LogisticRegression

- implemented LR
- changed classes tree

src/app.py

@@ -1,34 +1,48 @@
 from learning.data import Dataset
-from learning.supervised import LinearRegression
-from learning.ml import MLRegression
+from learning.supervised import LinearRegression, LogisticRegression, MultiLogisticRegression
+from learning.ml import MLAlgorithm
 from typing import Callable
 
-def auto_mpg() -> tuple[int, MLRegression]:
-    df = Dataset("datasets\\auto-mpg.csv", "MPG")
+def auto_mpg() -> tuple[int, MLAlgorithm]:
+    ds = Dataset("datasets\\auto-mpg.csv", "MPG")
 
-    df.to_numbers(["HP"])
-    df.handle_na()
-    df.regularize(excepts=["Cylinders","Year","Origin"])
-    return (1000, LinearRegression(df, learning_rate=0.0001))
+    ds.to_numbers(["HP"])
+    ds.handle_na()
+    ds.regularize(excepts=["Cylinders","Year","Origin"])
+    return (1000, LinearRegression(ds.as_ndarray(), learning_rate=0.0001))
 
-def automobile() -> tuple[int, MLRegression]:
-    df = Dataset("datasets\\regression\\automobile.csv", "symboling")
+def automobile() -> tuple[int, MLAlgorithm]:
+    ds = Dataset("datasets\\regression\\automobile.csv", "symboling")
 
     attributes_to_modify = ["fuel-system", "engine-type", "drive-wheels", "body-style", "make", "engine-location", "aspiration", "fuel-type", "num-of-cylinders", "num-of-doors"]
-    df.factorize(attributes_to_modify)
-    df.to_numbers(["normalized-losses", "bore", "stroke", "horsepower", "peak-rpm", "price"])
-    df.handle_na()
-    df.regularize(excepts=attributes_to_modify)
-    return (1000, LinearRegression(df, learning_rate=0.004))
+    ds.factorize(attributes_to_modify)
+    ds.to_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))
 
-def power_plant() -> tuple[int, MLRegression]:
-    df = Dataset("datasets\\regression\\power-plant.csv", "energy-output")
-    df.regularize()
-    return (80, LinearRegression(df, learning_rate=0.1))
+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))
+
+
+def electrical_grid() -> tuple[int, MLAlgorithm]:
+    ds = Dataset("datasets\\classification\\electrical_grid.csv", "stabf")
+    ds.factorize(["stabf"])
+    ds.regularize()
+    return (1000, LogisticRegression(ds.as_ndarray(), learning_rate=0.08))
+
+def frogs() -> tuple[int, MLAlgorithm]:
+    ds = Dataset("datasets\\classification\\frogs.csv", "Species")
+    ds.remove(["Family", "Genus", "RecordID"])
+    ds.factorize(["Species"])
+    return (1000, MultiLogisticRegression(ds.as_ndarray(), learning_rate=0.08))
 
 
 
-def learn_dataset(function:Callable[..., tuple[int, MLRegression]], epochs:int=100000, verbose=True)-> None:
+
+def learn_dataset(function:Callable[..., tuple[int, MLAlgorithm]], epochs:int=10000, verbose=True)-> MLAlgorithm:
     skip, ml = function()
     ml.learn(epochs, verbose=verbose)
 
@@ -38,8 +52,8 @@ def learn_dataset(function:Callable[..., tuple[int, MLRegression]], epochs:int=1
     print(f"Loss value: tests={err_tests:1.5f}, valid={err_valid:1.5f}, learn={err_learn:1.5f}")
 
     ml.plot(skip=skip)
-
-
+    return ml
 
 if __name__ == "__main__":
-    learn_dataset(automobile)
+    ml = learn_dataset(electrical_grid)
+    print(ml.accuracy(ml.testset))