speedy-utils 1.0.3__py3-none-any.whl → 1.0.5__py3-none-any.whl

speedy/common/utils_print.py

@@ -1,138 +0,0 @@
-# utils/utils_print.py
-
-import copy
-import json
-import pprint
-import textwrap
-from typing import Any, Dict, List, Optional
-
-from IPython.display import HTML, display
-from pandas import get_option
-from tabulate import tabulate
-
-# from .utils_cache import is_interactive_env  # Adjust based on actual implementation
-# from .utils_misc import is_interactive
-
-
-def display_pretty_table_html(data: Dict) -> None:
-    """
-    Display a pretty HTML table in Jupyter notebooks.
-    """
-    table = "<table>"
-    for key, value in data.items():
-        table += f"<tr><td>{key}</td><td>{value}</td></tr>"
-    table += "</table>"
-    display(HTML(table))
-
-def fprint(
-    input_data: Any,
-    key_ignore: Optional[List[str]] = None,
-    key_keep: Optional[List[str]] = None,
-    max_width: int = 100,
-    indent: int = 2,
-    depth: Optional[int] = None,
-    table_format: str = "grid",
-    str_wrap_width: int = 80,
-) -> None:
-    """
-    Pretty print structured data.
-    """
-
-    def is_interactive_env():
-        """Check if the environment is interactive (e.g., Jupyter notebook)."""
-        try:
-            shell = get_option().__class__.__name__
-            return shell == "ZMQInteractiveShell"
-        except NameError:
-            return False
-
-    def remove_keys(d: Dict, keys: List[str]) -> Dict:
-        """Remove specified keys from a dictionary."""
-        for key in keys:
-            parts = key.split(".")
-            sub_dict = d
-            for part in parts[:-1]:
-                sub_dict = sub_dict.get(part, {})
-            sub_dict.pop(parts[-1], None)
-        return d
-
-    def keep_keys(d: Dict, keys: List[str]) -> Dict:
-        """Keep only specified keys in a dictionary."""
-        result = {}
-        for key in keys:
-            parts = key.split(".")
-            sub_source = d
-            sub_result = result
-            for part in parts[:-1]:
-                if part not in sub_source:
-                    break
-                sub_result = sub_result.setdefault(part, {})
-                sub_source = sub_source[part]
-            else:
-                sub_result[parts[-1]] = copy.deepcopy(sub_source.get(parts[-1]))
-        return result
-
-    if hasattr(input_data, "to_dict"):
-        input_data = input_data.to_dict()
-
-    processed_data = copy.deepcopy(input_data)
-
-    if isinstance(processed_data, dict):
-        if key_keep is not None:
-            processed_data = keep_keys(processed_data, key_keep)
-        elif key_ignore is not None:
-            processed_data = remove_keys(processed_data, key_ignore)
-
-        if is_interactive_env():
-            display_pretty_table_html(processed_data)
-            return
-
-    if isinstance(processed_data, dict):
-        table = [[k, v] for k, v in processed_data.items()]
-        print(
-            tabulate(
-                table,
-                headers=["Key", "Value"],
-                tablefmt=table_format,
-                maxcolwidths=[None, max_width],
-            )
-        )
-    elif isinstance(processed_data, str):
-        wrapped_text = textwrap.fill(processed_data, width=str_wrap_width)
-        print(wrapped_text)
-    else:
-        printer = pprint.PrettyPrinter(width=max_width, indent=indent, depth=depth)
-        printer.pprint(processed_data)
-
-
-def print_table(data: Any) -> None:
-    """
-    Print data as a table.
-    """
-
-    def __get_table(data: Any) -> str:
-        if isinstance(data, str):
-            try:
-                data = json.loads(data)
-            except json.JSONDecodeError as exc:
-                raise ValueError("String input could not be decoded as JSON") from exc
-
-        if isinstance(data, list):
-            if all(isinstance(item, dict) for item in data):
-                headers = list(data[0].keys())
-                rows = [list(item.values()) for item in data]
-                return tabulate(rows, headers=headers)
-            else:
-                raise ValueError("List must contain dictionaries")
-
-        if isinstance(data, dict):
-            headers = ["Key", "Value"]
-            rows = list(data.items())
-            return tabulate(rows, headers=headers)
-
-        raise TypeError(
-            "Input data must be a list of dictionaries, a dictionary, or a JSON string"
-        )
-
-    table = __get_table(data)
-    print(table)

speedy/multi_worker.py

@@ -1,121 +0,0 @@
-import inspect
-import os
-from concurrent.futures import ThreadPoolExecutor
-from multiprocessing import Pool
-from typing import Any, Callable, List
-import asyncio
-from loguru import logger
-from tqdm import tqdm
-
-
-def multi_thread(
-    func: Callable,
-    inputs: List[Any],
-    workers: int = 4,
-    verbose: bool = True,
-    desc: str | None = None,
-) -> List[Any]:
-    if desc is None:
-        fn_name = func.__name__
-        try:
-            source_file = inspect.getsourcefile(func) or "<string>"
-            source_line = inspect.getsourcelines(func)[1]
-            file_line = f"{source_file}:{source_line}"
-        except (TypeError, OSError):
-            file_line = "Unknown location"
-        desc = f"{fn_name} at {file_line}"
-
-    with ThreadPoolExecutor(max_workers=workers) as executor:
-        # Use executor.map to apply func to inputs in order
-        map_func = executor.map(func, inputs)
-        if verbose:
-            results = list(tqdm(map_func, total=len(inputs), desc=desc))
-        else:
-            results = list(map_func)
-    return results
-
-
-def _init_pool_processes(func):
-    global _func
-    _func = func
-
-
-def _pool_process_executor(args):
-    # Unpack arguments if necessary
-    if isinstance(args, tuple):
-        return _func(*args)
-    else:
-        return _func(args)
-
-
-def multi_process(
-    func: Callable,
-    inputs: List[Any],
-    workers: int = 16,
-    verbose: bool = True,
-    desc: str = "",
-) -> List[Any]:
-    if not desc:
-        fn_name = func.__name__
-        try:
-            source_file = inspect.getsourcefile(func) or "<string>"
-            source_line = inspect.getsourcelines(func)[1]
-            file_line = f"{source_file}:{source_line}"
-        except (TypeError, OSError):
-            file_line = "Unknown location"
-        desc = f"{fn_name} at {file_line}"
-
-    if os.environ.get("DEBUG", "0") == "1":
-        logger.info("DEBUGGING set num workers to 1")
-        workers = 1
-
-    logger.info("Multi-processing {} | Num samples: {}", desc, len(inputs))
-
-    results = []
-    with Pool(
-        processes=workers, initializer=_init_pool_processes, initargs=(func,)
-    ) as pool:
-        try:
-            if verbose:
-                for result in tqdm(
-                    pool.imap(_pool_process_executor, inputs),
-                    total=len(inputs),
-                    desc=desc,
-                ):
-                    results.append(result)
-            else:
-                results = pool.map(_pool_process_executor, inputs)
-        except Exception as e:
-            logger.error(f"[multiprocess] Error {e}")
-
-    return results
-
-
-async def async_multi_thread(f, inputs, desc="", user_tqdm=True):
-    """
-    Uasge:
-        inputs = list(range(10))
-        def function(i):
-            time.sleep(1)
-            return 1/i
-        results = await amulti_thread(function, inputs)
-    """
-
-    def ensure_output_idx(idx_i):
-        idx, i = idx_i
-        return idx, f(i)
-
-    tasks = [asyncio.to_thread(ensure_output_idx, i) for i in enumerate(inputs)]
-    if not desc:
-        desc = f"{f.__name__}"
-
-    pbar = tqdm(total=len(inputs), desc=desc, disable=not user_tqdm)
-    results = [None] * len(inputs)
-    for task in asyncio.as_completed(tasks):
-        idx, result = await task
-        results[idx] = result
-        pbar.update(1)
-    return results
-
-
-__all__ = ["multi_thread", "multi_process", "async_multi_thread"]

speedy_utils-1.0.3.dist-info/METADATA

@@ -1,22 +0,0 @@
-Metadata-Version: 2.1
-Name: speedy-utils
-Version: 1.0.3
-Summary: Fast and easy-to-use package for data science
-Home-page: https://github.com/anhvth/speedy
-Author: AnhVTH
-Author-email: anhvth.226@gmail.com
-Requires-Dist: numpy
-Requires-Dist: requests
-Requires-Dist: xxhash
-Requires-Dist: loguru
-Requires-Dist: fastcore
-Requires-Dist: debugpy
-Requires-Dist: ipywidgets
-Requires-Dist: jupyterlab
-Requires-Dist: ipdb
-Requires-Dist: scikit-learn
-Requires-Dist: matplotlib
-Requires-Dist: pandas
-Requires-Dist: tabulate
-Requires-Dist: pydantic
-

speedy_utils-1.0.3.dist-info/RECORD

@@ -1,12 +0,0 @@
-speedy/__init__.py,sha256=GYw4FDnK1hy8_WpJxJyJEBCYh4IU5joxwG_s7uqIKKg,1147
-speedy/multi_worker.py,sha256=kmk_Km6LkOUVntxmPKSYubMXFJBPoLoZW9NVi4UA9kc,3394
-speedy/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-speedy/common/clock.py,sha256=q92SvdJLZyCtuq8C6m7GjS6_foI8yyspsKzeR_M1owo,2033
-speedy/common/utils_cache.py,sha256=_qxGyISJBM-r0NDSUCYSEWnEsqprORdw3yXmIkns1D4,5656
-speedy/common/utils_io.py,sha256=X2zFgVzfYM094auApGjYOO43NgnG5P_g7rOObzPYTrQ,3472
-speedy/common/utils_misc.py,sha256=ooMb0xEjC-HrQSQQCTRlEqcrGTJptmA43azSi6BhiD4,1479
-speedy/common/utils_print.py,sha256=jh_ihzWTEiPpFRiLoj6It8Zo_3tPxYi8MU1J3Nw3vwk,4273
-speedy_utils-1.0.3.dist-info/METADATA,sha256=6rSrp8BSLNGKxb7jvIO4LnK90575ycvZqBr8EFW_Tzw,538
-speedy_utils-1.0.3.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-speedy_utils-1.0.3.dist-info/top_level.txt,sha256=eJxFW_gum7StgovqwA4v-9UndgnnWr4kUqcozY-aBmI,7
-speedy_utils-1.0.3.dist-info/RECORD,,

speedy_utils-1.0.3.dist-info/top_level.txt

@@ -1 +0,0 @@
-speedy