Merge pull request #68 from emlearn/logistic-regression

Add logistic regression

Author: jonnor

Makefile

@@ -37,6 +37,7 @@ MODULES = emlearn_trees \
 	emlearn_iir_q15 \
 	emlearn_arrayutils \
 	emlearn_linreg \
+	emlearn_logreg \
 	emlearn_cnn_int8 \
 	emlearn_cnn_fp32
 
@@ -83,7 +84,7 @@ webassembly: $(WEBASSEMBLY_MICROPYTHON)
 
 
 check_unix: $(UNIX_MICROPYTHON)
-	$(UNIX_MICROPYTHON) tests/test_all.py test_iir,test_fft,test_arrayutils,test_linreg
+	$(UNIX_MICROPYTHON) tests/test_all.py test_iir,test_fft,test_arrayutils,test_linreg,test_logreg
 	# TODO: enable more modules
 
 rp2: $(PORT_DIR)
@@ -105,6 +106,7 @@ clean:
 	make -C src/emlearn_trees/ ARCH=$(ARCH) MPY_DIR=$(MPY_DIR_ABS) V=1 clean
 	make -C src/emlearn_neighbors/ ARCH=$(ARCH) MPY_DIR=$(MPY_DIR_ABS) V=1 clean
 	make -C src/emlearn_iir/ ARCH=$(ARCH) MPY_DIR=$(MPY_DIR_ABS) V=1 clean
+	make -C src/emlearn_logreg/ ARCH=$(ARCH) MPY_DIR=$(MPY_DIR_ABS) V=1 clean
 	rm -rf ./dist
 
 RELEASE_NAME = emlearn-micropython-$(VERSION)

examples/datasets/cancer/X_test.npy

@@ -0,0 +1,52 @@
+#!/usr/bin/env python3
+"""Download and preprocess the Breast Cancer Wisconsin dataset."""
+
+from pathlib import Path
+import os
+
+import numpy as np
+from sklearn.datasets import load_breast_cancer
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+
+def main():
+
+    here = os.path.dirname(__file__)
+
+    OUTPUT_DIR = Path(here)
+    OUTPUT_DIR.mkdir(exist_ok=True)
+
+    FILENAMES = {
+        'X_train': OUTPUT_DIR / 'X_train.npy',
+        'X_test': OUTPUT_DIR / 'X_test.npy',
+        'y_train': OUTPUT_DIR / 'y_train.npy',
+        'y_test': OUTPUT_DIR / 'y_test.npy',
+    }
+
+    X, y = load_breast_cancer(return_X_y=True)
+    scaler = StandardScaler()
+    X = scaler.fit_transform(X).astype('float32')
+    y = y.astype('float32')
+
+    X_train, X_test, y_train, y_test = train_test_split(
+        X,
+        y,
+        test_size=0.25,
+        random_state=42,
+        stratify=y,
+    )
+
+    np.save(FILENAMES['X_train'], X_train)
+    np.save(FILENAMES['X_test'], X_test)
+    np.save(FILENAMES['y_train'], y_train)
+    np.save(FILENAMES['y_test'], y_test)
+
+    print('Saved datasets:')
+    print(f"  X_train: {X_train.shape} -> {FILENAMES['X_train']}")
+    print(f"  X_test : {X_test.shape} -> {FILENAMES['X_test']}")
+    print(f"  y_train: {y_train.shape} -> {FILENAMES['y_train']}")
+    print(f"  y_test : {y_test.shape} -> {FILENAMES['y_test']}")
+
+
+if __name__ == '__main__':
+    main()

examples/datasets/cancer/X_train.npy

@@ -0,0 +1,33 @@
+
+import os.path
+
+import numpy as np
+from sklearn.datasets import load_wine
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+
+def main():
+
+    here = os.path.dirname(__file__)
+    out_dir = here
+
+    wine = load_wine()
+    X = wine.data.astype(np.float32)
+    y = wine.target.astype(np.float32)
+
+    scaler = StandardScaler()
+    X = scaler.fit_transform(X).astype(np.float32)
+
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.25, random_state=42, stratify=y
+    )
+
+    np.save(os.path.join(out_dir, 'X_train.npy'), X_train)
+    np.save(os.path.join(out_dir, 'X_test.npy'), X_test)
+    np.save(os.path.join(out_dir, 'y_train.npy'), y_train)
+    np.save(os.path.join(out_dir, 'y_test.npy'), y_test)
+
+    print('Wrote to', out_dir)
+
+if __name__ == '__main__':
+    main()