spotforecast2 0.2.0__tar.gz → 0.2.2__tar.gz

{spotforecast2-0.2.0 → spotforecast2-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: spotforecast2
-Version: 0.2.0
+Version: 0.2.2
 Summary: Forecasting with spot
 Author: bartzbeielstein
 Author-email: bartzbeielstein <32470350+bartzbeielstein@users.noreply.github.com>

{spotforecast2-0.2.0 → spotforecast2-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "spotforecast2"
-version = "0.2.0"
+version = "0.2.2"
 description = "Forecasting with spot"
 readme = "README.md"
 authors = [

{spotforecast2-0.2.0 → spotforecast2-0.2.2}/src/spotforecast2/data/fetch_data.py

@@ -44,57 +44,90 @@ def get_data_home(data_home: Optional[Union[str, Path]] = None) -> Path:
 
 
 def fetch_data(
-    filename: str = "data_in.csv",
+    filename: Optional[str] = None,
+    dataframe: Optional[pd.DataFrame] = None,
     columns: Optional[list] = None,
     index_col: int = 0,
     parse_dates: bool = True,
     dayfirst: bool = False,
     timezone: str = "UTC",
 ) -> pd.DataFrame:
-    """Fetches the integrated raw dataset from a CSV file.
+    """Fetches the integrated raw dataset from a CSV file or processes a DataFrame.
 
     Args:
-        filename (str):
-            Filename of the CSV file containing the dataset. It must be located in the data home directory, which can be get or set using `get_data_home()`.
+        filename (str, optional):
+            Filename of the CSV file containing the dataset. Must be located in the 
+            data home directory. If both filename and dataframe are None, defaults to "data_in.csv".
+        dataframe (pd.DataFrame, optional):
+            A pandas DataFrame to process. If provided, it will be processed with
+            proper timezone handling. Mutually exclusive with filename.
         columns (list, optional):
             List of columns to be included in the dataset. If None, all columns are included.
-            If an empty list is provided, a ValueError is blocked.
+            If an empty list is provided, a ValueError is raised.
         index_col (int):
-            Column index to be used as the index.
+            Column index to be used as the index (only used when loading from CSV).
         parse_dates (bool):
-            Whether to parse dates in the index column.
+            Whether to parse dates in the index column (only used when loading from CSV).
         dayfirst (bool):
-            Whether the day comes first in date parsing.
+            Whether the day comes first in date parsing (only used when loading from CSV).
         timezone (str):
-            Timezone to set for the datetime index.
+            Timezone to set for the datetime index. If a DataFrame with naive index is provided,
+            it will be localized to this timezone then converted to UTC. Default: "UTC".
 
     Returns:
-        pd.DataFrame: The integrated raw dataset.
+        pd.DataFrame: The integrated raw dataset with UTC timezone.
 
     Raises:
-        ValueError: If columns is an empty list.
+        ValueError: If columns is an empty list or if both filename and dataframe are provided.
+        FileNotFoundError: If CSV file does not exist.
 
     Examples:
+        Load from CSV (default):
         >>> from spotforecast2.data.fetch_data import fetch_data
         >>> data = fetch_data(columns=["col1", "col2"])
         >>> data.head()
                         Header1  Header2  Header3
+        
+        Load from specific CSV:
+        >>> data = fetch_data(filename="custom_data.csv")
+        
+        Process a DataFrame:
+        >>> import pandas as pd
+        >>> df = pd.DataFrame({"value": [1, 2, 3]}, 
+        ...                   index=pd.date_range("2024-01-01", periods=3, freq="h"))
+        >>> data = fetch_data(dataframe=df, timezone="Europe/Berlin")
+        >>> data.index.tz
+        <UTC>
     """
     if columns is not None and len(columns) == 0:
         raise ValueError("columns must be specified and cannot be empty.")
-
-    csv_path = get_data_home() / filename
-    if not Path(csv_path).is_file():
-        raise FileNotFoundError(f"The file {csv_path} does not exist.")
-
-    dataset = Data.from_csv(
-        csv_path=csv_path,
-        index_col=index_col,
-        parse_dates=parse_dates,
-        dayfirst=dayfirst,
-        timezone=timezone,
-        columns=columns,
-    )
+    
+    if filename is not None and dataframe is not None:
+        raise ValueError("Cannot specify both filename and dataframe. Please provide only one.")
+
+    # Process DataFrame if provided
+    if dataframe is not None:
+        dataset = Data.from_dataframe(
+            df=dataframe,
+            timezone=timezone,
+            columns=columns,
+        )
+    else:
+        # Load from CSV file
+        if filename is None:
+            filename = "data_in.csv"
+        csv_path = get_data_home() / filename
+        if not Path(csv_path).is_file():
+            raise FileNotFoundError(f"The file {csv_path} does not exist.")
+
+        dataset = Data.from_csv(
+            csv_path=csv_path,
+            index_col=index_col,
+            parse_dates=parse_dates,
+            dayfirst=dayfirst,
+            timezone=timezone,
+            columns=columns,
+        )
 
     return dataset.data
 

{spotforecast2-0.2.0 → spotforecast2-0.2.2}/src/spotforecast2/processing/n2n_predict.py

@@ -314,13 +314,15 @@ def n2n_predict(
 
     if verbose:
         print("--- Starting n2n_predict ---")
-        print("Fetching data...")
 
-    # Fetch data
+    # Handle data input - fetch_data handles both CSV and DataFrame
     if data is not None:
-        if TARGET is not None:
-            data = data[TARGET]
+        if verbose:
+            print("Using provided dataframe...")
+        data = fetch_data(dataframe=data, columns=TARGET)
     else:
+        if verbose:
+            print("Fetching data from CSV...")
         data = fetch_data(columns=TARGET)
 
     START, END, COV_START, COV_END = get_start_end(

{spotforecast2-0.2.0 → spotforecast2-0.2.2}/src/spotforecast2/processing/n2n_predict_with_covariates.py

@@ -868,8 +868,16 @@ def n2n_predict_with_covariates(
     if verbose:
         print("\n[1/9] Loading and preparing target data...")
 
+    # Handle data input - fetch_data handles both CSV and DataFrame
     if data is None:
-        data = fetch_data()
+        if verbose:
+            print("  Fetching data from CSV...")
+        data = fetch_data(timezone=timezone)
+    else:
+        if verbose:
+            print("  Using provided dataframe...")
+        data = fetch_data(dataframe=data, timezone=timezone)
+    
     target_columns = data.columns.tolist()
 
     if verbose: