eqc-models 0.9.9__py3-none-any.whl → 0.10.0__py3-none-any.whl

eqc_models-0.9.9.data/platlib/eqc_models/ml/classifierqboost.py

@@ -1,423 +0,0 @@
-# (C) Quantum Computing Inc., 2024.
-# Import libs
-import os
-import sys
-import time
-import datetime
-import json
-import warnings
-from functools import wraps
-import numpy as np
-from sklearn.tree import DecisionTreeClassifier
-from sklearn.naive_bayes import GaussianNB
-from sklearn.linear_model import LogisticRegression
-from sklearn.gaussian_process import GaussianProcessClassifier
-from sklearn.gaussian_process.kernels import RBF
-
-from eqc_models.ml.classifierbase import ClassifierBase
-
-def timer(func):
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        beg_time = time.time()
-        val = func(*args, **kwargs)
-        end_time = time.time()
-        tot_time = end_time - beg_time
-
-        print(
-            "Runtime of %s: %0.2f seconds!"
-            % (
-                func.__name__,
-                tot_time,
-            )
-        )
-
-        return val
-
-    return wrapper
-
-class WeakClassifierDct:
-    def __init__(
-        self,
-        fea_ind_list,
-        X_train,
-        y_train,
-        max_depth=10,
-        min_samples_split=100,
-    ):
-        assert X_train.shape[0] == len(y_train)
-
-        self.fea_ind_list = fea_ind_list
-        self.X_train = X_train
-        self.y_train = y_train
-        self.clf = DecisionTreeClassifier(
-            max_depth=max_depth,
-            min_samples_split=min_samples_split,
-            random_state=0,
-        )
-
-    def train(self):
-        X_tmp = self.X_train.transpose()[self.fea_ind_list].transpose()
-
-        self.clf.fit(X_tmp, self.y_train)
-
-    def predict(self, X):
-        X_tmp = X.transpose()[self.fea_ind_list].transpose()
-
-        return self.clf.predict(X_tmp)
-
-
-class WeakClassifierNB:
-    def __init__(self, fea_ind_list, X_train, y_train):
-        assert X_train.shape[0] == len(y_train)
-
-        self.fea_ind_list = fea_ind_list
-        self.X_train = X_train
-        self.y_train = y_train
-        self.clf = GaussianNB()
-
-    def train(self):
-        X_tmp = self.X_train.transpose()[self.fea_ind_list].transpose()
-
-        self.clf.fit(X_tmp, self.y_train)
-
-    def predict(self, X):
-        X_tmp = X.transpose()[self.fea_ind_list].transpose()
-
-        return self.clf.predict(X_tmp)
-
-
-class WeakClassifierLG:
-    def __init__(self, fea_ind_list, X_train, y_train):
-        assert X_train.shape[0] == len(y_train)
-
-        self.fea_ind_list = fea_ind_list
-        self.X_train = X_train
-        self.y_train = y_train
-        self.clf = LogisticRegression(random_state=0)
-
-    def train(self):
-        X_tmp = self.X_train.transpose()[self.fea_ind_list].transpose()
-
-        self.clf.fit(X_tmp, self.y_train)
-
-    def predict(self, X):
-        X_tmp = X.transpose()[self.fea_ind_list].transpose()
-
-        return self.clf.predict(X_tmp)
-
-
-class WeakClassifierGP:
-    def __init__(self, fea_ind_list, X_train, y_train):
-        assert X_train.shape[0] == len(y_train)
-
-        self.fea_ind_list = fea_ind_list
-        self.X_train = X_train
-        self.y_train = y_train
-        self.clf = GaussianProcessClassifier(
-            kernel=1.0 * RBF(1.0),
-            random_state=0,
-        )
-
-    def train(self):
-        X_tmp = self.X_train.transpose()[self.fea_ind_list].transpose()
-
-        self.clf.fit(X_tmp, self.y_train)
-
-    def predict(self, X):
-        X_tmp = X.transpose()[self.fea_ind_list].transpose()
-
-        return self.clf.predict(X_tmp)
-
-
-class QBoostClassifier(ClassifierBase):
-    """An implementation of QBoost classifier that uses QCi's Dirac-3.
-
-    Parameters
-    ----------
-    relaxation_schedule: Relaxation schedule used by Dirac-3;
-    default: 2.
-
-    num_samples: Number of samples used by Dirac-3; default: 1.
-
-    lambda_coef: A penalty multiplier; default: 0.
-
-    weak_cls_schedule: Weak classifier schedule. Is either 1, 2,
-    or 3; default: 2.
-
-    weak_cls_type: Type of weak classifier
-        - dct: Decison tree classifier
-        - nb: Naive Baysian classifier
-        - lg: Logistic regression
-        - gp: Gaussian process classifier
-
-    default: dct.
-
-    weak_max_depth: Max depth of the tree. Applied only when
-    weak_cls_type="dct". Default: 10.
-
-    weak_min_samples_split: The minimum number of samples required
-    to split an internal node. Applied only when
-    weak_cls_type="dct". Default: 100.
-
-    Examples
-    -----------
-
-    >>> from sklearn import datasets
-    >>> from sklearn.preprocessing import MinMaxScaler
-    >>> from sklearn.model_selection import train_test_split
-    >>> iris = datasets.load_iris()
-    >>> X = iris.data
-    >>> y = iris.target
-    >>> scaler = MinMaxScaler()
-    >>> X = scaler.fit_transform(X)
-    >>> for i in range(len(y)):
-    ...     if y[i] == 0:
-    ...         y[i] = -1
-    ...     elif y[i] == 2:
-    ...         y[i] = 1
-    >>> X_train, X_test, y_train, y_test = train_test_split(
-    ...     X,
-    ...     y,
-    ...     test_size=0.2,
-    ...     random_state=42,
-    ... )
-    >>> from eqc_models.ml.classifierqboost import QBoostClassifier
-    >>> obj = QBoostClassifier(
-    ...     relaxation_schedule=2,
-    ...     num_samples=1,
-    ...     lambda_coef=0.0,
-    ... )
-    >>> from contextlib import redirect_stdout
-    >>> import io
-    >>> f = io.StringIO()
-    >>> with redirect_stdout(f):
-    ...    obj = obj.fit(X_train, y_train)
-    ...    y_train_prd = obj.predict(X_train)
-    ...    y_test_prd = obj.predict(X_test)
-    """
-    def __init__(
-        self,
-        relaxation_schedule=2,
-        num_samples=1,
-        lambda_coef=0,
-        weak_cls_schedule=2,
-        weak_cls_type="lg",
-        weak_max_depth=10,
-        weak_min_samples_split=100,
-    ):
-        super(QBoostClassifier).__init__()
-
-        assert weak_cls_schedule in [1, 2, 3]
-        assert weak_cls_type in ["dct", "nb", "lg", "gp"]
-
-        self.relaxation_schedule = relaxation_schedule
-        self.num_samples = num_samples
-        self.lambda_coef = lambda_coef
-        self.weak_cls_schedule = weak_cls_schedule
-        self.weak_cls_type = weak_cls_type
-        self.weak_max_depth = weak_max_depth
-        self.weak_min_samples_split = weak_min_samples_split
-        self.h_list = []
-        self.classes_ = None
-
-    @timer
-    def _build_weak_classifiers(self, X, y):
-        n_records = X.shape[0]
-        n_dims = X.shape[1]
-
-        assert len(y) == n_records
-
-        self.h_list = []
-
-        for l in range(n_dims):
-            if self.weak_cls_type == "dct":
-                weak_classifier = WeakClassifierDct(
-                    [l],
-                    X,
-                    y,
-                    self.weak_max_depth,
-                    self.weak_min_samples_split,
-                )
-            elif self.weak_cls_type == "nb":
-                weak_classifier = WeakClassifierNB([l], X, y)
-            elif self.weak_cls_type == "lg":
-                weak_classifier = WeakClassifierLG([l], X, y)
-            elif self.weak_cls_type == "gp":
-                weak_classifier = WeakClassifierGP([l], X, y)
-
-            weak_classifier.train()
-
-            self.h_list.append(weak_classifier)
-
-        if self.weak_cls_schedule >= 2:
-            for i in range(n_dims):
-                for j in range(i + 1, n_dims):
-                    if self.weak_cls_type == "dct":
-                        weak_classifier = WeakClassifierDct(
-                            [i, j],
-                            X,
-                            y,
-                            self.weak_max_depth,
-                            self.weak_min_samples_split,
-                        )
-                    elif self.weak_cls_type == "nb":
-                        weak_classifier = WeakClassifierNB([i, j], X, y)
-                    elif self.weak_cls_type == "lg":
-                        weak_classifier = WeakClassifierLG([i, j], X, y)
-                    elif self.weak_cls_type == "gp":
-                        weak_classifier = WeakClassifierGP([i, j], X, y)
-
-                    weak_classifier.train()
-                    self.h_list.append(weak_classifier)
-
-        if self.weak_cls_schedule >= 3:
-            for i in range(n_dims):
-                for j in range(i + 1, n_dims):
-                    for k in range(j + 1, n_dims):
-                        if self.weak_cls_type == "dct":
-                            weak_classifier = WeakClassifierDct(
-                                [i, j, k],
-                                X,
-                                y,
-                                self.weak_max_depth,
-                                self.weak_min_samples_split,
-                            )
-                        elif self.weak_cls_type == "nb":
-                            weak_classifier = WeakClassifierNB(
-                                [i, j, k], X, y
-                            )
-                        elif self.weak_cls_type == "lg":
-                            weak_classifier = WeakClassifierLG(
-                                [i, j, k], X, y
-                            )
-                        elif self.weak_cls_type == "gp":
-                            weak_classifier = WeakClassifierGP(
-                                [i, j, k], X, y
-                            )
-                        weak_classifier.train()
-                        self.h_list.append(weak_classifier)
-
-        return
-
-    def fit(self, X, y):
-        """
-        Build a QBoost classifier from the training set (X, y).
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-        The training input samples.
-
-        y : array-like of shape (n_samples,)
-        The target values.
-
-        Returns
-        -------
-        Response of Dirac-3 in JSON format.
-        """
-
-        assert X.shape[0] == y.shape[0], "Inconsistent sizes!"
-
-        assert set(y) == {-1, 1}, "Target values should be in {-1, 1}"
-
-        self.classes_ = set(y)
-
-        J, C, sum_constraint = self.get_hamiltonian(X, y)
-
-        assert J.shape[0] == J.shape[1], "Inconsistent hamiltonian size!"
-        assert J.shape[0] == C.shape[0], "Inconsistent hamiltonian size!"
-
-        self.set_model(J, C, sum_constraint)
-
-        sol, response = self.solve()
-
-        assert len(sol) == C.shape[0], "Inconsistent solution size!"
-
-        self.params = self.convert_sol_to_params(sol)
-
-        assert len(self.params) == len(self.h_list), "Inconsistent size!"
-
-        return response
-
-    def predict_raw(self, X: np.array):
-        """
-        Predict raw output of the classifier for input X.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-
-        Returns
-        -------
-        y : ndarray of shape (n_samples,)
-        The predicted raw output of the classifier.
-        """
-
-        n_records = X.shape[0]
-        n_classifiers = len(self.h_list)
-
-        y = np.zeros(shape=(n_records), dtype=np.float32)
-        h_vals = np.array(
-            [self.h_list[i].predict(X) for i in range(n_classifiers)]
-        )
-
-        y = np.tensordot(self.params, h_vals, axes=(0, 0))
-
-        return y
-
-    def predict(self, X: np.array):
-        """
-        Predict classes for X.
-
-        Parameters
-        ----------
-        X : {array-like, sparse matrix} of shape (n_samples, n_features)
-
-        Returns
-        -------
-        y : ndarray of shape (n_samples,)
-        The predicted classes.
-        """
-
-        y = self.predict_raw(X)
-        y = np.sign(y)
-
-        return y
-
-    @timer
-    def get_hamiltonian(
-        self,
-        X: np.array,
-        y: np.array,
-    ):
-        self._build_weak_classifiers(X, y)
-        
-        print("Built %d weak classifiers!" % len(self.h_list))
-        
-        n_classifiers = len(self.h_list)
-        n_records = X.shape[0]
-
-        J = np.zeros(
-            shape=(n_classifiers, n_classifiers), dtype=np.float32
-        )
-        C = np.zeros(shape=(n_classifiers,), dtype=np.float32)
-
-        h_vals = np.array(
-            [self.h_list[i].predict(X) for i in range(n_classifiers)]
-        )
-
-        for i in range(n_classifiers):
-            for j in range(n_classifiers):
-                J[i][j] = sum(h_vals[i] * h_vals[j])
-                if i == j:
-                    J[i][i] += self.lambda_coef
-
-            C[i] = -2.0 * sum(y * h_vals[i])
-
-        C = C.reshape((n_classifiers, 1))
-
-        return J, C, 1.0
-
-    def convert_sol_to_params(self, sol):
-        return np.array(sol)

eqc_models-0.9.9.dist-info/RECORD

@@ -1,52 +0,0 @@
-eqc_models-0.9.9.data/platlib/compile_extensions.py,sha256=GNbNr9Pao2NwFUr29qEGrYSHvIlagnPcUqo3pgB5Trk,660
-eqc_models-0.9.9.data/platlib/eqc_models/__init__.py,sha256=njh-tvfgnAIVBGw9FXFv6XQOAgwrnBG23dU9dipa1Jg,585
-eqc_models-0.9.9.data/platlib/eqc_models/decoding.py,sha256=G3JgbIFzvZ3DIKW0kZ1JeTMIZmrc8hy9kzdbX2Xv5Og,637
-eqc_models-0.9.9.data/platlib/eqc_models/algorithms/__init__.py,sha256=lzQoMMSs2QTqp5suEYNvcQaSEN16d0LwIsZ1mRstumU,135
-eqc_models-0.9.9.data/platlib/eqc_models/algorithms/base.py,sha256=qfQQTwuVyewn7Qpg1_SVoD_7TsdA8vdwSKGqOeZSmNI,204
-eqc_models-0.9.9.data/platlib/eqc_models/algorithms/penaltymultiplier.py,sha256=gV48irx3q9yvMsCRqv2fa8DGQEOUkgVNGbZdNzI-3Tc,7057
-eqc_models-0.9.9.data/platlib/eqc_models/allocation/__init__.py,sha256=op_udrapTlWrakTuQId3M0ggo-Y1w4nGJLPcYKOQ-8I,239
-eqc_models-0.9.9.data/platlib/eqc_models/allocation/allocation.py,sha256=PAQn4M75Zegeoy0i6r3hycWs4TKeRglHk05TvwZOoLk,15506
-eqc_models-0.9.9.data/platlib/eqc_models/allocation/portbase.py,sha256=BTnYYduHydPbrE2yQr_Sgv3XJACH_GpIJstuMrfGqCU,3269
-eqc_models-0.9.9.data/platlib/eqc_models/allocation/portmomentum.py,sha256=oMod63rNDC-01dLZjmhUb24SN3_GVgfc6CItgQL_obI,3756
-eqc_models-0.9.9.data/platlib/eqc_models/assignment/__init__.py,sha256=CX_QYl8P1meajV8gcVs6hm07VhoLVe8uu436t7-1XQo,86
-eqc_models-0.9.9.data/platlib/eqc_models/assignment/qap.py,sha256=WMiQQmTORsgi2w7kbmMA1xo-93dESLECWqYTF-zkmTs,2963
-eqc_models-0.9.9.data/platlib/eqc_models/assignment/setpartition.py,sha256=-DJjPgsSMslEjfo3iDdXbKHQ9Lfc3cHlNc-9DtkJnW0,6202
-eqc_models-0.9.9.data/platlib/eqc_models/base/__init__.py,sha256=RwZguuucmsuOSVqfPLBqj-wzinBOzcgO-2ifFU-DCqg,2885
-eqc_models-0.9.9.data/platlib/eqc_models/base/base.py,sha256=kpnOb1dw0aaQyassIYKNlS6rIH1fNvZMI-NKPosAEMk,4856
-eqc_models-0.9.9.data/platlib/eqc_models/base/constraints.py,sha256=KMPyCdt_8GMWLnVEdpzw1T1WqXm2f7Lh629ClUH7XDY,8271
-eqc_models-0.9.9.data/platlib/eqc_models/base/operators.py,sha256=9nCeN6fRP-_YBfs-Gm57D-O_376qcOQiqGDuVlSlf00,7392
-eqc_models-0.9.9.data/platlib/eqc_models/base/polyeval.c,sha256=pgQX0_7JsrLKEhFrjBN8wJb0hTGRh3BUL90NygNHgFk,438291
-eqc_models-0.9.9.data/platlib/eqc_models/base/polyeval.cpython-310-darwin.so,sha256=QT8AOraG_it1u1LzIqeU4xuYtdmc7XyUcqIb4OqnutM,101136
-eqc_models-0.9.9.data/platlib/eqc_models/base/polyeval.pyx,sha256=76Bf99Jt1_rLh5byrZxAjavE2F4_yCysirViqOBFIXw,2547
-eqc_models-0.9.9.data/platlib/eqc_models/base/polynomial.py,sha256=dlWqL-PgSzV1UX-1S-MDwEL4sp3vs3h0vdRkv4JYfLo,12981
-eqc_models-0.9.9.data/platlib/eqc_models/base/quadratic.py,sha256=BHZKniUvSq30pZgzguVasdO39BCEYue_wi5AIklPGS8,8062
-eqc_models-0.9.9.data/platlib/eqc_models/graph/__init__.py,sha256=Cpo4jb630U57J0lS_iZddE_W3v9N4ijUb7xZRIYuguo,95
-eqc_models-0.9.9.data/platlib/eqc_models/graph/base.py,sha256=nYZCSCzshnuJKuc25M2YXcOqOhIa1-0R9rRbtIXDr84,1888
-eqc_models-0.9.9.data/platlib/eqc_models/graph/hypergraph.py,sha256=ABvutT0NOdIEpUF4TjUzboE4Y_J5iUZyj6-AzKr4R28,13268
-eqc_models-0.9.9.data/platlib/eqc_models/graph/maxcut.py,sha256=o8xVsAwTa9jcpmsIoCQ5z7HSstVdraT8TENomdT519o,4132
-eqc_models-0.9.9.data/platlib/eqc_models/graph/maxkcut.py,sha256=OFZwmC3wWpIJWVHOb9wkUeka0g0bOHrwf-mx0VZvt58,5807
-eqc_models-0.9.9.data/platlib/eqc_models/ml/__init__.py,sha256=CLfraacr0FrD5ynxlNB6cyNy0lpbavcQT45TvkDrNvY,369
-eqc_models-0.9.9.data/platlib/eqc_models/ml/classifierbase.py,sha256=1yXufiUGpaiBjI2evMiwfYn-Zr-SnWwCnvtREqprtJw,2184
-eqc_models-0.9.9.data/platlib/eqc_models/ml/classifierqboost.py,sha256=REfAVIWDTDbshObBGoH-9QdOHVnt-OCGjh-lRNwI2HU,12350
-eqc_models-0.9.9.data/platlib/eqc_models/ml/classifierqsvm.py,sha256=b6TdwlghR84UoQpfUThwMwNF_wmkABbCqOn6T1uY2dA,6636
-eqc_models-0.9.9.data/platlib/eqc_models/ml/clustering.py,sha256=yhh6jlgwZiQVn9h2pnYBlzVTCocK7rzsEurSQxCn5FQ,9486
-eqc_models-0.9.9.data/platlib/eqc_models/ml/clusteringbase.py,sha256=AvQbt6jeocBAGCuAmXHKyr3wLWqYUtBDq9PbsEOSlSc,2632
-eqc_models-0.9.9.data/platlib/eqc_models/ml/decomposition.py,sha256=Nsnq0GmINpbGOszndgCHXqKdECNpiNiampBrHPU_Gjg,8943
-eqc_models-0.9.9.data/platlib/eqc_models/ml/forecast.py,sha256=fFcBxQK9ZryfEuyvlr9HXicHoZRzLFybimYYttzhI9E,7403
-eqc_models-0.9.9.data/platlib/eqc_models/ml/forecastbase.py,sha256=s-6nUMvtYqG07r7MmmkFVj8_QqgeGkD-HVoEEDTE2bk,3654
-eqc_models-0.9.9.data/platlib/eqc_models/ml/regressor.py,sha256=LA1woXCnefG0wfoOxilX1kszgCUmfNcbQgs_WZ4Ai0o,5683
-eqc_models-0.9.9.data/platlib/eqc_models/ml/regressorbase.py,sha256=H5E8-8pUji1oH5JRdS37LJQoHuKt2JU8eXCZp-ZaEM4,2109
-eqc_models-0.9.9.data/platlib/eqc_models/ml/reservoir.py,sha256=cPRvpCaWLYTBkui35jCssHcOPQgSQZallrG6Ac9djVI,2827
-eqc_models-0.9.9.data/platlib/eqc_models/sequence/__init__.py,sha256=VXlYufO3GYFsM00oii9Cite2WsQEF8XTwRcjLPH_Zlg,92
-eqc_models-0.9.9.data/platlib/eqc_models/sequence/tsp.py,sha256=YM641FTyK5NkgRGxHrU1QmMkEU0gf77nEmIElTqa6Qw,7680
-eqc_models-0.9.9.data/platlib/eqc_models/solvers/__init__.py,sha256=hTjJI4F0FNDgQlK_oRHJxLIkg6of3I1-nEqU_3RL4Gk,542
-eqc_models-0.9.9.data/platlib/eqc_models/solvers/qciclient.py,sha256=Vnfqa1N6JSzigb-mbqXj6g0r-1wOkeYzmEmctId1VCo,26975
-eqc_models-0.9.9.data/platlib/eqc_models/utilities/__init__.py,sha256=SI2U7JKmPWSiq-F1WcSyfd7l9V6nbOZv_p8quMAZaT0,340
-eqc_models-0.9.9.data/platlib/eqc_models/utilities/fileio.py,sha256=alWPTfjGFx6Iio9HZAAWtYcLmZsBBifg6S6_YbFMQhk,1088
-eqc_models-0.9.9.data/platlib/eqc_models/utilities/polynomial.py,sha256=WoEBUAyiYBjwPvFWEjsynfmiBsbNqveKDZjXqiNQ6dk,4283
-eqc_models-0.9.9.data/platlib/eqc_models/utilities/qplib.py,sha256=Do-MjmCFdI5HyDOAjfoz4_5lugySLMBlMAWDLUWx2OA,15796
-eqc_models-0.9.9.dist-info/LICENSE.txt,sha256=8eh0oqsNNVR1Jk-13gkqRRSo2axtUU5kp2KzH4f9u3U,11354
-eqc_models-0.9.9.dist-info/METADATA,sha256=5wKP-BI_1v8byksYXgQhrgD8KeB6we9P4SC6ereXb_8,7071
-eqc_models-0.9.9.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-eqc_models-0.9.9.dist-info/top_level.txt,sha256=9ZfFeKNEvkRlKWoUnfcZ9TzmTdgdsuPEnTPy11Hqf4Q,30
-eqc_models-0.9.9.dist-info/RECORD,,