ocf-data-sampler 0.3.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

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/select/dropout.py

@@ -12,7 +12,7 @@ import xarray as xr
 def apply_sampled_dropout_time(
     t0: pd.Timestamp,
     dropout_timedeltas: list[pd.Timedelta],
-    dropout_frac: float,
+    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.
@@ -20,28 +20,42 @@ def apply_sampled_dropout_time(
     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
+        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
     """
-    # sample dropout time
-    if dropout_frac > 0 and len(dropout_timedeltas) == 0:
-        raise ValueError("To apply dropout, dropout_timedeltas must be provided")
+    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")
 
-    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
+
+        dropout_time = t0 + np.random.choice(dropout_timedeltas,p=dropout_frac)
+
+        return da.where(da.time_utc <= dropout_time)
+
+
+
+    # old logic
     else:
-        dropout_time = t0 + np.random.choice(dropout_timedeltas)
+        # 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)
+        # 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.dist-info → ocf_data_sampler-0.3.1.dist-info}/METADATA

@@ -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.dist-info → ocf_data_sampler-0.3.1.dist-info}/RECORD

@@ -2,7 +2,7 @@ ocf_data_sampler/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,
 ocf_data_sampler/utils.py,sha256=2NEl70ySdTpr0pbLRk4LGklvXe1Nv1hun9XKcDw7-44,610
 ocf_data_sampler/config/__init__.py,sha256=O29mbH0XG2gIY1g3BaveGCnpBO2SFqdu-qzJ7a6evl0,223
 ocf_data_sampler/config/load.py,sha256=LL-7wemI8o4KPkx35j-wQ3HjsMvDgqXr7G46IcASfnU,632
-ocf_data_sampler/config/model.py,sha256=xX2PPywEFGYDsx_j9DX1GlwMRq3ovJR-mhmysMt_mO0,11116
+ocf_data_sampler/config/model.py,sha256=Jss8UDJAaQIBDr9megX2pERoT0ocFmwLNFC8pCWN6VA,12386
 ocf_data_sampler/config/save.py,sha256=m8SPw5rXjkMm1rByjh3pK5StdBi4e8ysnn3jQopdRaI,1064
 ocf_data_sampler/data/uk_gsp_locations_20220314.csv,sha256=RSh7DRh55E3n8lVAaWXGTaXXHevZZtI58td4d4DhGos,10415772
 ocf_data_sampler/data/uk_gsp_locations_20250109.csv,sha256=XZISFatnbpO9j8LwaxNKFzQSjs6hcHFsV8a9uDDpy2E,9055334
@@ -32,7 +32,7 @@ ocf_data_sampler/numpy_sample/satellite.py,sha256=RaYzYIcB1AmDrKeiqSpn4QVfBH-QMe
 ocf_data_sampler/numpy_sample/site.py,sha256=zfYBjK3CJrIaKH1QdKXU7gwOxTqONt527y3nJ9TRnwc,1325
 ocf_data_sampler/numpy_sample/sun_position.py,sha256=5tt-zNm6aRuZMsxZPaAxyg7HeikswfZCeHWXTHuO2K0,1555
 ocf_data_sampler/select/__init__.py,sha256=mK7Wu_-j9IXGTYrOuDf5yDDuU5a306b0iGKTAooNg_s,210
-ocf_data_sampler/select/dropout.py,sha256=9gPyDF7bGmvSoMjMPu1j0gTZFHNFqsT3ToIo9mFNA00,1565
+ocf_data_sampler/select/dropout.py,sha256=BYpv8L771faPOyN7SdIJ5cwkpDve-ohClj95jjsHmjg,1973
 ocf_data_sampler/select/fill_time_periods.py,sha256=TlGxp1xiAqnhdWfLy0pv3FuZc00dtimjWdLzr4JoTGA,865
 ocf_data_sampler/select/find_contiguous_time_periods.py,sha256=etkr6LuB7zxkfzWJ6SgHiULdRuFzFlq5bOUNd257Qx4,11545
 ocf_data_sampler/select/geospatial.py,sha256=CDExkl36eZOKmdJPzUr_K0Wn3axHqv5nYo-EkSiINcc,5032
@@ -56,7 +56,7 @@ ocf_data_sampler/torch_datasets/utils/validation_utils.py,sha256=YqmT-lExWlI8_ul
 scripts/download_gsp_location_data.py,sha256=rRDXMoqX-RYY4jPdxhdlxJGhWdl6r245F5UARgKV6P4,3121
 scripts/refactor_site.py,sha256=skzvsPP0Cn9yTKndzkilyNcGz4DZ88ctvCJ0XrBdc2A,3135
 utils/compute_icon_mean_stddev.py,sha256=a1oWMRMnny39rV-dvu8rcx85sb4bXzPFrR1gkUr4Jpg,2296
-ocf_data_sampler-0.3.0.dist-info/METADATA,sha256=Kq7LhwcpxOpfu4S4NOq-JHFJYI7eeeuxPleNPx6UMLE,12224
-ocf_data_sampler-0.3.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ocf_data_sampler-0.3.0.dist-info/top_level.txt,sha256=LEFU4Uk-PEo72QGLAfnVZIUEm37Q8mKuMeg_Xk-p33g,31
-ocf_data_sampler-0.3.0.dist-info/RECORD,,
+ocf_data_sampler-0.3.1.dist-info/METADATA,sha256=pQpPqmpTlUiZnPY1Q_xZr1Z-GrKSATG_P77YYHpWm6Y,12224
+ocf_data_sampler-0.3.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ocf_data_sampler-0.3.1.dist-info/top_level.txt,sha256=LEFU4Uk-PEo72QGLAfnVZIUEm37Q8mKuMeg_Xk-p33g,31
+ocf_data_sampler-0.3.1.dist-info/RECORD,,