+    # Step 2: Save df in SQLite3 db as '{tablename}_new'
+    with sqlite3.connect(db_path) as conn:
+        new_table_name = f"{tablename}_new"
+
+        # Check if the new table already exists, create if not
+        cursor = conn.cursor()
+        cursor.execute(f"PRAGMA table_info({new_table_name})")
+        if cursor.fetchall() == []:  # Table does not exist
+            # Create a table using the DataFrame's column names and types
+            columns_with_types = ', '.join(
+                f'"{col}" {map_dtype(dtype)}' for col, dtype in zip(df.columns, df.dtypes)
+            )
+            create_table_query = f'CREATE TABLE "{new_table_name}" ({columns_with_types})'
+            conn.execute(create_table_query)
+
+        # Insert data into the new table
+        df.to_sql(new_table_name, conn, if_exists='replace', index=False)
+
+        # Step 3: If '{tablename}_new' is not empty, delete table '{tablename}' (if it exists), and rename '{tablename}_new' to '{tablename}'
+        # Check if the new table is not empty
+        cursor.execute(f"SELECT COUNT(*) FROM {new_table_name}")
+        count = cursor.fetchone()[0]
+
+        if count > 0:
+            # Drop the old table if it exists
+            conn.execute(f"DROP TABLE IF EXISTS {tablename}")
+            # Rename the new table to the old table name
+            conn.execute(f"ALTER TABLE {new_table_name} RENAME TO {tablename}")
+
+

{rgwfuncs-0.0.7.dist-info → rgwfuncs-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.7
+Version: 0.0.9
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson
@@ -77,7 +77,7 @@ A `rgwml.config` file (located at `vi ~/Documents/rgwml.config) is required for
           "project_id": ""
         }
       ],
-    "vm_presets": [
+      "vm_presets": [
         {
           "name": "main_server",
           "host": "",
@@ -85,34 +85,34 @@ A `rgwml.config` file (located at `vi ~/Documents/rgwml.config) is required for
           "ssh_key_path": ""
         }
       ],
-    "cloud_storage_presets": [
+      "cloud_storage_presets": [
         {
           "name": "gcs_bucket_name",
-          "credential_path": "path/to/your/credentials.json"
+          "credential_path": "/path/to/your/credentials.json"
         }
       ],
-    "telegram_bot_presets": [
-      {
-        "name": "rgwml-bot",
-        "chat_id": "",
-        "bot_token": ""
-      }
-    ],
-    "slack_bot_presets": [
-      {
-        "name": "labs-channel",
-        "channel_id": "",
-        "bot_token": ""
-      }
-    ],
-    "gmail_bot_presets": [
-      {
-        "name": "info@xyz.com",
-        "service_account_credentials_path": "/home/user/Documents/credentials/your_creds.json"
-      }
-    ]
-  }
-
+      "telegram_bot_presets": [
+        {
+          "name": "rgwml-bot",
+          "chat_id": "",
+          "bot_token": ""
+        }
+      ],
+      "slack_bot_presets": [
+        {
+          "name": "labs-channel",
+          "channel_id": "",
+          "bot_token": ""
+        }
+      ],
+      "gmail_bot_presets": [
+        {
+          "name": "info@xyz.com",
+          "service_account_credentials_path": "/path/to/your/credentials.json"
+        }
+      ]
+    }
+    
 --------------------------------------------------------------------------------
 
 ## Basic Usage
@@ -1151,6 +1151,30 @@ Perform a right join on two DataFrames.
 
 --------------------------------------------------------------------------------
 
+### 45. `sync_dataframe_to_sqlite_database`
+Processes and saves a DataFrame to an SQLite database, adding a timestamp column and replacing the existing table if needed. Creates the table if it does not exist.
+
+• Parameters:
+  - `db_path` (str): Path to the SQLite database file.
+  - `tablename` (str): The name of the table in the database.
+  - `df` (pd.DataFrame): The DataFrame to be processed and saved.
+
+• Returns:
+  - None
+
+• Example:
+
+    from rgwfuncs import sync_dataframe_to_sqlite_database
+    import pandas as pd
+
+    df = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    db_path = 'my_database.db'
+    tablename = 'my_table'
+
+    sync_dataframe_to_sqlite_database(db_path, tablename, df)
+
+--------------------------------------------------------------------------------
+
 ## Additional Info
 
 For more information, refer to each function’s docstring by calling:

rgwfuncs-0.0.9.dist-info/RECORD

@@ -0,0 +1,8 @@
+rgwfuncs/__init__.py,sha256=BP8Nh8ivyCCz8Ga-21JW3NWInJFOElKoIfRuioJRWbA,1076
+rgwfuncs/df_lib.py,sha256=3PYfu_zs8HfL56C9Sb41jzoyaG9Oc7x5MZQYvo1zy6M,62930
+rgwfuncs-0.0.9.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
+rgwfuncs-0.0.9.dist-info/METADATA,sha256=tJiGspLMJbt78FGyyvf3w10ZbWCn17PJ4070wUsH1ew,32058
+rgwfuncs-0.0.9.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+rgwfuncs-0.0.9.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
+rgwfuncs-0.0.9.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.9.dist-info/RECORD,,

rgwfuncs-0.0.7.dist-info/RECORD

@@ -1,8 +0,0 @@
-rgwfuncs/__init__.py,sha256=o4BBYVERWwAx8dknJ03yVCHqV9o8D1qrRgFeJrtpDWg,1041
-rgwfuncs/df_lib.py,sha256=vYKElOUyMqBMC5EYA6vaqknpmVoOzNIyOWdJxMlzGcs,61137
-rgwfuncs-0.0.7.dist-info/LICENSE,sha256=7EI8xVBu6h_7_JlVw-yPhhOZlpY9hP8wal7kHtqKT_E,1074
-rgwfuncs-0.0.7.dist-info/METADATA,sha256=CoUF-aVOBZmywYKpz2fLgd18Y0YRQieXGYp1E6ggMw8,31226
-rgwfuncs-0.0.7.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-rgwfuncs-0.0.7.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.7.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.7.dist-info/RECORD,,