new pkg

Author: shubhvjain

.github/workflows/workflow.yml

@@ -1,4 +1,4 @@
-name: Publish Python 🐍 distribution 📦 to PyPI
+name: Publish to PyPI
 
 on: 
   push:
@@ -7,7 +7,7 @@ on:
 
 jobs:
   build:
-    name: Build distribution 📦
+    name: Build distribution 
     runs-on: ubuntu-latest
 
     steps:
@@ -30,7 +30,7 @@ jobs:
         path: dist/
 
   publish-to-pypi:
-    name: Publish Python 🐍 distribution 📦 to PyPI
+    name: Publish to PyPI
     needs:
     - build
     runs-on: ubuntu-latest

codegreen_core/data/entsoe.py

@@ -47,6 +47,8 @@
     "Biomass": ["Biomass"],
 }
 
+
+
 # helper methods
 
 
@@ -287,6 +289,7 @@ def get_actual_production_percentage(country, start, end, interval60=False) -> d
       - `data_available`: A boolean indicating if data was successfully retrieved.
       - `data`: A pandas DataFrame containing the energy data if available, empty DataFrame if not.
       - `time_interval` : the time interval of the DataFrame
+      - `columns` :  a dict with column description
     :rtype: dict
     """
     try:
@@ -371,6 +374,7 @@ def get_actual_production_percentage(country, start, end, interval60=False) -> d
             "data": _format_energy_data(table),
             "data_available": True,
             "time_interval": duration,
+            "columns":gen_cols_from_data(table)
         }
     except Exception as e:
         # print(e)
@@ -380,8 +384,38 @@ def get_actual_production_percentage(country, start, end, interval60=False) -> d
             "data_available": False,
             "error": e,
             "time_interval": 0,
+            "columns":None
         }
 
+def gen_cols_from_data(df):
+    """generates list of columns for the given energy generation dataframe"""
+    allAddkeys = [
+            "Wind",
+            "Solar",
+            "Nuclear",
+            "Hydroelectricity",
+            "Geothermal",
+            "Natural Gas",
+            "Petroleum",
+            "Coal",
+            "Biomass",
+    ]
+
+    allCols = df.columns.tolist()
+    # find out which columns are present in the data out of all the possible columns in both the categories
+    renPresent = list(set(allCols).intersection(renewableSources))
+    nonRenPresent = list(set(allCols).intersection(nonRenewableSources))
+
+    cols = {
+            "renewable" : renPresent,
+            "nonRenewable": nonRenPresent,
+            "percentage":[]
+        }
+    for ky in allAddkeys:
+            fieldName = ky + "_per"
+            cols["percentage"].append(fieldName)
+    return cols
+
 
 def get_forecast_percent_renewable(
     country: str, start: datetime, end: datetime

codegreen_core/data/main.py

@@ -58,6 +58,7 @@ def energy(country, start_time, end_time, type="generation") -> dict:
         - **data** (*pandas.DataFrame*): The retrieved energy data if available; an empty DataFrame otherwise.
         - **time_interval** (*int*): The time interval of the DataFrame (constant value: ``60``).
         - **source** (*str*): Specifies the origin of the retrieved data. Defaults to ``'public_data'``, indicating it was fetched from an external source. If the offline storage feature is enabled, this value may change if the data is available locally.
+        - **columns** : a dict of columns for renewable and non renewable energy sources in the data
 
     :rtype: dict
 
@@ -99,15 +100,16 @@ def energy(country, start_time, end_time, type="generation") -> dict:
             offline_data = off.get_offline_data(country,start_time,end_time)
             if offline_data["available"] is True and offline_data["partial"] is False and offline_data["data"] is not None:
                 # todo fix this if partial get remaining data and merge instead of fetching the complete data
-                return {"data":offline_data["data"],"data_available":True,"error":"None","time_interval":60,"source":offline_data["source"]}
+                return {"data":offline_data["data"],"data_available":True,"error":"None","time_interval":60,"source":offline_data["source"],"columns":et.gen_cols_from_data(offline_data["data"])}
             else:
                 energy_data = et.get_actual_production_percentage(country, start_time, end_time, interval60=True)
-                energy_data["data"] = energy_data["data"]
+                #energy_data["data"] = energy_data["data"]
                 energy_data["source"] = "public_data"
+                #energy_data["columns"] = 
                 return energy_data            
         elif type == "forecast":
             energy_data = et.get_forecast_percent_renewable(country, start_time, end_time)
-            energy_data["data"] = energy_data["data"]
+            # energy_data["data"] = energy_data["data"]
             return energy_data
     else:
         raise CodegreenDataError(Message.NO_ENERGY_SOURCE)

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "codegreen_core"
-version = "0.0.4"
+version = "0.0.5"
 description = "This package helps you become aware of the carbon footprint of your computation"
 authors = ["Anne Hartebrodt <anne.hartebrodt@fau.de>","Shubh Vardhan Jain <shubh.v.jain@fau.de>"]
 readme = "README.md"