data-manipulation 0.41__tar.gz → 0.43__tar.gz

{data_manipulation-0.41/data_manipulation.egg-info → data_manipulation-0.43}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation
-Version: 0.41
+Version: 0.43
 Summary: Powerful data manipulation
 Home-page: https://github.com/shawnngtq/data-manipulation
 Author: Shawn Ng
@@ -32,6 +32,7 @@ Requires-Dist: pandas
 Requires-Dist: psycopg
 Requires-Dist: psycopg2
 Requires-Dist: pyspark
+Requires-Dist: python-dotenv
 Requires-Dist: sqlalchemy
 
 

{data_manipulation-0.41 → data_manipulation-0.43}/data_manipulation/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-06-02T13:56:45+0800",
+ "date": "2024-09-02T21:39:52+0800",
  "dirty": false,
  "error": null,
- "full-revisionid": "87e16d5a881cc730eaa2b216d040ab445495cac6",
- "version": "0.41"
+ "full-revisionid": "f2d4c730c96dee3f05eb05b05a1b29a8f92d40a1",
+ "version": "0.43"
 }
 '''  # END VERSION_JSON
 

{data_manipulation-0.41 → data_manipulation-0.43}/data_manipulation/base.py

@@ -2,10 +2,7 @@ import itertools
 import os
 import re
 import subprocess
-from ast import literal_eval
-from distutils.util import strtobool
 from typing import List
-from urllib.parse import urlencode
 
 from loguru import logger
 
@@ -121,6 +118,22 @@ def get_country_name_variation() -> dict:
     return variations
 
 
+def get_country_code_variation() -> dict:
+    variations = {
+        "BA": ["BOSNIA"],
+        "BW": ["AFRICA"],
+        "CN": ["REPUBLIC OF CHINA"],
+        "CZ": ["CZECH REPUBLIC"],
+        "KR": ["REPUBLIC OF KOREA"],
+        "MK": ["MACEDONIA"],
+        "RU": ["RUSSIAN FEDERATION"],
+        "SK": ["SLAVONIC", "SLOVAK REPUBLIC"],
+        "TR": ["TURKEY", "TURKIYE"],
+        "US": ["UNITED STATES"],
+    }
+    return variations
+
+
 def list_tuple_without_none(list_tuple: list | tuple) -> list | tuple:
     """
     Return the given list / tuple without None variation
@@ -165,6 +178,8 @@ def list_tuple_without_none(list_tuple: list | tuple) -> list | tuple:
 
 def string_boolean_to_int(boolean_str_rep: str) -> int:
     """
+    DEPRECATED from python 3.12 onwards
+
     Return integer from given string boolean. 1 instead of "true"/"True"/"1". Reference from https://docs.python.org/3/distutils/apiref.html#distutils.util.strtobool
 
     Parameters
@@ -189,7 +204,12 @@ def string_boolean_to_int(boolean_str_rep: str) -> int:
     -------
     int
         _description_
+
+    Reference
+    ---------
+    - https://docs.python.org/3.10/library/distutils.html
     """
+    from distutils.util import strtobool
 
     int_ = strtobool(string_str_to_str(boolean_str_rep))
     return int_
@@ -224,6 +244,7 @@ def string_dlt_to_dlt(dlt_str_rep: str) -> dict | list | tuple:
     dict | list | tuple
         _description_
     """
+    from ast import literal_eval
 
     dlt = literal_eval(dlt_str_rep)
     return dlt
@@ -383,6 +404,7 @@ def create_encode_url(url: str, query_params: dict = {}) -> str:
     str
         encoded url
     """
+    from urllib.parse import urlencode
 
     return f"{url}{urlencode(query_params)}"
 

{data_manipulation-0.41 → data_manipulation-0.43}/data_manipulation/boto3_.py

@@ -1,7 +1,4 @@
 import os
-from email.mime.application import MIMEApplication
-from email.mime.multipart import MIMEMultipart
-from email.mime.text import MIMEText
 
 from loguru import logger
 
@@ -44,6 +41,9 @@ def send_aws_ses_email(
     ---------
     - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/ses/client/send_raw_email.html
     """
+    from email.mime.application import MIMEApplication
+    from email.mime.multipart import MIMEMultipart
+    from email.mime.text import MIMEText
 
     from botocore.exceptions import BotoCoreError, ClientError
 

{data_manipulation-0.41 → data_manipulation-0.43}/data_manipulation/pandas_.py

@@ -20,6 +20,30 @@ def config_pandas_display():
     pd.set_option("display.expand_frame_repr", True)
 
 
+# JUPYTER
+def is_running_in_jupyter():
+    """
+    Running in jupyter?
+
+    Returns
+    -------
+    bool
+        True means running in jupyter env
+    """
+    try:
+        # Check if the IPython module is available
+        from IPython import get_ipython
+
+        # Check if we are in a notebook environment
+        if "IPKernelApp" in get_ipython().config:
+            return True
+        else:
+            return False
+    # IPython module not found, not running in Jupyter Notebook
+    except ImportError:
+        return False
+
+
 # COLUMN
 def add_type_columns(dataframe):
     """

{data_manipulation-0.41 → data_manipulation-0.43}/data_manipulation/pyspark_.py

@@ -3,7 +3,6 @@ import multiprocessing
 import os
 
 import pyspark
-import pyspark.sql.functions as F
 
 
 # CONFIG
@@ -135,6 +134,8 @@ def add_dummy_columns(dataframe, columns, value):
     -------
     df : pyspark.sql.dataframe.DataFrame
     """
+    import pyspark.sql.functions as F
+
     if not isinstance(dataframe, pyspark.sql.dataframe.DataFrame):
         raise TypeError("Argument must be a Pyspark dataframe ...")
     if not isinstance(columns, list):
@@ -312,6 +313,8 @@ def rename(dataframe, columns):
     -------
     df : pyspark.sql.dataframe.DataFrame
     """
+    import pyspark.sql.functions as F
+
     if not isinstance(dataframe, pyspark.sql.dataframe.DataFrame):
         raise TypeError("Argument must be a Pyspark dataframe ...")
     if not isinstance(columns, dict):
@@ -388,6 +391,7 @@ def group_count(dataframe, columns, n=10):
     -------
     df : pyspark.sql.dataframe.DataFrame
     """
+    import pyspark.sql.functions as F
 
     if not isinstance(dataframe, pyspark.sql.dataframe.DataFrame):
         raise TypeError("Argument must be a Pyspark dataframe ...")

{data_manipulation-0.41 → data_manipulation-0.43/data_manipulation.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation
-Version: 0.41
+Version: 0.43
 Summary: Powerful data manipulation
 Home-page: https://github.com/shawnngtq/data-manipulation
 Author: Shawn Ng
@@ -32,6 +32,7 @@ Requires-Dist: pandas
 Requires-Dist: psycopg
 Requires-Dist: psycopg2
 Requires-Dist: pyspark
+Requires-Dist: python-dotenv
 Requires-Dist: sqlalchemy
 
 

{data_manipulation-0.41 → data_manipulation-0.43}/data_manipulation.egg-info/requires.txt

@@ -11,4 +11,5 @@ pandas
 psycopg
 psycopg2
 pyspark
+python-dotenv
 sqlalchemy

{data_manipulation-0.41 → data_manipulation-0.43}/setup.py

@@ -35,6 +35,7 @@ DEPENDENCIES = [
     "psycopg",
     "psycopg2",
     "pyspark",
+    "python-dotenv",
     "sqlalchemy",
 ]