halib 0.2.1__py3-none-any.whl → 0.2.3__py3-none-any.whl

halib/filetype/csvfile.py

@@ -1,19 +1,13 @@
+import csv
+import textwrap
 import pandas as pd
+import pygwalker as pyg
 from tabulate import tabulate
 from rich.console import Console
-from rich import print as rprint
-from rich import inspect
-from rich.pretty import pprint
-from tqdm import tqdm
-from loguru import logger
 from itables import init_notebook_mode, show
-import pygwalker as pyg
-import textwrap
-import csv
 
 console = Console()
 
-
 def read(file, separator=","):
     df = pd.read_csv(file, separator)
     return df

halib/filetype/ipynb.py

@@ -1,10 +1,8 @@
-from contextlib import contextmanager
-from pathlib import Path
-
 import ipynbname
+from pathlib import Path
+from contextlib import contextmanager
 
-from ..common import console, now_str
-
+from ..common.common import now_str
 
 @contextmanager
 def gen_ipynb_name(

halib/filetype/jsonfile.py

@@ -1,17 +1,14 @@
 import json
 
-
 def read(file):
     with open(file) as f:
         data = json.load(f)
         return data
 
-
 def write(data_dict, outfile):
     with open(outfile, "w") as json_file:
         json.dump(data_dict, json_file)
 
-
 def beautify(json_str):
     formatted_json = json_str
     try:

halib/filetype/textfile.py

@@ -4,7 +4,6 @@ def read_line_by_line(file_path):
         lines = [line.rstrip() for line in lines]
         return lines
 
-
 def write(lines, outfile, append=False):
     mode = "a" if append else "w"
     with open(outfile, mode, encoding="utf-8") as f:

halib/filetype/videofile.py

@@ -1,11 +1,100 @@
+import os
 import cv2
-import textfile
 import enlighten
+
 from enum import Enum
-from ..system import filesys
 from tube_dl import Youtube, Playlist
 from moviepy.video.io.ffmpeg_tools import ffmpeg_extract_subclip
 
+from . import textfile
+from . import csvfile
+from ..system import filesys
+
+class VideoUtils:
+    @staticmethod
+    def _default_meta_extractor(video_path):
+        """Default video metadata extractor function."""
+        # Open the video file
+        cap = cv2.VideoCapture(video_path)
+
+        # Check if the video was opened successfully
+        if not cap.isOpened():
+            print(f"Error: Could not open video file {video_path}")
+            return None
+
+        # Get the frame count
+        frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+        # Get the FPS
+        fps = cap.get(cv2.CAP_PROP_FPS)
+
+        # get frame size
+        width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+        # Release the video capture object
+        cap.release()
+
+        meta_dict = {
+            "video_path": video_path,
+            "width": width,
+            "height": height,
+            "frame_count": frame_count,
+            "fps": fps,
+        }
+        return meta_dict
+
+    @staticmethod
+    def get_video_meta_dict(video_path, meta_dict_extractor_func=None):
+        assert os.path.exists(video_path), f"Video file {video_path} does not exist"
+        if meta_dict_extractor_func and callable(meta_dict_extractor_func):
+            assert (
+                meta_dict_extractor_func.__code__.co_argcount == 1
+            ), "meta_dict_extractor_func must take exactly one argument (video_path)"
+            meta_dict = meta_dict_extractor_func(video_path)
+            assert isinstance(
+                meta_dict, dict
+            ), "meta_dict_extractor_func must return a dictionary"
+            assert "video_path" in meta_dict, "meta_dict must contain 'video_path'"
+        else:
+            meta_dict = VideoUtils._default_meta_extractor(video_path=video_path)
+        return meta_dict
+
+    @staticmethod
+    def get_video_dir_meta_df(
+        video_dir,
+        video_exts=[".mp4", ".avi", ".mov", ".mkv"],
+        search_recursive=False,
+        csv_outfile=None,
+    ):
+        assert os.path.exists(video_dir), f"Video directory {video_dir} does not exist"
+        video_files = filesys.filter_files_by_extension(
+            video_dir, video_exts, recursive=search_recursive
+        )
+        assert (
+            len(video_files) > 0
+        ), f"No video files found in {video_dir} with extensions {video_exts}"
+        video_meta_list = []
+        for vfile in video_files:
+            meta_dict = VideoUtils.get_video_meta_dict(vfile)
+            if meta_dict:
+                video_meta_list.append(meta_dict)
+        dfmk = csvfile.DFCreator()
+        columns = list(video_meta_list[0].keys())
+        assert len(columns) > 0, "No video metadata found"
+        assert "video_path" in columns, "video_path column not found in video metadata"
+        # move video_path to the first column
+        columns.remove("video_path")
+        columns.insert(0, "video_path")
+        dfmk.create_table("video_meta", columns)
+        rows = [[meta[col] for col in columns] for meta in video_meta_list]
+        dfmk.insert_rows("video_meta", rows)
+        dfmk.fill_table_from_row_pool("video_meta")
+
+        if csv_outfile:
+            dfmk["video_meta"].to_csv(csv_outfile, index=False, sep=";")
+        return dfmk["video_meta"].copy()
+
 
 class VideoResolution(Enum):
     VR480p = "720x480"

halib/filetype/yamlfile.py

@@ -2,15 +2,15 @@ import time
 import networkx as nx
 from rich import inspect
 from rich.pretty import pprint
-from omegaconf import OmegaConf
 from rich.console import Console
+
+from omegaconf import OmegaConf
 from argparse import ArgumentParser
 
-from ..research.mics import *
+from ..system.path import *
 
 console = Console()
 
-
 def _load_yaml_recursively(
     yaml_file, yaml_files=[], share_nx_graph=nx.DiGraph(), log_info=False
 ):

halib/online/projectmake.py

@@ -1,17 +1,18 @@
 # coding=utf-8
-import json
+
 import os
+import json
+import pycurl
 import shutil
-from argparse import ArgumentParser
-from io import BytesIO
+import certifi
 import subprocess
+from io import BytesIO
+
+from argparse import ArgumentParser
 
-import certifi
-import pycurl
 from ..filetype import jsonfile
 from ..system import filesys
 
-
 def get_curl(url, user_and_pass, verbose=True):
     c = pycurl.Curl()
     c.setopt(pycurl.VERBOSE, verbose)

halib/online/tele_noti.py

@@ -0,0 +1,165 @@
+# 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\halib\online\tele_noti_cfg.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())

halib/research/core/base_config.py

@@ -0,0 +1,144 @@
+import os
+from rich.pretty import pprint
+from abc import ABC, abstractmethod
+from typing import List, Optional, TypeVar, Generic
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from dataclass_wizard import YAMLWizard
+
+
+class NamedConfig(ABC):
+    """
+    Base class for named configurations.
+    All configurations should have a name.
+    """
+
+    @abstractmethod
+    def get_name(self):
+        """
+        Get the name of the configuration.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+
+@dataclass
+class AutoNamedConfig(YAMLWizard, NamedConfig):
+    """
+    Mixin that automatically implements get_name() by returning self.name.
+    Classes using this MUST have a 'name' field.
+    """
+
+    name: Optional[str] = None
+
+    def get_name(self):
+        return self.name
+
+    def __post_init__(self):
+        # Enforce the "MUST" rule here
+        if self.name is None:
+            # We allow None during initial load, but it must be set before usage
+            # or handled by the loader.
+            pass
+
+T = TypeVar("T", bound=AutoNamedConfig)
+
+class BaseSelectorConfig(Generic[T]):
+    """
+    Base class to handle the logic of selecting an item from a list by name.
+    """
+
+    def _resolve_selection(self, items: List[T], selected_name: str, context: str) -> T:
+        if selected_name is None:
+            raise ValueError(f"No {context} selected in the configuration.")
+
+        # Create a lookup dict for O(1) access, or just iterate if list is short
+        for item in items:
+            if item.name == selected_name:
+                return item
+
+        raise ValueError(
+            f"{context.capitalize()} '{selected_name}' not found in the configuration list."
+        )
+
+
+class ExpBaseConfig(ABC, YAMLWizard):
+    """
+    Base class for configuration objects.
+    What a cfg class must have:
+    1 - a dataset cfg
+    2 - a metric cfg
+    3 - a method cfg
+    """
+
+    # Save to yaml fil
+    def save_to_outdir(
+        self, filename: str = "__config.yaml", outdir=None, override: bool = False
+    ) -> None:
+        """
+        Save the configuration to the output directory.
+        """
+        if outdir is not None:
+            output_dir = outdir
+        else:
+            output_dir = self.get_outdir()
+        os.makedirs(output_dir, exist_ok=True)
+        assert (output_dir is not None) and (
+            os.path.isdir(output_dir)
+        ), f"Output directory '{output_dir}' does not exist or is not a directory."
+        file_path = os.path.join(output_dir, filename)
+        if os.path.exists(file_path) and not override:
+            pprint(
+                f"File '{file_path}' already exists. Use 'override=True' to overwrite."
+            )
+        else:
+            # method of YAMLWizard to_yaml_file
+            self.to_yaml_file(file_path)
+
+    @classmethod
+    @abstractmethod
+    # load from a custom YAML file
+    def from_custom_yaml_file(cls, yaml_file: str):
+        """Load a configuration from a custom YAML file."""
+        pass
+
+    @abstractmethod
+    def get_cfg_name(self):
+        """
+        Get the name of the configuration.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def get_outdir(self):
+        """
+        Get the output directory for the configuration.
+        This method should be implemented in subclasses.
+        """
+        return None
+
+    @abstractmethod
+    def get_general_cfg(self):
+        """
+        Get the general configuration like output directory, log settings, SEED, etc.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def get_dataset_cfg(self) -> NamedConfig:
+        """
+        Get the dataset configuration.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def get_metric_cfg(self) -> NamedConfig:
+        """
+        Get the metric configuration.
+        This method should be implemented in subclasses.
+        """
+        pass

halib/research/core/base_exp.py

@@ -0,0 +1,157 @@
+from abc import ABC, abstractmethod
+from typing import Tuple, Any, Optional
+from base_config import ExpBaseConfig
+from ..perf.perfcalc import PerfCalc
+from ..perf.perfmetrics import MetricsBackend
+
+# ! SEE https://github.com/hahv/base_exp for sample usage
+class BaseExperiment(PerfCalc, ABC):
+    """
+    Base class for experiments.
+    Orchestrates the experiment pipeline using a pluggable metrics backend.
+    """
+
+    def __init__(self, config: ExpBaseConfig):
+        self.config = config
+        self.metric_backend = None
+        # Flag to track if init_general/prepare_dataset has run
+        self._is_env_ready = False
+
+    # -----------------------
+    # PerfCalc Required Methods
+    # -----------------------
+    def get_dataset_name(self):
+        return self.config.get_dataset_cfg().get_name()
+
+    def get_experiment_name(self):
+        return self.config.get_cfg_name()
+
+    def get_metric_backend(self):
+        if not self.metric_backend:
+            self.metric_backend = self.prepare_metrics(self.config.get_metric_cfg())
+        return self.metric_backend
+
+    # -----------------------
+    # Abstract Experiment Steps
+    # -----------------------
+    @abstractmethod
+    def init_general(self, general_cfg):
+        """Setup general settings like SEED, logging, env variables."""
+        pass
+
+    @abstractmethod
+    def prepare_dataset(self, dataset_cfg):
+        """Load/prepare dataset."""
+        pass
+
+    @abstractmethod
+    def prepare_metrics(self, metric_cfg) -> MetricsBackend:
+        """
+        Prepare the metrics for the experiment.
+        This method should be implemented in subclasses.
+        """
+        pass
+
+    @abstractmethod
+    def before_exec_exp_once(self, *args, **kwargs):
+        """Optional: any setup before exec_exp. Note this is called once per run_exp."""
+        pass
+
+    @abstractmethod
+    def exec_exp(self, *args, **kwargs) -> Optional[Tuple[Any, Any]]:
+        """Run experiment process, e.g.: training/evaluation loop.
+        Return: either `None` or a tuple of (raw_metrics_data, extra_data) for calc_and_save_exp_perfs
+        """
+        pass
+
+    @abstractmethod
+    def exec_eval(self, *args, **kwargs) -> Optional[Tuple[Any, Any]]:
+        """Run evaluation process.
+        Return: either `None` or a tuple of (raw_metrics_data, extra_data) for calc_and_save_exp_perfs
+        """
+        pass
+
+    # -----------------------
+    # Internal Helpers
+    # -----------------------
+    def _validate_and_unpack(self, results):
+        if results is None:
+            return None
+        if not isinstance(results, (tuple, list)) or len(results) != 2:
+            raise ValueError("exec must return (metrics_data, extra_data)")
+        return results[0], results[1]
+
+    def _prepare_environment(self, force_reload: bool = False):
+        """
+        Common setup. Skips if already initialized, unless force_reload is True.
+        """
+        if self._is_env_ready and not force_reload:
+            # Environment is already prepared, skipping setup.
+            return
+
+        # 1. Run Setup
+        self.init_general(self.config.get_general_cfg())
+        self.prepare_dataset(self.config.get_dataset_cfg())
+
+        # 2. Update metric backend (refresh if needed)
+        self.metric_backend = self.prepare_metrics(self.config.get_metric_cfg())
+
+        # 3. Mark as ready
+        self._is_env_ready = True
+
+    # -----------------------
+    # Main Experiment Runner
+    # -----------------------
+    def run_exp(self, should_calc_metrics=True, reload_env=False, *args, **kwargs):
+        """
+        Run the whole experiment pipeline.
+        :param reload_env: If True, forces dataset/general init to run again.
+        :param should_calc_metrics: Whether to calculate and save metrics after execution.
+        :kwargs Params:
+            + 'outfile' to save csv file results,
+            + 'outdir' to set output directory for experiment results.
+            + 'return_df' to return a DataFrame of results instead of a dictionary.
+
+        Full pipeline:
+            1. Init
+            2. Prepare Environment (General + Dataset + Metrics)
+            3. Save Config
+            4. Execute
+            5. Calculate & Save Metrics
+        """
+        self._prepare_environment(force_reload=reload_env)
+
+        # Any pre-exec setup (loading models, etc)
+        self.before_exec_exp_once(*args, **kwargs)
+        # Save config before running
+        self.config.save_to_outdir()
+
+        # Execute experiment
+        results = self.exec_exp(*args, **kwargs)
+
+        if should_calc_metrics and results is not None:
+            metrics_data, extra_data = self._validate_and_unpack(results)
+            # Calculate & Save metrics
+            perf_results = self.calc_perfs(
+                raw_metrics_data=metrics_data, extra_data=extra_data, *args, **kwargs
+            )
+            return perf_results
+        else:
+            return results
+
+    # -----------------------
+    # Main Experiment Evaluator
+    # -----------------------
+    def eval_exp(self, reload_env=False, *args, **kwargs):
+        """
+        Run evaluation only.
+        :param reload_env: If True, forces dataset/general init to run again.
+        """
+        self._prepare_environment(force_reload=reload_env)
+        results = self.exec_eval(*args, **kwargs)
+        if results is not None:
+            metrics_data, extra_data = self._validate_and_unpack(results)
+            return self.calc_perfs(
+                raw_metrics_data=metrics_data, extra_data=extra_data, *args, **kwargs
+            )
+        return None