ocf-data-sampler 0.3.0__tar.gz → 0.3.1__tar.gz

{ocf_data_sampler-0.3.0 → ocf_data_sampler-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocf-data-sampler
-Version: 0.3.0
+Version: 0.3.1
 Author: James Fulton, Peter Dudfield
 Author-email: Open Climate Fix team <info@openclimatefix.org>
 License: MIT License

{ocf_data_sampler-0.3.0 → ocf_data_sampler-0.3.1}/ocf_data_sampler/config/model.py

@@ -90,11 +90,10 @@ class DropoutMixin(Base):
         "negative or zero.",
     )
 
-    dropout_fraction: float = Field(
+    dropout_fraction: float|list[float] = Field(
         default=0,
-        description="Chance of dropout being applied to each sample",
-        ge=0,
-        le=1,
+        description="Either a float(Chance of dropout being applied to each sample) or a list of "
+        "floats (probability that dropout of the corresponding timedelta is applied)",
     )
 
     @field_validator("dropout_timedeltas_minutes")
@@ -105,6 +104,36 @@ class DropoutMixin(Base):
                 raise ValueError("Dropout timedeltas must be negative")
         return v
 
+
+    @field_validator("dropout_fraction")
+    def dropout_fractions(cls, dropout_frac: float|list[float]) -> float|list[float]:
+        """Validate 'dropout_frac'."""
+        from math import isclose
+        if isinstance(dropout_frac, float):
+            if not (dropout_frac <= 1):
+                raise ValueError("Input should be less than or equal to 1")
+            elif not (dropout_frac >= 0):
+                raise ValueError("Input should be greater than or equal to 0")
+
+        elif isinstance(dropout_frac, list):
+            if not dropout_frac:
+                raise ValueError("List cannot be empty")
+
+            if not all(isinstance(i, float) for i in dropout_frac):
+                raise ValueError("All elements in the list must be floats")
+
+            if not all(0 <= i <= 1 for i in dropout_frac):
+                raise ValueError("Each float in the list must be between 0 and 1")
+
+            if not isclose(sum(dropout_frac), 1.0, rel_tol=1e-9):
+                raise ValueError("Sum of all floats in the list must be 1.0")
+
+
+        else:
+            raise TypeError("Must be either a float or a list of floats")
+        return dropout_frac
+
+
     @model_validator(mode="after")
     def dropout_instructions_consistent(self) -> "DropoutMixin":
         """Validator for dropout instructions."""

ocf_data_sampler-0.3.1/ocf_data_sampler/select/dropout.py

@@ -0,0 +1,61 @@
+"""Functions for simulating dropout in time series data.
+
+This is used for the following types of data: GSP, Satellite and Site
+This is not used for NWP
+"""
+
+import numpy as np
+import pandas as pd
+import xarray as xr
+
+
+def apply_sampled_dropout_time(
+    t0: pd.Timestamp,
+    dropout_timedeltas: list[pd.Timedelta],
+    dropout_frac: float|list[float],
+    da: xr.DataArray,
+) -> xr.DataArray:
+    """Randomly pick a dropout time from a list of timedeltas and apply dropout time to the data.
+
+    Args:
+        t0: The forecast init-time
+        dropout_timedeltas: List of timedeltas relative to t0 to pick from
+        dropout_frac: Either a probability that dropout will be applied.
+            This should be between 0 and 1 inclusive.
+            Or a list of probabilities for each of the corresponding timedeltas
+        da: Xarray DataArray with 'time_utc' coordinate
+    """
+    if  isinstance(dropout_frac, list):
+        # checking if len match
+        if len(dropout_frac) != len(dropout_timedeltas):
+            raise ValueError("Lengths of dropout_frac and dropout_timedeltas should match")
+
+
+
+
+        dropout_time = t0 + np.random.choice(dropout_timedeltas,p=dropout_frac)
+
+        return da.where(da.time_utc <= dropout_time)
+
+
+
+    # old logic
+    else:
+        # sample dropout time
+        if dropout_frac > 0 and len(dropout_timedeltas) == 0:
+            raise ValueError("To apply dropout, dropout_timedeltas must be provided")
+
+
+        if not (0 <= dropout_frac <= 1):
+            raise ValueError("dropout_frac must be between 0 and 1 inclusive")
+
+        if (len(dropout_timedeltas) == 0) or (np.random.uniform() >= dropout_frac):
+            dropout_time = None
+        else:
+            dropout_time = t0 + np.random.choice(dropout_timedeltas)
+
+        # apply dropout time
+        if dropout_time is None:
+            return da
+        # This replaces the times after the dropout with NaNs
+        return da.where(da.time_utc <= dropout_time)

{ocf_data_sampler-0.3.0 → ocf_data_sampler-0.3.1}/ocf_data_sampler.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ocf-data-sampler
-Version: 0.3.0
+Version: 0.3.1
 Author: James Fulton, Peter Dudfield
 Author-email: Open Climate Fix team <info@openclimatefix.org>
 License: MIT License

ocf_data_sampler-0.3.0/ocf_data_sampler/select/dropout.py

@@ -1,47 +0,0 @@
-"""Functions for simulating dropout in time series data.
-
-This is used for the following types of data: GSP, Satellite and Site
-This is not used for NWP
-"""
-
-import numpy as np
-import pandas as pd
-import xarray as xr
-
-
-def apply_sampled_dropout_time(
-    t0: pd.Timestamp,
-    dropout_timedeltas: list[pd.Timedelta],
-    dropout_frac: float,
-    da: xr.DataArray,
-) -> xr.DataArray:
-    """Randomly pick a dropout time from a list of timedeltas and apply dropout time to the data.
-
-    Args:
-        t0: The forecast init-time
-        dropout_timedeltas: List of timedeltas relative to t0 to pick from
-        dropout_frac: Probability that dropout will be applied.
-            This should be between 0 and 1 inclusive
-        da: Xarray DataArray with 'time_utc' coordinate
-    """
-    # sample dropout time
-    if dropout_frac > 0 and len(dropout_timedeltas) == 0:
-        raise ValueError("To apply dropout, dropout_timedeltas must be provided")
-
-    for t in dropout_timedeltas:
-        if t > pd.Timedelta("0min"):
-            raise ValueError("Dropout timedeltas must be negative")
-
-    if not (0 <= dropout_frac <= 1):
-        raise ValueError("dropout_frac must be between 0 and 1 inclusive")
-
-    if (len(dropout_timedeltas) == 0) or (np.random.uniform() >= dropout_frac):
-        dropout_time = None
-    else:
-        dropout_time = t0 + np.random.choice(dropout_timedeltas)
-
-    # apply dropout time
-    if dropout_time is None:
-        return da
-    # This replaces the times after the dropout with NaNs
-    return da.where(da.time_utc <= dropout_time)