Skip to content

Added RetroFit class v1
Compare
Choose a tag to compare
@AdrianAntico AdrianAntico released this 10 Sep 22:09
· 216 commits to main since this release
V0.1.1
ca3c28a

Added the first version of many for the RetroFit class for machine learning

####################################
# Goals
####################################

Class Initialization
Model Initialization
Training
Grid Tuning
Scoring
Model Evaluation
Model Interpretation

####################################
# Functions
####################################

ML1_Single_Train()
ML1_Single_Score()

####################################
# Attributes
####################################

self.ModelArgs = ModelArgs
self.ModelArgsNames = [*self.ModelArgs]
self.Runs = len(self.ModelArgs)
self.DataSets = DataSets
self.DataSetsNames = [*self.DataSets]
self.ModelList = dict()
self.ModelListNames = []
self.FitList = dict()
self.FitListNames = []
self.EvaluationList = dict()
self.EvaluationListNames = []
self.InterpretationList = dict()
self.InterpretationListNames = []
self.CompareModelsList = dict()
self.CompareModelsListNames = []

####################################
# Example Usage
####################################

# Setup Environment
import timeit
import datatable as dt
from datatable import sort, f, by
import retrofit
from retrofit import FeatureEngineering as fe
from retrofit import MachineLearning as ml

# Load some data
# BechmarkData.csv is located is the tests folder
Path = "./BenchmarkData.csv"
data = dt.fread(Path)

# Create partitioned data sets
Data = fe.FE2_AutoDataParition(
  data=data, 
  ArgsList=None, 
  DateColumnName=None, 
  PartitionType='random', 
  Ratios=[0.7,0.2,0.1], 
  ByVariables=None, 
  Sort=False, 
  Processing='datatable', 
  InputFrame='datatable', 
  OutputFrame='datatable')

# Prepare modeling data sets
DataSets = ml.ML0_GetModelData(
  Processing='Ftrl',
  TrainData=Data['TrainData'],
  ValidationData=Data['ValidationData'],
  TestData=Data['TestData'],
  ArgsList=None,
  TargetColumnName='Leads',
  NumericColumnNames=['XREGS1', 'XREGS2', 'XREGS3'],
  CategoricalColumnNames=['MarketingSegments', 'MarketingSegments2', 'MarketingSegments3', 'Label'],
  TextColumnNames=None,
  WeightColumnName=None,
  Threads=-1,
  InputFrame='datatable')

# Get args list for algorithm and target type
ModelArgs = ml.ML0_Parameters(
  Algorithms='Ftrl', 
  TargetType="Regression", 
  TrainMethod="Train")

# Initialize RetroFit
x = RetroFit(ModelArgs, DataSets)

# Train Model
x.ML1_Single_Train(Algorithm='Ftrl')

# Score data
x.ML1_Single_Score(DataName=x.DataSetsNames[2], ModelName=x.ModelListNames[0], Algorithm='Ftrl')

# Scoring data names
x.DataSets.keys()

# Check ModelArgs Dict
x.ModelArgs

# Check the names of data sets collected
x.DataSetsNames

# List of model names
x.ModelListNames

# List of model fitted names
x.FitListNames

# List of comparisons
x.CompareModelsListNames
Assets 2
Loading