rgwfuncs 0.0.113__py3-none-any.whl → 0.0.116__py3-none-any.whl

rgwfuncs/__init__.py

@@ -1,7 +1,7 @@
 # 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, drop_duplicates, drop_duplicates_retain_first, drop_duplicates_retain_last, filter_dataframe, filter_indian_mobiles, first_n_rows, from_raw_data, insert_dataframe_in_sqlite_database, last_n_rows, left_join, limit_dataframe, load_data_from_aws_athena_query, load_data_from_big_query, load_data_from_path, load_data_from_query, load_data_from_sqlite_path, load_fresh_data_or_pull_from_cache, 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
+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, drop_duplicates, drop_duplicates_retain_first, drop_duplicates_retain_last, filter_dataframe, filter_indian_mobiles, first_n_rows, from_raw_data, insert_dataframe_in_sqlite_database, last_n_rows, left_join, limit_dataframe, load_data_from_aws_athena_query, load_data_from_big_query, load_data_from_path, load_data_from_query, load_data_from_snowflake, load_data_from_sqlite_path, load_fresh_data_or_pull_from_cache, 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
 from .interactive_shell_lib import interactive_shell
 from .docs_lib import docs
 from .str_lib import heading, send_telegram_message, sub_heading, title

rgwfuncs/df_lib.py

@@ -20,6 +20,9 @@ from email.mime.text import MIMEText
 from email.mime.base import MIMEBase
 from email import encoders
 from googleapiclient.discovery import build
+import snowflake.connector
+from cryptography.hazmat.primitives import serialization
+from cryptography.hazmat.backends import default_backend
 import base64
 import boto3
 from typing import Optional, Dict, List, Tuple, Any, Callable, Union
@@ -563,6 +566,129 @@ def load_data_from_big_query(
     return pd.DataFrame(rows, columns=columns)
 
 
+def load_data_from_snowflake(
+    query: str,
+    private_key_path: Optional[str] = None,
+    private_key_password: Optional[str] = None,
+    account: Optional[str] = None,
+    user: Optional[str] = None,
+    warehouse: Optional[str] = None,
+    database: Optional[str] = None,
+    schema: Optional[str] = None,
+    preset: Optional[str] = None
+) -> pd.DataFrame:
+    """
+    Load data from Snowflake with a query, returning a DataFrame.
+
+    Parameters:
+        query (str): The SQL query to execute.
+        private_key_path (Optional[str]): Path to the private key file (PEM).
+        private_key_password (Optional[str]): Password for the encrypted private key (if any).
+        account (Optional[str]): Snowflake account identifier.
+        user (Optional[str]): Snowflake username.
+        warehouse (Optional[str]): Snowflake warehouse name.
+        database (Optional[str]): Snowflake database name.
+        schema (Optional[str]): Snowflake schema name.
+        preset (Optional[str]): Name of the Snowflake preset in the .rgwfuncsrc file.
+
+    Returns:
+        pd.DataFrame: DataFrame with the query results.
+
+    Raises:
+        ValueError: If both preset and direct creds are mixed, neither provided,
+                    or required creds missing.
+        FileNotFoundError: If no '.rgwfuncsrc' found for preset.
+        RuntimeError: If preset not found or missing details.
+    """
+    def get_config() -> dict:
+        """Hunt for '.rgwfuncsrc' upwards like a sane person."""
+        current_dir = os.getcwd()
+        while True:
+            config_path = os.path.join(current_dir, '.rgwfuncsrc')  # Wait, your example had .rgwfuncsrc, assuming that's not a typo.
+            if os.path.isfile(config_path):
+                with open(config_path, 'r', encoding='utf-8') as f:
+                    content = f.read().strip()
+                    if not content:
+                        raise ValueError(f"Empty config at {config_path}'")
+                    try:
+                        return json.loads(content)
+                    except json.JSONDecodeError as e:
+                        raise ValueError(f"JSON crap in {config_path}: {e}")
+            parent = os.path.dirname(current_dir)
+            if parent == current_dir:
+                raise FileNotFoundError("Can't find '.rgwfuncsrc' anywhere useful")
+            current_dir = parent
+
+    def get_db_preset(config: dict, preset_name: str) -> dict:
+        """Grab the preset or complain."""
+        db_presets = config.get('db_presets', [])
+        for p in db_presets:
+            if p.get('name') == preset_name:
+                return p
+        raise RuntimeError(f"Preset '{preset_name}' missing, go add it")
+
+    # Input validation—because people are idiots and will screw this up
+    direct_creds = [private_key_path, private_key_password, account, user, warehouse, database, schema]
+    has_direct = any(d is not None for d in direct_creds)
+    if preset and has_direct:
+        raise ValueError("Don't mix preset with direct params, pick one")
+    if not preset and not has_direct:  # Wait, better: require at least the core ones
+        if not private_key_path or not account or not user:
+            raise ValueError("Need private_key_path, account, and user if no preset")
+    if not preset and not preset:
+        raise ValueError("Provide preset or direct creds")
+
+    # Load creds from preset
+    if preset:
+        config = get_config()
+        creds = get_db_preset(config, preset)
+        if creds.get('db_type') != 'snowflake':
+            raise ValueError(f"Preset '{preset}' isn't for Snowflake")
+        private_key_path = creds.get('private_key_path')
+        private_key_password = creds.get('private_key_password')
+        account = creds.get('account')
+        user = creds.get('user')
+        warehouse = creds.get('warehouse')
+        database = creds.get('database')
+        schema = creds.get('schema')
+        if not private_key_path or not account or not user:
+            raise ValueError(f"Missing key creds in preset '{preset}'")
+
+    # Load the damn private key
+    if not os.path.exists(private_key_path):
+        raise FileNotFoundError(f"Private key missing at {private_key_path}")
+    with open(private_key_path, "rb") as key_file:
+        pkey_data = key_file.read()
+        private_key = serialization.load_pem_private_key(
+            pkey_data,
+            password=private_key_password.encode() if private_key_password else None,
+            backend=default_backend()
+        )
+
+    # Connect and query—keep it tight, no bloat
+    try:
+        conn = {
+            'account': account,
+            'user': user,
+            'private_key': private_key,
+        }
+        if warehouse:
+            conn['warehouse'] = warehouse
+        if database:
+            conn['database'] = database
+        if schema:
+            conn['schema'] = schema
+        conn = snowflake.connector.connect(**conn)
+        cur = conn.cursor()
+        results = cur.execute(query).fetchall()
+        columns = [desc[0] for desc in cur.description]
+        cur.close()
+        conn.close()
+        return pd.DataFrame(results, columns=columns)
+    except Exception as e:
+        raise RuntimeError(f"Query bombed: {e}")
+
+
 def load_data_from_aws_athena_query(
     query: str,
     aws_region: Optional[str] = None,

{rgwfuncs-0.0.113.dist-info → rgwfuncs-0.0.116.dist-info}/METADATA

@@ -1,9 +1,7 @@
 Metadata-Version: 2.4
 Name: rgwfuncs
-Version: 0.0.113
+Version: 0.0.116
 Summary: A functional programming paradigm for mathematical modelling and data science
-Home-page: https://github.com/ryangerardwilson/rgwfuncs
-Author: Ryan Gerard Wilson
 Author-email: Ryan Gerard Wilson <ryangerardwilson@gmail.com>
 Project-URL: Homepage, https://github.com/ryangerardwilson/rgwfuncs
 Project-URL: Issues, https://github.com/ryangerardwilson/rgwfuncs
@@ -25,6 +23,7 @@ Requires-Dist: slack-sdk
 Requires-Dist: google-api-python-client
 Requires-Dist: boto3
 Requires-Dist: pyfiglet
+Requires-Dist: snowflake-connector-python
 Dynamic: license-file
 
 # RGWFUNCS

rgwfuncs-0.0.116.dist-info/RECORD

@@ -0,0 +1,10 @@
+rgwfuncs/__init__.py,sha256=G0i_r5bBDuhGgKCCGaSs0sz0_ZdBicaYRtjZLyR-ntY,1380
+rgwfuncs/df_lib.py,sha256=RvCBf-YU9LaM-Ilzt60e9JB-AMcFyS5PH9w6E_7pmuw,90516
+rgwfuncs/docs_lib.py,sha256=i63NzX-V8cGhikYdtkRGAEe2VcuwpXxDUyTRa9xI7l8,1972
+rgwfuncs/interactive_shell_lib.py,sha256=YeJBW9YgH5Nv77ONdOyIKFgtf0ItXStdlKGN9GGf8bU,4228
+rgwfuncs/str_lib.py,sha256=vQ4CYzSLYDIWh4WM1Kjhbg6DqbX4rX6VKdJ_EBJJVyE,11322
+rgwfuncs-0.0.116.dist-info/licenses/LICENSE,sha256=jLvt20gcUZYB8UOvyBvyKQ1qhYYhD__qP7ZDx2lPFkU,1062
+rgwfuncs-0.0.116.dist-info/METADATA,sha256=8Pa7P34dybjZqBmUc5ZCMn6id264sdaqSm_mf2TxUBk,42931
+rgwfuncs-0.0.116.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+rgwfuncs-0.0.116.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
+rgwfuncs-0.0.116.dist-info/RECORD,,

rgwfuncs-0.0.113.dist-info/RECORD

@@ -1,11 +0,0 @@
-rgwfuncs/__init__.py,sha256=WafmLtqJRnQ7LWU7Son0inje75tF-m6qHJqrmCgiM84,1354
-rgwfuncs/df_lib.py,sha256=lcKrMj8IpxWxnWkBFekWBQd9-Ed2nXTsHo57gTeATjE,85153
-rgwfuncs/docs_lib.py,sha256=i63NzX-V8cGhikYdtkRGAEe2VcuwpXxDUyTRa9xI7l8,1972
-rgwfuncs/interactive_shell_lib.py,sha256=YeJBW9YgH5Nv77ONdOyIKFgtf0ItXStdlKGN9GGf8bU,4228
-rgwfuncs/str_lib.py,sha256=vQ4CYzSLYDIWh4WM1Kjhbg6DqbX4rX6VKdJ_EBJJVyE,11322
-rgwfuncs-0.0.113.dist-info/licenses/LICENSE,sha256=jLvt20gcUZYB8UOvyBvyKQ1qhYYhD__qP7ZDx2lPFkU,1062
-rgwfuncs-0.0.113.dist-info/METADATA,sha256=a7_g8iP1CxnhsQJFe7kmnYa6eIahl0jiRLlq4B7B-Ww,42972
-rgwfuncs-0.0.113.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-rgwfuncs-0.0.113.dist-info/entry_points.txt,sha256=j-c5IOPIQ0252EaOV6j6STio56sbXl2C4ym_fQ0lXx0,43
-rgwfuncs-0.0.113.dist-info/top_level.txt,sha256=aGuVIzWsKiV1f2gCb6mynx0zx5ma0B1EwPGFKVEMTi4,9
-rgwfuncs-0.0.113.dist-info/RECORD,,

rgwfuncs-0.0.113.dist-info/entry_points.txt

@@ -1,2 +0,0 @@
-[console_scripts]
-rgwfuncs = rgwfuncs:main