annif.backend.nn_ensemble.NNEnsembleBackend.initialize() - Code Metrics - Inspection of "Merge branch 'update-dependencies-v1.0' into issue..." - NatLibFi/Annif - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — issue703-python-3.11-support ( f59527...05d52a )

by Juho

created 2023-08-15 12:08 UTC

NNEnsembleBackend.initialize() A

↳ Parent: annif.backend.nn_ensemble

Complexity

Conditions

Size

Total Lines	17
Code Lines	14

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	4
eloc	14
nop	2
dl	0
loc	17
rs	9.7
c	0
b	0
f	0

"""Neural network based ensemble backend that combines results from multiple
projects."""
from __future__ import annotations

import os.path
import shutil
from io import BytesIO
from typing import TYPE_CHECKING, Any

import joblib
import lmdb
import numpy as np
import tensorflow.keras.backend as K
from scipy.sparse import csc_matrix, csr_matrix
from tensorflow.keras.layers import Add, Dense, Dropout, Flatten, Input, Layer
from tensorflow.keras.models import Model, load_model
from tensorflow.keras.utils import Sequence

import annif.corpus
import annif.parallel
import annif.util
from annif.exception import NotInitializedException, NotSupportedException
from annif.suggestion import SuggestionBatch, vector_to_suggestions

from . import backend, ensemble

if TYPE_CHECKING:
    from tensorflow.python.framework.ops import EagerTensor

    from annif.corpus.document import DocumentCorpus


def idx_to_key(idx: int) -> bytes:
    """convert an integer index to a binary key for use in LMDB"""
    return b"%08d" % idx


def key_to_idx(key: memoryview | bytes) -> int:
    """convert a binary LMDB key to an integer index"""
    return int(key)


class LMDBSequence(Sequence):
    """A sequence of samples stored in a LMDB database."""

    def __init__(self, txn, batch_size):
        self._txn = txn
        cursor = txn.cursor()
        if cursor.last():
            # Counter holds the number of samples in the database
            self._counter = key_to_idx(cursor.key()) + 1
        else:  # empty database
            self._counter = 0
        self._batch_size = batch_size

    def add_sample(self, inputs: np.ndarray, targets: np.ndarray) -> None:
        # use zero-padded 8-digit key
        key = idx_to_key(self._counter)
        self._counter += 1
        # convert the sample into a sparse matrix and serialize it as bytes
        sample = (csc_matrix(inputs), csr_matrix(targets))
        buf = BytesIO()
        joblib.dump(sample, buf)
        buf.seek(0)
        self._txn.put(key, buf.read())

    def __getitem__(self, idx: int) -> tuple[np.ndarray, np.ndarray]:
        """get a particular batch of samples"""
        cursor = self._txn.cursor()
        first_key = idx * self._batch_size
        cursor.set_key(idx_to_key(first_key))
        input_arrays = []
        target_arrays = []
        for key, value in cursor.iternext():
            if key_to_idx(key) >= (first_key + self._batch_size):
                break
            input_csr, target_csr = joblib.load(BytesIO(value))
            input_arrays.append(input_csr.toarray())
            target_arrays.append(target_csr.toarray().flatten())
        return np.array(input_arrays), np.array(target_arrays)

    def __len__(self) -> int:
        """return the number of available batches"""
        return int(np.ceil(self._counter / self._batch_size))


class MeanLayer(Layer):
    """Custom Keras layer that calculates mean values along the 2nd axis."""

    def call(self, inputs: EagerTensor) -> EagerTensor:
        return K.mean(inputs, axis=2)


class NNEnsembleBackend(backend.AnnifLearningBackend, ensemble.BaseEnsembleBackend):
    """Neural network ensemble backend that combines results from multiple
    projects"""

    name = "nn_ensemble"

    MODEL_FILE = "nn-model.h5"
    LMDB_FILE = "nn-train.mdb"

    DEFAULT_PARAMETERS = {
        "nodes": 100,
        "dropout_rate": 0.2,
        "optimizer": "adam",
        "epochs": 10,
        "learn-epochs": 1,
        "lmdb_map_size": 1024 * 1024 * 1024,
    }

    # defaults for uninitialized instances
    _model = None

    def initialize(self, parallel: bool = False) -> None:
        super().initialize(parallel)
        if self._model is not None:
            return  # already initialized
        if parallel:
            # Don't load TF model just before parallel execution,
            # since it won't work after forking worker processes
            return
        model_filename = os.path.join(self.datadir, self.MODEL_FILE)
        if not os.path.exists(model_filename):
            raise NotInitializedException(
                "model file {} not found".format(model_filename),
                backend_id=self.backend_id,
            )
        self.debug("loading Keras model from {}".format(model_filename))
        self._model = load_model(
            model_filename, custom_objects={"MeanLayer": MeanLayer}
        )

    def _merge_source_batches(
        self,
        batch_by_source: dict[str, SuggestionBatch],
        sources: list[tuple[str, float]],
        params: dict[str, Any],
    ) -> SuggestionBatch:
        src_weight = dict(sources)
        score_vectors = np.array(
            [
                [
                    np.sqrt(suggestions.as_vector())
                    * src_weight[project_id]
                    * len(batch_by_source)
                    for suggestions in batch
                ]
                for project_id, batch in batch_by_source.items()
            ],
            dtype=np.float32,
        ).transpose(1, 2, 0)
        prediction = self._model(score_vectors).numpy()
        return SuggestionBatch.from_sequence(
            [
                vector_to_suggestions(row, limit=int(params["limit"]))
                for row in prediction
            ],
            self.project.subjects,
        )

    def _create_model(self, sources: list[tuple[str, float]]) -> None:
        self.info("creating NN ensemble model")

        inputs = Input(shape=(len(self.project.subjects), len(sources)))

        flat_input = Flatten()(inputs)
        drop_input = Dropout(rate=float(self.params["dropout_rate"]))(flat_input)
        hidden = Dense(int(self.params["nodes"]), activation="relu")(drop_input)
        drop_hidden = Dropout(rate=float(self.params["dropout_rate"]))(hidden)
        delta = Dense(
            len(self.project.subjects),
            kernel_initializer="zeros",
            bias_initializer="zeros",
        )(drop_hidden)

        mean = MeanLayer()(inputs)

        predictions = Add()([mean, delta])

        self._model = Model(inputs=inputs, outputs=predictions)
        self._model.compile(
            optimizer=self.params["optimizer"],
            loss="binary_crossentropy",
            metrics=["top_k_categorical_accuracy"],
        )
        if "lr" in self.params:
            self._model.optimizer.learning_rate.assign(float(self.params["lr"]))

        summary = []
        self._model.summary(print_fn=summary.append)
        self.debug("Created model: \n" + "\n".join(summary))

    def _train(
        self,
        corpus: DocumentCorpus,
        params: dict[str, Any],
        jobs: int = 0,
    ) -> None:
        sources = annif.util.parse_sources(self.params["sources"])
        self._create_model(sources)
        self._fit_model(
            corpus,
            epochs=int(params["epochs"]),
            lmdb_map_size=int(params["lmdb_map_size"]),
            n_jobs=jobs,
        )

    def _corpus_to_vectors(
        self,
        corpus: DocumentCorpus,
        seq: LMDBSequence,
        n_jobs: int,
    ) -> None:
        # pass corpus through all source projects
        sources = dict(annif.util.parse_sources(self.params["sources"]))

        # initialize the source projects before forking, to save memory
        self.info(f"Initializing source projects: {', '.join(sources.keys())}")
        for project_id in sources.keys():
            project = self.project.registry.get_project(project_id)
            project.initialize(parallel=True)

        psmap = annif.parallel.ProjectSuggestMap(
            self.project.registry,
            list(sources.keys()),
            backend_params=None,
            limit=None,
            threshold=0.0,
        )

        jobs, pool_class = annif.parallel.get_pool(n_jobs)

        self.info("Processing training documents...")
        with pool_class(jobs) as pool:
            for hits, subject_set in pool.imap_unordered(
                psmap.suggest, corpus.documents
            ):
                doc_scores = []
                for project_id, p_hits in hits.items():
                    vector = p_hits.as_vector()
                    doc_scores.append(
                        np.sqrt(vector) * sources[project_id] * len(sources)
                    )
                score_vector = np.array(doc_scores, dtype=np.float32).transpose()
                true_vector = subject_set.as_vector(len(self.project.subjects))
                seq.add_sample(score_vector, true_vector)

    def _open_lmdb(self, cached, lmdb_map_size):
        lmdb_path = os.path.join(self.datadir, self.LMDB_FILE)
        if not cached and os.path.exists(lmdb_path):
            shutil.rmtree(lmdb_path)
        return lmdb.open(lmdb_path, map_size=lmdb_map_size, writemap=True)

    def _fit_model(
        self,
        corpus: DocumentCorpus,
        epochs: int,
        lmdb_map_size: int,
        n_jobs: int = 1,
    ) -> None:
        env = self._open_lmdb(corpus == "cached", lmdb_map_size)
        if corpus != "cached":
            if corpus.is_empty():
                raise NotSupportedException(
                    "Cannot train nn_ensemble project with no documents"
                )
            with env.begin(write=True, buffers=True) as txn:
                seq = LMDBSequence(txn, batch_size=32)
                self._corpus_to_vectors(corpus, seq, n_jobs)
        else:
            self.info("Reusing cached training data from previous run.")
        # fit the model using a read-only view of the LMDB
        self.info("Training neural network model...")
        with env.begin(buffers=True) as txn:
            seq = LMDBSequence(txn, batch_size=32)
            self._model.fit(seq, verbose=True, epochs=epochs)

        annif.util.atomic_save(self._model, self.datadir, self.MODEL_FILE)

    def _learn(
        self,
        corpus: DocumentCorpus,
        params: dict[str, Any],
    ) -> None:
        self.initialize()
        self._fit_model(
            corpus, int(params["learn-epochs"]), int(params["lmdb_map_size"])
        )


1			"""Neural network based ensemble backend that combines results from multiple
2			projects."""
3			from __future__ import annotations
4
5			import os.path
6			import shutil
7			from io import BytesIO
8			from typing import TYPE_CHECKING, Any
9
10			import joblib
11			import lmdb
12			import numpy as np
13			import tensorflow.keras.backend as K
14			from scipy.sparse import csc_matrix, csr_matrix
15			from tensorflow.keras.layers import Add, Dense, Dropout, Flatten, Input, Layer
16			from tensorflow.keras.models import Model, load_model
17			from tensorflow.keras.utils import Sequence
18
19			import annif.corpus
20			import annif.parallel
21			import annif.util
22			from annif.exception import NotInitializedException, NotSupportedException
23			from annif.suggestion import SuggestionBatch, vector_to_suggestions
24
25			from . import backend, ensemble
26
27			if TYPE_CHECKING:
28			from tensorflow.python.framework.ops import EagerTensor
29
30			from annif.corpus.document import DocumentCorpus
31
32
33			def idx_to_key(idx: int) -> bytes:
34			"""convert an integer index to a binary key for use in LMDB"""
35			return b"%08d" % idx
36
37
38			def key_to_idx(key: memoryview \| bytes) -> int:
39			"""convert a binary LMDB key to an integer index"""
40			return int(key)
41
42
43			class LMDBSequence(Sequence):
44			"""A sequence of samples stored in a LMDB database."""
45
46			def __init__(self, txn, batch_size):
47			self._txn = txn
48			cursor = txn.cursor()
49			if cursor.last():
50			# Counter holds the number of samples in the database
51			self._counter = key_to_idx(cursor.key()) + 1
52			else: # empty database
53			self._counter = 0
54			self._batch_size = batch_size
55
56			def add_sample(self, inputs: np.ndarray, targets: np.ndarray) -> None:
57			# use zero-padded 8-digit key
58			key = idx_to_key(self._counter)
59			self._counter += 1
60			# convert the sample into a sparse matrix and serialize it as bytes
61			sample = (csc_matrix(inputs), csr_matrix(targets))
62			buf = BytesIO()
63			joblib.dump(sample, buf)
64			buf.seek(0)
65			self._txn.put(key, buf.read())
66
67			def __getitem__(self, idx: int) -> tuple[np.ndarray, np.ndarray]:
68			"""get a particular batch of samples"""
69			cursor = self._txn.cursor()
70			first_key = idx * self._batch_size
71			cursor.set_key(idx_to_key(first_key))
72			input_arrays = []
73			target_arrays = []
74			for key, value in cursor.iternext():
75			if key_to_idx(key) >= (first_key + self._batch_size):
76			break
77			input_csr, target_csr = joblib.load(BytesIO(value))
78			input_arrays.append(input_csr.toarray())
79			target_arrays.append(target_csr.toarray().flatten())
80			return np.array(input_arrays), np.array(target_arrays)
81
82			def __len__(self) -> int:
83			"""return the number of available batches"""
84			return int(np.ceil(self._counter / self._batch_size))
85
86
87			class MeanLayer(Layer):
88			"""Custom Keras layer that calculates mean values along the 2nd axis."""
89
90			def call(self, inputs: EagerTensor) -> EagerTensor:
91			return K.mean(inputs, axis=2)
92
93
94			class NNEnsembleBackend(backend.AnnifLearningBackend, ensemble.BaseEnsembleBackend):
95			"""Neural network ensemble backend that combines results from multiple
96			projects"""
97
98			name = "nn_ensemble"
99
100			MODEL_FILE = "nn-model.h5"
101			LMDB_FILE = "nn-train.mdb"
102
103			DEFAULT_PARAMETERS = {
104			"nodes": 100,
105			"dropout_rate": 0.2,
106			"optimizer": "adam",
107			"epochs": 10,
108			"learn-epochs": 1,
109			"lmdb_map_size": 1024 * 1024 * 1024,
110			}
111
112			# defaults for uninitialized instances
113			_model = None
114
115			def initialize(self, parallel: bool = False) -> None:
116			super().initialize(parallel)
117			if self._model is not None:
118			return # already initialized
119			if parallel:
120			# Don't load TF model just before parallel execution,
121			# since it won't work after forking worker processes
122			return
123			model_filename = os.path.join(self.datadir, self.MODEL_FILE)
124			if not os.path.exists(model_filename):
125			raise NotInitializedException(
126			"model file {} not found".format(model_filename),
127			backend_id=self.backend_id,
128			)
129			self.debug("loading Keras model from {}".format(model_filename))
130			self._model = load_model(
131			model_filename, custom_objects={"MeanLayer": MeanLayer}
132			)
133
134			def _merge_source_batches(
135			self,
136			batch_by_source: dict[str, SuggestionBatch],
137			sources: list[tuple[str, float]],
138			params: dict[str, Any],
139			) -> SuggestionBatch:
140			src_weight = dict(sources)
141			score_vectors = np.array(
142			[
143			[
144			np.sqrt(suggestions.as_vector())
145			* src_weight[project_id]
146			* len(batch_by_source)
147			for suggestions in batch
148			]
149			for project_id, batch in batch_by_source.items()
150			],
151			dtype=np.float32,
152			).transpose(1, 2, 0)
153			prediction = self._model(score_vectors).numpy()
154			return SuggestionBatch.from_sequence(
155			[
156			vector_to_suggestions(row, limit=int(params["limit"]))
157			for row in prediction
158			],
159			self.project.subjects,
160			)
161
162			def _create_model(self, sources: list[tuple[str, float]]) -> None:
163			self.info("creating NN ensemble model")
164
165			inputs = Input(shape=(len(self.project.subjects), len(sources)))
166
167			flat_input = Flatten()(inputs)
168			drop_input = Dropout(rate=float(self.params["dropout_rate"]))(flat_input)
169			hidden = Dense(int(self.params["nodes"]), activation="relu")(drop_input)
170			drop_hidden = Dropout(rate=float(self.params["dropout_rate"]))(hidden)
171			delta = Dense(
172			len(self.project.subjects),
173			kernel_initializer="zeros",
174			bias_initializer="zeros",
175			)(drop_hidden)
176
177			mean = MeanLayer()(inputs)
178
179			predictions = Add()([mean, delta])
180
181			self._model = Model(inputs=inputs, outputs=predictions)
182			self._model.compile(
183			optimizer=self.params["optimizer"],
184			loss="binary_crossentropy",
185			metrics=["top_k_categorical_accuracy"],
186			)
187			if "lr" in self.params:
188			self._model.optimizer.learning_rate.assign(float(self.params["lr"]))
189
190			summary = []
191			self._model.summary(print_fn=summary.append)
192			self.debug("Created model: \n" + "\n".join(summary))
193
194			def _train(
195			self,
196			corpus: DocumentCorpus,
197			params: dict[str, Any],
198			jobs: int = 0,
199			) -> None:
200			sources = annif.util.parse_sources(self.params["sources"])
201			self._create_model(sources)
202			self._fit_model(
203			corpus,
204			epochs=int(params["epochs"]),
205			lmdb_map_size=int(params["lmdb_map_size"]),
206			n_jobs=jobs,
207			)
208
209			def _corpus_to_vectors(
210			self,
211			corpus: DocumentCorpus,
212			seq: LMDBSequence,
213			n_jobs: int,
214			) -> None:
215			# pass corpus through all source projects
216			sources = dict(annif.util.parse_sources(self.params["sources"]))
217
218			# initialize the source projects before forking, to save memory
219			self.info(f"Initializing source projects: {', '.join(sources.keys())}")
220			for project_id in sources.keys():
221			project = self.project.registry.get_project(project_id)
222			project.initialize(parallel=True)
223
224			psmap = annif.parallel.ProjectSuggestMap(
225			self.project.registry,
226			list(sources.keys()),
227			backend_params=None,
228			limit=None,
229			threshold=0.0,
230			)
231
232			jobs, pool_class = annif.parallel.get_pool(n_jobs)
233
234			self.info("Processing training documents...")
235			with pool_class(jobs) as pool:
236			for hits, subject_set in pool.imap_unordered(
237			psmap.suggest, corpus.documents
238			):
239			doc_scores = []
240			for project_id, p_hits in hits.items():
241			vector = p_hits.as_vector()
242			doc_scores.append(
243			np.sqrt(vector) * sources[project_id] * len(sources)
244			)
245			score_vector = np.array(doc_scores, dtype=np.float32).transpose()
246			true_vector = subject_set.as_vector(len(self.project.subjects))
247			seq.add_sample(score_vector, true_vector)
248
249			def _open_lmdb(self, cached, lmdb_map_size):
250			lmdb_path = os.path.join(self.datadir, self.LMDB_FILE)
251			if not cached and os.path.exists(lmdb_path):
252			shutil.rmtree(lmdb_path)
253			return lmdb.open(lmdb_path, map_size=lmdb_map_size, writemap=True)
254
255			def _fit_model(
256			self,
257			corpus: DocumentCorpus,
258			epochs: int,
259			lmdb_map_size: int,
260			n_jobs: int = 1,
261			) -> None:
262			env = self._open_lmdb(corpus == "cached", lmdb_map_size)
263			if corpus != "cached":
264			if corpus.is_empty():
265			raise NotSupportedException(
266			"Cannot train nn_ensemble project with no documents"
267			)
268			with env.begin(write=True, buffers=True) as txn:
269			seq = LMDBSequence(txn, batch_size=32)
270			self._corpus_to_vectors(corpus, seq, n_jobs)
271			else:
272			self.info("Reusing cached training data from previous run.")
273			# fit the model using a read-only view of the LMDB
274			self.info("Training neural network model...")
275			with env.begin(buffers=True) as txn:
276			seq = LMDBSequence(txn, batch_size=32)
277			self._model.fit(seq, verbose=True, epochs=epochs)
278
279			annif.util.atomic_save(self._model, self.datadir, self.MODEL_FILE)
280
281			def _learn(
282			self,
283			corpus: DocumentCorpus,
284			params: dict[str, Any],
285			) -> None:
286			self.initialize()
287			self._fit_model(
288			corpus, int(params["learn-epochs"]), int(params["lmdb_map_size"])
289			)
290

NatLibFi / Annif

Push — issue703-python-3.11-support ( f59527...05d52a )

NNEnsembleBackend.initialize() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like