spotforecast2 0.0.1__tar.gz → 0.0.2__tar.gz

{spotforecast2-0.0.1 → spotforecast2-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: spotforecast2
-Version: 0.0.1
+Version: 0.0.2
 Summary: Forecasting with spot
 Author: bartzbeielstein
 Author-email: bartzbeielstein <32470350+bartzbeielstein@users.noreply.github.com>

{spotforecast2-0.0.1 → spotforecast2-0.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "spotforecast2"
-version = "0.0.1"
+version = "0.0.2"
 description = "Forecasting with spot"
 readme = "README.md"
 authors = [

{spotforecast2-0.0.1 → spotforecast2-0.0.2}/src/spotforecast2/data/fetch_data.py

@@ -44,7 +44,7 @@ def get_data_home(data_home: Optional[Union[str, Path]] = None) -> Path:
 
 
 def fetch_data(
-    filename: str = "integrated_raw_data.csv",
+    filename: str = "data_in.csv",
     columns: Optional[list] = None,
     index_col: int = 0,
     parse_dates: bool = True,
@@ -56,8 +56,9 @@ def fetch_data(
     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()`.
-        columns (list):
-            List of columns to be included in the dataset. Must be specified.
+        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.
         parse_dates (bool):
@@ -71,7 +72,7 @@ def fetch_data(
         pd.DataFrame: The integrated raw dataset.
 
     Raises:
-        ValueError: If columns is None or empty.
+        ValueError: If columns is an empty list.
 
     Examples:
         >>> from spotforecast2.data.fetch_data import fetch_data
@@ -79,7 +80,7 @@ def fetch_data(
         >>> data.head()
                         Header1  Header2  Header3
     """
-    if columns is None or len(columns) == 0:
+    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

spotforecast2-0.0.2/src/spotforecast2/processing/agg_predict.py

@@ -0,0 +1,61 @@
+from typing import Dict, Optional, Union, List
+import pandas as pd
+import numpy as np
+
+
+def agg_predict(
+    predictions: pd.DataFrame,
+    weights: Optional[Union[Dict[str, float], List[float], np.ndarray]] = None,
+) -> pd.Series:
+    """Aggregates multiple prediction columns into a single combined prediction series.
+
+    The combination is a weighted sum of the prediction columns. If no weights are provided,
+    a default weighting scheme based on specific predefined columns is used.
+
+    Args:
+        predictions (pd.DataFrame): DataFrame containing the prediction columns.
+        weights (Optional[Union[Dict[str, float], List[float], np.ndarray]]):
+            Dictionary mapping column names to their weights, or a list/array of weights
+            corresponding to the order of columns in `predictions`.
+            If None, defaults to summing all columns (weight=1.0 for each column).
+
+    Returns:
+        pd.Series: A Series containing the aggregated values.
+
+    Raises:
+        ValueError: If a column specified in weights (or default weights) is missing from predictions.
+        ValueError: If weights is a list/array and its length does not match the number of columns in predictions.
+
+    Examples:
+        >>> df = pd.DataFrame({"A": [1, 2], "B": [3, 4]})
+        >>> agg_predict(df, weights={"A": 1.0, "B": -1.0})
+        0   -2.0
+        1   -2.0
+        dtype: float64
+        >>> agg_predict(df, weights=[0.5, 2.0])
+        0    6.5
+        1    9.0
+        dtype: float64
+    """
+    if weights is None:
+        # Default to summing all columns
+        weights = {col: 1.0 for col in predictions.columns}
+
+    if isinstance(weights, (list, np.ndarray)):
+        if len(weights) != len(predictions.columns):
+            raise ValueError(
+                f"Length of weights ({len(weights)}) does not match number of columns in predictions ({len(predictions.columns)})"
+            )
+        # Convert to dictionary using column order
+        weights = dict(zip(predictions.columns, weights))
+
+    combined = pd.Series(0.0, index=predictions.index)
+
+    missing_cols = [col for col in weights.keys() if col not in predictions.columns]
+    if missing_cols:
+        raise ValueError(f"Missing columns in predictions dataframe: {missing_cols}")
+
+    for col, weight in weights.items():
+        combined += predictions[col] * weight
+
+    return combined

spotforecast2-0.0.2/src/spotforecast2/processing/n2n_predict.py

@@ -0,0 +1,117 @@
+import pandas as pd
+from typing import List, Optional, Tuple, Dict, Any
+from spotforecast2.forecaster.recursive import ForecasterEquivalentDate
+from spotforecast2.data.fetch_data import fetch_data
+from spotforecast2.preprocessing.curate_data import basic_ts_checks
+from spotforecast2.preprocessing.curate_data import agg_and_resample_data
+from spotforecast2.preprocessing.outlier import mark_outliers
+
+from spotforecast2.preprocessing.split import split_rel_train_val_test
+from spotforecast2.forecaster.utils import predict_multivariate
+from spotforecast2.model_selection import TimeSeriesFold, backtesting_forecaster
+from spotforecast2.preprocessing.curate_data import get_start_end
+
+
+def n2n_predict(
+    columns: Optional[List[str]] = None,
+    forecast_horizon: int = 24,
+    contamination: float = 0.01,
+    window_size: int = 72,
+    verbose: bool = True,
+) -> Tuple[pd.DataFrame, Optional[Dict[str, Any]]]:
+    """
+    End-to-end prediction function replicating the workflow from 01_base_predictor combined with fetch_data.
+
+    Args:
+        columns: List of target columns to forecast. If None, uses a default set (defined internally or from data).
+                 Note: fetch_data now supports None to return all columns.
+        forecast_horizon: Number of steps to forecast.
+        contamination: Contamination factor for outlier detection.
+        window_size: Window size for weighting (not fully utilized in main flow but kept for consistency).
+        verbose: Whether to print progress logs.
+
+    Returns:
+        Tuple containing:
+            - predictions (pd.DataFrame): The multi-output predictions.
+            - metrics (Optional[Dict]): Dictionary containing backtesting metrics if performed.
+    """
+    if columns is not None:
+        TARGET = columns
+    else:
+        TARGET = None
+
+    if verbose:
+        print("--- Starting n2n_predict ---")
+        print("Fetching data...")
+
+    # Fetch data
+    data = fetch_data(columns=TARGET)
+
+    START, END, COV_START, COV_END = get_start_end(
+        data=data,
+        forecast_horizon=forecast_horizon,
+        verbose=verbose,
+    )
+
+    basic_ts_checks(data, verbose=verbose)
+
+    data = agg_and_resample_data(data, verbose=verbose)
+
+    # --- Outlier Handling ---
+    if verbose:
+        print("Handling outliers...")
+
+    # data_old = data.copy() # kept in notebook, maybe useful for debugging but not used logic-wise here
+    data, outliers = mark_outliers(
+        data, contamination=contamination, random_state=1234, verbose=verbose
+    )
+
+    # --- Missing Data (Imputation) ---
+    if verbose:
+        print("Imputing missing data...")
+
+    missing_indices = data.index[data.isnull().any(axis=1)]
+    if verbose:
+        n_missing = len(missing_indices)
+        pct_missing = (n_missing / len(data)) * 100
+        print(f"Number of rows with missing values: {n_missing}")
+        print(f"Percentage of rows with missing values: {pct_missing:.2f}%")
+
+    data = data.ffill()
+    data = data.bfill()
+
+    # --- Train, Val, Test Split ---
+    if verbose:
+        print("Splitting data...")
+    data_train, data_val, data_test = split_rel_train_val_test(
+        data, perc_train=0.8, perc_val=0.2, verbose=verbose
+    )
+
+    # --- Model Fit ---
+    if verbose:
+        print("Fitting models...")
+
+    end_validation = pd.concat([data_train, data_val]).index[-1]
+
+    baseline_forecasters = {}
+
+    for target in data.columns:
+        forecaster = ForecasterEquivalentDate(offset=pd.DateOffset(days=1), n_offsets=1)
+
+        forecaster.fit(y=data.loc[:end_validation, target])
+
+        baseline_forecasters[target] = forecaster
+
+    if verbose:
+        print("✓ Multi-output baseline system trained")
+
+    
+    # --- Predict ---
+    if verbose:
+        print("Generating predictions...")
+
+    predictions = predict_multivariate(
+        baseline_forecasters, steps_ahead=forecast_horizon
+    )
+
+    return predictions