halib 0.1.99__py3-none-any.whl → 0.2.2__py3-none-any.whl

halib/__init__.py

@@ -56,8 +56,7 @@ from .filetype.yamlfile import load_yaml
 from .system import cmd
 from .system import filesys as fs
 from .filetype import csvfile
-from .cuda import tcuda
-from .common import (
+from .common.common import (
     console,
     console_log,
     ConsoleLog,
@@ -65,6 +64,7 @@ from .common import (
     norm_str,
     pprint_box,
     pprint_local_path,
+    tcuda
 )
 
 # for log
@@ -76,7 +76,7 @@ from timebudget import timebudget
 import omegaconf
 from omegaconf import OmegaConf
 from omegaconf.dictconfig import DictConfig
-from .rich_color import rcolor_str, rcolor_palette, rcolor_palette_all, rcolor_all_str
+from .common.rich_color import rcolor_str, rcolor_palette, rcolor_palette_all, rcolor_all_str
 
 # for visualization
 import seaborn as sns

halib/common/common.py

@@ -0,0 +1,178 @@
+import os
+import re
+import arrow
+import importlib
+
+import rich
+from rich import print
+from rich.panel import Panel
+from rich.console import Console
+from rich.pretty import pprint, Pretty
+
+from pathlib import Path, PureWindowsPath
+
+
+console = Console()
+
+
+def seed_everything(seed=42):
+    import random
+    import numpy as np
+
+    random.seed(seed)
+    np.random.seed(seed)
+    # import torch if it is available
+    try:
+        import torch
+
+        torch.manual_seed(seed)
+        torch.cuda.manual_seed(seed)
+        torch.cuda.manual_seed_all(seed)
+        torch.backends.cudnn.deterministic = True
+        torch.backends.cudnn.benchmark = False
+    except ImportError:
+        pprint("torch not imported, skipping torch seed_everything")
+        pass
+
+
+def now_str(sep_date_time="."):
+    assert sep_date_time in [
+        ".",
+        "_",
+        "-",
+    ], "sep_date_time must be one of '.', '_', or '-'"
+    now_string = arrow.now().format(f"YYYYMMDD{sep_date_time}HHmmss")
+    return now_string
+
+
+def norm_str(in_str):
+    # Replace one or more whitespace characters with a single underscore
+    norm_string = re.sub(r"\s+", "_", in_str)
+    # Remove leading and trailing spaces
+    norm_string = norm_string.strip()
+    return norm_string
+
+
+def pprint_box(obj, title="", border_style="green"):
+    """
+    Pretty print an object in a box.
+    """
+    rich.print(
+        Panel(Pretty(obj, expand_all=True), title=title, border_style=border_style)
+    )
+
+
+def console_rule(msg, do_norm_msg=True, is_end_tag=False):
+    msg = norm_str(msg) if do_norm_msg else msg
+    if is_end_tag:
+        console.rule(f"</{msg}>")
+    else:
+        console.rule(f"<{msg}>")
+
+
+def console_log(func):
+    def wrapper(*args, **kwargs):
+        console_rule(func.__name__)
+        result = func(*args, **kwargs)
+        console_rule(func.__name__, is_end_tag=True)
+        return result
+
+    return wrapper
+
+
+class ConsoleLog:
+    def __init__(self, message):
+        self.message = message
+
+    def __enter__(self):
+        console_rule(self.message)
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        console_rule(self.message, is_end_tag=True)
+        if exc_type is not None:
+            print(f"An exception of type {exc_type} occurred.")
+            print(f"Exception message: {exc_value}")
+
+
+def linux_to_wins_path(path: str) -> str:
+    """
+    Convert a Linux-style WSL path (/mnt/c/... or /mnt/d/...) to a Windows-style path (C:\...).
+    """
+    # Handle only /mnt/<drive>/... style
+    if (
+        path.startswith("/mnt/")
+        and len(path) > 6
+        and path[5].isalpha()
+        and path[6] == "/"
+    ):
+        drive = path[5].upper()  # Extract drive letter
+        win_path = f"{drive}:{path[6:]}"  # Replace "/mnt/c/" with "C:/"
+    else:
+        win_path = path  # Return unchanged if not a WSL-style path
+    # Normalize to Windows-style backslashes
+    return str(PureWindowsPath(win_path))
+
+
+def pprint_local_path(
+    local_path: str, get_wins_path: bool = False, tag: str = ""
+) -> str:
+    """
+    Pretty-print a local path with emoji and clickable file:// URI.
+
+    Args:
+        local_path: Path to file or directory (Linux or Windows style).
+        get_wins_path: If True on Linux, convert WSL-style path to Windows style before printing.
+        tag: Optional console log tag.
+
+    Returns:
+        The file URI string.
+    """
+    p = Path(local_path).resolve()
+    type_str = "📄" if p.is_file() else "📁" if p.is_dir() else "❓"
+
+    if get_wins_path and os.name == "posix":
+        # Try WSL → Windows conversion
+        converted = linux_to_wins_path(str(p))
+        if converted != str(p):  # Conversion happened
+            file_uri = str(PureWindowsPath(converted).as_uri())
+        else:
+            file_uri = p.as_uri()
+    else:
+        file_uri = p.as_uri()
+
+    content_str = f"{type_str} [link={file_uri}]{file_uri}[/link]"
+
+    if tag:
+        with ConsoleLog(tag):
+            console.print(content_str)
+    else:
+        console.print(content_str)
+
+    return file_uri
+
+
+def tcuda():
+    NOT_INSTALLED = "Not Installed"
+    GPU_AVAILABLE = "GPU(s) Available"
+    ls_lib = ["torch", "tensorflow"]
+    lib_stats = {lib: NOT_INSTALLED for lib in ls_lib}
+    for lib in ls_lib:
+        spec = importlib.util.find_spec(lib)
+        if spec:
+            if lib == "torch":
+                import torch
+
+                lib_stats[lib] = str(torch.cuda.device_count()) + " " + GPU_AVAILABLE
+            elif lib == "tensorflow":
+                import tensorflow as tf
+
+                lib_stats[lib] = (
+                    str(len(tf.config.list_physical_devices("GPU")))
+                    + " "
+                    + GPU_AVAILABLE
+                )
+    console.rule("<CUDA Library Stats>")
+    pprint(lib_stats)
+    console.rule("</CUDA Library Stats>")
+    return lib_stats

halib/common/rich_color.py

@@ -0,0 +1,285 @@
+from rich.console import Console
+from rich.pretty import pprint
+from rich.table import Table
+from rich.text import Text
+from rich.panel import Panel
+
+# List of colors
+# ! https://rich.readthedocs.io/en/stable/appendix/colors.html
+all_colors = [
+    "black",
+    "red",
+    "green",
+    "yellow",
+    "blue",
+    "magenta",
+    "cyan",
+    "white",
+    "bright_black",
+    "bright_red",
+    "bright_green",
+    "bright_yellow",
+    "bright_blue",
+    "bright_magenta",
+    "bright_cyan",
+    "bright_white",
+    "grey0",
+    "navy_blue",
+    "dark_blue",
+    "blue3",
+    "blue1",
+    "dark_green",
+    "deep_sky_blue4",
+    "dodger_blue3",
+    "dodger_blue2",
+    "green4",
+    "spring_green4",
+    "turquoise4",
+    "deep_sky_blue3",
+    "dodger_blue1",
+    "dark_cyan",
+    "light_sea_green",
+    "deep_sky_blue2",
+    "deep_sky_blue1",
+    "green3",
+    "spring_green3",
+    "cyan3",
+    "dark_turquoise",
+    "turquoise2",
+    "green1",
+    "spring_green2",
+    "spring_green1",
+    "medium_spring_green",
+    "cyan2",
+    "cyan1",
+    "purple4",
+    "purple3",
+    "blue_violet",
+    "grey37",
+    "medium_purple4",
+    "slate_blue3",
+    "royal_blue1",
+    "chartreuse4",
+    "pale_turquoise4",
+    "steel_blue",
+    "steel_blue3",
+    "cornflower_blue",
+    "dark_sea_green4",
+    "cadet_blue",
+    "sky_blue3",
+    "chartreuse3",
+    "sea_green3",
+    "aquamarine3",
+    "medium_turquoise",
+    "steel_blue1",
+    "sea_green2",
+    "sea_green1",
+    "dark_slate_gray2",
+    "dark_red",
+    "dark_magenta",
+    "orange4",
+    "light_pink4",
+    "plum4",
+    "medium_purple3",
+    "slate_blue1",
+    "wheat4",
+    "grey53",
+    "light_slate_grey",
+    "medium_purple",
+    "light_slate_blue",
+    "yellow4",
+    "dark_sea_green",
+    "light_sky_blue3",
+    "sky_blue2",
+    "chartreuse2",
+    "pale_green3",
+    "dark_slate_gray3",
+    "sky_blue1",
+    "chartreuse1",
+    "light_green",
+    "aquamarine1",
+    "dark_slate_gray1",
+    "deep_pink4",
+    "medium_violet_red",
+    "dark_violet",
+    "purple",
+    "medium_orchid3",
+    "medium_orchid",
+    "dark_goldenrod",
+    "rosy_brown",
+    "grey63",
+    "medium_purple2",
+    "medium_purple1",
+    "dark_khaki",
+    "navajo_white3",
+    "grey69",
+    "light_steel_blue3",
+    "light_steel_blue",
+    "dark_olive_green3",
+    "dark_sea_green3",
+    "light_cyan3",
+    "light_sky_blue1",
+    "green_yellow",
+    "dark_olive_green2",
+    "pale_green1",
+    "dark_sea_green2",
+    "pale_turquoise1",
+    "red3",
+    "deep_pink3",
+    "magenta3",
+    "dark_orange3",
+    "indian_red",
+    "hot_pink3",
+    "hot_pink2",
+    "orchid",
+    "orange3",
+    "light_salmon3",
+    "light_pink3",
+    "pink3",
+    "plum3",
+    "violet",
+    "gold3",
+    "light_goldenrod3",
+    "tan",
+    "misty_rose3",
+    "thistle3",
+    "plum2",
+    "yellow3",
+    "khaki3",
+    "light_yellow3",
+    "grey84",
+    "light_steel_blue1",
+    "yellow2",
+    "dark_olive_green1",
+    "dark_sea_green1",
+    "honeydew2",
+    "light_cyan1",
+    "red1",
+    "deep_pink2",
+    "deep_pink1",
+    "magenta2",
+    "magenta1",
+    "orange_red1",
+    "indian_red1",
+    "hot_pink",
+    "medium_orchid1",
+    "dark_orange",
+    "salmon1",
+    "light_coral",
+    "pale_violet_red1",
+    "orchid2",
+    "orchid1",
+    "orange1",
+    "sandy_brown",
+    "light_salmon1",
+    "light_pink1",
+    "pink1",
+    "plum1",
+    "gold1",
+    "light_goldenrod2",
+    "navajo_white1",
+    "misty_rose1",
+    "thistle1",
+    "yellow1",
+    "light_goldenrod1",
+    "khaki1",
+    "wheat1",
+    "cornsilk1",
+    "grey100",
+    "grey3",
+    "grey7",
+    "grey11",
+    "grey15",
+    "grey19",
+    "grey23",
+    "grey27",
+    "grey30",
+    "grey35",
+    "grey39",
+    "grey42",
+    "grey46",
+    "grey50",
+    "grey54",
+    "grey58",
+    "grey62",
+    "grey66",
+    "grey70",
+    "grey74",
+    "grey78",
+    "grey82",
+    "grey85",
+    "grey89",
+    "grey93",
+]
+
+basic_colors = [
+    "black",
+    "red",
+    "green",
+    "yellow",
+    "blue",
+    "magenta",
+    "cyan",
+    "white",
+    "bright_black",
+    "bright_red",
+    "bright_green",
+    "bright_yellow",
+    "bright_blue",
+    "bright_magenta",
+    "bright_cyan",
+    "bright_white",
+]
+
+def rcolor_all_str():
+    pprint(all_colors)
+
+def rcolor_basic_str():
+    pprint(basic_colors)
+
+def rcolor_str(in_str, color="white"):
+    assert color in all_colors, f"color must be one of {all_colors}"
+    return f"[{color}]{in_str}[/{color}]"
+
+def rcolor_palette(color_list):
+    # make sure all colors are valid (in all_colors)
+    for color in color_list:
+        assert (
+            color in all_colors
+        ), f"color must be a valid color. call <rcolor_all_str()> or <rcolor_palette_all()> to see all valid colors"
+    # Initialize console
+    console = Console()
+
+    # Create a table with horizontal lines and six columns
+    table = Table(show_header=True, header_style="bold magenta", show_lines=True)
+
+    # Define the columns
+    table.add_column("Color Name 1", style="bold")
+    table.add_column("Sample 1", style="bold")
+    table.add_column("Color Name 2", style="bold")
+    table.add_column("Sample 2", style="bold")
+    table.add_column("Color Name 3", style="bold")
+    table.add_column("Sample 3", style="bold")
+
+    # Adjust the number of rows needed for the table
+    num_colors = len(color_list)
+    num_rows = (num_colors + 2) // 3  # Ceiling division to ensure all colors fit
+
+    # Add rows to the table
+    for i in range(num_rows):
+        color1 = color_list[i * 3] if i * 3 < num_colors else ""
+        color2 = color_list[i * 3 + 1] if i * 3 + 1 < num_colors else ""
+        color3 = color_list[i * 3 + 2] if i * 3 + 2 < num_colors else ""
+        filled_rect1 = Text(" " * 10, style=f"on {color1}") if color1 else ""
+        filled_rect2 = Text(" " * 10, style=f"on {color2}") if color2 else ""
+        filled_rect3 = Text(" " * 10, style=f"on {color3}") if color3 else ""
+        table.add_row(color1, filled_rect1, color2, filled_rect2, color3, filled_rect3)
+
+    # Print the table
+    console.print(table)
+
+def rcolor_palette_basic():
+    rcolor_palette(basic_colors)
+
+def rcolor_palette_all():
+    rcolor_palette(all_colors)

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)