Refactor Dataset

- better finalize function
- support for one-hot-encoding

src/app.py

@@ -1,43 +1,43 @@
-from learning.data import Dataset
-from learning.supervised import LinearRegression, LogisticRegression, MultiLogisticRegression
+from learning.data import Dataset, TargetType
+from learning.supervised import LinearRegression, LogisticRegression, MultiLayerPerceptron
 from learning.ml import MLAlgorithm
 from typing import Callable
 
 def auto_mpg() -> tuple[int, MLAlgorithm]:
-    ds = Dataset("datasets\\auto-mpg.csv", "MPG")
+    ds = Dataset("datasets\\auto-mpg.csv", "MPG", TargetType.Regression)
 
-    ds.to_numbers(["HP"])
+    ds.numbers(["HP"])
     ds.handle_na()
-    ds.regularize(excepts=["Cylinders","Year","Origin"])
-    return (1000, LinearRegression(ds.as_ndarray(), learning_rate=0.0001))
+    ds.normalize(excepts=["Cylinders","Year","Origin"])
+    return (1000, LinearRegression(ds, learning_rate=0.0001))
 
 def automobile() -> tuple[int, MLAlgorithm]:
-    ds = Dataset("datasets\\regression\\automobile.csv", "symboling")
+    ds = Dataset("datasets\\regression\\automobile.csv", "symboling", TargetType.Regression)
 
     attributes_to_modify = ["fuel-system", "engine-type", "drive-wheels", "body-style", "make", "engine-location", "aspiration", "fuel-type", "num-of-cylinders", "num-of-doors"]
     ds.factorize(attributes_to_modify)
-    ds.to_numbers(["normalized-losses", "bore", "stroke", "horsepower", "peak-rpm", "price"])
+    ds.numbers(["normalized-losses", "bore", "stroke", "horsepower", "peak-rpm", "price"])
     ds.handle_na()
-    ds.regularize(excepts=attributes_to_modify)
-    return (1000, LinearRegression(ds.as_ndarray(), learning_rate=0.004))
+    ds.normalize(excepts=attributes_to_modify)
+    return (1000, LinearRegression(ds, learning_rate=0.004))
 
 def power_plant() -> tuple[int, MLAlgorithm]:
-    ds = Dataset("datasets\\regression\\power-plant.csv", "energy-output")
-    ds.regularize()
-    return (80, LinearRegression(ds.as_ndarray(), learning_rate=0.1))
+    ds = Dataset("datasets\\regression\\power-plant.csv", "energy-output", TargetType.Regression)
+    ds.normalize()
+    return (80, LinearRegression(ds, learning_rate=0.1))
 
 
 def electrical_grid() -> tuple[int, MLAlgorithm]:
-    ds = Dataset("datasets\\classification\\electrical_grid.csv", "stabf")
+    ds = Dataset("datasets\\classification\\electrical_grid.csv", "stabf", TargetType.Classification)
     ds.factorize(["stabf"])
-    ds.regularize()
-    return (1000, LogisticRegression(ds.as_ndarray(), learning_rate=0.08))
+    ds.normalize()
+    return (1000, LogisticRegression(ds, learning_rate=0.08))
 
 def frogs() -> tuple[int, MLAlgorithm]:
-    ds = Dataset("datasets\\classification\\frogs.csv", "Species")
+    ds = Dataset("datasets\\classification\\frogs.csv", "Species", TargetType.MultiClassification)
     ds.remove(["Family", "Genus", "RecordID"])
     ds.factorize(["Species"])
-    return (1000, MultiLogisticRegression(ds.as_ndarray(), learning_rate=0.08))
+    return (1000, MultiLayerPerceptron(ds, learning_rate=0.08))
 
 
 
@@ -55,5 +55,5 @@ def learn_dataset(function:Callable[..., tuple[int, MLAlgorithm]], epochs:int=10
     return ml
 
 if __name__ == "__main__":
-    ml = learn_dataset(electrical_grid)
+    ml = learn_dataset(automobile)
     print(ml.accuracy(ml.testset))