Release V0.1.0

AdrianAntico · Sep 4, 2021 · 5ef6c1c · 5ef6c1c
1 parent f90f066
commit 5ef6c1c
Show file tree

Hide file tree

Showing 9 changed files with 203 additions and 13 deletions.
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-![Version: 0.0.9](https://img.shields.io/static/v1?label=Version&message=0.0.9&color=blue&?style=plastic)
+![Version: 0.0.1](https://img.shields.io/static/v1?label=Version&message=0.1.0&color=blue&?style=plastic)
 ![Python](https://img.shields.io/badge/Python-3.6%20%7C%203.7%20%7C%203.8%20%7C%203.9-blue)
 ![Build: Passing](https://img.shields.io/static/v1?label=Build&message=passing&color=brightgreen)
 [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://GitHub.com/Naereen/StrapDown.js/graphs/commit-activity)
@@ -16,7 +16,7 @@ This package is currently in its beginning stages. I'll be working off a bluepri
 pip install git+https://github.com/AdrianAntico/RetroFit.git#egg=retrofit
 
 # From pypi
-pip install retrofit==0.0.9
+pip install retrofit==0.1.0
 
 # Check out R package RemixAutoML
 https://github.com/AdrianAntico/RemixAutoML
@@ -314,8 +314,6 @@ print(data.names)
 
 
 
-
-
 #### **FE0_AutoDiff()**
 <p>
 
@@ -681,7 +679,7 @@ ArgsList = DataSets['ArgsList']
 <details><summary>Function Description</summary>
 <p>
 
-<code>ML0_GetModelData()</code> Automatically create data sets chosen ML algorithm
+<code>ML0_GetModelData()</code> Automatically create data sets chosen ML algorithm. Currently supports catboost, xgboost, and lightgbm.
 
 </p>
 </details>
@@ -697,6 +695,10 @@ import retrofit
 from retrofit import FeatureEngineering as fe
 from retrofit import MachineLearning as ml
 
+############################################################################################
+# CatBoost
+############################################################################################
+
 # Load some data
 data = dt.fread("C:/Users/Bizon/Documents/GitHub/BenchmarkData.csv")
     
@@ -737,6 +739,96 @@ DataSets = ml.ML0_GetModelData(
 catboost_train = DataSets['train_data']
 catboost_validation = DataSets['validation_data']
 catboost_test = DataSets['test_data']
+
+############################################################################################
+# XGBoost
+############################################################################################
+
+# Load some data
+data = dt.fread("C:/Users/Bizon/Documents/GitHub/BenchmarkData.csv")
+    
+# Create partitioned data sets
+DataSets = fe.FE2_AutoDataParition(
+  data=data, 
+  ArgsList=None, 
+  DateColumnName='CalendarDateColumn', 
+  PartitionType='random', 
+  Ratios=[0.70,0.20,0.10], 
+  ByVariables=None, 
+  Processing='datatable', 
+  InputFrame='datatable', 
+  OutputFrame='datatable')
+
+# Collect partitioned data
+TrainData = DataSets['TrainData']
+ValidationData = DataSets['ValidationData']
+TestData = DataSets['TestData']
+del DataSets
+
+# Create xgboost data sets
+DataSets = ml.ML0_GetModelData(
+  TrainData=TrainData, 
+  ValidationData=ValidationData, 
+  TestData=TestData, 
+  ArgsList=None, 
+  TargetColumnName='Leads', 
+  NumericColumnNames=['XREGS1', 'XREGS2', 'XREGS3'], 
+  CategoricalColumnNames=['MarketingSegments','MarketingSegments2','MarketingSegments3','Label'], 
+  TextColumnNames=None, 
+  WeightColumnName=None, 
+  Threads=-1, 
+  Processing='xgboost', 
+  InputFrame='datatable')
+  
+# Collect xgboost training data
+xgboost_train = DataSets['train_data']
+xgboost_validation = DataSets['validation_data']
+xgboost_test = DataSets['test_data']
+
+############################################################################################
+# LightGBM
+############################################################################################
+
+# Load some data
+data = dt.fread("C:/Users/Bizon/Documents/GitHub/BenchmarkData.csv")
+    
+# Create partitioned data sets
+DataSets = fe.FE2_AutoDataParition(
+  data=data, 
+  ArgsList=None, 
+  DateColumnName='CalendarDateColumn', 
+  PartitionType='random', 
+  Ratios=[0.70,0.20,0.10], 
+  ByVariables=None, 
+  Processing='datatable', 
+  InputFrame='datatable', 
+  OutputFrame='datatable')
+
+# Collect partitioned data
+TrainData = DataSets['TrainData']
+ValidationData = DataSets['ValidationData']
+TestData = DataSets['TestData']
+del DataSets
+
+# Create lightgbm data sets
+DataSets = ml.ML0_GetModelData(
+  TrainData=TrainData, 
+  ValidationData=ValidationData, 
+  TestData=TestData, 
+  ArgsList=None, 
+  TargetColumnName='Leads', 
+  NumericColumnNames=['XREGS1', 'XREGS2', 'XREGS3'], 
+  CategoricalColumnNames=['MarketingSegments','MarketingSegments2','MarketingSegments3','Label'], 
+  TextColumnNames=None, 
+  WeightColumnName=None, 
+  Threads=-1, 
+  Processing='lightgbm', 
+  InputFrame='datatable')
+  
+# Collect lightgbm training data
+lightgbm_train = DataSets['train_data']
+lightgbm_validation = DataSets['validation_data']
+lightgbm_test = DataSets['test_data']
 ```
 
 </p>

diff --git a/dist/retrofit-0.0.9-py3-none-any.whl b/dist/retrofit-0.0.9-py3-none-any.whl
diff --git a/dist/retrofit-0.0.9.tar.gz b/dist/retrofit-0.0.9.tar.gz
diff --git a/dist/retrofit-0.1.0-py3-none-any.whl b/dist/retrofit-0.1.0-py3-none-any.whl
diff --git a/dist/retrofit-0.1.0.tar.gz b/dist/retrofit-0.1.0.tar.gz
diff --git a/retrofit.egg-info/PKG-INFO b/retrofit.egg-info/PKG-INFO
@@ -13,7 +13,7 @@ Classifier: Programming Language :: Python :: 3
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
-![Version: 0.0.9](https://img.shields.io/static/v1?label=Version&message=0.0.9&color=blue&?style=plastic)
+![Version: 0.0.1](https://img.shields.io/static/v1?label=Version&message=0.1.0&color=blue&?style=plastic)
 ![Python](https://img.shields.io/badge/Python-3.6%20%7C%203.7%20%7C%203.8%20%7C%203.9-blue)
 ![Build: Passing](https://img.shields.io/static/v1?label=Build&message=passing&color=brightgreen)
 [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://GitHub.com/Naereen/StrapDown.js/graphs/commit-activity)
@@ -31,7 +31,7 @@ This package is currently in its beginning stages. I'll be working off a bluepri
 pip install git+https://github.com/AdrianAntico/RetroFit.git#egg=retrofit
 
 # From pypi
-pip install retrofit==0.0.9
+pip install retrofit==0.1.0
 
 # Check out R package RemixAutoML
 https://github.com/AdrianAntico/RemixAutoML
@@ -329,8 +329,6 @@ print(data.names)
 
 
 
-
-
 #### **FE0_AutoDiff()**
 <p>
 
@@ -696,7 +694,7 @@ ArgsList = DataSets['ArgsList']
 <details><summary>Function Description</summary>
 <p>
 
-<code>ML0_GetModelData()</code> Automatically create data sets chosen ML algorithm
+<code>ML0_GetModelData()</code> Automatically create data sets chosen ML algorithm. Currently supports catboost, xgboost, and lightgbm.
 
 </p>
 </details>
@@ -712,6 +710,10 @@ import retrofit
 from retrofit import FeatureEngineering as fe
 from retrofit import MachineLearning as ml
 
+############################################################################################
+# CatBoost
+############################################################################################
+
 # Load some data
 data = dt.fread("C:/Users/Bizon/Documents/GitHub/BenchmarkData.csv")
 
@@ -752,6 +754,96 @@ DataSets = ml.ML0_GetModelData(
 catboost_train = DataSets['train_data']
 catboost_validation = DataSets['validation_data']
 catboost_test = DataSets['test_data']
+
+############################################################################################
+# XGBoost
+############################################################################################
+
+# Load some data
+data = dt.fread("C:/Users/Bizon/Documents/GitHub/BenchmarkData.csv")
+
+# Create partitioned data sets
+DataSets = fe.FE2_AutoDataParition(
+  data=data, 
+  ArgsList=None, 
+  DateColumnName='CalendarDateColumn', 
+  PartitionType='random', 
+  Ratios=[0.70,0.20,0.10], 
+  ByVariables=None, 
+  Processing='datatable', 
+  InputFrame='datatable', 
+  OutputFrame='datatable')
+
+# Collect partitioned data
+TrainData = DataSets['TrainData']
+ValidationData = DataSets['ValidationData']
+TestData = DataSets['TestData']
+del DataSets
+
+# Create xgboost data sets
+DataSets = ml.ML0_GetModelData(
+  TrainData=TrainData, 
+  ValidationData=ValidationData, 
+  TestData=TestData, 
+  ArgsList=None, 
+  TargetColumnName='Leads', 
+  NumericColumnNames=['XREGS1', 'XREGS2', 'XREGS3'], 
+  CategoricalColumnNames=['MarketingSegments','MarketingSegments2','MarketingSegments3','Label'], 
+  TextColumnNames=None, 
+  WeightColumnName=None, 
+  Threads=-1, 
+  Processing='xgboost', 
+  InputFrame='datatable')
+
+# Collect xgboost training data
+xgboost_train = DataSets['train_data']
+xgboost_validation = DataSets['validation_data']
+xgboost_test = DataSets['test_data']
+
+############################################################################################
+# LightGBM
+############################################################################################
+
+# Load some data
+data = dt.fread("C:/Users/Bizon/Documents/GitHub/BenchmarkData.csv")
+
+# Create partitioned data sets
+DataSets = fe.FE2_AutoDataParition(
+  data=data, 
+  ArgsList=None, 
+  DateColumnName='CalendarDateColumn', 
+  PartitionType='random', 
+  Ratios=[0.70,0.20,0.10], 
+  ByVariables=None, 
+  Processing='datatable', 
+  InputFrame='datatable', 
+  OutputFrame='datatable')
+
+# Collect partitioned data
+TrainData = DataSets['TrainData']
+ValidationData = DataSets['ValidationData']
+TestData = DataSets['TestData']
+del DataSets
+
+# Create lightgbm data sets
+DataSets = ml.ML0_GetModelData(
+  TrainData=TrainData, 
+  ValidationData=ValidationData, 
+  TestData=TestData, 
+  ArgsList=None, 
+  TargetColumnName='Leads', 
+  NumericColumnNames=['XREGS1', 'XREGS2', 'XREGS3'], 
+  CategoricalColumnNames=['MarketingSegments','MarketingSegments2','MarketingSegments3','Label'], 
+  TextColumnNames=None, 
+  WeightColumnName=None, 
+  Threads=-1, 
+  Processing='lightgbm', 
+  InputFrame='datatable')
+
+# Collect lightgbm training data
+lightgbm_train = DataSets['train_data']
+lightgbm_validation = DataSets['validation_data']
+lightgbm_test = DataSets['test_data']
 ```
 
 </p>

diff --git a/retrofit/FeatureEngineering.py b/retrofit/FeatureEngineering.py
@@ -209,7 +209,7 @@ def FE0_AutoLags(data = None, ArgsList=None, LagColumnNames = None, DateColumnNa
     return dict(data = data, ArgsList = ArgsList)
 
 
-def FE0_AutoRollStats(data = None, ArgsList=None, RollColumnNames = None, DateColumnName = None, ByVariables = None, MovingAvg_Periods = 2, MovingSD_Periods = None, MovingMin_Periods = None, MovingMax_Periods = None, ImputeValue = -1, Sort = True, Processing='datatable', InputFrame='datatable', OutputFrame='datatable'):
+def FE0_AutoRollStats(data = None, ArgsList=None, RollColumnNames = None, DateColumnName = None, ByVariables = None, MovingAvg_Periods = None, MovingSD_Periods = None, MovingMin_Periods = None, MovingMax_Periods = None, ImputeValue = -1, Sort = True, Processing='datatable', InputFrame='datatable', OutputFrame='datatable'):
     """
     # Goal:
     Automatically generate rolling averages, standard deviations, mins and maxes for multiple periods for multiple variables and by variables

diff --git a/retrofit/MachineLearning.py b/retrofit/MachineLearning.py
@@ -10,7 +10,7 @@ def ML0_GetModelData(TrainData=None, ValidationData=None, TestData=None, ArgsLis
     Create modeling objects for specific algorithms. E.g. create train, valid, and test objects for catboost
     
     # Output
-    Return frames for catboost, xgboost, lightgbm, etc.
+    Return frames for catboost, xgboost, and lightgbm, currently.
     
     # Parameters
     TrainData:              Source data. Either a datatable frame, polars frame, or pandas frame. The function will run either datatable code or polars code. If your input frame is pandas
@@ -23,7 +23,7 @@ def ML0_GetModelData(TrainData=None, ValidationData=None, TestData=None, ArgsLis
     TextColumnNames:        List of integers for the lookback lengths
     WeightColumnName:       Value to fill the NA's for beginning of series
     Threads:                Number of threads to utilize if available for the algorithm
-    Processing:             'datatable' or 'polars'. Choose the package you want to do your processing
+    Processing:             'catboost', 'xgboost', or 'lightgbm'
     InputFrame:             'datatable', 'polars', or 'pandas' If you input Frame is 'pandas', it will be converted to a datatable Frame for generating the new columns
 
     # ML0_GetModelData Example:

diff --git a/retrofit/utils.py b/retrofit/utils.py
@@ -1,3 +1,9 @@
+# Module: utils
+# Author: Adrian Antico <adrianantico@gmail.com>
+# License: MIT
+# Release: retrofit 0.1.0
+# Last modified : 2021-09-03
+
 def cumsum(x):
   """
   Create a list of summed up values from another list