__init__.py 20.6 KB
Newer Older
1 2
from future import standard_library
standard_library.install_aliases()
3 4


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
5
from future.utils import with_metaclass
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
6
from functools import partial
7

8
import os.path
9
import os
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
10
import re
11
import pickle
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
12
import logging
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
13
import copy
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
14
import pprint
15 16 17 18 19 20

import inspect
import sys
import subprocess
import importlib
import yaml
21
import threading
22
import nltk
23

24
from .. import models, utils
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
25
from .. import api
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
26

27

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
28 29
logger = logging.getLogger(__name__)

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
30 31 32 33 34 35 36 37
try:
    from gsitk.evaluation.evaluation import Evaluation as Eval
    from sklearn.pipeline import Pipeline
    GSITK_AVAILABLE = True
except ImportError:
    logger.warn('GSITK is not installed. Some functions will be unavailable.')
    GSITK_AVAILABLE = False

38

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
39
class PluginMeta(models.BaseMeta):
40
    _classes = {}
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
41 42 43 44 45 46

    def __new__(mcs, name, bases, attrs, **kwargs):
        plugin_type = []
        if hasattr(bases[0], 'plugin_type'):
            plugin_type += bases[0].plugin_type
        plugin_type.append(name)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
47
        alias = attrs.get('name', name)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
48
        attrs['plugin_type'] = plugin_type
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
49 50 51
        attrs['name'] = alias
        if 'description' not in attrs:
            doc = attrs.get('__doc__', None)
52 53 54 55 56
            if doc:
                attrs['description'] = doc
            else:
                logger.warn(('Plugin {} does not have a description. '
                             'Please, add a short summary to help other developers').format(name))
57
        cls = super(PluginMeta, mcs).__new__(mcs, name, bases, attrs)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
58 59 60 61 62 63 64 65

        if alias in mcs._classes:
            if os.environ.get('SENPY_TESTING', ""):
                raise Exception(('The type of plugin {} already exists. '
                                'Please, choose a different name').format(name))
            else:
                logger.warn('Overloading plugin class: {}'.format(alias))
        mcs._classes[alias] = cls
66 67 68 69 70
        return cls

    @classmethod
    def for_type(cls, ptype):
        return cls._classes[ptype]
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
71 72 73


class Plugin(with_metaclass(PluginMeta, models.Plugin)):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
74 75 76 77 78 79 80 81 82 83 84
    '''
    Base class for all plugins in senpy.
    A plugin must provide at least these attributes:

        - version
        - description (or docstring)
        - author

    Additionally, they may provide a URL (url) of a repository or website.

    '''
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
85 86

    def __init__(self, info=None, data_folder=None, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
87 88 89 90
        """
        Provides a canonical name for plugins and serves as base for other
        kinds of plugins.
        """
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
91
        logger.debug("Initialising {}".format(info))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
92
        super(Plugin, self).__init__(**kwargs)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
93 94
        if info:
            self.update(info)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
95
        self.validate()
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
96
        self.id = 'endpoint:plugins/{}_{}'.format(self['name'], self['version'])
97
        self.is_activated = False
98
        self._lock = threading.Lock()
99
        self._directory = os.path.abspath(os.path.dirname(inspect.getfile(self.__class__)))
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114

        data_folder = data_folder or os.getcwd()
        subdir = os.path.join(data_folder, self.name)

        self._data_paths = [
            data_folder,
            subdir,
            self._directory,
            os.path.join(self._directory, 'data'),
        ]

        if os.path.exists(subdir):
            data_folder = subdir
        self.data_folder = data_folder

115 116 117 118 119
        self._log = logging.getLogger('{}.{}'.format(__name__, self.name))

    @property
    def log(self):
        return self._log
120

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
121
    def validate(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
122 123 124 125 126 127
        missing = []
        for x in ['name', 'description', 'version']:
            if x not in self:
                missing.append(x)
        if missing:
            raise models.Error('Missing configuration parameters: {}'.format(missing))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
128

129 130 131
    def get_folder(self):
        return os.path.dirname(inspect.getfile(self.__class__))

132 133 134 135 136 137
    def activate(self):
        pass

    def deactivate(self):
        pass

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
138 139 140 141 142 143 144 145
    def test(self, test_cases=None):
        if not test_cases:
            if not hasattr(self, 'test_cases'):
                raise AttributeError(('Plugin {} [{}] does not have any defined '
                                      'test cases').format(self.id,
                                                           inspect.getfile(self.__class__)))
            test_cases = self.test_cases
        for case in test_cases:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
146
            try:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
147
                self.test_case(case)
148
                self.log.debug('Test case passed:\n{}'.format(pprint.pformat(case)))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
149
            except Exception as ex:
150
                self.log.warn('Test case failed:\n{}'.format(pprint.pformat(case)))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
151 152
                raise

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
153 154 155
    def test_case(self, case):
        entry = models.Entry(case['entry'])
        given_parameters = case.get('params', case.get('parameters', {}))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
156
        expected = case.get('expected', None)
157
        should_fail = case.get('should_fail', False)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
158 159
        try:
            params = api.parse_params(given_parameters, self.extra_params)
160 161 162 163 164 165 166
            res = list(self.analyse_entries([entry, ], params))

            if not isinstance(expected, list):
                expected = [expected]
            utils.check_template(res, expected)
            for r in res:
                r.validate()
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
167
        except models.Error:
168
            if should_fail:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
169
                return
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
170
            raise
171
        assert not should_fail
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
172

173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188
    def find_file(self, fname):
        for p in self._data_paths:
            alternative = os.path.join(p, fname)
            if os.path.exists(alternative):
                return alternative
        raise IOError('File does not exist: {}'.format(fname))

    def open(self, fpath, mode='r'):
        if 'w' in mode:
            # When writing, only use absolute paths or data_folder
            if not os.path.isabs(fpath):
                fpath = os.path.join(self.data_folder, fpath)
        else:
            fpath = self.find_file(fpath)

        return open(fpath, mode=mode)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
189

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
190 191
    def serve(self, debug=True, **kwargs):
        utils.easy(plugin_list=[self, ], plugin_folder=None, debug=debug, **kwargs)
192

193

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
194
# For backwards compatibility
195 196 197
SenpyPlugin = Plugin


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
198 199 200 201
class Analysis(Plugin):
    '''
    A subclass of Plugin that analyses text and provides an annotation.
    '''
202

203
    def analyse(self, *args, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
204
        raise NotImplementedError(
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
205
            'Your plugin should implement either analyse or analyse_entry')
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
206 207 208 209 210 211 212 213

    def analyse_entry(self, entry, parameters):
        """ An implemented plugin should override this method.
        This base method is here to adapt old style plugins which only
        implement the *analyse* function.
        Note that this method may yield an annotated entry or a list of
        entries (e.g. in a tokenizer)
        """
214
        text = entry['nif:isString']
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
215 216 217 218 219
        params = copy.copy(parameters)
        params['input'] = text
        results = self.analyse(**params)
        for i in results.entries:
            yield i
220

221 222
    def analyse_entries(self, entries, parameters):
        for entry in entries:
223
            self.log.debug('Analysing entry with plugin {}: {}'.format(self, entry))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
224 225 226 227 228 229 230 231 232 233 234 235 236
            results = self.analyse_entry(entry, parameters)
            if inspect.isgenerator(results):
                for result in results:
                    yield result
            else:
                yield results

    def test_case(self, case):
        if 'entry' not in case and 'input' in case:
            entry = models.Entry(_auto_id=False)
            entry.nif__isString = case['input']
            case['entry'] = entry
        super(Analysis, self).test_case(case)
237

238

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
239 240 241 242 243 244 245 246
AnalysisPlugin = Analysis


class Conversion(Plugin):
    '''
    A subclass of Plugins that convert between different annotation models.
    e.g. a conversion of emotion models, or normalization of sentiment values.
    '''
247
    pass
248

249

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
250 251 252 253 254 255 256
ConversionPlugin = Conversion


class SentimentPlugin(Analysis, models.SentimentPlugin):
    '''
    Sentiment plugins provide sentiment annotation (using Marl)
    '''
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
257 258
    minPolarityValue = 0
    maxPolarityValue = 1
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
259

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
260 261
    def test_case(self, case):
        if 'polarity' in case:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
262
            expected = case.get('expected', {})
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
263 264 265 266 267 268 269 270 271 272 273 274 275
            s = models.Sentiment(_auto_id=False)
            s.marl__hasPolarity = case['polarity']
            if 'sentiments' not in expected:
                expected['sentiments'] = []
            expected['sentiments'].append(s)
            case['expected'] = expected
        super(SentimentPlugin, self).test_case(case)


class EmotionPlugin(Analysis, models.EmotionPlugin):
    '''
    Emotion plugins provide emotion annotation (using Onyx)
    '''
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
276 277
    minEmotionValue = 0
    maxEmotionValue = 1
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
278 279


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
280 281 282 283
class EmotionConversion(Conversion):
    '''
    A subclass of Conversion that converts emotion annotations using different models
    '''
284
    pass
285 286


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
287 288 289
EmotionConversionPlugin = EmotionConversion


290 291 292 293 294 295 296
class Box(AnalysisPlugin):
    '''
    Black box plugins delegate analysis to a function.
    The flow is like so:

    .. code-block::

297
                   entry --> input() --> predict_one() --> output() --> entry'
298 299 300 301 302 303 304 305 306 307 308 309 310 311 312


    In other words: their ``input`` method convers a query (entry and a set of parameters) into
    the input to the box method. The ``output`` method convers the results given by the box into
    an entry that senpy can handle.
    '''

    def input(self, entry, params=None):
        '''Transforms a query (entry+param) into an input for the black box'''
        return entry

    def output(self, output, entry=None, params=None):
        '''Transforms the results of the black box into an entry'''
        return output

313
    def predict_one(self, input):
314 315 316 317 318
        raise NotImplementedError('You should define the behavior of this plugin')

    def analyse_entries(self, entries, params):
        for entry in entries:
            input = self.input(entry=entry, params=params)
319
            results = self.predict_one(input=input)
320 321
            yield self.output(output=results, entry=entry, params=params)

322 323 324 325
    def fit(self, X=None, y=None):
        return self

    def transform(self, X):
326
        return [self.predict_one(x) for x in X]
327 328 329 330 331 332 333 334 335 336 337 338 339

    def predict(self, X):
        return self.transform(X)

    def fit_transform(self, X, y):
        self.fit(X, y)
        return self.transform(X)

    def as_pipe(self):
        pipe = Pipeline([('plugin', self)])
        pipe.name = self.name
        return pipe

340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385

class TextBox(Box):
    '''A black box plugin that takes only text as input'''

    def input(self, entry, params):
        entry = super(TextBox, self).input(entry, params)
        return entry['nif:isString']


class SentimentBox(TextBox, SentimentPlugin):
    '''
    A box plugin where the output is only a polarity label or a tuple (polarity, polarityValue)
    '''

    def output(self, output, entry, **kwargs):
        s = models.Sentiment()
        try:
            label, value = output
        except ValueError:
            label, value = output, None
        s.prov(self)
        s.polarity = label
        if value is not None:
            s.polarityValue = value
        entry.sentiments.append(s)
        return entry


class EmotionBox(TextBox, EmotionPlugin):
    '''
    A box plugin where the output is only an a tuple of emotion labels
    '''

    def output(self, output, entry, **kwargs):
        if not isinstance(output, list):
            output = [output]
        s = models.EmotionSet()
        entry.emotions.append(s)
        for label in output:
            e = models.Emotion(onyx__hasEmotionCategory=label)
            s.append(e)
        return entry


class MappingMixin(object):

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
386 387 388 389 390 391 392 393
    @property
    def mappings(self):
        return self._mappings

    @mappings.setter
    def mappings(self, value):
        self._mappings = value

394 395 396 397 398 399 400 401
    def output(self, output, entry, params):
        output = self.mappings.get(output,
                                   self.mappings.get('default', output))
        return super(MappingMixin, self).output(output=output,
                                                entry=entry,
                                                params=params)


402 403 404
class ShelfMixin(object):
    @property
    def sh(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
405
        if not hasattr(self, '_sh') or self._sh is None:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
406
            self._sh = {}
407
            if os.path.isfile(self.shelf_file):
408
                try:
409
                    with self.open(self.shelf_file, 'rb') as p:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
410
                        self._sh = pickle.load(p)
411
                except (IndexError, EOFError, pickle.UnpicklingError):
412
                    self.log.warning('Corrupted shelf file: {}'.format(self.shelf_file))
413 414
                    if not self.get('force_shelf', False):
                        raise
415 416 417 418
        return self._sh

    @sh.deleter
    def sh(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
419 420
        if os.path.isfile(self.shelf_file):
            os.remove(self.shelf_file)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
421
            del self._sh
422
        self.save()
423

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
424 425 426 427
    @sh.setter
    def sh(self, value):
        self._sh = value

428 429
    @property
    def shelf_file(self):
430 431 432 433 434 435 436
        if not hasattr(self, '_shelf_file') or not self._shelf_file:
            self._shelf_file = os.path.join(self.data_folder, self.name + '.p')
        return self._shelf_file

    @shelf_file.setter
    def shelf_file(self, value):
        self._shelf_file = value
437

438
    def save(self):
439
        self.log.debug('Saving pickle')
440
        if hasattr(self, '_sh') and self._sh is not None:
441
            with self.open(self.shelf_file, 'wb') as f:
442
                pickle.dump(self._sh, f)
443 444


445
def pfilter(plugins, plugin_type=Analysis, **kwargs):
446 447 448 449 450 451
    """ Filter plugins by different criteria """
    if isinstance(plugins, models.Plugins):
        plugins = plugins.plugins
    elif isinstance(plugins, dict):
        plugins = plugins.values()
    logger.debug('#' * 100)
452 453 454 455
    logger.debug('plugin_type {}'.format(plugin_type))
    if plugin_type:
        if isinstance(plugin_type, PluginMeta):
            plugin_type = plugin_type.__name__
456
        try:
457 458
            plugin_type = plugin_type[0].upper() + plugin_type[1:]
            pclass = globals()[plugin_type]
459 460 461 462
            logger.debug('Class: {}'.format(pclass))
            candidates = filter(lambda x: isinstance(x, pclass),
                                plugins)
        except KeyError:
463
            raise models.Error('{} is not a valid type'.format(plugin_type))
464 465 466 467 468 469 470 471 472 473 474 475 476
    else:
        candidates = plugins

    logger.debug(candidates)

    def matches(plug):
        res = all(getattr(plug, k, None) == v for (k, v) in kwargs.items())
        logger.debug(
            "matching {} with {}: {}".format(plug.name, kwargs, res))
        return res

    if kwargs:
        candidates = filter(matches, candidates)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
477
    return candidates
478 479


480 481 482
def load_module(name, root=None):
    if root:
        sys.path.append(root)
483
    tmp = importlib.import_module(name)
484 485
    if root:
        sys.path.remove(root)
486 487 488
    return tmp


489
def _log_subprocess_output(process):
490 491 492 493 494 495 496
    for line in iter(process.stdout.readline, b''):
        logger.info('%r', line)
    for line in iter(process.stderr.readline, b''):
        logger.error('%r', line)


def install_deps(*plugins):
497
    installed = False
498
    nltk_resources = set()
499 500 501
    for info in plugins:
        requirements = info.get('requirements', [])
        if requirements:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
502
            pip_args = [sys.executable, '-m', 'pip', 'install']
503 504 505 506 507 508
            for req in requirements:
                pip_args.append(req)
            logger.info('Installing requirements: ' + str(requirements))
            process = subprocess.Popen(pip_args,
                                       stdout=subprocess.PIPE,
                                       stderr=subprocess.PIPE)
509
            _log_subprocess_output(process)
510
            exitcode = process.wait()
511
            installed = True
512
            if exitcode != 0:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
513
                raise models.Error("Dependencies not properly installed: {}".format(pip_args))
514 515 516
        nltk_resources |= set(info.get('nltk_resources', []))

    installed |= nltk.download(list(nltk_resources))
517
    return installed
518 519


520 521
is_plugin_file = re.compile(r'.*\.senpy$|senpy_[a-zA-Z0-9_]+\.py$|'
                            '^(?!test_)[a-zA-Z0-9_]+_plugin.py$')
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
522 523


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
524 525 526 527 528 529 530 531 532 533
def find_plugins(folders):
    for search_folder in folders:
        for root, dirnames, filenames in os.walk(search_folder):
            # Do not look for plugins in hidden or special folders
            dirnames[:] = [d for d in dirnames if d[0] not in ['.', '_']]
            for filename in filter(is_plugin_file.match, filenames):
                fpath = os.path.join(root, filename)
                yield fpath


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
534
def from_path(fpath, install_on_fail=False, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
535 536 537 538 539 540 541 542 543
    logger.debug("Loading plugin from {}".format(fpath))
    if fpath.endswith('.py'):
        # We asume root is the dir of the file, and module is the name of the file
        root = os.path.dirname(fpath)
        module = os.path.basename(fpath)[:-3]
        for instance in _from_module_name(module=module, root=root, **kwargs):
            yield instance
    else:
        info = parse_plugin_info(fpath)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
544
        yield from_info(info, install_on_fail=install_on_fail, **kwargs)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
545 546 547 548 549 550 551 552 553 554


def from_folder(folders, loader=from_path, **kwargs):
    plugins = []
    for fpath in find_plugins(folders):
        for plugin in loader(fpath, **kwargs):
            plugins.append(plugin)
    return plugins


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
555
def from_info(info, root=None, install_on_fail=True, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
556
    if any(x not in info for x in ('module',)):
557
        raise ValueError('Plugin info is not valid: {}'.format(info))
558 559
    module = info["module"]

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
560 561 562
    if not root and '_path' in info:
        root = os.path.dirname(info['_path'])

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
563 564 565 566 567 568
    fun = partial(one_from_module, module, root=root, info=info, **kwargs)
    try:
        return fun()
    except (ImportError, LookupError):
        install_deps(info)
        return fun()
569 570


571
def parse_plugin_info(fpath):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
572
    logger.debug("Parsing plugin info: {}".format(fpath))
573 574
    with open(fpath, 'r') as f:
        info = yaml.load(f)
575
    info['_path'] = fpath
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
576
    return info
577 578


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
579
def from_module(module, **kwargs):
580

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
581 582 583 584 585 586
    if inspect.ismodule(module):
        res = _from_loaded_module(module, **kwargs)
    else:
        res = _from_module_name(module, **kwargs)
    for p in res:
        yield p
587

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614

def one_from_module(module, root, info, **kwargs):
    if '@type' in info:
        cls = PluginMeta.from_type(info['@type'])
        return cls(info=info, **kwargs)
    instance = next(from_module(module=module, root=root, info=info, **kwargs), None)
    if not instance:
        raise Exception("No valid plugin for: {}".format(module))
    return instance


def _classes_in_module(module):
    for _, obj in inspect.getmembers(module):
        if inspect.isclass(obj) and inspect.getmodule(obj) == module:
            logger.debug(("Found plugin class:"
                          " {}@{}").format(obj, inspect.getmodule(obj)))
            yield obj


def _instances_in_module(module):
    for _, obj in inspect.getmembers(module):
        if isinstance(obj, Plugin) and inspect.getmodule(obj) == module:
            logger.debug(("Found plugin instance:"
                          " {}@{}").format(obj, inspect.getmodule(obj)))
            yield obj


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
615 616
def _from_module_name(module, root, info=None, **kwargs):
    module = load_module(module, root)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
617 618 619 620 621 622 623 624 625
    for plugin in _from_loaded_module(module=module, root=root, info=info, **kwargs):
        yield plugin


def _from_loaded_module(module, info=None, **kwargs):
    for cls in _classes_in_module(module):
        yield cls(info=info, **kwargs)
    for instance in _instances_in_module(module):
        yield instance
626 627 628


def evaluate(plugins, datasets, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
629 630 631
    if not GSITK_AVAILABLE:
        raise Exception('GSITK is not available. Install it to use this function.')

632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
    ev = Eval(tuples=None,
              datasets=datasets,
              pipelines=[plugin.as_pipe() for plugin in plugins])
    ev.evaluate()
    results = ev.results
    evaluations = evaluations_to_JSONLD(results, **kwargs)
    return evaluations


def evaluations_to_JSONLD(results, flatten=False):
    '''
    Map the evaluation results to a JSONLD scheme
    '''

    evaluations = list()
    metric_names = ['accuracy', 'precision_macro', 'recall_macro',
                    'f1_macro', 'f1_weighted', 'f1_micro', 'f1_macro']

    for index, row in results.iterrows():
        evaluation = models.Evaluation()
        if row.get('CV', True):
            evaluation['@type'] = ['StaticCV', 'Evaluation']
        evaluation.evaluatesOn = row['Dataset']
        evaluation.evaluates = row['Model']
        i = 0
        if flatten:
            metric = models.Metric()
            for name in metric_names:
                metric[name] = row[name]
            evaluation.metrics.append(metric)
        else:
            # We should probably discontinue this representation
            for name in metric_names:
                metric = models.Metric()
                metric['@id'] = 'Metric' + str(i)
                metric['@type'] = name.capitalize()
                metric.value = row[name]
                evaluation.metrics.append(metric)
                i += 1
        evaluations.append(evaluation)
    return evaluations