Release V0.1.5

Feature Engineering Class

README.md

@@ -1,4 +1,4 @@
-![Version: 0.1.4](https://img.shields.io/static/v1?label=Version&message=0.1.4&color=blue&?style=plastic)
+![Version: 0.1.5](https://img.shields.io/static/v1?label=Version&message=0.1.5&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==0.1.4
+pip install retrofit==0.1.5
 
 # Check out R package RemixAutoML
 https://github.com/AdrianAntico/RemixAutoML
@@ -2538,38 +2538,91 @@ x.FitListNames
 import pkg_resources
 import timeit
 import datatable as dt
-from datatable import sort, f, by
 import retrofit
-from retrofit import FeatureEngineering_old as fe
+from retrofit import DatatableFE as dtfe
 from retrofit import MachineLearning as ml
 
 # Load some data
 FilePath = pkg_resources.resource_filename('retrofit', 'datasets/ClassificationData.csv') 
 data = dt.fread(FilePath)
 
+# Instantiate Feature Engineering Class
+FE = dtfe.FE()
+
+# Create some lags
+data = FE.FE0_AutoLags(
+    data,
+    LagColumnNames=['Independent_Variable1', 'Independent_Variable2'],
+    DateColumnName='DateTime',
+    ByVariables='Factor_1',
+    LagPeriods=[1,2],
+    ImputeValue=-1,
+    Sort=True,
+    use_saved_args=False)
+
+# Create some rolling stats
+data = FE.FE0_AutoRollStats(
+    data,
+    RollColumnNames=['Independent_Variable1','Independent_Variable2'],
+    DateColumnName='DateTime',
+    ByVariables='Factor_1',
+    MovingAvg_Periods=[1,2],
+    MovingSD_Periods=[2,3],
+    MovingMin_Periods=[1,2],
+    MovingMax_Periods=[1,2],
+    ImputeValue=-1,
+    Sort=True,
+    use_saved_args=False)
+
+# Create some diffs
+data = FE.FE0_AutoDiff(
+    data,
+    DateColumnName='DateTime',
+    ByVariables=['Factor_1','Factor_2','Factor_3'],
+    DiffNumericVariables='Independent_Variable1',
+    DiffDateVariables=None,
+    DiffGroupVariables=None,
+    NLag1=0,
+    NLag2=1,
+    Sort=True,
+    use_saved_args=False)
+
 # Dummify
-Output = fe.FE1_DummyVariables(
+data = FE.FE1_DummyVariables(
   data = data, 
-  ArgsList = None, 
   CategoricalColumnNames = ['Factor_1','Factor_2','Factor_3'],
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
-data = Output['data']
+  use_saved_args=False)
 data = data[:, [name not in ['Factor_1','Factor_2','Factor_3'] for name in data.names]]
 
+# Create Calendar Vars
+data = FE.FE1_AutoCalendarVariables(
+    data,
+    DateColumnNames='DateTime',
+    CalendarVariables=['wday','month','quarter'],
+    use_saved_args=False)
+
+# Type conversions for modeling
+data = FE.FE1_ColTypeConversions(
+    data,
+    Int2Float=True,
+    Bool2Float=True,
+    RemoveDateCols=True,
+    RemoveStrCols=False,
+    SkipCols=None,
+    use_saved_args=False)
+
+# Drop Text Cols (no word2vec yet)
+data = data[:, [z for z in data.names if z not in ['Comment']]]
+
 # Create partitioned data sets
-DataFrames = fe.FE2_AutoDataParition(
-  data = data, 
-  ArgsList = None, 
+DataFrames = FE.FE2_AutoDataPartition(
+  data, 
   DateColumnName = None, 
   PartitionType = 'random', 
   Ratios = [0.7,0.2,0.1], 
   ByVariables = None, 
-  Sort = False, 
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
+  Sort = False,
+  use_saved_args = False)
 
 # Features
 Features = [z for z in list(data.names) if not z in ['Adrian','DateTime','Comment','Weights']]
@@ -2642,38 +2695,53 @@ x.FitListNames
 import pkg_resources
 import timeit
 import datatable as dt
-from datatable import sort, f, by
 import retrofit
-from retrofit import FeatureEngineering_old as fe
+from retrofit import DatatableFE as dtfe
 from retrofit import MachineLearning as ml
 
 # Load some data
 FilePath = pkg_resources.resource_filename('retrofit', 'datasets/MultiClassData.csv') 
 data = dt.fread(FilePath)
 
+# Instantiate Feature Engineering Class
+FE = dtfe.FE()
+
 # Dummify
-Output = fe.FE1_DummyVariables(
+data = FE.FE1_DummyVariables(
   data = data, 
-  ArgsList = None, 
   CategoricalColumnNames = ['Factor_2','Factor_3'],
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
-data = Output['data']
+  use_saved_args=False)
 data = data[:, [name not in ['Factor_2','Factor_3'] for name in data.names]]
 
+# Create Calendar Vars
+data = FE.FE1_AutoCalendarVariables(
+    data,
+    DateColumnNames='DateTime',
+    CalendarVariables=['wday','month','quarter'],
+    use_saved_args=False)
+
+# Type conversions for modeling
+data = FE.FE1_ColTypeConversions(
+    data,
+    Int2Float=True,
+    Bool2Float=True,
+    RemoveDateCols=True,
+    RemoveStrCols=False,
+    SkipCols=None,
+    use_saved_args=False)
+
+# Drop Text Cols (no word2vec yet)
+data = data[:, [z for z in data.names if z not in ['Comment']]]
+
 # Create partitioned data sets
-DataFrames = fe.FE2_AutoDataParition(
-  data = data, 
-  ArgsList = None, 
+DataFrames = FE.FE2_AutoDataPartition(
+  data, 
   DateColumnName = None, 
   PartitionType = 'random', 
   Ratios = [0.7,0.2,0.1], 
   ByVariables = None, 
-  Sort = False, 
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
+  Sort = False,
+  use_saved_args = False)
 
 # Features
 Features = [z for z in list(data.names) if not z in ['Adrian','DateTime','Comment','Weights']]

retrofit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: retrofit
-Version: 0.1.4
+Version: 0.1.5
 Summary: AutoML, Forecasting, NLP, Image Classification, Feature Engineering, Model Evaluation, Model Interpretation, Fast Processing.
 Home-page: https://github.com/AdrianAntico/retrofit
 Author-email: adrianantico@gmail.com
@@ -12,7 +12,7 @@ Classifier: Programming Language :: Python :: 3
 Description-Content-Type: text/markdown
 License-File: LICENSE
 
-![Version: 0.1.4](https://img.shields.io/static/v1?label=Version&message=0.1.4&color=blue&?style=plastic)
+![Version: 0.1.5](https://img.shields.io/static/v1?label=Version&message=0.1.5&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)
@@ -30,7 +30,7 @@ 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==0.1.4
+pip install retrofit==0.1.5
 
 # Check out R package RemixAutoML
 https://github.com/AdrianAntico/RemixAutoML
@@ -2552,38 +2552,91 @@ x.FitListNames
 import pkg_resources
 import timeit
 import datatable as dt
-from datatable import sort, f, by
 import retrofit
-from retrofit import FeatureEngineering_old as fe
+from retrofit import DatatableFE as dtfe
 from retrofit import MachineLearning as ml
 
 # Load some data
 FilePath = pkg_resources.resource_filename('retrofit', 'datasets/ClassificationData.csv') 
 data = dt.fread(FilePath)
 
+# Instantiate Feature Engineering Class
+FE = dtfe.FE()
+
+# Create some lags
+data = FE.FE0_AutoLags(
+    data,
+    LagColumnNames=['Independent_Variable1', 'Independent_Variable2'],
+    DateColumnName='DateTime',
+    ByVariables='Factor_1',
+    LagPeriods=[1,2],
+    ImputeValue=-1,
+    Sort=True,
+    use_saved_args=False)
+
+# Create some rolling stats
+data = FE.FE0_AutoRollStats(
+    data,
+    RollColumnNames=['Independent_Variable1','Independent_Variable2'],
+    DateColumnName='DateTime',
+    ByVariables='Factor_1',
+    MovingAvg_Periods=[1,2],
+    MovingSD_Periods=[2,3],
+    MovingMin_Periods=[1,2],
+    MovingMax_Periods=[1,2],
+    ImputeValue=-1,
+    Sort=True,
+    use_saved_args=False)
+
+# Create some diffs
+data = FE.FE0_AutoDiff(
+    data,
+    DateColumnName='DateTime',
+    ByVariables=['Factor_1','Factor_2','Factor_3'],
+    DiffNumericVariables='Independent_Variable1',
+    DiffDateVariables=None,
+    DiffGroupVariables=None,
+    NLag1=0,
+    NLag2=1,
+    Sort=True,
+    use_saved_args=False)
+
 # Dummify
-Output = fe.FE1_DummyVariables(
+data = FE.FE1_DummyVariables(
   data = data, 
-  ArgsList = None, 
   CategoricalColumnNames = ['Factor_1','Factor_2','Factor_3'],
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
-data = Output['data']
+  use_saved_args=False)
 data = data[:, [name not in ['Factor_1','Factor_2','Factor_3'] for name in data.names]]
 
+# Create Calendar Vars
+data = FE.FE1_AutoCalendarVariables(
+    data,
+    DateColumnNames='DateTime',
+    CalendarVariables=['wday','month','quarter'],
+    use_saved_args=False)
+
+# Type conversions for modeling
+data = FE.FE1_ColTypeConversions(
+    data,
+    Int2Float=True,
+    Bool2Float=True,
+    RemoveDateCols=True,
+    RemoveStrCols=False,
+    SkipCols=None,
+    use_saved_args=False)
+
+# Drop Text Cols (no word2vec yet)
+data = data[:, [z for z in data.names if z not in ['Comment']]]
+
 # Create partitioned data sets
-DataFrames = fe.FE2_AutoDataParition(
-  data = data, 
-  ArgsList = None, 
+DataFrames = FE.FE2_AutoDataPartition(
+  data, 
   DateColumnName = None, 
   PartitionType = 'random', 
   Ratios = [0.7,0.2,0.1], 
   ByVariables = None, 
-  Sort = False, 
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
+  Sort = False,
+  use_saved_args = False)
 
 # Features
 Features = [z for z in list(data.names) if not z in ['Adrian','DateTime','Comment','Weights']]
@@ -2656,38 +2709,53 @@ x.FitListNames
 import pkg_resources
 import timeit
 import datatable as dt
-from datatable import sort, f, by
 import retrofit
-from retrofit import FeatureEngineering_old as fe
+from retrofit import DatatableFE as dtfe
 from retrofit import MachineLearning as ml
 
 # Load some data
 FilePath = pkg_resources.resource_filename('retrofit', 'datasets/MultiClassData.csv') 
 data = dt.fread(FilePath)
 
+# Instantiate Feature Engineering Class
+FE = dtfe.FE()
+
 # Dummify
-Output = fe.FE1_DummyVariables(
+data = FE.FE1_DummyVariables(
   data = data, 
-  ArgsList = None, 
   CategoricalColumnNames = ['Factor_2','Factor_3'],
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
-data = Output['data']
+  use_saved_args=False)
 data = data[:, [name not in ['Factor_2','Factor_3'] for name in data.names]]
 
+# Create Calendar Vars
+data = FE.FE1_AutoCalendarVariables(
+    data,
+    DateColumnNames='DateTime',
+    CalendarVariables=['wday','month','quarter'],
+    use_saved_args=False)
+
+# Type conversions for modeling
+data = FE.FE1_ColTypeConversions(
+    data,
+    Int2Float=True,
+    Bool2Float=True,
+    RemoveDateCols=True,
+    RemoveStrCols=False,
+    SkipCols=None,
+    use_saved_args=False)
+
+# Drop Text Cols (no word2vec yet)
+data = data[:, [z for z in data.names if z not in ['Comment']]]
+
 # Create partitioned data sets
-DataFrames = fe.FE2_AutoDataParition(
-  data = data, 
-  ArgsList = None, 
+DataFrames = FE.FE2_AutoDataPartition(
+  data, 
   DateColumnName = None, 
   PartitionType = 'random', 
   Ratios = [0.7,0.2,0.1], 
   ByVariables = None, 
-  Sort = False, 
-  Processing = 'datatable', 
-  InputFrame = 'datatable', 
-  OutputFrame = 'datatable')
+  Sort = False,
+  use_saved_args = False)
 
 # Features
 Features = [z for z in list(data.names) if not z in ['Adrian','DateTime','Comment','Weights']]