halib 0.1.47__py3-none-any.whl → 0.1.49__py3-none-any.whl

halib/research/torchloader.py

@@ -0,0 +1,162 @@
+"""
+ * @author Hoang Van-Ha
+ * @email hoangvanhauit@gmail.com
+ * @create date 2024-03-27 15:40:22
+ * @modify date 2024-03-27 15:40:22
+ * @desc this module works as a utility tools for finding the best configuration for dataloader (num_workers, batch_size, pin_menory, etc.) that fits your hardware.
+"""
+from argparse import ArgumentParser
+from ..common import *
+from ..filetype import csvfile
+from ..filetype.yamlfile import load_yaml
+from rich import inspect
+from torch.utils.data import DataLoader
+from torchvision import datasets, transforms
+from tqdm import tqdm
+from typing import Union
+import itertools as it  # for cartesian product
+import os
+import time
+import traceback
+
+
+def parse_args():
+    parser = ArgumentParser(description="desc text")
+    parser.add_argument("-cfg", "--cfg", type=str, help="cfg file for searching")
+    return parser.parse_args()
+
+
+def get_test_range(cfg: dict, search_item="num_workers"):
+    item_search_cfg = cfg["search_space"].get(search_item, None)
+    if item_search_cfg is None:
+        raise ValueError(f"search_item: {search_item} not found in cfg")
+    if isinstance(item_search_cfg, list):
+        return item_search_cfg
+    elif isinstance(item_search_cfg, dict):
+        if "mode" in item_search_cfg:
+            mode = item_search_cfg["mode"]
+            assert mode in ["range", "list"], f"mode: {mode} not supported"
+            value_in_mode = item_search_cfg.get(mode, None)
+            if value_in_mode is None:
+                raise ValueError(f"mode<{mode}>: data not found in <{search_item}>")
+            if mode == "range":
+                assert len(value_in_mode) == 3, f"range must have 3 values: start, stop, step"
+                start = value_in_mode[0]
+                stop = value_in_mode[1]
+                step = value_in_mode[2]
+                return list(range(start, stop, step))
+            elif mode == "list":
+                return item_search_cfg["list"]
+    else:
+        return [item_search_cfg]  # for int, float, str, bool, etc.
+
+
+def load_an_batch(loader_iter):
+    start = time.time()
+    next(loader_iter)
+    end = time.time()
+    return end - start
+
+
+def test_dataloader_with_cfg(origin_dataloader: DataLoader, cfg: Union[dict, str]):
+    try:
+        if isinstance(cfg, str):
+            cfg = load_yaml(cfg, to_dict=True)
+        dfmk = csvfile.DFCreator()
+        search_items = ["batch_size", "num_workers", "persistent_workers", "pin_memory"]
+        batch_limit = cfg["general"]["batch_limit"]
+        csv_cfg = cfg["general"]["to_csv"]
+        log_batch_info = cfg["general"]["log_batch_info"]
+
+        save_to_csv = csv_cfg["enabled"]
+        log_dir = csv_cfg["log_dir"]
+        filename = csv_cfg["filename"]
+        filename = f"{now_str()}_{filename}.csv"
+        outfile = os.path.join(log_dir, filename)
+
+        dfmk.create_table(
+            "cfg_search",
+            (search_items + ["avg_time_taken"]),
+        )
+        ls_range_test = []
+        for item in search_items:
+            range_test = get_test_range(cfg, search_item=item)
+            range_test = [(item, i) for i in range_test]
+            ls_range_test.append(range_test)
+
+        all_combinations = list(it.product(*ls_range_test))
+
+        rows = []
+        for cfg_idx, combine in enumerate(all_combinations):
+            console.rule(f"Testing cfg {cfg_idx+1}/{len(all_combinations)}")
+            inspect(combine)
+            batch_size = combine[search_items.index("batch_size")][1]
+            num_workers = combine[search_items.index("num_workers")][1]
+            persistent_workers = combine[search_items.index("persistent_workers")][1]
+            pin_memory = combine[search_items.index("pin_memory")][1]
+
+            test_dataloader = DataLoader(origin_dataloader.dataset, batch_size=batch_size, num_workers=num_workers, persistent_workers=persistent_workers, pin_memory=pin_memory, shuffle=True)
+            row = [
+                batch_size,
+                num_workers,
+                persistent_workers,
+                pin_memory,
+                0.0,
+            ]
+
+            # calculate the avg time taken to load the data for <batch_limit> batches
+            trainiter = iter(test_dataloader)
+            time_elapsed = 0
+            pprint('Start testing...')
+            for i in tqdm(range(batch_limit)):
+                single_batch_time = load_an_batch(trainiter)
+                if log_batch_info:
+                    pprint(f"Batch {i+1} took {single_batch_time:.4f} seconds to load")
+                time_elapsed += single_batch_time
+            row[-1] = time_elapsed / batch_limit
+            rows.append(row)
+        dfmk.insert_rows('cfg_search', rows)
+        dfmk.fill_table_from_row_pool('cfg_search')
+        with ConsoleLog("results"):
+            csvfile.fn_display_df(dfmk['cfg_search'])
+            if save_to_csv:
+                dfmk["cfg_search"].to_csv(outfile, index=False)
+                console.print(f"[red] Data saved to <{outfile}> [/red]")
+
+    except Exception as e:
+        traceback.print_exc()
+        print(e)
+        # get current directory of this python file
+        current_dir = os.path.dirname(os.path.realpath(__file__))
+        standar_cfg_path = os.path.join(current_dir, "torchloader_search.yaml")
+        pprint(
+            f"Make sure you get the  right <cfg.yaml> file. An example of <cfg.yaml> file can be found at this path: {standar_cfg_path}"
+        )
+        return
+
+def main():
+    args = parse_args()
+    cfg_yaml = args.cfg
+    cfg_dict = load_yaml(cfg_yaml, to_dict=True)
+
+    # Define transforms for data augmentation and normalization
+    transform = transforms.Compose(
+        [
+            transforms.RandomHorizontalFlip(),  # Randomly flip images horizontally
+            transforms.RandomRotation(10),  # Randomly rotate images by 10 degrees
+            transforms.ToTensor(),  # Convert images to PyTorch tensors
+            transforms.Normalize(
+                (0.5, 0.5, 0.5), (0.5, 0.5, 0.5)
+            ),  # Normalize pixel values to [-1, 1]
+        ]
+    )
+    test_dataset = datasets.CIFAR10(
+        root="./data", train=False, download=True, transform=transform
+    )
+    batch_size = 64
+    train_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=True)
+    test_dataloader_with_cfg(train_loader, cfg_dict)
+
+
+if __name__ == "__main__":
+    main()

halib/research/wandb_op.py

@@ -0,0 +1,116 @@
+import glob
+from rich.pretty import pprint
+import os
+import subprocess
+import argparse
+import wandb
+from tqdm import tqdm
+from rich.console import Console
+console = Console()
+
+def sync_runs(outdir):
+    outdir = os.path.abspath(outdir)
+    assert os.path.exists(outdir), f"Output directory {outdir} does not exist."
+    sub_dirs = [name for name in os.listdir(outdir) if os.path.isdir(os.path.join(outdir, name))]
+    assert len(sub_dirs) > 0, f"No subdirectories found in {outdir}."
+    console.rule("Parent Directory")
+    console.print(f"[yellow]{outdir}[/yellow]")
+
+    exp_dirs = [os.path.join(outdir, sub_dir) for sub_dir in sub_dirs]
+    wandb_dirs = []
+    for exp_dir in exp_dirs:
+        wandb_dirs.extend(glob.glob(f"{exp_dir}/wandb/*run-*"))
+    if len(wandb_dirs) == 0:
+        console.print(f"No wandb runs found in {outdir}.")
+        return
+    else:
+        console.print(f"Found [bold]{len(wandb_dirs)}[/bold] wandb runs in {outdir}.")
+        for i, wandb_dir in enumerate(wandb_dirs):
+            console.rule(f"Syncing wandb run {i + 1}/{len(wandb_dirs)}")
+            console.print(f"Syncing: {wandb_dir}")
+            process = subprocess.Popen(
+                ["wandb", "sync", wandb_dir],
+                stdout=subprocess.PIPE,
+                stderr=subprocess.STDOUT,
+                text=True,
+            )
+
+            for line in process.stdout:
+                console.print(line.strip())
+                if " ERROR Error while calling W&B API" in line:
+                    break
+            process.stdout.close()
+            process.wait()
+            if process.returncode != 0:
+                console.print(f"[red]Error syncing {wandb_dir}. Return code: {process.returncode}[/red]")
+            else:
+                console.print(f"Successfully synced {wandb_dir}.")
+
+def delete_runs(project, pattern=None):
+    console.rule("Delete W&B Runs")
+    confirm_msg = f"Are you sure you want to delete all runs in"
+    confirm_msg += f" \n\tproject: [red]{project}[/red]"
+    if pattern:
+        confirm_msg += f"\n\tpattern: [blue]{pattern}[/blue]"
+
+    console.print(confirm_msg)
+    confirmation = input(f"This action cannot be undone. [y/N]: ").strip().lower()
+    if confirmation != "y":
+        print("Cancelled.")
+        return
+
+    print("Confirmed. Proceeding...")
+    api = wandb.Api()
+    runs = api.runs(project)
+
+    deleted = 0
+    console.rule("Deleting W&B Runs")
+    if len(runs) == 0:
+        print("No runs found in the project.")
+        return
+    for run in tqdm(runs):
+        if pattern is None or pattern in run.name:
+            run.delete()
+            console.print(f"Deleted run: [red]{run.name}[/red]")
+            deleted += 1
+
+    console.print(f"Total runs deleted: {deleted}")
+
+
+def valid_argument(args):
+    if args.op == "sync":
+        assert os.path.exists(args.outdir), f"Output directory {args.outdir} does not exist."
+    elif args.op == "delete":
+        assert isinstance(args.project, str) and len(args.project.strip()) > 0, "Project name must be a non-empty string."
+    else:
+        raise ValueError(f"Unknown operation: {args.op}")
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Operations on W&B runs")
+    parser.add_argument("-op", "--op", type=str, help="Operation to perform", default="sync", choices=["delete", "sync"])
+    parser.add_argument("-prj", "--project", type=str, default="fire-paper2-2025", help="W&B project name")
+    parser.add_argument("-outdir", "--outdir", type=str, help="arg1 description", default="./zout/train")
+    parser.add_argument("-pt", "--pattern",
+        type=str,
+        default=None,
+        help="Run name pattern to match for deletion",
+    )
+
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    # Validate arguments, stop if invalid
+    valid_argument(args)
+
+    op = args.op
+    if op == "sync":
+        sync_runs(args.outdir)
+    elif op == "delete":
+        delete_runs(args.project, args.pattern)
+    else:
+        raise ValueError(f"Unknown operation: {op}")
+
+if __name__ == "__main__":
+    main()

halib/utils/listop.py

@@ -0,0 +1,13 @@
+def subtract(list_a, list_b):
+    return [item for item in list_a if item not in list_b]
+
+
+def union(list_a, list_b, no_duplicate=False):
+    if no_duplicate:
+        return list(set(list_a) | set(list_b))
+    else:
+        return list_a + list_b
+
+
+def intersection(list_a, list_b):
+    return list(set(list_a) & set(list_b))

halib/utils/tele_noti.py

@@ -0,0 +1,166 @@
+# Watch a log file and send a telegram message when train reaches a certain epoch or end
+
+import os
+import yaml
+import asyncio
+import telegram
+import pandas as pd
+
+from rich.pretty import pprint
+from rich.console import Console
+import plotly.graph_objects as go
+
+from ..system import filesys as fs
+from ..filetype import textfile, csvfile
+
+from argparse import ArgumentParser
+
+tele_console = Console()
+
+
+def parse_args():
+    parser = ArgumentParser(description="desc text")
+    parser.add_argument(
+        "-cfg",
+        "--cfg",
+        type=str,
+        help="yaml file for tele",
+        default=r"E:\Dev\halib\cfg_tele_noti.yaml",
+    )
+
+    return parser.parse_args()
+
+
+def get_watcher_message_df(target_file, num_last_lines):
+    file_ext = fs.get_file_name(target_file, split_file_ext=True)[1]
+    supported_ext = [".txt", ".log", ".csv"]
+    assert (
+        file_ext in supported_ext
+    ), f"File extension {file_ext} not supported. Supported extensions are {supported_ext}"
+    last_lines_df = None
+    if file_ext in [".txt", ".log"]:
+        lines = textfile.read_line_by_line(target_file)
+        if num_last_lines > len(lines):
+            num_last_lines = len(lines)
+        last_line_arr = lines[-num_last_lines:]
+        # add a line start with word "epoch"
+        epoch_info_list = "Epoch: n/a"
+        for line in reversed(lines):
+            if "epoch" in line.lower():
+                epoch_info_list = line
+                break
+        last_line_arr.insert(0, epoch_info_list)  # insert at the beginning
+        dfCreator = csvfile.DFCreator()
+        dfCreator.create_table("last_lines", ["line"])
+        last_line_arr = [[line] for line in last_line_arr]
+        dfCreator.insert_rows("last_lines", last_line_arr)
+        dfCreator.fill_table_from_row_pool("last_lines")
+        last_lines_df = dfCreator["last_lines"].copy()
+    else:
+        df = pd.read_csv(target_file)
+        num_rows = len(df)
+        if num_last_lines > num_rows:
+            num_last_lines = num_rows
+        last_lines_df = df.tail(num_last_lines)
+    return last_lines_df
+
+
+def df2img(df: pd.DataFrame, output_img_dir, decimal_places, out_img_scale):
+    df = df.round(decimal_places)
+    fig = go.Figure(
+        data=[
+            go.Table(
+                header=dict(values=list(df.columns), align="center"),
+                cells=dict(
+                    values=df.values.transpose(),
+                    fill_color=[["white", "lightgrey"] * df.shape[0]],
+                    align="center",
+                ),
+            )
+        ]
+    )
+    if not os.path.exists(output_img_dir):
+        os.makedirs(output_img_dir)
+    img_path = os.path.normpath(os.path.join(output_img_dir, "last_lines.png"))
+    fig.write_image(img_path, scale=out_img_scale)
+    return img_path
+
+
+def compose_message_and_img_path(
+    target_file, project, num_last_lines, decimal_places, out_img_scale, output_img_dir
+):
+    context_msg = f">> Project: {project} \n>> File: {target_file} \n>> Last {num_last_lines} lines:"
+    msg_df = get_watcher_message_df(target_file, num_last_lines)
+    try:
+        img_path = df2img(msg_df, output_img_dir, decimal_places, out_img_scale)
+    except Exception as e:
+        pprint(f"Error: {e}")
+        img_path = None
+    return context_msg, img_path
+
+
+async def send_to_telegram(cfg_dict, interval_in_sec):
+    # pprint(cfg_dict)
+    token = cfg_dict["telegram"]["token"]
+    chat_id = cfg_dict["telegram"]["chat_id"]
+
+    noti_settings = cfg_dict["noti_settings"]
+    project = noti_settings["project"]
+    target_file = noti_settings["target_file"]
+    num_last_lines = noti_settings["num_last_lines"]
+    output_img_dir = noti_settings["output_img_dir"]
+    decimal_places = noti_settings["decimal_places"]
+    out_img_scale = noti_settings["out_img_scale"]
+
+    bot = telegram.Bot(token=token)
+    async with bot:
+        try:
+            context_msg, img_path = compose_message_and_img_path(
+                target_file,
+                project,
+                num_last_lines,
+                decimal_places,
+                out_img_scale,
+                output_img_dir,
+            )
+            time_now = next_time = pd.Timestamp.now().strftime("%Y-%m-%d %H:%M:%S")
+            sep_line = "-" * 50
+            context_msg = f"{sep_line}\n>> Time: {time_now}\n{context_msg}"
+            # calculate the next time to send message
+            next_time = pd.Timestamp.now() + pd.Timedelta(seconds=interval_in_sec)
+            next_time = next_time.strftime("%Y-%m-%d %H:%M:%S")
+            next_time_info = f"Next msg: {next_time}"
+            tele_console.rule()
+            tele_console.print("[green] Send message to telegram [/green]")
+            tele_console.print(
+                f"[red] Next message will be sent at <{next_time}> [/red]"
+            )
+            await bot.send_message(text=context_msg, chat_id=chat_id)
+            if img_path:
+                await bot.send_photo(chat_id=chat_id, photo=open(img_path, "rb"))
+            await bot.send_message(text=next_time_info, chat_id=chat_id)
+        except Exception as e:
+            pprint(f"Error: {e}")
+            pprint("Message not sent to telegram")
+
+
+async def run_forever(cfg_path):
+    cfg_dict = yaml.safe_load(open(cfg_path, "r"))
+    noti_settings = cfg_dict["noti_settings"]
+    interval_in_min = noti_settings["interval_in_min"]
+    interval_in_sec = int(interval_in_min * 60)
+    pprint(
+        f"Message will be sent every {interval_in_min} minutes or {interval_in_sec} seconds"
+    )
+    while True:
+        await send_to_telegram(cfg_dict, interval_in_sec)
+        await asyncio.sleep(interval_in_sec)
+
+
+async def main():
+    args = parse_args()
+    await run_forever(args.cfg)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())