Merge pull request #216 from ltsaprounis/adam_forecaster

Adam forecaster

.github/workflows/python_ci.yml

@@ -0,0 +1,16 @@
+name: Python CI
+
+on:
+    push:
+        branches: [Python]
+    pull_request:
+        branches: [Python]
+
+jobs:
+    linting:
+        runs-on: ubuntu-latest
+        steps:
+            - uses: actions/checkout@v4
+            - uses: chartboost/ruff-action@v1
+              with:
+                src: "./python"

python/pyproject.toml

@@ -10,14 +10,8 @@ readme = "README.md"
 requires-python = ">=3.8,<3.11"
 dependencies = ["pybind11[global]>=2.6.0", "numpy>=1.14"]
 
-# [tool.setuptools.packages]
-# find = {}
-
 [project.optional-dependencies]
-dev = ["flake8", "black", "pytest", "pydocstyle", "pre-commit", "ipykernel"]
-
-# [tool.pytest.ini_options]
-# addopts = "--ignore=../src/carma"
+dev = ["pytest", "ruff", "pre-commit", "ipykernel"]
 
 [tool.scikit-build]
 # wheel.expand-macos-universal-tags = true
@@ -28,3 +22,77 @@ ninja.make-fallback = true
 cmake.verbose = true
 ninja.minimum-version = "1.5"
 cmake.minimum-version = "3.25"
+
+[tool.ruff]
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "venv",
+    "tools/cookiecutter_templates",
+]
+
+# Same as Black.
+line-length = 88
+indent-width = 4
+
+# Assume Python 3.8
+target-version = "py38"
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+# Rules for ruff are found here: https://docs.astral.sh/ruff/rules/
+select = [
+    "E4",
+    "E7",
+    "E9",
+    "E501",
+    "F",
+    "I",    # isort rules
+    "N",    # PEP-8 naming rules 
+]
+ignore = [
+    # uppercase names are used for matrices
+    "N803", # allow uppercase argument names 
+    "N806", # allow uppercase variable names
+]
+
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.format]
+# Like Black, use double quotes for strings.
+quote-style = "double"
+
+# Like Black, indent with spaces, rather than tabs.
+indent-style = "space"
+
+# Like Black, respect magic trailing commas.
+skip-magic-trailing-comma = false
+
+# Like Black, automatically detect the appropriate line ending.
+line-ending = "auto"

python/smooth/adam_general/adam_profile.py

@@ -1,8 +1,8 @@
 import numpy as np
 
 
-def adamProfileCreator(
-    lagsModelAll, lagsModelMax, obsAll, lags=None, yIndex=None, yClasses=None
+def adam_profile_creator(
+    lags_model_all, lags_model_max, obs_all, lags=None, y_index=None, y_classes=None
 ):
     """
     Creates recent profile and the lookup table for adam.
@@ -14,50 +14,55 @@ def adamProfileCreator(
     yIndex (list): The indices needed to get the specific dates (optional).
     yClasses (list): The class used for the actual data (optional).
     Returns:
-    dict: A dictionary with 'recent' (profilesRecentTable) and 'lookup' (indexLookupTable) as keys.
+    dict: A dictionary with 'recent' (profilesRecentTable) and 'lookup'
+    (indexLookupTable) as keys.
     """
     # Initialize matrices
-    profilesRecentTable = np.zeros((len(lagsModelAll), lagsModelMax))
-    indexLookupTable = np.ones((len(lagsModelAll), obsAll + lagsModelMax))
-    profileIndices = (
-        np.arange(1, lagsModelMax * len(lagsModelAll) + 1)
-        .reshape(-1, len(lagsModelAll))
+    profiles_recent_table = np.zeros((len(lags_model_all), lags_model_max))
+    index_lookup_table = np.ones((len(lags_model_all), obs_all + lags_model_max))
+    profile_indices = (
+        np.arange(1, lags_model_max * len(lags_model_all) + 1)
+        .reshape(-1, len(lags_model_all))
         .T
     )
 
     # Update matrices based on lagsModelAll
-    for i, lag in enumerate(lagsModelAll):
+    for i, lag in enumerate(lags_model_all):
         # Create the matrix with profiles based on the provided lags.
         # For every row, fill the first 'lag' elements from 1 to lag
-        profilesRecentTable[i, : lag[0]] = np.arange(1, lag[0] + 1)
+        profiles_recent_table[i, : lag[0]] = np.arange(1, lag[0] + 1)
 
-        # For the i-th row in indexLookupTable, fill with a repeated sequence starting from lagsModelMax to the end of the row.
-        # The repeated sequence is the i-th row of profileIndices, repeated enough times to cover 'obsAll' observations.
+        # For the i-th row in indexLookupTable, fill with a repeated sequence starting
+        # from lagsModelMax to the end of the row.
+        # The repeated sequence is the i-th row of profileIndices, repeated enough times
+        # to cover 'obsAll' observations.
         # '- 1' at the end adjusts these values to Python's zero-based indexing.
-        indexLookupTable[i, lagsModelMax : (lagsModelMax + obsAll)] = (  # noqa
+        index_lookup_table[i, lags_model_max : (lags_model_max + obs_all)] = (
             np.tile(
-                profileIndices[i, : lagsModelAll[i][0]],
-                int(np.ceil(obsAll / lagsModelAll[i][0])),
-            )[0:obsAll]
+                profile_indices[i, : lags_model_all[i][0]],
+                int(np.ceil(obs_all / lags_model_all[i][0])),
+            )[0:obs_all]
             - 1
         )
 
-        # Extract unique values from from lagsModelMax to lagsModelMax + obsAll of indexLookupTable
+        # Extract unique values from from lagsModelMax to lagsModelMax + obsAll of
+        # indexLookupTable
         unique_values = np.unique(
-            indexLookupTable[i, lagsModelMax : lagsModelMax + obsAll]  # noqa
+            index_lookup_table[i, lags_model_max : lags_model_max + obs_all]  # noqa
         )
 
         # fix the head of teh data before the sample starts
-        # Repeat the unique values lagsModelMax times and then trim the sequence to only keep the first lagsModelMax elements
-        indexLookupTable[i, :lagsModelMax] = np.tile(unique_values, lagsModelMax)[
-            -lagsModelMax:
+        # Repeat the unique values lagsModelMax times and then trim the sequence to only
+        # keep the first lagsModelMax elements
+        index_lookup_table[i, :lags_model_max] = np.tile(unique_values, lags_model_max)[
+            -lags_model_max:
         ]
 
     # Convert to int!
-    indexLookupTable = indexLookupTable.astype(int)
+    index_lookup_table = index_lookup_table.astype(int)
 
     # Note: I skip andling of special cases (e.g., daylight saving time, leap years)
     return {
-        "recent": np.array(profilesRecentTable, dtype="float64"),
-        "lookup": np.array(indexLookupTable, dtype="int64"),
+        "recent": np.array(profiles_recent_table, dtype="float64"),
+        "lookup": np.array(index_lookup_table, dtype="int64"),
     }

python/smooth/adam_general/sma.py

@@ -1,13 +1,14 @@
 import numpy as np
-from smooth.adam_general._adam_general import adam_fitter
-from smooth.adam_general.adam_profile import adamProfileCreator
+
+from smooth.adam_general._adam_general import adam_fitter, adam_forecaster
+from smooth.adam_general.adam_profile import adam_profile_creator
 
 
 def sma(y, order=1, h=10, holdout=False):
     """SMA"""
     y = y.astype(np.float64)
 
-    ic = lambda e: np.sum(e**2)
+    # ic = lambda e: np.sum(e**2)
     obs_all = len(y) + h * (1 - holdout)
     obs_in_sample = len(y) - h * holdout
     y_in_sample = y
@@ -25,14 +26,14 @@ def sma(y, order=1, h=10, holdout=False):
     def creator_sma(order):
         # lags_model_all = np.ones(shape=(order, 1))
         # This needs to be a vector of values
-        lags_model_all = np.arange(1, order+1, dtype="int32").reshape(order, 1)
+        lags_model_all = np.arange(1, order + 1, dtype="int32").reshape(order, 1)
         lags_model_max = int(max(lags_model_all))
         obs_states = obs_in_sample + lags_model_max
 
-        profiles_recent_table, index_lookup_table = adamProfileCreator(
-            lagsModelAll=lags_model_all,
-            lagsModelMax=lags_model_max,
-            obsAll=obs_all
+        profiles_recent_table, index_lookup_table = adam_profile_creator(
+            lags_model_all=lags_model_all,
+            lags_model_max=lags_model_max,
+            obs_all=obs_all,
         ).values()
 
         # # This needs to be generated by a profileCreator() function
@@ -45,19 +46,40 @@ def creator_sma(order):
         #     np.arange(order), (obs_all + lags_model_max, 1)
         # ).T
 
-        matF = np.ones((order, order)) / order
-        matWt = np.ones((obs_in_sample, order))
+        mat_F = np.ones((order, order)) / order
+        mat_Wt = np.ones((obs_in_sample, order))
 
-        vecG = np.ones(order) / order
+        vec_G = np.ones(order) / order
         # matVt = np.zeros((order, obs_states))
-        matVt = np.empty((order, obs_states))
+        mat_Vt = np.empty((order, obs_states))
         # matVt.fill(np.nan)
 
         adam_fitted = adam_fitter(
-            matrixVt=matVt,
-            matrixWt=matWt,
-            matrixF=matF,
-            vectorG=vecG,
+            matrixVt=mat_Vt,
+            matrixWt=mat_Wt,
+            matrixF=mat_F,
+            vectorG=vec_G,
+            lags=lags_model_all,
+            indexLookupTable=index_lookup_table,
+            profilesRecent=profiles_recent_table,
+            E=E_type,
+            T=T_type,
+            S=S_type,
+            nNonSeasonal=components_num_ETS,
+            nSeasonal=components_num_ETS_seasonal,
+            nArima=order,
+            nXreg=xreg_number,
+            constant=constant_required,
+            vectorYt=y_in_sample,
+            vectorOt=ot,
+            backcast=True,
+        )
+
+        fitted_args = dict(
+            matrixVt=mat_Vt,
+            matrixWt=mat_Wt,
+            matrixF=mat_F,
+            vectorG=vec_G,
             lags=lags_model_all,
             indexLookupTable=index_lookup_table,
             profilesRecent=profiles_recent_table,
@@ -74,6 +96,31 @@ def creator_sma(order):
             backcast=True,
         )
 
-        return adam_fitted
+        return adam_fitted, fitted_args
+
+    sma_fitted, fitted_args = creator_sma(order=order)
+
+    # need to convert some inputs to the expected dtypes. This is a temporary fix.
+    fitted_args["lags"] = np.array(fitted_args["lags"], dtype="uint64")
+    fitted_args["indexLookupTable"] = np.array(
+        fitted_args["indexLookupTable"], dtype="uint64"
+    )
+
+    sma_forecast = adam_forecaster(
+        matrixWt=fitted_args["matrixWt"],
+        matrixF=fitted_args["matrixF"],
+        lags=fitted_args["lags"],
+        indexLookupTable=fitted_args["indexLookupTable"],
+        profilesRecent=sma_fitted["profile"],
+        E=fitted_args["E"],
+        T=fitted_args["T"],
+        S=fitted_args["S"],
+        nNonSeasonal=fitted_args["nNonSeasonal"],
+        nSeasonal=fitted_args["nSeasonal"],
+        nArima=fitted_args["nArima"],
+        nXreg=fitted_args["nXreg"],
+        constant=fitted_args["constant"],
+        horizon=h,
+    )
 
-    return creator_sma(order=order)
+    return sma_forecast

python/smooth/adam_general/test_script.py

@@ -1,7 +1,8 @@
 import numpy as np
+
 from smooth.adam_general.sma import sma
 
 if __name__ == "__main__":
     y = np.arange(0, 100)
     results = sma(y, order=5)
-    print(results["yFitted"])
+    print(results)