make release-tag: Merge branch 'master' into stable

sintel-dev · Oct 24, 2023 · 6ffb4a8 · 6ffb4a8
2 parents 0e72c40 + bc6d5c9
commit 6ffb4a8
Show file tree

Hide file tree

Showing 15 changed files with 159 additions and 128 deletions.
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -14,7 +14,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: [3.8]
+        python-version: ['3.10']
         os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
     - uses: actions/checkout@v1
@@ -32,8 +32,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.6', '3.7', '3.8', '3.9']
-        os: [ubuntu-20.04]
+        python-version: ['3.8', '3.9', '3.10', '3.11']
+        os: [ubuntu-latest]
     steps:
     - uses: actions/checkout@v1
     - name: Set up Python ${{ matrix.python-version }}
@@ -50,8 +50,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.6', '3.7', '3.8', '3.9']
-        os: [ubuntu-20.04, macos-latest]
+        python-version: ['3.8', '3.9', '3.10', '3.11']
+        os: [ubuntu-latest, macos-latest]
     steps:
     - uses: actions/checkout@v1
     - name: Set up Python ${{ matrix.python-version }}
@@ -68,8 +68,8 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        python-version: ['3.6', '3.7', '3.8', '3.9']
-        os: [ubuntu-20.04, macos-latest, windows-latest]
+        python-version: ['3.8', '3.9', '3.10', '3.11']
+        os: [ubuntu-latest, macos-latest, windows-latest]
     steps:
     - uses: actions/checkout@v1
     - name: Set up Python ${{ matrix.python-version }}

diff --git a/HISTORY.md b/HISTORY.md
@@ -1,9 +1,18 @@
 # History
 
+## 0.2.0 – 2023-10-24
+
+* Upgrade python tests & remove python 3.7 [Issue #11](https://github.com/sintel-dev/ml-stars/issues/11) - by @sarahmish
+* Add deprecation warning for old ARIMA primitive [Issue #10](https://github.com/sintel-dev/ml-stars/issues/10) - by @sarahmish
+* Remove python 3.6 [Issue #9](https://github.com/sintel-dev/ml-stars/issues/9) - by @sarahmish
+* Add support for python 3.10 & 3.11 [Issue #8](https://github.com/sintel-dev/ml-stars/issues/8) - by @sarahmish
+
+
 ## 0.1.3 – 2023-09-25
 
 * Update ``keras`` adapter [Issue #7](https://github.com/sintel-dev/ml-stars/issues/7) - by @sarahmish
 
+
 ## 0.1.2 – 2023-08-04
 
 * Add python 3.9 [Issue #6](https://github.com/sintel-dev/ml-stars/issues/6) - by @sarahmish

diff --git a/README.md b/README.md
@@ -31,7 +31,7 @@ combine third party tools or implement new functionalities from scratch.
 
 ## Requirements
 
-**ml-stars** has been developed and tested on [Python 3.6, 3.7, 3.8, and 3.9](https://www.python.org/downloads/)
+**ml-stars** has been developed and tested on [Python 3.8, 3.9, 3.10, and 3.11](https://www.python.org/downloads/)
 
 Also, although it is not strictly required, the usage of a
 [virtualenv](https://virtualenv.pypa.io/en/latest/) is highly recommended in order to avoid

diff --git a/docs/getting_started/install.rst b/docs/getting_started/install.rst
@@ -10,7 +10,7 @@ Requirements
 
 Python
 ~~~~~~
-**ml-stars** has been tested on **GNU/Linux**, and **macOS** systems running `Python 3.6, 3.7, or 3.8`_ installed.
+**ml-stars** has been tested on **GNU/Linux**, and **macOS** systems running `Python 3.8, 3.9, 3.10, or 3.11`_ installed.
 
 Also, although it is not strictly required, the usage of a `virtualenv`_ is highly recommended in
 order to avoid having conflicts with other software installed in the system where you are trying to run **ml-stars**.
@@ -45,7 +45,7 @@ from its sources, in the editable mode, and also including some additional depen
 order to be able to run the tests and build the documentation. Instructions about this process
 can be found in the :ref:`contributing` guide.
 
-.. _Python 3.6, 3.7, or 3.8: https://docs.python-guide.org/starting/installation/
+.. _Python 3.8, 3.9, 3.10, or 3.11: https://docs.python-guide.org/starting/installation/
 .. _virtualenv: https://virtualenv.pypa.io/en/latest/
 .. _pip: https://pip.pypa.io
 .. _PyPI: https://pypi.org/

diff --git a/mlstars/__init__.py b/mlstars/__init__.py
@@ -2,7 +2,7 @@
 
 __author__ = 'MIT Data To AI Lab'
 __email__ = '[email protected]'
-__version__ = '0.1.3'
+__version__ = '0.2.0.dev0'
 
 import os
 

diff --git a/mlstars/adapters/statsmodels.py b/mlstars/adapters/statsmodels.py
@@ -1,11 +1,19 @@
+import warnings
+
 import numpy as np
-from statsmodels.tsa import arima_model
+from statsmodels.tsa.arima import model
+
+_ARIMA_MODEL_DEPRECATION_WARNING = (
+    "statsmodels.tsa.arima_model.Arima is deprecated "
+    "and will be removed in a future version. Please use "
+    "statsmodels.tsa.arima.model.ARIMA instead."
+)
 
 
 class ARIMA(object):
-    """A Wrapper for the statsmodels.tsa.arima_model.ARIMA class."""
+    """A Wrapper for the statsmodels.tsa.arima.model.ARIMA class."""
 
-    def __init__(self, p, d, q, steps):
+    def __init__(self, p, d, q, trend, steps):
         """Initialize the ARIMA object.
 
         Args:
@@ -15,12 +23,19 @@ def __init__(self, p, d, q, steps):
                 Integer denoting the degree of differencing.
             q (int):
                 Integer denoting the order of the moving-average model.
+            trend (str):
+                Parameter controlling the deterministic trend. Can be specified
+                as a string where 'c' indicates a constant term, 't' indicates
+                a linear trend in time, and 'ct' includes both.
             steps (int):
                 Integer denoting the number of time steps to predict ahead.
         """
+        warnings.warn(_ARIMA_MODEL_DEPRECATION_WARNING, DeprecationWarning)
+
         self.p = p
         self.d = d
         self.q = q
+        self.trend = trend
         self.steps = steps
 
     def predict(self, X):
@@ -45,8 +60,8 @@ def predict(self, X):
 
         num_sequences = len(X)
         for sequence in range(num_sequences):
-            arima = arima_model.ARIMA(X[sequence], order=(self.p, self.d, self.q))
-            arima_fit = arima.fit(disp=0)
+            arima = model.ARIMA(X[sequence], order=(self.p, self.d, self.q), trend=self.trend)
+            arima_fit = arima.fit()
             arima_results.append(arima_fit.forecast(self.steps)[0])
 
         arima_results = np.asarray(arima_results)

diff --git a/mlstars/custom/timeseries_preprocessing.py b/mlstars/custom/timeseries_preprocessing.py
@@ -111,53 +111,6 @@ def rolling_window_sequences(X, index, window_size, target_size, step_size, targ
     return np.asarray(out_X), np.asarray(out_y), np.asarray(X_index), np.asarray(y_index)
 
 
-_TIME_SEGMENTS_AVERAGE_DEPRECATION_WARNING = (
-    "mlstars.custom.timeseries_preprocessing.time_segments_average "
-    "is deprecated and will be removed in a future version. Please use "
-    "mlstars.custom.timeseries_preprocessing.time_segments_aggregate instead."
-)
-
-
-def time_segments_average(X, interval, time_column):
-    """Compute average of values over given time span.
-
-    Args:
-        X (ndarray or pandas.DataFrame):
-            N-dimensional sequence of values.
-        interval (int):
-            Integer denoting time span to compute average of.
-        time_column (int):
-            Column of X that contains time values.
-
-    Returns:
-        ndarray, ndarray:
-            * Sequence of averaged values.
-            * Sequence of index values (first index of each averaged segment).
-    """
-    warnings.warn(_TIME_SEGMENTS_AVERAGE_DEPRECATION_WARNING, DeprecationWarning)
-
-    if isinstance(X, np.ndarray):
-        X = pd.DataFrame(X)
-
-    X = X.sort_values(time_column).set_index(time_column)
-
-    start_ts = X.index.values[0]
-    max_ts = X.index.values[-1]
-
-    values = list()
-    index = list()
-
-    while start_ts <= max_ts:
-        end_ts = start_ts + interval
-        subset = X.loc[start_ts:end_ts - 1]
-        means = subset.mean(skipna=True).values
-        values.append(means)
-        index.append(start_ts)
-        start_ts = end_ts
-
-    return np.asarray(values), np.asarray(index)
-
-
 def time_segments_aggregate(X, interval, time_column, method=['mean']):
     """Aggregate values over given time span.
 
@@ -269,4 +222,8 @@ def cutoff_window_sequences(X, timeseries, window_size, cutoff_time=None, time_i
 
         output.append(selected.values)
 
-    return np.array(output)
+    output = np.array(output, dtype=object)
+    if output.ndim >= 2:
+        output = output.astype(float)
+
+    return output
diff --git a/mlstars/primitives/statsmodels.tsa.arima.model.ARIMA.json b/mlstars/primitives/statsmodels.tsa.arima.model.ARIMA.json
@@ -0,0 +1,67 @@
+{
+    "name": "statsmodels.tsa.arima.model.ARIMA",
+    "contributors": [
+        "Alexander Geiger <[email protected]>",
+        "Sarah Alnegheimish <[email protected]>"
+    ],
+    "description": "ARIMA Model",
+    "classifiers": {
+        "type": "estimator",
+        "subtype": "regressor"
+    },
+    "modalities": [],
+    "primitive": "mlstars.adapters.statsmodels.ARIMA",
+    "produce": {
+        "method": "predict",
+        "args": [
+            {
+                "name": "X",
+                "type": "ndarray"
+            }
+        ],
+        "output": [
+            {
+                "name": "y",
+                "type": "ndarray"
+            }
+        ]
+    },
+    "hyperparameters": {
+        "fixed": {
+            "trend": {
+                "type": "str",
+                "default": "t"
+            },
+            "steps": {
+                "type": "int",
+                "default": 10
+            }
+        },
+        "tunable": {
+            "p": {
+                "type": "int",
+                "default": 1,
+                "range": [
+                    0,
+                    40
+                ]
+            },
+            "d": {
+                "type": "int",
+                "default": 0,
+                "range": [
+                    0,
+                    3
+                ]
+            },
+            "q": {
+                "type": "int",
+                "default": 0,
+                "range": [
+                    0,
+                    12
+                ]
+            }
+        }
+    }
+}
diff --git a/mlstars/primitives/statsmodels.tsa.arima_model.Arima.json b/mlstars/primitives/statsmodels.tsa.arima_model.Arima.json
@@ -3,7 +3,7 @@
     "contributors": [
         "Alexander Geiger <[email protected]>"
     ],
-    "description": "ARIMA Model",
+    "description": "ARIMA Model; mstatsmodels.tsa.arima_model.Arima is deprecated and will be removed in a future version. Please use statsmodels.tsa.arima.model.ARIMA instead.",
     "classifiers": {
         "type": "estimator",
         "subtype": "regressor"
@@ -27,6 +27,10 @@
     },
     "hyperparameters": {
         "fixed": {
+            "trend": {
+                "type": "str",
+                "default": "t"
+            },
             "steps": {
                 "type": "int",
                 "default": 10

diff --git a/setup.cfg b/setup.cfg
@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.3
+current_version = 0.2.0.dev0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?

diff --git a/setup.py b/setup.py
@@ -10,15 +10,15 @@
     history = history_file.read()
 
 install_requires = [
-    'Keras>=2.4,<2.13',
-    'mlblocks>=0.6',
-    'numpy<1.21.0,>=1.16.0',
-    'pandas>=1,<2',
-    'scikit-learn>=0.21,<1.2',
-    'scipy>=1.1.0,<2',
-    'statsmodels>=0.9.0,<0.13',
-    'tensorflow>=2,<2.13',
-    'xgboost>=0.72.1,<1',
+    'Keras>=2.4,<2.15',
+    'mlblocks>=0.6.1',
+    'numpy>=1.17.4,<2',
+    'pandas>=1,<3',
+    'scikit-learn>=0.22,<1.2',
+    'scipy>=1.4.1,<2',
+    'statsmodels>=0.12.0,<0.15',
+    'tensorflow>=2.2,<2.15',
+    'xgboost>=0.72.1,<2',
 
     # fix google/protobuf/descriptor
     'protobuf<4',
@@ -46,10 +46,8 @@
     'nbsphinx>=0.5.0,<0.7',
     'Sphinx>=3,<3.3',
     'pydata-sphinx-theme<0.5',
-    'autodocsumm>=0.1.10,<1',
     'markupsafe<2.1.0',
-    'ipython>=6.5,<7.5',
-    'mistune>=0.7,<2',
+    'ipython>=6.5,<9',
     'Jinja2>=2,<3',
 
     # style check
@@ -68,6 +66,7 @@
     # Advanced testing
     'coverage>=4.5.1',
     'tox>=2.9.1',
+    'invoke',
 ]
 
 setup(
@@ -79,10 +78,10 @@
         'License :: OSI Approved :: MIT License',
         'Natural Language :: English',
         'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9',
+        'Programming Language :: Python :: 3.10',
+        'Programming Language :: Python :: 3.11',
     ],
     description='Primitives and Pipelines for Time Series Data.',
     entry_points={
@@ -104,11 +103,11 @@
     keywords='mlstars',
     name='ml-stars',
     packages=find_packages(include=['mlstars', 'mlstars.*']),
-    python_requires='>=3.6,<3.10',
+    python_requires='>=3.8,<3.12',
     setup_requires=setup_requires,
     test_suite='tests',
     tests_require=tests_require,
     url='https://github.com/sintel-dev/ml-stars',
-    version='0.1.3',
+    version='0.2.0.dev0',
     zip_safe=False,
 )
diff --git a/tests/adapters/test_pandas.py b/tests/adapters/test_pandas.py
@@ -3,7 +3,7 @@
 
 import numpy as np
 import pandas as pd
-from pandas.util.testing import assert_frame_equal
+from pandas.testing import assert_frame_equal
 
 from mlstars.adapters.pandas import resample