rgwfuncs 0.0.5__tar.gz → 0.0.7__tar.gz

{rgwfuncs-0.0.5/src/rgwfuncs.egg-info → rgwfuncs-0.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: rgwfuncs
-Version: 0.0.5
+Version: 0.0.7
 Summary: A functional programming paradigm for mathematical modelling and data science
 Home-page: https://github.com/ryangerardwilson/rgwfunc
 Author: Ryan Gerard Wilson
@@ -28,16 +28,90 @@ Requires-Dist: google-api-python-client
 
 ***By Ryan Gerard Wilson (https://ryangerardwilson.com)***
 
-This library provides a variety of functions for manipulating and analyzing pandas DataFrames. 
+This library is meant to make ML/ Data Science pipelines more readable. It assumes a linux environment, and the existence of a `rgwml.config` file for certain features (like db querying, sending data to slack, etc.)
 
 --------------------------------------------------------------------------------
 
 ## Installation
 
 Install the package using:
-bash
-pip install rgwfuncs
 
+    pip install rgwfuncs
+
+--------------------------------------------------------------------------------
+
+## Create a `rgwml.config` File
+
+A `rgwml.config` file (located at `vi ~/Documents/rgwml.config) is required for MSSQL, CLICKHOUSE, MYSQL, GOOGLE BIG QUERY, SLACK, TELEGRAM, and GMAIL integrations.
+
+    {
+      "db_presets" : [
+        {
+          "name": "mssql_db9",
+          "db_type": "mssql",
+          "host": "",
+          "username": "",
+          "password": "",
+          "database": ""
+        },
+        {
+          "name": "clickhouse_db7",
+          "db_type": "clickhouse",
+          "host": "",
+          "username": "",
+          "password": "",
+          "database": ""
+        },
+        {
+          "name": "mysql_db2",
+          "db_type": "mysql",
+          "host": "",
+          "username": "",
+          "password": "",
+          "database": ""
+        },
+        {
+          "name": "bq_db1",
+          "db_type": "google_big_query",
+          "json_file_path": "",
+          "project_id": ""
+        }
+      ],
+    "vm_presets": [
+        {
+          "name": "main_server",
+          "host": "",
+          "ssh_user": "",
+          "ssh_key_path": ""
+        }
+      ],
+    "cloud_storage_presets": [
+        {
+          "name": "gcs_bucket_name",
+          "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"
+      }
+    ]
+  }
 
 --------------------------------------------------------------------------------
 
@@ -978,6 +1052,103 @@ Retain only rows with uncommon column values between two DataFrames.
     print(df_uncommon)
     
 
+--------------------------------------------------------------------------------
+
+### 41. `union_join`
+Perform a union join, concatenating two DataFrames and dropping duplicates.
+
+• Parameters:
+  - `df1` (pd.DataFrame): First DataFrame.
+  - `df2` (pd.DataFrame): Second DataFrame.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame with the union of `df1` and `df2`, without duplicates.
+
+• Example:
+
+    from rgwfuncs import union_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Value': [20, 30, 40]})
+
+    df_union = union_join(df1, df2)
+    print(df_union)
+
+--------------------------------------------------------------------------------
+
+### 42. `bag_union_join`
+Perform a bag union join, concatenating two DataFrames without dropping duplicates.
+
+• Parameters:
+  - `df1` (pd.DataFrame): First DataFrame.
+  - `df2` (pd.DataFrame): Second DataFrame.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame with the concatenated data of `df1` and `df2`.
+
+• Example:
+
+    from rgwfuncs import bag_union_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Value': [20, 30, 40]})
+
+    df_bag_union = bag_union_join(df1, df2)
+    print(df_bag_union)
+
+--------------------------------------------------------------------------------
+
+### 43. `left_join`
+Perform a left join on two DataFrames.
+
+• Parameters:
+  - `df1` (pd.DataFrame): The left DataFrame.
+  - `df2` (pd.DataFrame): The right DataFrame.
+  - `left_on` (str): Column name in `df1` to join on.
+  - `right_on` (str): Column name in `df2` to join on.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame as the result of a left join.
+
+• Example:
+
+    from rgwfuncs import left_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Extra': ['A', 'B', 'C']})
+
+    df_left_join = left_join(df1, df2, 'ID', 'ID')
+    print(df_left_join)
+
+--------------------------------------------------------------------------------
+
+### 44. `right_join`
+Perform a right join on two DataFrames.
+
+• Parameters:
+  - `df1` (pd.DataFrame): The left DataFrame.
+  - `df2` (pd.DataFrame): The right DataFrame.
+  - `left_on` (str): Column name in `df1` to join on.
+  - `right_on` (str): Column name in `df2` to join on.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame as the result of a right join.
+
+• Example:
+
+    from rgwfuncs import right_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Extra': ['A', 'B', 'C']})
+
+    df_right_join = right_join(df1, df2, 'ID', 'ID')
+    print(df_right_join)
+
+
 --------------------------------------------------------------------------------
 
 ## Additional Info

{rgwfuncs-0.0.5 → rgwfuncs-0.0.7}/README.md

@@ -2,16 +2,90 @@
 
 ***By Ryan Gerard Wilson (https://ryangerardwilson.com)***
 
-This library provides a variety of functions for manipulating and analyzing pandas DataFrames. 
+This library is meant to make ML/ Data Science pipelines more readable. It assumes a linux environment, and the existence of a `rgwml.config` file for certain features (like db querying, sending data to slack, etc.)
 
 --------------------------------------------------------------------------------
 
 ## Installation
 
 Install the package using:
-bash
-pip install rgwfuncs
 
+    pip install rgwfuncs
+
+--------------------------------------------------------------------------------
+
+## Create a `rgwml.config` File
+
+A `rgwml.config` file (located at `vi ~/Documents/rgwml.config) is required for MSSQL, CLICKHOUSE, MYSQL, GOOGLE BIG QUERY, SLACK, TELEGRAM, and GMAIL integrations.
+
+    {
+      "db_presets" : [
+        {
+          "name": "mssql_db9",
+          "db_type": "mssql",
+          "host": "",
+          "username": "",
+          "password": "",
+          "database": ""
+        },
+        {
+          "name": "clickhouse_db7",
+          "db_type": "clickhouse",
+          "host": "",
+          "username": "",
+          "password": "",
+          "database": ""
+        },
+        {
+          "name": "mysql_db2",
+          "db_type": "mysql",
+          "host": "",
+          "username": "",
+          "password": "",
+          "database": ""
+        },
+        {
+          "name": "bq_db1",
+          "db_type": "google_big_query",
+          "json_file_path": "",
+          "project_id": ""
+        }
+      ],
+    "vm_presets": [
+        {
+          "name": "main_server",
+          "host": "",
+          "ssh_user": "",
+          "ssh_key_path": ""
+        }
+      ],
+    "cloud_storage_presets": [
+        {
+          "name": "gcs_bucket_name",
+          "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"
+      }
+    ]
+  }
 
 --------------------------------------------------------------------------------
 
@@ -952,6 +1026,103 @@ Retain only rows with uncommon column values between two DataFrames.
     print(df_uncommon)
     
 
+--------------------------------------------------------------------------------
+
+### 41. `union_join`
+Perform a union join, concatenating two DataFrames and dropping duplicates.
+
+• Parameters:
+  - `df1` (pd.DataFrame): First DataFrame.
+  - `df2` (pd.DataFrame): Second DataFrame.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame with the union of `df1` and `df2`, without duplicates.
+
+• Example:
+
+    from rgwfuncs import union_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Value': [20, 30, 40]})
+
+    df_union = union_join(df1, df2)
+    print(df_union)
+
+--------------------------------------------------------------------------------
+
+### 42. `bag_union_join`
+Perform a bag union join, concatenating two DataFrames without dropping duplicates.
+
+• Parameters:
+  - `df1` (pd.DataFrame): First DataFrame.
+  - `df2` (pd.DataFrame): Second DataFrame.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame with the concatenated data of `df1` and `df2`.
+
+• Example:
+
+    from rgwfuncs import bag_union_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Value': [20, 30, 40]})
+
+    df_bag_union = bag_union_join(df1, df2)
+    print(df_bag_union)
+
+--------------------------------------------------------------------------------
+
+### 43. `left_join`
+Perform a left join on two DataFrames.
+
+• Parameters:
+  - `df1` (pd.DataFrame): The left DataFrame.
+  - `df2` (pd.DataFrame): The right DataFrame.
+  - `left_on` (str): Column name in `df1` to join on.
+  - `right_on` (str): Column name in `df2` to join on.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame as the result of a left join.
+
+• Example:
+
+    from rgwfuncs import left_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Extra': ['A', 'B', 'C']})
+
+    df_left_join = left_join(df1, df2, 'ID', 'ID')
+    print(df_left_join)
+
+--------------------------------------------------------------------------------
+
+### 44. `right_join`
+Perform a right join on two DataFrames.
+
+• Parameters:
+  - `df1` (pd.DataFrame): The left DataFrame.
+  - `df2` (pd.DataFrame): The right DataFrame.
+  - `left_on` (str): Column name in `df1` to join on.
+  - `right_on` (str): Column name in `df2` to join on.
+
+• Returns:
+  - pd.DataFrame: A new DataFrame as the result of a right join.
+
+• Example:
+
+    from rgwfuncs import right_join
+    import pandas as pd
+
+    df1 = pd.DataFrame({'ID': [1, 2, 3], 'Value': [10, 20, 30]})
+    df2 = pd.DataFrame({'ID': [2, 3, 4], 'Extra': ['A', 'B', 'C']})
+
+    df_right_join = right_join(df1, df2, 'ID', 'ID')
+    print(df_right_join)
+
+
 --------------------------------------------------------------------------------
 
 ## Additional Info

{rgwfuncs-0.0.5 → rgwfuncs-0.0.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rgwfuncs"
-version = "0.0.5"
+version = "0.0.7"
 authors = [
   { name = "Ryan Gerard Wilson", email = "ryangerardwilson@gmail.com" },
 ]

{rgwfuncs-0.0.5 → rgwfuncs-0.0.7}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = rgwfuncs
-version = 0.0.5
+version = 0.0.7
 author = Ryan Gerard Wilson
 author_email = ryangerardwilson@gmail.com
 description = A functional programming paradigm for mathematical modelling and data science

rgwfuncs-0.0.7/src/rgwfuncs/__init__.py

@@ -0,0 +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