edmt 1.0.6.dev1__tar.gz → 1.0.7.dev1__tar.gz

{edmt-1.0.6.dev1 → edmt-1.0.7.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: edmt
-Version: 1.0.6.dev1
+Version: 1.0.7.dev1
 Summary: Environmental Data Management Toolbox
 Author-email: "Odero, Kuloba & musasia" <francisodero10@gmail.com>
 License: MIT License
@@ -26,8 +26,8 @@ License: MIT License
         SOFTWARE.
         
 Project-URL: Homepage, https://github.com/envdmt/EDMT/
+Project-URL: Documentation, https://envdmt.github.io/EDMT/
 Keywords: geospatial,gis,earth-engine,remote-sensing,conservation,spatial-analysis,geopandas
-Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Education
@@ -53,7 +53,6 @@ Requires-Dist: fiona<1.10.1,>=1.9.6
 Requires-Dist: tqdm>=4
 Requires-Dist: requests<3,>=2.28
 Requires-Dist: matplotlib>=3.9
-Requires-Dist: mapclassify>=2.7
 Dynamic: license-file
 
 <h1 align="center">EDMT — Environmental Data Management Toolbox</h1>
@@ -63,18 +62,16 @@ Dynamic: license-file
   <a href="https://pypi.org/project/edmt/">
     <img src="https://img.shields.io/pypi/v/edmt.svg" alt="PyPI version" />
   </a>
-
-  <!-- Codecov -->
-  <!-- <a href="https://codecov.io/gh/envdmt/EDMT">
-    <img src="https://codecov.io/gh/envdmt/EDMT/branch/main/graph/badge.svg" alt="codecov" />
-  </a> -->
-
-
   <!-- Docs -->
   <a href="https://envdmt.github.io/EDMT/">
     <img src="https://img.shields.io/badge/docs-passing-brightgreen.svg" alt="docs" />
   </a>
 
+  <!-- Tests -->
+  <a href="https://github.com/envdmt/EDMT/actions?query=workflow%3ATests">
+    <img src="https://github.com/envdmt/EDMT/workflows/Tests/badge.svg" alt="tests" />
+  </a>
+
   <!-- Jupyter -->
   <img src="https://img.shields.io/badge/Jupyter-Lab-orange.svg" alt="Jupyter Lab" />
 
@@ -83,30 +80,48 @@ Dynamic: license-file
 </p>
 
 
-## Overview
+------------------------------------------------------------------------
 
-**EDMT (Environmental Data Management Toolbox)** is a lightweight Python library designed to make environmental data ingestion, cleaning, transformation, and basic analysis workflows easier and more reproducible. It provides a set of tools and helper functions tailored to the common needs of environmental scientists, data engineers, and analysts working with diverse observational and sensor-derived datasets.
+# Overview
 
-It provides modular tools for:
+EDMT (Environmental Data Management Toolbox) is a lightweight Python library for working with environmental and geospatial datasets. It provides practical utilities for data ingestion, cleaning, transformation, and exploratory analysis, helping researchers and analysts build reproducible data workflows.
 
-- Data ingestion (CSV, sensors, exports, logs)
-- Cleaning & quality control
-- Time-series handling
-- Spatial & temporal transformations
-- Basic analytics & summaries
-- Reusable, reproducible workflows
+EDMT integrates well with the Python scientific stack and is particularly useful when working with time-series environmental data, spatial datasets, and monitoring data pipelines.
 
-Why EDMT?
+It is designed for:
 
-Environmental data workflows often require stitching together formats, checks, and cleaning steps that are repetitive and error-prone. EDMT centralizes these common operations into reusable Python functions and classes, helping you:
+-   Environmental scientists
+-   Conservation and wildlife monitoring teams
+-   GIS and geospatial developers
+-   Data analysts working with environmental datasets
 
-- Save development time and reduce duplication
-- Standardize procedures across different projects
-- Improve reproducibility and traceability of results
+------------------------------------------------------------------------
 
----
+# Installation
 
-## Installation
+Install directly from PyPI:
 
-```bash
+``` bash
 pip install edmt
+```
+
+------------------------------------------------------------------------
+
+# Typical Use Cases
+
+EDMT can support workflows such as:
+
+-   Environmental monitoring pipelines
+-   Remote sensing preprocessing
+-   Field data quality control
+-   Environmental research and reporting
+
+------------------------------------------------------------------------
+
+# Documentation
+
+Full documentation is available here:
+
+https://envdmt.github.io/EDMT/
+
+------------------------------------------------------------------------

edmt-1.0.7.dev1/README.md

@@ -0,0 +1,70 @@
+<h1 align="center">EDMT — Environmental Data Management Toolbox</h1>
+
+<p align="center">
+  <!-- PyPI -->
+  <a href="https://pypi.org/project/edmt/">
+    <img src="https://img.shields.io/pypi/v/edmt.svg" alt="PyPI version" />
+  </a>
+  <!-- Docs -->
+  <a href="https://envdmt.github.io/EDMT/">
+    <img src="https://img.shields.io/badge/docs-passing-brightgreen.svg" alt="docs" />
+  </a>
+
+  <!-- Tests -->
+  <a href="https://github.com/envdmt/EDMT/actions?query=workflow%3ATests">
+    <img src="https://github.com/envdmt/EDMT/workflows/Tests/badge.svg" alt="tests" />
+  </a>
+
+  <!-- Jupyter -->
+  <img src="https://img.shields.io/badge/Jupyter-Lab-orange.svg" alt="Jupyter Lab" />
+
+  <!-- License -->
+  <img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="license" />
+</p>
+
+
+------------------------------------------------------------------------
+
+# Overview
+
+EDMT (Environmental Data Management Toolbox) is a lightweight Python library for working with environmental and geospatial datasets. It provides practical utilities for data ingestion, cleaning, transformation, and exploratory analysis, helping researchers and analysts build reproducible data workflows.
+
+EDMT integrates well with the Python scientific stack and is particularly useful when working with time-series environmental data, spatial datasets, and monitoring data pipelines.
+
+It is designed for:
+
+-   Environmental scientists
+-   Conservation and wildlife monitoring teams
+-   GIS and geospatial developers
+-   Data analysts working with environmental datasets
+
+------------------------------------------------------------------------
+
+# Installation
+
+Install directly from PyPI:
+
+``` bash
+pip install edmt
+```
+
+------------------------------------------------------------------------
+
+# Typical Use Cases
+
+EDMT can support workflows such as:
+
+-   Environmental monitoring pipelines
+-   Remote sensing preprocessing
+-   Field data quality control
+-   Environmental research and reporting
+
+------------------------------------------------------------------------
+
+# Documentation
+
+Full documentation is available here:
+
+https://envdmt.github.io/EDMT/
+
+------------------------------------------------------------------------

{edmt-1.0.6.dev1 → edmt-1.0.7.dev1}/edmt/base/base.py

@@ -1,22 +1,27 @@
 import logging
-logger = logging.getLogger(__name__)
 import base64
 import http.client
+from typing import Optional, Union
 import requests
 import pandas as pd
 from io import StringIO
 import time
 
+logger = logging.getLogger(__name__)
 logging.basicConfig(level=logging.WARNING)
 
 class AirdataBaseClass:
-    def __init__(self, api_key):
+    def __init__(self, api_key: str, skip_auth: bool = False):
         self.api_key = api_key
         self.base_url = "api.airdata.com"
         self.authenticated = False
         self.auth_header = self._get_auth_header()
 
-        self.authenticate(validate=True)
+        if not skip_auth:
+            self.authenticate(validate=True)
+        else:
+            self.authenticated = True
+            self.auth_header = {"Authorization": "Bearer fake_token"}
 
     def _get_auth_header(self):
         key_with_colon = self.api_key + ":"
@@ -62,11 +67,11 @@ class AirdataBaseClass:
 
 
 def ExtractCSV(
-    row, 
-    col : str,
-    max_retries : int = 3, 
-    timeout : int = 15
-    ) -> pd.DataFrame:
+    row: Union[dict, pd.Series],
+    col: str,
+    max_retries: int = 3,
+    timeout: int = 15
+    ) -> Optional[pd.DataFrame]:
     """
     Fetches a CSV file from a URL specified in a given column of a metadata record.
 

{edmt-1.0.6.dev1 → edmt-1.0.7.dev1}/edmt/contrib/utils.py

@@ -12,7 +12,6 @@ def clean_vars(addl_kwargs={}, **kwargs):
 
 
 def normalize_column(df, col):
-    # print(col)
     for k, v in pd.json_normalize(df.pop(col), sep="__").add_prefix(f"{col}__").items():
         df[k] = v.values
 
@@ -30,10 +29,17 @@ def clean_time_cols(df,columns = []):
 
 def format_iso_time(date_string: str) -> str:
     try:
-        return pd.to_datetime(date_string).isoformat()
-    except ValueError:
-        raise ValueError(f"Failed to parse timestamp'{date_string}'")
-    
+        dt = pd.to_datetime(date_string)
+        if isinstance(dt, (pd.DatetimeIndex, pd.Series)):
+            if len(dt) == 0:
+                raise ValueError("Empty datetime collection")
+            dt = dt[0]
+        if pd.isna(dt):
+            raise ValueError("Invalid timestamp (NaT)")
+        return dt.isoformat()
+    except (ValueError, TypeError, AttributeError):
+        raise ValueError(f"Failed to parse timestamp '{date_string}'")   
+
 
 def norm_exp(df: pd.DataFrame, cols : Union[str, list]) -> pd.DataFrame:
     """
@@ -97,7 +103,6 @@ def append_cols(df: pd.DataFrame, cols: Union[str, list]):
     return df[remaining_cols + cols]
 
 
-
 def dict_expand(data,cols):
   dfs_to_join = []
   df_processed = data.copy()

{edmt-1.0.6.dev1 → edmt-1.0.7.dev1}/edmt/conversion/__init__.py

@@ -3,19 +3,22 @@ from .conversion import (
     generate_uuid,
     generate_cmap,
     get_utm_epsg,
-    convert_distance,
     convert_time,
     convert_speed,
-    convert_temperature
+    convert_distance,
+    convert_temperature,
+    format_temperature
 )
 
+
 __all__ = [
     'sdf_to_gdf', 
     'generate_uuid',
     'generate_cmap',
     'get_utm_epsg',
-    'convert_distance',
     'convert_time',
     'convert_speed',
-    'convert_temperature'
+    'convert_distance',
+    'convert_temperature',
+    'format_temperature'
     ]

{edmt-1.0.6.dev1 → edmt-1.0.7.dev1}/edmt/conversion/conversion.py

@@ -158,6 +158,7 @@ def sdf_to_gdf(sdf, crs=None):
 
     return gdf
 
+
 def _is_valid_uuid(val) -> bool:
     if pd.isna(val):
         return False
@@ -551,14 +552,13 @@ def convert_temperature(value: float, unit_from: str, unit_to: str) -> float:
     return round(out, 3)
 
 
-def format_temperature(value: float, unit: str, decimals: int = 1, symbol: bool = True) -> str:
+def format_temperature(value: float, unit: str, symbol: bool = True) -> str:
     """
     Formats a temperature value with unit, e.g. '23.5 °C' or '296.6 K'.
 
     Args:
         value (float): Temperature value.
         unit (str): Unit to display (C, F, K).
-        decimals (int): Decimal places.
         symbol (bool): If True, uses °C/°F, and K without degree symbol.
 
     Returns:
@@ -568,14 +568,12 @@ def format_temperature(value: float, unit: str, decimals: int = 1, symbol: bool
     if u not in temp_units:
         raise ValueError(f"Unsupported temperature unit: {unit!r}. Valid: {', '.join(temp_units)}")
 
-    val_str = f"{float(value):.{int(decimals)}f}"
-
     if not symbol:
-        return f"{val_str} {u}"
+        return f"{value} {u}"
 
     if u in ("C", "F"):
-        return f"{val_str} °{u}"
-    return f"{val_str} K"
+        return f"{value} °{u}"
+    return f"{value} K"