Add Partial Least Squares Regression (PLSR)

.github/workflows/build.yaml

@@ -8,8 +8,7 @@ jobs:
   build-linux:
     runs-on: ubuntu-24.04
     env:
-      MPY_DIR: ./micropython
-      MICROPYTHON_BIN: ./micropython/ports/unix/build-nomodules/micropython
+      MICROPYTHON_BIN: ./dependencies/micropython/ports/unix/build-nomodules/micropython
     steps:
     - uses: actions/checkout@v4
       with:
@@ -19,15 +18,10 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - uses: actions/checkout@v4
-      with:
-        repository: micropython/micropython
-        path: micropython
-        ref: v1.27.0
     - name: Install Python dependencies
       run: pip install -r requirements.txt
     - name: Setup MicroPython X86
-      working-directory: micropython
+      working-directory: ./dependencies/micropython
       run: |
         source tools/ci.sh && ci_unix_32bit_setup && ci_unix_standard_build
         mv ./ports/unix/build-standard/ ./ports/unix/build-nomodules/
@@ -47,8 +41,7 @@ jobs:
   build-arm:
     runs-on: ubuntu-24.04
     env:
-      MPY_DIR: ./micropython
-      MICROPYTHON_BIN: ./micropython/ports/unix/build-nomodules/micropython
+      MICROPYTHON_BIN: ./dependencies/micropython/ports/unix/build-nomodules/micropython
     steps:
     - uses: actions/checkout@v4
       with:
@@ -58,20 +51,15 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - uses: actions/checkout@v4
-      with:
-        repository: micropython/micropython
-        path: micropython
-        ref: v1.27.0
     - name: Install Python dependencies
       run: pip install -r requirements.txt
     - name: Setup MicroPython ARM
-      working-directory: micropython
+      working-directory: ./dependencies/micropython
       run: |
         source tools/ci.sh && ci_rp2_setup
         make -C mpy-cross
     - name: Setup MicroPython RP2 port
-      working-directory: micropython/ports/rp2
+      working-directory: ./dependencies/micropython/ports/rp2
       run: |
         make submodules
         make clean
@@ -92,8 +80,7 @@ jobs:
   build-esp32:
     runs-on: ubuntu-24.04
     env:
-      MPY_DIR: ./micropython
-      MICROPYTHON_BIN: ./micropython/ports/unix/build-nomodules/micropython
+      IDF_VER: v5.5.1
     steps:
     - uses: actions/checkout@v4
       with:
@@ -103,29 +90,24 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - uses: actions/checkout@v4
-      with:
-        repository: micropython/micropython
-        path: micropython
-        ref: v1.27.0
     - name: Install Python dependencies
       run: pip install -r requirements.txt
 
     - name: Setup MicroPython ESP32
-      working-directory: micropython
+      working-directory: ./dependencies/micropython
       run: |
         source tools/ci.sh && ci_esp32_idf_setup
         make -C mpy-cross
     - name: Setup submodules esp32
-      working-directory: micropython/ports/esp32
+      working-directory: ./dependencies/micropython/ports/esp32
       run: source ../../esp-idf/export.sh && make submodules
     - name: Build custom firmware with extmod, ESP32
       run: |
-        source micropython/esp-idf/export.sh && pip install -r requirements.txt
+        source ./dependencies/micropython/esp-idf/export.sh && pip install -r requirements.txt
         make extmod PORT=esp32 BOARD=ESP32_GENERIC_S3
         make extmod PORT=esp32 BOARD=ESP32_GENERIC
     - name: Build module xtensawin
-      run: source micropython/esp-idf/export.sh && pip install -r requirements.txt && make dist ARCH=xtensawin V=1
+      run: source ./dependencies/micropython/esp-idf/export.sh && pip install -r requirements.txt && make dist ARCH=xtensawin V=1
     - name: Archive dist artifacts
       uses: actions/upload-artifact@v4
       with:
@@ -136,8 +118,7 @@ jobs:
   build-riscv:
     runs-on: ubuntu-24.04
     env:
-      MPY_DIR: ./micropython
-      MICROPYTHON_BIN: ./micropython/ports/unix/build-nomodules/micropython
+      IDF_VER: v5.5.1
     steps:
     - uses: actions/checkout@v4
       with:
@@ -147,28 +128,23 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - uses: actions/checkout@v4
-      with:
-        repository: micropython/micropython
-        path: micropython
-        ref: v1.27.0
     - name: Install Python dependencies
       run: pip install -r requirements.txt
 
     - name: Setup MicroPython ESP32
-      working-directory: micropython
+      working-directory: ./dependencies/micropython
       run: |
         source tools/ci.sh && ci_esp32_idf_setup && ci_gcc_riscv_setup
         make -C mpy-cross
     - name: Setup submodules esp32
-      working-directory: micropython/ports/esp32
+      working-directory: ./dependencies/micropython/ports/esp32
       run: source ../../esp-idf/export.sh && make submodules
     - name: Build custom firmware with extmod, ESP32
       run: |
-        source micropython/esp-idf/export.sh && pip install -r requirements.txt
+        source ./dependencies/micropython/esp-idf/export.sh && pip install -r requirements.txt
         echo make extmod PORT=esp32 BOARD=ESP32_GENERIC_C6
     - name: Build nadmod xtensawin
-      run: source micropython/esp-idf/export.sh && pip install -r requirements.txt && make dist ARCH=rv32imc V=1
+      run: source ./dependencies/micropython/esp-idf/export.sh && pip install -r requirements.txt && make dist ARCH=rv32imc V=1
     - name: Archive dist artifacts
       uses: actions/upload-artifact@v4
       with:
@@ -179,9 +155,7 @@ jobs:
   build-macos:
     runs-on: macos-latest
     env:
-      MPY_DIR: ./micropython
-      MICROPYTHON_BIN: ./micropython/ports/unix/build-nomodules/micropython
-
+      MICROPYTHON_BIN: ./dependencies/micropython/ports/unix/build-nomodules/micropython
     steps:
     - uses: actions/checkout@v4
       with:
@@ -195,15 +169,10 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - uses: actions/checkout@v4
-      with:
-        repository: micropython/micropython
-        path: micropython
-        ref: v1.27.0
     - name: Install Python dependencies
       run: pip install -r requirements.txt
     - name: Setup MicroPython X86
-      working-directory: micropython
+      working-directory: ./dependencies/micropython
       run: |
         make -C mpy-cross CFLAGS_EXTRA=-Wno-error
         make -C ports/unix submodules
@@ -226,8 +195,7 @@ jobs:
   build-webassembly:
     runs-on: ubuntu-latest
     env:
-      MPY_DIR: ./micropython
-      MICROPYTHON_BIN: ./micropython/ports/unix/build-nomodules/micropython
+      MICROPYTHON_BIN: ./dependencies/micropython/ports/unix/build-nomodules/micropython
     steps:
     - uses: actions/checkout@v4
       with:
@@ -237,24 +205,19 @@ jobs:
     - uses: actions/setup-python@v5
       with:
         python-version: '3.10'
-    - uses: actions/checkout@v4
-      with:
-        repository: jonnor/micropython
-        path: micropython
-        ref: webassembly-extra-cflags
     - name: Install Python dependencies
       run: pip install -r requirements.txt
     - name: Setup MicroPython
-      working-directory: micropython
+      working-directory: ./dependencies/micropython
       run: |
         npm install terser
         git clone https://github.com/emscripten-core/emsdk.git
         (cd emsdk && ./emsdk install 4.0.21 && ./emsdk activate 4.0.21)
         make -C mpy-cross CFLAGS_EXTRA=-Wno-error
     - name: Build Webassembly
       run: |
-        source ${MPY_DIR}/emsdk/emsdk_env.sh
-        make -C ${MPY_DIR}/ports/webassembly submodules
+        source ./dependencies/micropython/emsdk/emsdk_env.sh
+        make -C ./dependencies/micropython/ports/webassembly submodules
         make webassembly V=1
     - name: Archive dist artifacts
       uses: actions/upload-artifact@v4

.gitmodules

@@ -4,3 +4,6 @@
 [submodule "dependencies/CMSIS-DSP"]
 	path = dependencies/CMSIS-DSP
 	url = https://github.com/ARM-software/CMSIS-DSP.git
+[submodule "dependencies/micropython"]
+	path = dependencies/micropython
+	url = https://github.com/jonnor/micropython.git

Makefile

@@ -1,7 +1,7 @@
 
 ARCH ?= x64
 MPY_ABI_VERSION ?= 6.3
-MPY_DIR ?= ../micropython
+MPY_DIR ?= ./dependencies/micropython
 MICROPYTHON_BIN ?= micropython
 
 # extmod settings
@@ -10,7 +10,7 @@ BOARD=ESP32_GENERIC_S3
 
 VERSION := $(shell git describe --tags --always)
 
-MPY_DIR_ABS = $(abspath $(MPY_DIR)) 
+MPY_DIR_ABS = $(abspath $(MPY_DIR))
 
 C_MODULES_SRC_PATH = $(abspath ./src)
 
@@ -39,6 +39,7 @@ MODULES = emlearn_trees \
 	emlearn_linreg \
 	emlearn_logreg \
 	emlearn_extratrees \
+	emlearn_plsr \
 	emlearn_cnn_int8 \
 	emlearn_cnn_fp32
 
@@ -62,6 +63,7 @@ emlearn_arrayutils_SRC = src/emlearn_arrayutils
 emlearn_linreg_SRC = src/emlearn_linreg
 emlearn_logreg_SRC = src/emlearn_logreg
 emlearn_extratrees_SRC = src/emlearn_extratrees
+emlearn_plsr_SRC = src/emlearn_plsr
 
 # Dependencies for each .mpy file: .c, .h, .py files, and Makefile
 $(foreach mod,$(MODULES),\
@@ -151,7 +153,10 @@ extmod: $(SRC_ALL) src/manifest_unix.py
 	cp -r $(PORT_BUILD_DIR)/micropython* $(PORT_DIST_DIR)
 
 
-.PHONY: clean unix
+.PHONY: clean unix codesize
+
+codesize:
+	python3 tools/code_size.py $(MPY_DIR_ABS)/ports/unix/build-standard
 
 clean:
 	make -C src/emlearn_trees/ ARCH=$(ARCH) MPY_DIR=$(MPY_DIR_ABS) V=1 clean

examples/datasets/airquality/prepare.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+"""Download and preprocess the Air Quality UCI dataset for PLS regression.
+
+Also computes sklearn PLSR reference results for comparison.
+Run with CPython: python3 examples/datasets/airquality/prepare.py
+"""
+
+from pathlib import Path
+import os
+import urllib.request
+import zipfile
+
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.cross_decomposition import PLSRegression
+from sklearn.metrics import r2_score, mean_squared_error
+
+
+def main():
+
+    here = os.path.dirname(__file__)
+    OUTPUT_DIR = Path(here)
+    OUTPUT_DIR.mkdir(exist_ok=True)
+
+    # Download
+    url = "https://archive.ics.uci.edu/ml/machine-learning-databases/00360/AirQualityUCI.zip"
+    zip_path = OUTPUT_DIR / "AirQualityUCI.zip"
+    if not zip_path.exists():
+        print("Downloading Air Quality UCI dataset...")
+        urllib.request.urlretrieve(url, zip_path)
+    with zipfile.ZipFile(zip_path, 'r') as zf:
+        zf.extractall(OUTPUT_DIR)
+
+    # Load and preprocess
+    csv_file = OUTPUT_DIR / "AirQualityUCI.csv"
+    df = pd.read_csv(csv_file, sep=';', decimal=',')
+    df = df.iloc[:, :-2]  # drop last two empty columns
+    df.replace(-200, np.nan, inplace=True)
+    df.dropna(inplace=True)
+
+    X = df.iloc[:, 2:].values.astype(np.float32)  # sensor columns
+    y = df["CO(GT)"].values.astype(np.float32)
+
+    scaler_X = StandardScaler()
+    X = scaler_X.fit_transform(X).astype(np.float32)
+
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42
+    )
+
+    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',
+    }
+
+    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']}")
+
+    # Sklearn PLSR reference results
+    print('\nSklearn PLSR reference:')
+    for nc in [3, 5]:
+        pls = PLSRegression(n_components=nc)
+        pls.fit(X_train, y_train)
+        y_pred = pls.predict(X_test).ravel()
+        mse = mean_squared_error(y_test, y_pred)
+        r2 = r2_score(y_test, y_pred)
+        print(f"  n_components={nc}: MSE={mse:.5f}, R^2={r2:.5f}")
+
+
+if __name__ == '__main__':
+    main()