Python sklearn.utils.check_array() Examples

def fit(self, X, y=None):
        """Compute the mean, whitening and dewhitening matrices.

        Parameters
        ----------
        X : array-like with shape [n_samples, n_features]
            The data used to compute the mean, whitening and dewhitening
            matrices.
        """
        X = check_array(X, accept_sparse=None, copy=self.copy,
                        ensure_2d=True)
        X = as_float_array(X, copy=self.copy)
        self.mean_ = X.mean(axis=0)
        X_ = X - self.mean_
        cov = np.dot(X_.T, X_) / (X_.shape[0]-1)
        U, S, _ = linalg.svd(cov)
        s = np.sqrt(S.clip(self.regularization))
        s_inv = np.diag(1./s)
        s = np.diag(s)
        self.whiten_ = np.dot(np.dot(U, s_inv), U.T)
        self.dewhiten_ = np.dot(np.dot(U, s), U.T)
        return self 

def transform(self, X, y=None):

        # scikit-learn checks
        X = check_array(X)

        if X.shape[1] != len(self.maximums_):
            raise ValueError("X has different shape than during fitting. "
                             "Expected %d, got %d." % (len(self.maximums_), X.shape[1]))

        return np.vstack((
            np.array([
                np.cos(2 * np.pi * x / (maximum + 1))
                for x, maximum in zip(X.T, self.maximums_)
            ]),
            np.array([
                np.sin(2 * np.pi * x / (maximum + 1))
                for x, maximum in zip(X.T, self.maximums_)
            ])
        )).T 

def fit_transform(self, X, y=None, sample_weight=None):
        X = check_array(X, accept_sparse=['csc'], ensure_2d=False)

        if sp.issparse(X):
            # Pre-sort indices to avoid that each individual tree of the
            # ensemble sorts the indices.
            X.sort_indices()

        X_, y_ = generate_discriminative_dataset(X)

        super(RandomForestEmbedding, self).fit(X_, y_,
                                               sample_weight=sample_weight)

        self.one_hot_encoder_ = OneHotEncoder(sparse=True)
        if self.sparse_output:
            return self.one_hot_encoder_.fit_transform(self.apply(X))
        return self.apply(X) 

def fit(self, X, y=None):
        """Fit detector. y is ignored in unsupervised methods.

        Parameters
        ----------
        X : numpy array of shape (n_samples, n_features)
            The input samples.

        y : Ignored
            Not used, present for API consistency by convention.

        Returns
        -------
        self : object
            Fitted estimator.
        """
        X = check_array(X)
        self._set_n_classes(y)
        self.decision_scores_ = self.decision_function(X)
        self._process_decision_scores()
        return self 

def decision_function(self, X):
        """Predict raw anomaly score of X using the fitted detector.

        The anomaly score of an input sample is computed based on different
        detector algorithms. For consistency, outliers are assigned with
        larger anomaly scores.

        Parameters
        ----------
        X : numpy array of shape (n_samples, n_features)
            The training input samples. Sparse matrices are accepted only
            if they are supported by the base estimator.

        Returns
        -------
        anomaly_scores : numpy array of shape (n_samples,)
            The anomaly score of the input samples.
        """
        check_is_fitted(self, ['discriminator'])
        X = check_array(X)
        pred_scores = self.discriminator.predict(X)
        return pred_scores 

def test_check_array_accept_sparse_type_exception():
    X = [[1, 2], [3, 4]]
    X_csr = sp.csr_matrix(X)
    invalid_type = SVR()

    msg = ("A sparse matrix was passed, but dense data is required. "
           "Use X.toarray() to convert to a dense numpy array.")
    assert_raise_message(TypeError, msg,
                         check_array, X_csr, accept_sparse=False)

    msg = ("Parameter 'accept_sparse' should be a string, "
           "boolean or list of strings. You provided 'accept_sparse={}'.")
    assert_raise_message(ValueError, msg.format(invalid_type),
                         check_array, X_csr, accept_sparse=invalid_type)

    msg = ("When providing 'accept_sparse' as a tuple or list, "
           "it must contain at least one string value.")
    assert_raise_message(ValueError, msg.format([]),
                         check_array, X_csr, accept_sparse=[])
    assert_raise_message(ValueError, msg.format(()),
                         check_array, X_csr, accept_sparse=())

    assert_raise_message(TypeError, "SVR",
                         check_array, X_csr, accept_sparse=[invalid_type]) 

def predict(self, X):

        check_is_fitted(self, "cluster_centers_")

        # Check that the array is good and attempt to convert it to
        # Numpy array if possible
        X = check_array(X)

        # Apply distance metric wrt. cluster centers (medoids)
        D = self.distance_func(X, Y=self.cluster_centers_)

        # Assign data points to clusters based on
        # which cluster assignment yields
        # the smallest distance
        labels = np.argmin(D, axis=1)

        return labels 

def load_data(dtype=np.float32, order='F'):
    """Load the data, then cache and memmap the train/test split"""
    ######################################################################
    # Load dataset
    safe_print("Loading dataset...")
    data = fetch_mldata('MNIST original')
    X = check_array(data['data'], dtype=dtype, order=order)
    y = data["target"]

    # Normalize features
    X = X / 255

    # Create train-test split (as [Joachims, 2006])
    safe_print("Creating train-test split...")
    n_train = 60000
    X_train = X[:n_train]
    y_train = y[:n_train]
    X_test = X[n_train:]
    y_test = y[n_train:]

    return X_train, X_test, y_train, y_test 

def fit(self, X, y=None):
        """Fit detector. y is ignored in unsupervised methods.

        Parameters
        ----------
        X : numpy array of shape (n_samples, n_features)
            The input samples.

        y : Ignored
            Not used, present for API consistency by convention.

        Returns
        -------
        self : object
            Fitted estimator.
        """

        # validate inputs X and y (optional)
        X = check_array(X)
        self._set_n_classes(y)
        self.decision_scores_ = self.decision_function(X)
        self._process_decision_scores()

        return self 

def transform(self, X):
        """Transforms X to cluster-distance space.

        Parameters
        ----------
        X : {array-like, sparse matrix}, shape (n_query, n_features), \
                or (n_query, n_indexed) if metric == 'precomputed'
            Data to transform.

        Returns
        -------
        X_new : {array-like, sparse matrix}, shape=(n_query, n_clusters)
            X transformed in the new space of distances to cluster centers.
        """
        X = check_array(X, accept_sparse=["csr", "csc"])

        if self.metric == "precomputed":
            check_is_fitted(self, "medoid_indices_")
            return X[:, self.medoid_indices_]
        else:
            check_is_fitted(self, "cluster_centers_")

            Y = self.cluster_centers_
            return pairwise_distances(X, Y=Y, metric=self.metric) 

def transform(self, X):
        """Apply the approximate feature map to X.

        Parameters
        ----------
        X : {array-like}, shape (n_samples, n_features)
            New data, where n_samples in the number of samples
            and n_features is the number of features.

        Returns
        -------
        X_new : array-like, shape (n_samples, n_components)
        """
        X = check_array(X, dtype=np.float64)
        X_padded = self._pad_with_zeros(X)
        HGPHBX = self._apply_approximate_gaussian_matrix(
            self._B, self._G, self._P, X_padded
        )
        VX = self._scale_transformed_data(self._S, HGPHBX)
        return self._phi(VX) 

def decision_function(self, X):
        """Predict raw anomaly score of X using the fitted detector.

        The anomaly score of an input sample is computed based on different
        detector algorithms. For consistency, outliers are assigned with
        larger anomaly scores.

        Parameters
        ----------
        X : numpy array of shape (n_samples, n_features)
            The training input samples. Sparse matrices are accepted only
            if they are supported by the base estimator.

        Returns
        -------
        anomaly_scores : numpy array of shape (n_samples,)
            The anomaly score of the input samples.
        """
        check_is_fitted(self, ['discriminator'])
        X = check_array(X)
        pred_scores = self.discriminator.predict(X)
        return pred_scores 

def test_check_input_false():
    X, y, _, _ = build_dataset(n_samples=20, n_features=10)
    X = check_array(X, order='F', dtype='float64')
    y = check_array(X, order='F', dtype='float64')
    clf = ElasticNet(selection='cyclic', tol=1e-8)
    # Check that no error is raised if data is provided in the right format
    clf.fit(X, y, check_input=False)
    # With check_input=False, an exhaustive check is not made on y but its
    # dtype is still cast in _preprocess_data to X's dtype. So the test should
    # pass anyway
    X = check_array(X, order='F', dtype='float32')
    clf.fit(X, y, check_input=False)
    # With no input checking, providing X in C order should result in false
    # computation
    X = check_array(X, order='C', dtype='float64')
    assert_raises(ValueError, clf.fit, X, y, check_input=False) 

def andb(arrs):
    """
    Sums arrays in `arrs`

    Parameters
    ----------
    arrs : :obj:`list`
        List of boolean or integer arrays to be summed

    Returns
    -------
    result : :obj:`numpy.ndarray`
        Integer array of summed `arrs`
    """

    # coerce to integer and ensure all arrays are the same shape
    arrs = [check_array(arr, dtype=int, ensure_2d=False, allow_nd=True) for arr in arrs]
    if not np.all([arr1.shape == arr2.shape for arr1 in arrs for arr2 in arrs]):
        raise ValueError('All input arrays must have same shape.')

    # sum across arrays
    result = np.sum(arrs, axis=0)

    return result 

def fit(self, X, y=None):
        """Fit data X by computing the binning thresholds.

        Parameters
        ----------
        X: array-like
            The data to bin

        Returns
        -------
        self : object
        """
        X = check_array(X)
        self.numerical_thresholds_ = _find_binning_thresholds(
            X, self.max_bins, subsample=self.subsample,
            random_state=self.random_state)

        self.n_bins_per_feature_ = np.array(
            [thresholds.shape[0] + 1
             for thresholds in self.numerical_thresholds_],
            dtype=np.uint32
        )

        return self 

def fit(self, X, y=None, **fit_params):
        """Choose equally spaces cut points."""

        # scikit-learn checks
        X = check_array(X)

        self.cut_points_ = [0] * X.shape[1]

        for i, x in enumerate(X.T):
            x_min = np.min(x)
            x_max = np.max(x)

            if x_min == x_max:
                self.cut_points_[i] = np.array([x_min])
            else:
                step = (x_max - x_min) / self.n_bins
                self.cut_points_[i] = np.arange(start=x_min+step, stop=x_max, step=step).tolist()

        return self 

def test_ordering():
    # Check that ordering is enforced correctly by validation utilities.
    # We need to check each validation utility, because a 'copy' without
    # 'order=K' will kill the ordering.
    X = np.ones((10, 5))
    for A in X, X.T:
        for copy in (True, False):
            B = check_array(A, order='C', copy=copy)
            assert B.flags['C_CONTIGUOUS']
            B = check_array(A, order='F', copy=copy)
            assert B.flags['F_CONTIGUOUS']
            if copy:
                assert A is not B

    X = sp.csr_matrix(X)
    X.data = X.data[::-1]
    assert not X.data.flags['C_CONTIGUOUS'] 

def fit(self, X, y=None, **fit_params):
        """Choose equally spaces cut points."""

        # scikit-learn checks
        X = check_array(X)

        step = 100 / self.n_bins

        self.cut_points_ = np.stack([
            np.percentile(X, q, axis=0)
            for q in np.arange(start=step, stop=100, step=step)
        ], axis=-1).tolist()

        return self 

def test_check_array_accept_large_sparse_no_exception(X_64bit):
    # When large sparse are allowed
    check_array(X_64bit, accept_large_sparse=True, accept_sparse=True) 

def test_check_array_accept_large_sparse_raise_exception(X_64bit):
    # When large sparse are not allowed
    msg = ("Only sparse matrices with 32-bit integer indices "
           "are accepted. Got int64 indices.")
    assert_raise_message(ValueError, msg,
                         check_array, X_64bit,
                         accept_sparse=True,
                         accept_large_sparse=False) 

def test_check_array_complex_data_error():
    X = np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]])
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X)

    # list of lists
    X = [[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X)

    # tuple of tuples
    X = ((1 + 2j, 3 + 4j, 5 + 7j), (2 + 3j, 4 + 5j, 6 + 7j))
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X)

    # list of np arrays
    X = [np.array([1 + 2j, 3 + 4j, 5 + 7j]),
         np.array([2 + 3j, 4 + 5j, 6 + 7j])]
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X)

    # tuple of np arrays
    X = (np.array([1 + 2j, 3 + 4j, 5 + 7j]),
         np.array([2 + 3j, 4 + 5j, 6 + 7j]))
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X)

    # dataframe
    X = MockDataFrame(
        np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]))
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X)

    # sparse matrix
    X = sp.coo_matrix([[0, 1 + 2j], [0, 0]])
    assert_raises_regex(
        ValueError, "Complex data not supported", check_array, X) 

def transform(self, X):
        if isinstance(X, pd.Series):
            return X.to_frame()
        X = as_float_array(X)
        X = check_array(X)
        return pd.DataFrame(X, index=self.index, columns=self.columns, dtype=self.dtype) 

def test_memmap():
    # Confirm that input validation code doesn't copy memory mapped arrays

    asflt = lambda x: as_float_array(x, copy=False)

    with NamedTemporaryFile(prefix='sklearn-test') as tmp:
        M = np.memmap(tmp, shape=(10, 10), dtype=np.float32)
        M[:] = 0

        for f in (check_array, np.asarray, asflt):
            X = f(M)
            X[:] = 1
            assert_array_equal(X.ravel(), M.ravel())
            X[:] = 0 

def test_check_array_warn_on_dtype_deprecation():
    X = np.asarray([[0.0], [1.0]])
    Y = np.asarray([[2.0], [3.0]])
    with pytest.warns(DeprecationWarning,
                      match="'warn_on_dtype' is deprecated"):
        check_array(X, warn_on_dtype=True)
    with pytest.warns(DeprecationWarning,
                      match="'warn_on_dtype' is deprecated"):
        check_X_y(X, Y, warn_on_dtype=True) 

def test_check_array_dtype_stability():
    # test that lists with ints don't get converted to floats
    X = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
    assert_equal(check_array(X).dtype.kind, "i")
    assert_equal(check_array(X, ensure_2d=False).dtype.kind, "i") 

def test_check_array_on_mock_dataframe():
    arr = np.array([[0.2, 0.7], [0.6, 0.5], [0.4, 0.1], [0.7, 0.2]])
    mock_df = MockDataFrame(arr)
    checked_arr = check_array(mock_df)
    assert_equal(checked_arr.dtype,
                 arr.dtype)
    checked_arr = check_array(mock_df, dtype=np.float32)
    assert_equal(checked_arr.dtype, np.dtype(np.float32)) 

def test_check_array_pandas_dtype_object_conversion():
    # test that data-frame like objects with dtype object
    # get converted
    X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]], dtype=np.object)
    X_df = MockDataFrame(X)
    assert_equal(check_array(X_df).dtype.kind, "f")
    assert_equal(check_array(X_df, ensure_2d=False).dtype.kind, "f")
    # smoke-test against dataframes with column named "dtype"
    X_df.dtype = "Hans"
    assert_equal(check_array(X_df, ensure_2d=False).dtype.kind, "f") 

def test_check_array_force_all_finiteinvalid(value, force_all_finite,
                                             match_msg, retype):
    X = retype(np.arange(4).reshape(2, 2).astype(np.float))
    X[0, 0] = value
    with pytest.raises(ValueError, match=match_msg):
        check_array(X, force_all_finite=force_all_finite,
                    accept_sparse=True) 

def test_check_array_force_all_finite_valid(value, force_all_finite, retype):
    X = retype(np.arange(4).reshape(2, 2).astype(np.float))
    X[0, 0] = value
    X_checked = check_array(X, force_all_finite=force_all_finite,
                            accept_sparse=True)
    assert_allclose_dense_sparse(X, X_checked) 

def decision_function(self, X):

        check_is_fitted(self, ['clf_', 'decision_scores_',
                               'labels_', '_scalar'])

        X = check_array(X)

        # construct the new feature space
        X_add = self._generate_new_features(X)
        X_new = np.concatenate((X, X_add), axis=1)

        pred_scores = self.clf_.predict_proba(X_new)[:, 1]
        return pred_scores.ravel()