spotforecast2 0.1.1__py3-none-any.whl → 0.2.1__py3-none-any.whl

spotforecast2/data/fetch_data.py

@@ -44,57 +44,80 @@ def get_data_home(data_home: Optional[Union[str, Path]] = None) -> Path:
 
 
 def fetch_data(
-    filename: str = "data_in.csv",
+    filename: Union[str, pd.DataFrame] = "data_in.csv",
     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 or pd.DataFrame):
+            Filename of the CSV file containing the dataset (located in data home directory)
+            or a pandas DataFrame. If DataFrame is provided, it will be processed with
+            proper timezone handling. Default: "data_in.csv".
         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.
         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.
+        FileNotFoundError: If CSV file does not exist.
 
     Examples:
+        Load from CSV:
         >>> from spotforecast2.data.fetch_data import fetch_data
         >>> data = fetch_data(columns=["col1", "col2"])
         >>> data.head()
                         Header1  Header2  Header3
+        
+        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(filename=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,
-    )
+    # Check if filename is actually a DataFrame
+    if isinstance(filename, pd.DataFrame):
+        # Use Data.from_dataframe for proper timezone handling
+        dataset = Data.from_dataframe(
+            df=filename,
+            timezone=timezone,
+            columns=columns,
+        )
+    else:
+        # Load from CSV file
+        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/processing/n2n_predict.py

@@ -210,6 +210,7 @@ def _model_directory_exists(model_dir: Union[str, Path]) -> bool:
 
 
 def n2n_predict(
+    data: Optional[pd.DataFrame] = None,
     columns: Optional[List[str]] = None,
     forecast_horizon: int = 24,
     contamination: float = 0.01,
@@ -233,6 +234,8 @@ def n2n_predict(
     Existing models are reused for prediction unless force_train=True.
 
     Args:
+        data: Optional DataFrame with target time series data. If None, fetches data automatically.
+            Default: None.
         columns: List of target columns to forecast. If None, uses all available columns.
             Default: None.
         forecast_horizon: Number of time steps to forecast ahead. Default: 24.
@@ -311,10 +314,16 @@ def n2n_predict(
 
     if verbose:
         print("--- Starting n2n_predict ---")
-        print("Fetching data...")
 
-    # Fetch data
-    data = fetch_data(columns=TARGET)
+    # Handle data input - fetch_data handles both CSV and DataFrame
+    if data is not None:
+        if verbose:
+            print("Using provided dataframe...")
+        data = fetch_data(filename=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(
         data=data,

spotforecast2/processing/n2n_predict_with_covariates.py

@@ -727,6 +727,7 @@ def _model_directory_exists(model_dir: Union[str, Path]) -> bool:
 
 
 def n2n_predict_with_covariates(
+    data: Optional[pd.DataFrame] = None,
     forecast_horizon: int = 24,
     contamination: float = 0.01,
     window_size: int = 72,
@@ -763,6 +764,8 @@ def n2n_predict_with_covariates(
     Existing models are reused for prediction unless force_train=True.
 
     Args:
+        data: Optional DataFrame with target time series data. If None, fetches data automatically.
+            Default: None.
         forecast_horizon: Number of time steps to forecast ahead. Default: 24.
         contamination: Contamination parameter for outlier detection. Default: 0.01.
         window_size: Rolling window size for gap detection. Default: 72.
@@ -865,7 +868,16 @@ def n2n_predict_with_covariates(
     if verbose:
         print("\n[1/9] Loading and preparing target data...")
 
-    data = fetch_data()
+    # Handle data input - fetch_data handles both CSV and DataFrame
+    if data is None:
+        if verbose:
+            print("  Fetching data from CSV...")
+        data = fetch_data(timezone=timezone)
+    else:
+        if verbose:
+            print("  Using provided dataframe...")
+        data = fetch_data(filename=data, timezone=timezone)
+    
     target_columns = data.columns.tolist()
 
     if verbose:

{spotforecast2-0.1.1.dist-info → spotforecast2-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: spotforecast2
-Version: 0.1.1
+Version: 0.2.1
 Summary: Forecasting with spot
 Author: bartzbeielstein
 Author-email: bartzbeielstein <32470350+bartzbeielstein@users.noreply.github.com>

{spotforecast2-0.1.1.dist-info → spotforecast2-0.2.1.dist-info}/RECORD

@@ -1,7 +1,7 @@
 spotforecast2/__init__.py,sha256=X9sBx15iz8yqr9iDJcrGJM5nhvnpaczXto4XV_GtfhE,59
 spotforecast2/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 spotforecast2/data/data.py,sha256=HEgr-FULaqHvuMeKTviOgYyo3GbxpGRTo3ZnmIU9w2Y,4422
-spotforecast2/data/fetch_data.py,sha256=LcHowE6tnjKPNMTCGr8h29ioGHT4xmj6l6iZmZkJdLU,6842
+spotforecast2/data/fetch_data.py,sha256=whefI8g3y7rQzzhOp3uB6L3VQdvu4p2qc6aWvkKSgD0,8010
 spotforecast2/exceptions.py,sha256=6gOji-3cP-YAisPoxXCcrEEbjTnfPN1YqEhGYhmyZ8Y,20499
 spotforecast2/forecaster/__init__.py,sha256=BbCOS2ouKcPC9VzcdprllVyqlZIyAWXCOvUAiInxDi4,140
 spotforecast2/forecaster/base.py,sha256=rXhcjY4AMpyQhkpbtLIA8OOrGEb8fU57SQiyeR9c9DQ,16748
@@ -31,8 +31,8 @@ spotforecast2/preprocessing/imputation.py,sha256=lmH-HumI_QLLm9aMESe_oZq84Axn60w
 spotforecast2/preprocessing/outlier.py,sha256=jZxAR870QtYner7b4gXk6LLGJw0juLq1VU4CGklYd3c,4208
 spotforecast2/preprocessing/split.py,sha256=mzzt5ltUZdVzfWtBBTQjp8E2MyqVdWUFtz7nN11urbU,5011
 spotforecast2/processing/agg_predict.py,sha256=VKlruB0x-eJKokkHyJxR87rZ4m53si3ODbrd0ibPlow,2378
-spotforecast2/processing/n2n_predict.py,sha256=dAj5yXD2JGXSqtl0VDkq0O_8FO_K9BCYG6osbJbWDFg,14494
-spotforecast2/processing/n2n_predict_with_covariates.py,sha256=5a1lYIQE1d-t4ZvSQDoW87G705eiIZxtrCn4w7U2bVw,40420
+spotforecast2/processing/n2n_predict.py,sha256=eClK0uccg_pKCnDfzWckFV6TWprTxskaY3whH_vJGs0,14911
+spotforecast2/processing/n2n_predict_with_covariates.py,sha256=xP7V_JB0xF7I5KlAqeR-U0ENwxZNSvSQvsPOLHjZWV8,40913
 spotforecast2/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 spotforecast2/utils/__init__.py,sha256=NrMt_xJLe4rbTFbsbgSQYeREohEOiYG5S-97e6Jj07I,1018
 spotforecast2/utils/convert_to_utc.py,sha256=hz8mJUHK9jDLUiN5LdNX5l3KZuOKlklyycB4zFdB9Ng,1405
@@ -42,6 +42,6 @@ spotforecast2/utils/generate_holiday.py,sha256=SHaPvPMt-abis95cChHf5ObyPwCTrzJ87
 spotforecast2/utils/validation.py,sha256=x9ypQzcneDhWJA_piiY4Q3_ogoGd1LTsZ7__MFeG9Fc,21618
 spotforecast2/weather/__init__.py,sha256=1Jco88pl0deNESgNATin83Nf5i9c58pxN7G-vNiOiu0,120
 spotforecast2/weather/weather_client.py,sha256=Ec_ywug6uoa71MfXM8RNbXEvtBtBzr-SUS5xq_HKtZE,9837
-spotforecast2-0.1.1.dist-info/WHEEL,sha256=5DEXXimM34_d4Gx1AuF9ysMr1_maoEtGKjaILM3s4w4,80
-spotforecast2-0.1.1.dist-info/METADATA,sha256=TMwW-WMXSoNRVw7oDLU3Ys_8JXhODgvXxXjSeokWaXs,3481
-spotforecast2-0.1.1.dist-info/RECORD,,
+spotforecast2-0.2.1.dist-info/WHEEL,sha256=5DEXXimM34_d4Gx1AuF9ysMr1_maoEtGKjaILM3s4w4,80
+spotforecast2-0.2.1.dist-info/METADATA,sha256=CZtz7eiMtA8zOF85_sLrApPp085fYOYPsI7btv7UdtY,3481
+spotforecast2-0.2.1.dist-info/RECORD,,