xlin 0.1.8__tar.gz → 0.1.10__tar.gz

{xlin-0.1.8 → xlin-0.1.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: xlin
-Version: 0.1.8
+Version: 0.1.10
 Summary: toolbox for LinXueyuan
 License: MIT
 Author: XiChen

{xlin-0.1.8 → xlin-0.1.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "xlin"
-version = "0.1.8"
+version = "0.1.10"
 description = "toolbox for LinXueyuan"
 authors = ["XiChen <23211526+LinXueyuanStdio@users.noreply.github.com>"]
 license = "MIT"

xlin-0.1.10/xlin/__init__.py

@@ -0,0 +1,9 @@
+from .ischinese import *
+from .jsonl import *
+from .metric import *
+from .multiprocess_mapping import *
+from .read_as_dataframe import *
+from .statistic import *
+from .util import *
+from .xls2xlsx import *
+from .yaml import *

xlin-0.1.10/xlin/metric.py

@@ -0,0 +1,53 @@
+
+def stream_average(avg_pre, cur_num_index, cur_num):
+    """
+    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
+    however, we don't know the length of the stream, so we use a moving average
+    so avg[n-1] = sum(nums[:n-1]) / (n-1)
+    so n * avg[n] = (n-1) * avg[n-1] + nums[n]
+    so avg[n] = avg[n-1] + (nums[n] - avg[n-1]) / n
+    we don't need to remember every nums before n
+
+    Usage:
+    >>> acc = 0
+    >>> nums = [1, 0, 1, 0, 0, 1, 1, 1, 0, 1]
+    >>> for i, num in enumerate(nums):
+    ...     acc = stream_average(acc, i, num)
+
+    :param avg_pre: (initially 0) average of previous numbers from index 0 to cur_num_index-1, i.e. avg[n-1]
+    :param cur_num_index: current number index starting from 0, i.e. n
+    :param cur_num: current number, i.e. nums[n]
+    :return: average of current number and previous numbers, i.e. avg[n]
+    """
+    return avg_pre + (cur_num - avg_pre) / (cur_num_index + 1)
+
+
+class AverageMeter:
+    """Computes and stores the average and current value"""
+
+    def __init__(self, name, fmt=':f'):
+        self.name = name
+        self.fmt = fmt
+        self.val = 0
+        self.avg = 0
+        self.sum = 0
+        self.count = 0
+        self.reset()
+
+    def reset(self):
+        self.val = 0
+        self.avg = 0
+        self.sum = 0
+        self.count = 0
+
+    def update(self, val, n=1):
+        self.val = val
+        self.sum += val * n
+        self.count += n
+        self.avg = self.sum / self.count
+
+    def __str__(self):
+        fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'
+        return fmtstr.format(**self.__dict__)
+

xlin-0.1.8/xlin/terminal_color.py

@@ -1,10 +0,0 @@
-
-blue = "\x1b[34m"
-cyan = "\x1b[36;21m"
-green = "\x1b[32;21m"
-orange = "\x1b[33;21m"
-grey = "\x1b[38;21m"
-yellow = "\x1b[33;21m"
-red = "\x1b[31;21m"
-bold_red = "\x1b[31;1m"
-reset = "\x1b[0m"

xlin-0.1.8/xlin/uuid.py

@@ -1,13 +0,0 @@
-from typing import *
-import uuid
-
-import pandas as pd
-
-
-def append_uuid_column(df: pd.DataFrame, uuid_key="uuid"):
-    rows = []
-    for i, row in df.iterrows():
-        row[uuid_key] = str(uuid.uuid4())
-        rows.append(row)
-    df = pd.DataFrame(rows)
-    return df