Category: Python

circuitpython 8.2.6 observations

whbeebe

I’ve written a script in CircuitPython 8.2.6 running on a Raspberry Pi Pico W. The latest versions of both CircuitPython and MicroPython (from which CircuitPython is derived) has implemented Python’s async/await concurrent support, which I have used to great effect below.

The listing starts with “identifying” code that tells me what some of the Pico W’s resources are. You don’t need them for the async portions, but it comes in handy when I’m trying to debug or create new CircuitPython applications, and I believe you’ll find them as useful as I have.

One other feature I’ve used is the Python ‘f’ string to print formatted strings with data. It’s a feature that’s been in regular Python for a few years now, and it’s been copied over to MicroPython and CircuitPython for nearly as long.

What follows is the code listing, after which I describe various section functionalities.

import boardimport digitalioimport gcimport microcontroller as mcimport osimport sysimport time# Introduce yourself#print(f"\n{os.uname().machine}")print(f"{sys.implementation.name} v{'.'.join(map(str,sys.implementation.version))}")print(f"CPU clock: {mc.cpu.frequency:,} Hz")print("-------------------------------\n")# Show available memory#print("Memory Stats - gc.mem_free()")print(f"Free: {gc.mem_free():,} Bytes")print("----------------------------\n")# Show flash size#flash = os.statvfs('/')flash_size = flash[0] * flash[2]flash_free = flash[0] * flash[3]print("Flash Stats- os.statvfs('/')")print(f"Size: {flash_size:,} Bytes\nFree: {flash_free:,} Bytes")print("----------------------------\n")# Check local WiFi network#import wifinetworks = {}for network in wifi.radio.start_scanning_networks():if len(network.ssid) > 0 and network.ssid[0] != '\x00':networks[network.ssid] = networkwifi.radio.stop_scanning_networks()print("WIFI: SCAN, SORTED BY SSID")for ssid in sorted(networks):print(f"SSID: {ssid:<24}- RSSI: {networks[ssid].rssi}")import binascii as baNAME = os.uname().sysname.upper()UNIQUE_ID = ba.hexlify(mc.cpu.uid).decode('ascii').upper()HOST_NAME = NAME + "-" + UNIQUE_ID[-4:]print()print(f"Board SSID: {HOST_NAME}")print("----------------------------\n")# Check for any I2C devices#import busioimport displayioimport adafruit_displayio_ssd1306 as ssd1306displayio.release_displays()i2c = busio.I2C(board.GP9, board.GP8)i2c.try_lock()i2c.scan()i2c.unlock()display_bus = displayio.I2CDisplay(i2c, device_address=60)display = ssd1306.SSD1306(display_bus, width=128, height=32)import asynciointerval_addition = 0.0async def blink(pin, interval):with digitalio.DigitalInOut(pin) as led:led.switch_to_output(value=False)while True:led.value = Trueawait asyncio.sleep(interval)led.value = Falseawait asyncio.sleep(interval + interval_addition)import rotaryio# SW - GP18 - push button# DT - GP19 - direction# CLK - GP20 - pulse out#async def rotary_encoder():global interval_additionencoder = rotaryio.IncrementalEncoder(board.GP20, board.GP19, 4)last_position = 0.0while True:position = encoder.positionif position != last_position and position >= 0:print(f"Off delay: + {position/10} sec")if position > last_position:interval_addition += 0.1else:interval_addition -= 0.1last_position = positionawait asyncio.sleep(0)import keypadasync def rotary_encoder_push(pin):with keypad.Keys((pin,), value_when_pressed = False) as keys:while True:event = keys.events.get()if event:if event.pressed:print("Rotary encoder pushed")elif event.released:print("Rotary encoder released")await asyncio.sleep(0)async def main():led1_task = asyncio.create_task(blink(board.GP16, 0.2))led2_task = asyncio.create_task(blink(board.GP17, 0.1))roto_task = asyncio.create_task(rotary_encoder())push_task = asyncio.create_task(rotary_encoder_push(board.GP18))await asyncio.gather(led1_task, led2_task, roto_task, push_task)asyncio.run(main())

Preamble Code

Lines 9 through 49 document the Pico W’s environment, which is how much memory and flash storage, and the WiFi environment. It’s the WiFi environment check I want to draw attention to in particular. It’s more robust than just about every other example on the web. It turned out that for whatever reason the call to wifi.radio.start_scanning_networks() returns duplicate entries and entries in which the SSID is full of nulls. I used a Python dictionary to eliminate duplicates and a character test to see if the first character of the SSID isn’t a null. The resultant dictionary is sorted by the dictionary keys (SSID), which makes the printing of local SSID access point names easier to read.

Checking for I2C Devices

Lines 51 through 61 dig deeper into the Pico W’s environment, in this case any devices attached via the I2C bus.

Asyncio

The last section of the code, lines 66 to 140, are the interesting parts. Line 66 imports the asyncio library, which we’ll use throughout the remaining code listing. Lines 70, 86, and 103 use the async keyword before the function definition to mark these functions as using concurrency, instead of threads, for multitasking. All the sleep(..) functions are now written as await asyncio.sleep(...) to work with the concurrency framework. Failure to use regular sleep instead of asyncio’s sleep will cause only the first function called to execute. Behind the scenes, asyncio’s sleep yields to allow any other scheduled concurrent threads to execute. Even a call with ‘0’ will yield, and return almost immediately after.

Lines 114 to 121 set up the running of the tasks. The way the tasks are written, none of them actually return, which means everything works as it’s intended to, which is all the time.

Oddball Problem

I have a small 128×32, 16 character by 4 line LCD display attached via I2C. For the longest time the code would fault at line 58 at startup, saying that pin GP9 was already being used, which was perplexing as hell as that was the first place in the code it was referenced. I finally found, in another forum post about another problem, the line at 57, which temporarily releases the display and thus the pin to be defined at line 58. Even more bazaar is that the I2C device scan returns nothing.

Finally, the print line at 93 shows up on the LCD display even though I don’t explicitly do that. The LCD display is echoing what goes out on the REPL all on its own. It’s as if CircuitPython, behind the scenes, is scanning and finding that LCD display and then using it without me setting it up that way. I have never encountered this kind of behavior before, either with earlier CircuitPython releases or anything from MicroPython, either.

little ai can’t write python code

whbeebe1 Comment

Two posts back I wrote about installing GPT4All on my M1 MacBook Pro. At first blush I was impressed, as it seemed to answer the softball questions I asked it correctly and with style. Then I got a little more serious and asked it this question:

write a python program that reads a directoryand prints out everything it finds

To which GPT4All Falcon gave this answer:

Here's an example Python program that uses the`os` module to read a directory and print outeverything it finds:
import os# Set the directory pathdir_path = '/path/to/directory'# Check if the directory existsif not os.path.exists(dir_path):print("Directory does not exist")return# Iterate through all files in the directoryfor file in os.listdir(dir_path):# Check if the file is a directoryif os.path.isdir(os.path.join(dir_path, file)):# If it's a directory, recursively call this functionprint("Directory:", file)print("Files:", os.listdir(os.path.join(dir_path, file)))# Check if the directory is emptyif not os.path.exists(dir_path):print("Directory does not exist")
This program uses the `os.listdir` functionto get a list of all files in the directoryand the `os.path.join` function to constructthe full path for each file.It then calls itself recursively on anydirectories it finds, printing out thedirectory name and its contents.

Let’s examine the Python code. There is a blatant error on line 9. Python does not allow the use of a return outside of a proceedure. If you need to exit a script due to some condition, then you use Python’s exit keyword.

The second problem are lines 19-21. They don’t do anything. The message on line 21 is the same as the message on line 8. If the block of code in lines 19-21 is to determine if the directory is empty then it should say that.

Let’s clean up the code enough to actually work.

#!/usr/bin/env python3import os# Set the directory pathdir_path = '.'# Check if the directory existsif not os.path.exists(dir_path):print("Directory does not exist")exit(1)# Iterate through all files in the directoryfor file in os.listdir(dir_path):# Check if the file is a directoryif os.path.isdir(os.path.join(dir_path, file)):# If it's a directory, recursively call this functionprint("Directory:", file)print("Files:", os.listdir(os.path.join(dir_path, file)))

Now let’s test it. I’ve created some dummy directories and files. Here’s what the utility tree shows.

├── foo│   ├── bar│   │   ├── five│   │   ├── seven│   │   └── six│   ├── four│   ├── one│   ├── three│   └── two├── foo2

Now let’s run our corrected AI code and look at the output.

Directory: fooFiles: ['three', 'one', 'two', 'bar', 'four']Directory: foo2Files: []

It’s unsurprisingly disappointing. There’s a comment on line 15 (16 in the corrected code) that says to “recursively call this function” if a directory is detected. It doesn’t in part because there are no functions, and because the test for a directory doesn’t do anything but print out if it’s a directory.

The code looks like during its learning phase it swept up someone’s Stack Overflow question, but didn’t know enough to look at any answers, assuming there were any. Whatever ideas I might have had to incorporate the Falcon model into anything have been pretty much squelched. I’ll install some others and give them a spin.

Links

ChatGPT Isn’t Coming for Your Coding Job — Wired — https://www.wired.com/story/chatgpt-coding-software-crisis/