data-manipulation 0.40__tar.gz → 0.42__tar.gz

{data_manipulation-0.40/data_manipulation.egg-info → data_manipulation-0.42}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation
-Version: 0.40
+Version: 0.42
 Summary: Powerful data manipulation
 Home-page: https://github.com/shawnngtq/data-manipulation
 Author: Shawn Ng
@@ -24,7 +24,10 @@ Requires-Dist: boto3
 Requires-Dist: django
 Requires-Dist: flask
 Requires-Dist: geopandas
+Requires-Dist: ipython
+Requires-Dist: loguru
 Requires-Dist: mysql-connector-python
+Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: psycopg
 Requires-Dist: psycopg2

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/_version.py

@@ -8,11 +8,11 @@ import json
 
 version_json = '''
 {
- "date": "2024-05-26T15:48:20+0800",
+ "date": "2024-08-03T10:19:19+0800",
  "dirty": false,
  "error": null,
- "full-revisionid": "805e0463f2f7f444a10afa22b658bc31ea864fed",
- "version": "0.40"
+ "full-revisionid": "30171014f9c6ac9bcb9c5aad60d40e662d35ab79",
+ "version": "0.42"
 }
 '''  # END VERSION_JSON
 

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/base.py

@@ -1,9 +1,13 @@
-import logging
+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
 
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 # DATA STRUCTURE
@@ -38,7 +42,6 @@ def clean_string(
     str
         Uppercase cleaned string
     """
-    import re
 
     if remove_parenthesis:
         string = re.sub(r"\(.*\)", "", string)
@@ -69,7 +72,6 @@ def get_string_case_combination(str_: str) -> list:
     list
         Case combinations
     """
-    import itertools
 
     return list(map("".join, itertools.product(*zip(str_.upper(), str_.lower()))))
 
@@ -119,6 +121,22 @@ 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
@@ -188,7 +206,6 @@ def string_boolean_to_int(boolean_str_rep: str) -> int:
     int
         _description_
     """
-    from distutils.util import strtobool
 
     int_ = strtobool(string_str_to_str(boolean_str_rep))
     return int_
@@ -223,7 +240,6 @@ 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
@@ -302,7 +318,6 @@ def get_path_files(path: str, keywords: list) -> list:
     list
         Sorted list
     """
-    import os
 
     list_ = []
     for file in sorted(os.listdir(path)):
@@ -335,7 +350,6 @@ def remove_path_file(path: str, keyword: str, n: int = 2) -> None:
     >>> get_path_files("test_base_folder", ["py"])
     ['test4.py', 'test5.py']
     """
-    import os
 
     to_delete = get_path_files(path=path, keywords=[keyword])[:-n]
     for file in to_delete:
@@ -385,7 +399,6 @@ 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-0.40 → data_manipulation-0.42}/data_manipulation/beautifulsoup_.py

@@ -1,8 +1,7 @@
-import logging
+import re
 from typing import Optional
 
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def preprocess(html: str) -> Optional[str]:
@@ -25,7 +24,6 @@ def preprocess(html: str) -> Optional[str]:
     Optional[str]
         cleaned html
     """
-    import re
 
     # remove leading and trailing whitespaces
     pattern = re.compile("(^[\s]+)|([\s]+$)", re.MULTILINE)

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/boto3_.py

@@ -1,7 +1,9 @@
-import logging
+import os
+from email.mime.application import MIMEApplication
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
 
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def send_aws_ses_email(
@@ -42,10 +44,6 @@ def send_aws_ses_email(
     ---------
     - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/ses/client/send_raw_email.html
     """
-    import os
-    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-0.40 → data_manipulation-0.42}/data_manipulation/cryptography_.py

@@ -1,9 +1,7 @@
-import logging
+import os
 
 from cryptography.fernet import Fernet
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def generate_fernet_key(output_directory: str, output_filename: str) -> bytes:
@@ -22,7 +20,6 @@ def generate_fernet_key(output_directory: str, output_filename: str) -> bytes:
     bytes
         Fernet key in bytes
     """
-    import os
 
     key = None
     if os.path.isdir(output_directory):

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/django_.py

@@ -1,7 +1,7 @@
-import logging
+import os
+import sys
 
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def init_django(django_dir: str, project_name: str) -> None:
@@ -15,8 +15,6 @@ def init_django(django_dir: str, project_name: str) -> None:
     project_name : str
         Django project name
     """
-    import os
-    import sys
 
     import django
 

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/kerberos_.py

@@ -1,8 +1,6 @@
-import logging
 import subprocess
 
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def keytab_valid(
@@ -24,6 +22,7 @@ def keytab_valid(
     subprocess.CompletedProcess
         Subprocess object
     """
+
     output = subprocess.run(
         f"kinit -kt {keytab_filepath} {principal_name}",
         capture_output=True,

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/mysql_connector_python_.py

@@ -1,10 +1,6 @@
-import logging
 from typing import Optional, Union
 
-import mysql.connector
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def create_connection(
@@ -13,7 +9,7 @@ def create_connection(
     user: str,
     password: str,
     port=3306,
-) -> mysql.connector.connection_cext.CMySQLConnection:
+):
     """
     Return MySQL connection
 
@@ -37,6 +33,8 @@ def create_connection(
     mysql.connector.connection_cext.CMySQLConnection
         Connection object
     """
+    import mysql.connector
+
     connection = None
     try:
         connection = mysql.connector.connect(
@@ -53,7 +51,7 @@ def create_connection(
 
 
 def execute_query(
-    connection: mysql.connector.connection_cext.CMySQLConnection,
+    connection,
     sql_query: str,
     data: Union[dict, tuple],
     commit=True,
@@ -77,6 +75,8 @@ def execute_query(
     Optional[int]
         Query id should be int
     """
+    import mysql.connector
+
     cursor = connection.cursor()
     try:
         cursor.execute(sql_query, data)

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/pandas_.py

@@ -1,13 +1,10 @@
-import logging
 import subprocess
 from itertools import combinations
 
 import numpy as np
 import pandas as pd
 from IPython.display import display
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 # CONFIG
@@ -23,6 +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-0.40 → data_manipulation-0.42}/data_manipulation/psycopg2_.py

@@ -1,11 +1,8 @@
-import logging
 from typing import Optional, Union
 
 import pandas as pd
 import psycopg2
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def create_connection(

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/psycopg_.py

@@ -1,11 +1,8 @@
-import logging
 from typing import Optional, Union
 
 import pandas as pd
 import psycopg
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def create_connection(

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/pyspark_.py

@@ -1,4 +1,7 @@
-import pandas as pd
+import math
+import multiprocessing
+import os
+
 import pyspark
 import pyspark.sql.functions as F
 
@@ -44,9 +47,6 @@ def config_spark_local(autoset=True):
     -------
     None
     """
-    import math
-    import multiprocessing
-    import os
 
     def round_down_or_one(x):
         if math.floor(x) == 0:
@@ -360,6 +360,7 @@ def group_count(dataframe, columns, n=10):
 
     Examples
     --------
+    >>> import pandas as pd
     >>> data = {'id': [1, 1, 1, 2, 2, 3], 'value': [5, 2, 5, 2135, 124390, 213]}
     >>> df = spark.createDataFrame(pd.DataFrame(data))
     >>> group_count(df, ["id"]).show()

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/smtplib_.py

@@ -1,3 +1,9 @@
+import logging
+import smtplib
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
+
+
 def send_email(
     logname: str,
     message_subject: str,
@@ -24,10 +30,6 @@ def send_email(
     smtp_address: str
         SMTP address
     """
-    import logging
-    import smtplib
-    from email.mime.multipart import MIMEMultipart
-    from email.mime.text import MIMEText
 
     if all(
         isinstance(i, str)

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation/sqlalchemy_.py

@@ -1,9 +1,5 @@
-import logging
-
 import sqlalchemy
-
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__file__)
+from loguru import logger
 
 
 def create_sqlalchemy_url(

{data_manipulation-0.40 → data_manipulation-0.42/data_manipulation.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: data_manipulation
-Version: 0.40
+Version: 0.42
 Summary: Powerful data manipulation
 Home-page: https://github.com/shawnngtq/data-manipulation
 Author: Shawn Ng
@@ -24,7 +24,10 @@ Requires-Dist: boto3
 Requires-Dist: django
 Requires-Dist: flask
 Requires-Dist: geopandas
+Requires-Dist: ipython
+Requires-Dist: loguru
 Requires-Dist: mysql-connector-python
+Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: psycopg
 Requires-Dist: psycopg2

{data_manipulation-0.40 → data_manipulation-0.42}/data_manipulation.egg-info/requires.txt

@@ -3,7 +3,10 @@ boto3
 django
 flask
 geopandas
+ipython
+loguru
 mysql-connector-python
+numpy
 pandas
 psycopg
 psycopg2

{data_manipulation-0.40 → data_manipulation-0.42}/setup.py

@@ -27,7 +27,10 @@ DEPENDENCIES = [
     "django",
     "flask",
     "geopandas",
+    "ipython",
+    "loguru",
     "mysql-connector-python",
+    "numpy",
     "pandas",
     "psycopg",
     "psycopg2",