xlin 0.1.39__py2.py3-none-any.whl → 0.2.3__py2.py3-none-any.whl

xlin/dataframe_util.py

@@ -306,3 +306,55 @@ def grouped_row(df: pd.DataFrame, key_col="query"):
     for i, row in df.iterrows():
         grouped[row[key_col]].append(row)
     return grouped
+
+def select_sub_df(
+    df: pd.DataFrame,
+    start_date: str,
+    end_date: str,
+    lookback_window: int = 0,
+    lookforward_window: int = 0,
+    include_end_date: bool = False,
+) -> pd.DataFrame:
+    """
+    从DataFrame中选择指定日期范围内的子DataFrame。
+
+    Args:
+        df (pd.DataFrame): 带有日期索引的DataFrame，index是日期。
+        start_date (str): 起始日期，格式'YYYY-MM-DD'。
+        end_date (str): 结束日期，格式'YYYY-MM-DD'。
+        lookback_window (int): 向后查看的天数，默认为0。
+        lookforward_window (int): 向前查看的天数，默认为0。
+        include_end_date (bool): 是否包含结束日期，默认为False。
+
+    Returns:
+        pd.DataFrame: 指定日期范围内的子DataFrame。
+    """
+    # 确保索引是DatetimeIndex类型
+    if not isinstance(df.index, pd.DatetimeIndex):
+        df.index = pd.to_datetime(df.index)
+
+    # 确保索引是有序的
+    if not df.index.is_monotonic_increasing:
+        df = df.sort_index()
+
+    # 获取索引的时区信息
+    tz = df.index.tz
+
+    # 创建带时区的切片日期
+    start = pd.Timestamp(start_date, tz=tz)
+    end = pd.Timestamp(end_date, tz=tz)
+
+    # 选择子DataFrame
+    try:
+        if lookback_window > 0:
+            start = start - pd.Timedelta(days=lookback_window)
+        if lookforward_window > 0:
+            end = end + pd.Timedelta(days=lookforward_window)
+        if include_end_date:
+            end = end + pd.Timedelta(days=1)
+        sub_df = df[start:end]
+    except KeyError:
+        print(f"日期 {start_date} 或 {end_date} 不在索引范围内。")
+        sub_df = pd.DataFrame()
+
+    return sub_df

xlin/datetime_util.py

@@ -1,14 +1,17 @@
 
 
+from typing import Literal, Optional, Union
 import datetime
 import random
 
+import pandas as pd
+
 
 date_str = datetime.datetime.now().strftime("%Y%m%d")
 datetime_str = datetime.datetime.now().strftime("%Y%m%d_%Hh%Mm%Ss")
 
 
-def random_timestamp(start_timestamp=None, end_timestamp=None):
+def random_timestamp(start_timestamp: Optional[float]=None, end_timestamp: Optional[float]=None):
     if start_timestamp is None:
         start_timestamp = datetime.datetime(2024, 1, 1).timestamp()
     if end_timestamp is None:
@@ -16,6 +19,157 @@ def random_timestamp(start_timestamp=None, end_timestamp=None):
     return random.uniform(start_timestamp, end_timestamp)
 
 
-def random_timestamp_str(start_timestamp=None, end_timestamp=None, format="%Y年%m月%d日%H时%M分"):
-    return datetime.datetime.fromtimestamp(random_timestamp(start_timestamp, end_timestamp)).strftime(format)
+def random_datetime(
+    start_datetime: Optional[datetime.datetime] = None,
+    end_datetime: Optional[datetime.datetime] = None,
+) -> datetime.datetime:
+    """
+    生成一个随机的 datetime 对象，范围在指定的开始和结束时间之间。
+    如果未指定，则默认范围为 2024 年 1 月 1 日到当前时间。
+    """
+    if start_datetime is None:
+        start_datetime = datetime.datetime(2024, 1, 1)
+    if end_datetime is None:
+        end_datetime = datetime.datetime.now()
+
+    random_timestamp_value = random.uniform(start_datetime.timestamp(), end_datetime.timestamp())
+    return datetime.datetime.fromtimestamp(random_timestamp_value)
+
+
+
+# 初始化中美节假日（可缓存）懒加载
+us_holidays = None # US(categories=US.supported_categories)
+cn_holidays = None # CN(categories=CN.supported_categories)
+
+
+def format_datetime_with_holiday(
+    dt: Union[datetime.datetime, str, pd.Series, float],
+    language: Literal["zh", "en"] = "zh",
+    with_time: bool = True,
+    with_weekday: bool = True,
+    with_holiday: bool = True,
+) -> Union[str, pd.Series]:
+    """
+    格式化时间为中文日期+英文星期几，附带中美节假日信息。
+    如：2024年01月01日 10:00:00 星期一 [假期: 🇨🇳 元旦, 🇺🇸 New Year's Day]
+    支持 datetime, str, pandas.Series 批处理。
+    Args:
+        dt: 待格式化的时间，可以是 datetime, str, pandas.Series 或 timestamp。
+        language: 语言选择，支持 "zh" 和 "en"
+        with_time: 是否包含时间
+        with_weekday: 是否包含星期几
+        with_holiday: 是否包含节假日信息
+    Returns:
+        格式化后的字符串或 pandas.Series
+    Raises:
+        ValueError: 如果输入类型不正确
+        ImportError: 如果未安装 'holidays' 库
+    """
+    language_dict = {
+        "zh": {
+            "weekday": ["星期一", "星期二", "星期三", "星期四", "星期五", "星期六", "星期日"],
+            "holiday": "假期",
+            "date_format": "%Y年%m月%d日",
+            "time_format": "%H:%M:%S",
+        },
+        "en": {
+            "weekday": ["Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday"],
+            "holiday": "Holiday",
+            "date_format": "%Y-%m-%d",
+            "time_format": "%H:%M:%S",
+        },
+    }
+
+    def _format_one(d: Union[datetime.datetime, str]) -> str:
+        if isinstance(d, str):
+            d = pd.to_datetime(d)
+        elif isinstance(d, float):
+            d = datetime.datetime.fromtimestamp(d)
+
+        if not isinstance(d, datetime.datetime):
+            raise ValueError("输入必须是 datetime, timestamp, str 或 pandas.Series 类型。")
+
+        formatted = d.strftime(language_dict[language]["date_format"])
+        if with_time:
+            formatted += " " + d.strftime(language_dict[language]["time_format"])
+        if with_weekday:
+            weekday_index = d.weekday()
+            formatted += " " + language_dict[language]["weekday"][weekday_index]
+        if not with_holiday:
+            return formatted
+        # 检查节假日
+        global us_holidays, cn_holidays
+        if not us_holidays or not cn_holidays:
+            try:
+                from holidays.countries import US, CN
+            except ImportError:
+                raise ImportError("请安装 'holidays' 库以支持节假日查询。可以使用 'pip install holidays' 安装。")
+            us_holidays = US(categories=US.supported_categories)
+            cn_holidays = CN(categories=CN.supported_categories)
+        tags = []
+        if d in cn_holidays:
+            tags.append(f"🇨🇳 {cn_holidays[d]}")
+        if d in us_holidays:
+            tags.append(f"🇺🇸 {us_holidays[d]}")
+
+        if tags:
+            holiday_str = language_dict[language]["holiday"]
+            formatted += f" [{holiday_str}: " + ", ".join(tags) + "]"
+        return formatted
+
+    if isinstance(dt, pd.Series):
+        return dt.apply(_format_one)
+    else:
+        return _format_one(dt)
+
+
+def format_timedelta(
+    delta: datetime.timedelta,
+    language: Literal["zh", "en"] = "zh",
+) -> str:
+    """
+    将 timedelta 格式化为精简的中文可读字符串，省略零值单位，四舍五入到秒
+
+    Args:
+        delta: 待格式化的时间间隔
+        language: 语言选择，支持 "zh" 和 "en"
+
+    Returns:
+        精简的中文时间字符串（如 "1天3小时5分" 或 "45秒"）
+    """
+    language_dict = {
+        "zh": {
+            "days": "天",
+            "hours": "小时",
+            "minutes": "分",
+            "seconds": "秒",
+        },
+        "en": {
+            "days": "days",
+            "hours": "hours",
+            "minutes": "minutes",
+            "seconds": "seconds",
+        },
+    }
+    # 处理负数时间（转为正数）
+    delta = abs(delta)
+
+    # 分解时间单位（四舍五入到秒）
+    days = delta.days
+    total_seconds = int(delta.total_seconds() + 0.5)  # 四舍五入到秒
+    hours, remainder = divmod(total_seconds, 3600)
+    minutes, seconds = divmod(remainder, 60)
+
+    # 构建结果列表，跳过零值单位
+    parts = []
+    if days > 0:
+        parts.append(f"{days}{language_dict[language]['days']}")
+    if hours > 0:
+        parts.append(f"{hours}{language_dict[language]['hours']}")
+    if minutes > 0:
+        parts.append(f"{minutes}{language_dict[language]['minutes']}")
+    if seconds > 0:
+        parts.append(f"{seconds}{language_dict[language]['seconds']}")
 
+    # 处理全零情况（如 timedelta(0)）
+    return "".join(parts) if parts else f"0{language_dict[language]['seconds']}"

xlin/file_util.py

@@ -1,11 +1,8 @@
 from typing import *
-from collections import defaultdict
 from pathlib import Path
 import os
-import asyncio
 import shutil
 
-import pandas as pd
 from loguru import logger
 
 def auto_retry_to_get_data(retry_times, request, data_key="data", *args, **kwargs):

xlin/image_util.py

@@ -6,6 +6,17 @@ from PIL import Image, ImageDraw, ImageFont
 import uuid
 import os
 
+import requests
+
+
+def read_image_http_url(image_url: str) -> Image.Image:
+    # 使用 requests 获取图像的二进制数据
+    response = requests.get(image_url)
+    image_data = response.content
+
+    # 使用 Pillow 将二进制数据转换为 Image.Image 对象
+    image = Image.open(BytesIO(image_data))
+    return image
 
 def image_to_base64(image: Image.Image) -> str:
     buffered = BytesIO()

xlin/metric.py

@@ -1,5 +1,5 @@
 
-def stream_average(avg_pre, cur_num_index, cur_num):
+def stream_average(avg_pre: float, cur_num_index: int, cur_num: float) -> float:
     """
     calculate the average of number in a stream
     given nums: List[float], calculate avg[n] = sum(nums[:n]) / len(nums[:n]) = sum(nums[:n]) / n

{xlin-0.1.39.dist-info → xlin-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: xlin
-Version: 0.1.39
+Version: 0.2.3
 Summary: toolbox for LinXueyuan
 License: MIT
 Author: LinXueyuanStdio
@@ -18,12 +18,15 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: Pillow
+Requires-Dist: holidays
 Requires-Dist: loguru
 Requires-Dist: pandas
 Requires-Dist: pyexcel
 Requires-Dist: pyexcel-xls
 Requires-Dist: pyexcel-xlsx
 Requires-Dist: pyyaml
+Requires-Dist: requests
 Requires-Dist: tqdm
 Requires-Dist: xlsxwriter
 Description-Content-Type: text/markdown

xlin-0.2.3.dist-info/RECORD

@@ -0,0 +1,17 @@
+xlin/__init__.py,sha256=CIhMAGhFgqwC6w16MzKcwo2mDjmaRUAcrlZFR3Am--I,321
+xlin/dataframe_util.py,sha256=zWpkGN-C9V9qVAVH8K4ElkPVu9pq4MjDbxwjJKSOO2o,12151
+xlin/datetime_util.py,sha256=MHi827LBuAOX6SSMb31staNBjmtnNOXwg7JDk73_pLU,6212
+xlin/file_util.py,sha256=QG7UiO-hePEB02H53lAWFanQvKlfFTPMhSPyQPma4dU,7199
+xlin/image_util.py,sha256=hSNQ5suCrxFXpQwP-wfUT1ig3SfEdC6msuVp2k7J7b8,8438
+xlin/jsonlist_util.py,sha256=dLgrgrSTvg_1plVRCEnilajPM_s3vYdVx2bCTqrZAN8,11316
+xlin/metric.py,sha256=mBaHy4ZkBbJxq7bCEF9NHdCRTaMcIIqfUj5JS8ElW98,1718
+xlin/multiprocess_util.py,sha256=-tskCWQlBBCOPycXLj9Y2MugYg-tHF_QYYWW7c1ixOk,17300
+xlin/statistic.py,sha256=ioJJjL4qwHiwNPeBFBB67keoAIbB-uZM51zkDYviar0,17037
+xlin/text_util.py,sha256=ejFD8-j8tLCbPlCPFg0Tu3MEMPEpF7R5_IpXXjl6qzA,735
+xlin/timing_util.py,sha256=nNVKtSXel-Cc8SF_BqPRNkyNDOjGqOMxTol-L1vpON4,1340
+xlin/xlsx_util.py,sha256=uSmXcDvIhi5Sq0LGidMXy0wErNBXdjaoa6EftYVjTXs,947
+xlin/yaml_util.py,sha256=kICi7G3Td5q2MaSXXt85qNTWoHMgjzt7pvn7r3C4dME,183
+xlin-0.2.3.dist-info/LICENSE,sha256=60ys6rRtc1dZOP8UjSUr9fAqhZudT3WpKe5WbMCralM,1066
+xlin-0.2.3.dist-info/METADATA,sha256=xI6UKJaM3MLUlp_YhkVaGA-50HNOKZzVHc6zWFZCbfE,8061
+xlin-0.2.3.dist-info/WHEEL,sha256=IrRNNNJ-uuL1ggO5qMvT1GGhQVdQU54d6ZpYqEZfEWo,92
+xlin-0.2.3.dist-info/RECORD,,

xlin-0.1.39.dist-info/RECORD

@@ -1,17 +0,0 @@
-xlin/__init__.py,sha256=CIhMAGhFgqwC6w16MzKcwo2mDjmaRUAcrlZFR3Am--I,321
-xlin/dataframe_util.py,sha256=Z8k3_XLMP5B13IMov2dQJhe-7dPh_YUJGokibWSx8II,10460
-xlin/datetime_util.py,sha256=jzdF-58PTb_ofBy6F-LBDnEmsTQ9jvoCgqKZJmyDtqE,687
-xlin/file_util.py,sha256=mYTABNywdYoSfh1RLJcH7l1FzgKTFWN2-JZMFzv-ehw,7270
-xlin/image_util.py,sha256=j1QlVXS-aikTDFDINbTmxjZi6CokPDTVlQ6_ABctMWQ,8109
-xlin/jsonlist_util.py,sha256=dLgrgrSTvg_1plVRCEnilajPM_s3vYdVx2bCTqrZAN8,11316
-xlin/metric.py,sha256=N7wJ35y-C-IaBr1I1CJ_37lTG7gA69zmn9Xg6xSwKoI,1690
-xlin/multiprocess_util.py,sha256=-tskCWQlBBCOPycXLj9Y2MugYg-tHF_QYYWW7c1ixOk,17300
-xlin/statistic.py,sha256=ioJJjL4qwHiwNPeBFBB67keoAIbB-uZM51zkDYviar0,17037
-xlin/text_util.py,sha256=ejFD8-j8tLCbPlCPFg0Tu3MEMPEpF7R5_IpXXjl6qzA,735
-xlin/timing_util.py,sha256=nNVKtSXel-Cc8SF_BqPRNkyNDOjGqOMxTol-L1vpON4,1340
-xlin/xlsx_util.py,sha256=uSmXcDvIhi5Sq0LGidMXy0wErNBXdjaoa6EftYVjTXs,947
-xlin/yaml_util.py,sha256=kICi7G3Td5q2MaSXXt85qNTWoHMgjzt7pvn7r3C4dME,183
-xlin-0.1.39.dist-info/LICENSE,sha256=60ys6rRtc1dZOP8UjSUr9fAqhZudT3WpKe5WbMCralM,1066
-xlin-0.1.39.dist-info/METADATA,sha256=d9F6S7LBxur58Jm817Kww54kVOBeWTRvc4R0AgOWYfw,7992
-xlin-0.1.39.dist-info/WHEEL,sha256=IrRNNNJ-uuL1ggO5qMvT1GGhQVdQU54d6ZpYqEZfEWo,92
-xlin-0.1.39.dist-info/RECORD,,