direl-ts-tool-kit 0.3.2__tar.gz → 0.4.1__tar.gz

{direl_ts_tool_kit-0.3.2 → direl_ts_tool_kit-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: direl-ts-tool-kit
-Version: 0.3.2
+Version: 0.4.1
 Summary: A toolbox for time series analysis and visualization.
 Home-page: https://gitlab.com/direl/direl_tool_kit
 Author: Diego Restrepo-Leal

{direl_ts_tool_kit-0.3.2 → direl_ts_tool_kit-0.4.1}/direl_ts_tool_kit/utilities/data_prep.py

@@ -1,3 +1,4 @@
+import numpy as np
 import pandas as pd
 
 
@@ -5,7 +6,7 @@ def parse_datetime_index(df_raw, date_column="date", format=None):
     """
     Parses a specified column into datetime objects and sets it as the DataFrame index.
 
-    This function prepares raw data for time series analysis by ensuring the 
+    This function prepares raw data for time series analysis by ensuring the
     DataFrame is indexed by the correct datetime type.
 
     Parameters
@@ -16,15 +17,15 @@ def parse_datetime_index(df_raw, date_column="date", format=None):
         The name of the column in 'df_raw' that contains the date/time information.
         Defaults to "date".
     format : str, optional
-        The explicit format string (e.g., '%Y%m%d', '%Y-%m-%d %H:%M:%S') 
-        to parse the dates, passed to `pd.to_datetime`. If None (default), 
+        The explicit format string (e.g., '%Y%m%d', '%Y-%m-%d %H:%M:%S')
+        to parse the dates, passed to `pd.to_datetime`. If None (default),
         Pandas attempts to infer the format automatically.
 
     Returns
     -------
     df_ts : pd.DataFrame
-        A copy of the original DataFrame with the specified date column removed 
-        and set as the DatetimeIndex. The returned DataFrame is ready for 
+        A copy of the original DataFrame with the specified date column removed
+        and set as the DatetimeIndex. The returned DataFrame is ready for
         time series operations.
     """
     if not format:
@@ -123,3 +124,38 @@ def reindex_and_aggregate(df_ts, column_name, freq="MS"):
     df_ts_new.notnull().apply(pd.Series.value_counts)
 
     return df_ts_new
+
+
+def remove_outliers_by_threshold(df_ts, column_name, lower_bound, upper_bound):
+    """
+    Replaces values in a specified column with NaN if they fall outside
+    a defined range (outlier removal).
+
+    This function identifies data points that are either below the lower
+    bound or above the upper bound and treats them as missing data.
+
+    Parameters
+    ----------
+    df_ts : pd.DataFrame
+        The time series DataFrame (must have a DatetimeIndex).
+    column_name : str
+        The name of the column where outlier detection will be performed (e.g., 'Temperature').
+    lower_bound : float or int
+        The minimum acceptable value. Values strictly below this bound are replaced by NaN.
+    upper_bound : float or int
+        The maximum acceptable value. Values strictly above this bound are replaced by NaN.
+
+    Returns
+    -------
+    pd.DataFrame
+        The DataFrame with outlier values in the specified column replaced by np.nan.
+    """
+    df_out = df_ts.copy()
+
+    outlier_index = df_out[
+        (df_out[column_name] < lower_bound) | (df_out[column_name] > upper_bound)
+    ].index
+
+    df_out.loc[outlier_index, column_name] = np.nan
+
+    return df_out

{direl_ts_tool_kit-0.3.2 → direl_ts_tool_kit-0.4.1}/direl_ts_tool_kit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: direl-ts-tool-kit
-Version: 0.3.2
+Version: 0.4.1
 Summary: A toolbox for time series analysis and visualization.
 Home-page: https://gitlab.com/direl/direl_tool_kit
 Author: Diego Restrepo-Leal

{direl_ts_tool_kit-0.3.2 → direl_ts_tool_kit-0.4.1}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="direl-ts-tool-kit",
-    version="0.3.2",
+    version="0.4.1",
     description="A toolbox for time series analysis and visualization.",
     long_description=open("README.md", encoding="utf-8").read(),
     long_description_content_type="text/markdown",