from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
from sklearn.preprocessing import StandardScaler, OneHotEncoder
At1 = column_pipeline("At1", NumberSelector, StandardScaler, {})
At2 = column_pipeline("At2", NumberSelector, StandardScaler, {})
Class = column_pipeline("Class", NumberSelector, OneHotEncoder, {"categories":"auto"})
Column_pipeline_Dictionary = {"At1":At1, "At2":At2, "Class":Class}
from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler
import numpy as np
_Sex = {"handle_unknown": "ignore"}
_Rings = {"categories": np.array(list(range(100))).reshape(1, -1)}
Sex = column_pipeline("Sex", TextSelector, OneHotEncoder, _Sex)
Length = column_pipeline("Length", NumberSelector, StandardScaler, {})
Diameter = column_pipeline("Diameter", NumberSelector, StandardScaler, {})
Height = column_pipeline("Height", NumberSelector, StandardScaler, {})
Whole_weight = column_pipeline("Whole_weight", NumberSelector, StandardScaler,
{})
Shucked_weight = column_pipeline("Shucked_weight", NumberSelector,
StandardScaler, {})
Viscera_weight = column_pipeline("Viscera_weight", NumberSelector,
StandardScaler, {})
Shell_weight = column_pipeline("Shell_weight", NumberSelector, StandardScaler,
{})
Rings = column_pipeline("Rings", NumberSelector, OneHotEncoder, _Rings)
Column_pipeline_Dictionary = {
"Sex": Sex,
"Length": Length,
"Diameter": Diameter,
"Height": Height,
"Whole_weight": Whole_weight,
"Shucked_weight": Shucked_weight,
from Helper.Transform.Columns.column_pipeline import column_pipeline
from Helper.Transform.Custom.nominal import _Identity
_ClumpThickness = {}
_CellSize = {}
_CellShape = {}
_MaginalAdhesion = {}
_EpithelialSize = {}
_BareNuclei = {}
_BlandChromatin = {}
_NormalNucleoli = {}
_Mitoses = {}
_Class = {}
ClumpThickness = column_pipeline("ClumpThickness", NumberSelector, _Identity,
_ClumpThickness)
CellSize = column_pipeline("CellSize", NumberSelector, _Identity, _CellSize)
CellShape = column_pipeline("CellShape", NumberSelector, _Identity, _CellShape)
MaginalAdhesion = column_pipeline("MarginalAdhesion", NumberSelector,
_Identity, _MaginalAdhesion)
EpithelialSize = column_pipeline("EpithelialSize", NumberSelector, _Identity,
_EpithelialSize)
BareNuclei = column_pipeline("BareNuclei", NumberSelector, _Identity,
_BareNuclei)
BlandChromatin = column_pipeline("BlandChromatin", NumberSelector, _Identity,
_BlandChromatin)
NormalNucleoli = column_pipeline("NormalNucleoli", NumberSelector, _Identity,
_NormalNucleoli)
Mitoses = column_pipeline("Mitoses", NumberSelector, _Identity, _Mitoses)
Class = column_pipeline("Class", NumberSelector, _Identity, _Class)
from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.ColumnSelector import ColumnSelector
from Helper.Transform.Selector.TypeSelector import TypeSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
from Helper.Load.classification import Classification
loadC = Classification("Data", "letter.dat", "letters-name.txt")
from sklearn.preprocessing import StandardScaler
from Helper.Transform.Custom.nominal import _Identity
continuous_ = {}
outputs_ = {}
inputs_number = column_pipeline(loadC.inputs, ColumnSelector, StandardScaler,
continuous_)
outputs = column_pipeline(*loadC.outputs, TextSelector, _Identity, outputs_)
Column_ = {"inputs": inputs_number, "output": outputs}
from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
from Helper.Transform.Custom.nominal import _LabelBinarizer
from sklearn.preprocessing import KBinsDiscretizer
_Age = {"n_bins": 15, "encode": "ordinal", "strategy": "uniform"}
_Year = {"n_bins": 10, "encode": "ordinal", "strategy": "uniform"}
_Positive = {"n_bins": 5, "encode": "ordinal", "strategy": "uniform"}
_Survival = {}
Age = column_pipeline("Age", NumberSelector, KBinsDiscretizer, _Age)
Year = column_pipeline("Year", NumberSelector, KBinsDiscretizer, _Year)
Positive = column_pipeline("Positive", NumberSelector, KBinsDiscretizer,
_Positive)
Survival = column_pipeline("Survival", TextSelector, _LabelBinarizer,
_Survival)
Column_pipeline_Dictionary = {
"Age": Age,
"Year": Year,
"Positive": Positive,
"Survival": Survival
}
from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
from Helper.Transform.Custom.nominal import _LabelBinarizer, _Identity
_Led1 = {}
_Led2 = {}
_Led3 = {}
_Led4 = {}
_Led5 = {}
_Led6 = {}
_Led7 = {}
_number = {}
Led1 = column_pipeline("Led1", NumberSelector, _LabelBinarizer, _Led1)
Led2 = column_pipeline("Led2", NumberSelector, _LabelBinarizer, _Led2)
Led3 = column_pipeline("Led3", NumberSelector, _LabelBinarizer, _Led3)
Led4 = column_pipeline("Led4", NumberSelector, _LabelBinarizer, _Led4)
Led5 = column_pipeline("Led5", NumberSelector, _LabelBinarizer, _Led5)
Led6 = column_pipeline("Led6", NumberSelector, _LabelBinarizer, _Led6)
Led7 = column_pipeline("Led7", NumberSelector, _LabelBinarizer, _Led7)
number = column_pipeline("Number", NumberSelector, _Identity, _number)
Column_pipeline_Dictionary = {
"Led1": Led1,
"Led2": Led2,
"Led3": Led3,
"Led4": Led4,
"Led5": Led5,
"Led6": Led6,
from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
from sklearn.preprocessing import StandardScaler
from Helper.Transform.Custom.nominal import _Identity
SepalLength_ = {}
SepalWidth_ = {}
PetalLength_ = {}
PetalWidth_ = {}
Class_ = {}
SepalLength = column_pipeline("SepalLength", NumberSelector, StandardScaler,
SepalLength_)
SepalWidth = column_pipeline("SepalWidth", NumberSelector, StandardScaler,
SepalWidth_)
PetalLength = column_pipeline("PetalLength", NumberSelector, StandardScaler,
PetalLength_)
PetalWidth = column_pipeline("PetalWidth", NumberSelector, StandardScaler,
PetalWidth_)
Class = column_pipeline("Class", NumberSelector, _Identity, Class_)
Column_pipeline_Dictionary = {
"SepalLength": SepalLength,
"SepalWidth": SepalWidth,
"PetalLength": PetalLength,
"PetalWidth": PetalWidth,
"Class": Class
}
from Helper.Transform.Selector.NumberSelector import NumberSelector
from Helper.Transform.Selector.ColumnSelector import ColumnSelector
from Helper.Transform.Selector.TypeSelector import TypeSelector
from Helper.Transform.Selector.TextSelector import TextSelector
from Helper.Transform.Columns.column_pipeline import column_pipeline
# is this a class? Hyperparameters too? I think these should be classes that take in a load
# object or a transform object.
name = "connect-4"
from Helper.Load.classification import Classification
loadC = Classification("Data", f"{name}.dat", f"{name}-names.txt")
from sklearn.preprocessing import OrdinalEncoder
from Helper.Transform.Custom.nominal import _Identity
continuous_ = {}
outputs_ = {}
inputs_number = column_pipeline(loadC.inputs, ColumnSelector, OrdinalEncoder, continuous_)
outputs = column_pipeline(*loadC.outputs, TextSelector, _Identity, outputs_)
Column_ = {
"inputs":inputs_number,
"output":outputs
}
