jzhou-utils 0.0.3__tar.gz

jzhou_utils-0.0.3/.gitignore

@@ -0,0 +1,5 @@
+
+/.ipynb_checkpoints
+/dist
+/untracked
+/src/jzhou_utils/.ipynb_checkpoints

jzhou_utils-0.0.3/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 homage-to-the-square
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

jzhou_utils-0.0.3/PKG-INFO

@@ -0,0 +1,21 @@
+Metadata-Version: 2.4
+Name: jzhou_utils
+Version: 0.0.3
+Summary: A small example package
+Project-URL: Homepage, https://github.com/pypa/sampleproject
+Project-URL: Issues, https://github.com/pypa/sampleproject/issues
+Author-email: Jason Zhou <author@example.com>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.9
+Requires-Dist: datetime
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: re
+Requires-Dist: requests
+Requires-Dist: typing
+Description-Content-Type: text/markdown
+
+This is a simple Python package for common data manipulations and other utils.

jzhou_utils-0.0.3/README.md

@@ -0,0 +1 @@
+This is a simple Python package for common data manipulations and other utils.

jzhou_utils-0.0.3/pyproject.toml

@@ -0,0 +1,32 @@
+[build-system]
+requires = ["hatchling >= 1.26"]
+build-backend = "hatchling.build"
+
+
+[project]
+name = "jzhou_utils"
+version = "0.0.3"
+dependencies = [
+    "requests",
+    "numpy",
+    "pandas",
+    "datetime",
+    "typing",
+    "re"
+]
+authors = [
+  { name="Jason Zhou", email="author@example.com" },
+]
+description = "A small example package"
+readme = "README.md"
+requires-python = ">=3.9"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+]
+license = "MIT"
+license-files = ["LICEN[CS]E*"]
+
+[project.urls]
+Homepage = "https://github.com/pypa/sampleproject"
+Issues = "https://github.com/pypa/sampleproject/issues"

jzhou_utils-0.0.3/readme.md

@@ -0,0 +1 @@
+This is a simple Python package for common data manipulations and other utils.

jzhou_utils-0.0.3/src/jzhou_utils/__init__.py

@@ -0,0 +1,3 @@
+from jzhou_utils.dt_utils import *
+from jzhou_utils.pd_utils import *
+from jzhou_utils.base_utils import *

jzhou_utils-0.0.3/src/jzhou_utils/base_utils.py

@@ -0,0 +1,27 @@
+import re
+from typing import List, Set, Any
+
+def map_dicts_values_to_keys(dict1, dict2) -> dict:
+    """
+        creates a new dictionary, which maps from keys of dict1 to values of dict2,
+            assuming that the values of dict1 are keys of dict2
+    """
+    return {k: dict2[v] for k, v in dict1.items() if v in dict2}
+
+def is_decimal(string):
+    return bool(re.match(r"^-?\d+(\.\d+)?$", string))
+
+def intersect_sets(sets: List[Set[Any]]) -> Set[Any]:
+    """
+    Compute the intersection of a list of sets.
+
+    Args:
+        sets (List[Set[Any]]): A list of set objects.
+
+    Returns:
+        Set[Any]: The intersection of all sets in the list.
+    """
+    if not sets:
+        return set()
+    
+    return set.intersection(*sets)

jzhou_utils-0.0.3/src/jzhou_utils/dt_utils.py

@@ -0,0 +1,30 @@
+import pandas as pd
+import datetime as dt
+from typing import Union
+
+def YYYMM_to_date(s: pd.Series) -> pd.Series:
+    """
+        converts series of integers into dates
+    """
+    return pd.to_datetime(s.astype(str), format='%Y%m').dt.date
+
+def date_id_to_date(date_id: Union[int, pd.Series]):
+    if isinstance(date_id, int):
+        return dt.datetime.strptime(str(date_id), '%Y%m%d').date()
+    else:
+        return pd.to_datetime(date_id.astype(str), format='%Y%m%d').dt.date
+
+def date_to_date_id(date: dt.date) -> int:
+    return int(date.strftime('%Y%m%d'))
+    
+def get_friday_of_isocalendar(iso_year, iso_week):
+    # Get the first day of the ISO week
+    first_day_of_week = dt.date(iso_year, 1, 1) + dt.timedelta(weeks=iso_week-1)
+    
+    # Adjust to the correct day of the week (Friday is 4)
+    # `first_day_of_week.weekday()` gives the weekday of the first day of the ISO week.
+    # We need to adjust to make sure we get the Friday of that week.
+    days_to_friday = (4 - first_day_of_week.weekday()) % 7
+    friday = first_day_of_week + dt.timedelta(days=days_to_friday)
+    return friday
+

jzhou_utils-0.0.3/src/jzhou_utils/pd_utils.py

@@ -0,0 +1,29 @@
+import pandas as pd
+
+"""
+    Df utils:
+"""
+
+def strip_excess_spaces_df(df: pd.DataFrame) -> pd.DataFrame:
+    """
+        Returns dataframe with leading + trailing spaces stripped for string columns
+        - from gpt, but note that this has high mem usage + slow effectiveness
+    """
+    df_cleaned = df.copy()
+    for col in df.columns:
+        if df[col].apply(lambda x: isinstance(x, str)).mean() > 0.1:
+            df_cleaned[col] = df[col].str.rstrip()
+    return df_cleaned
+
+
+def str_to_float_df(df: pd.DataFrame) -> pd.DataFrame:
+    """
+        Try to convert all string columns into floats or ints, depending on pd.to_numeric 
+    """
+    df_converted = df.copy()
+    for col in df_converted.columns:
+        try:
+            df_converted[col] = pd.to_numeric(df_converted[col], errors='raise')
+        except Exception as e:
+            pass  # Skip columns that can't be converted
+    return df_converted