__init__.py 19.3 KB
Newer Older
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
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
6

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
7
import os.path
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
8
import os
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
9
import re
10
import pickle
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
11
import logging
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
12
import copy
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
13
import pprint
14 15 16 17 18 19

import inspect
import sys
import subprocess
import importlib
import yaml
20
import threading
21

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
22
from .. import models, utils
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
23
from .. import api
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
24

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
25

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
26 27
logger = logging.getLogger(__name__)

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
28 29 30 31 32 33 34 35
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

36

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
37
class PluginMeta(models.BaseMeta):
38
    _classes = {}
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
39 40 41 42 43 44

    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
45
        alias = attrs.get('name', name)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
46
        attrs['plugin_type'] = plugin_type
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
47 48 49
        attrs['name'] = alias
        if 'description' not in attrs:
            doc = attrs.get('__doc__', None)
50 51 52 53 54
            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))
55
        cls = super(PluginMeta, mcs).__new__(mcs, name, bases, attrs)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
56 57 58 59 60 61 62 63

        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
64 65 66 67 68
        return cls

    @classmethod
    def for_type(cls, ptype):
        return cls._classes[ptype]
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
69 70 71


class Plugin(with_metaclass(PluginMeta, models.Plugin)):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
72 73 74 75 76 77 78 79 80 81 82
    '''
    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
83 84

    def __init__(self, info=None, data_folder=None, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
85 86 87 88
        """
        Provides a canonical name for plugins and serves as base for other
        kinds of plugins.
        """
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
89
        logger.debug("Initialising {}".format(info))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
90
        super(Plugin, self).__init__(**kwargs)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
91 92
        if info:
            self.update(info)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
93
        self.validate()
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
94
        self.id = 'plugins/{}_{}'.format(self['name'], self['version'])
95
        self.is_activated = False
96
        self._lock = threading.Lock()
97
        self.data_folder = data_folder or os.getcwd()
98

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
99
    def validate(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
100 101 102 103 104 105
        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
106

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
107 108 109
    def get_folder(self):
        return os.path.dirname(inspect.getfile(self.__class__))

110 111 112 113 114 115
    def activate(self):
        pass

    def deactivate(self):
        pass

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
116 117 118 119 120 121 122 123
    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
124
            try:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
125
                self.test_case(case)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
126
                logger.debug('Test case passed:\n{}'.format(pprint.pformat(case)))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
127 128
            except Exception as ex:
                logger.warn('Test case failed:\n{}'.format(pprint.pformat(case)))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
129 130
                raise

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
131 132 133
    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
134
        expected = case.get('expected', None)
135
        should_fail = case.get('should_fail', False)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
136 137
        try:
            params = api.parse_params(given_parameters, self.extra_params)
138 139 140 141 142 143 144
            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
145
        except models.Error:
146
            if should_fail:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
147
                return
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
148
            raise
149
        assert not should_fail
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
150

151 152 153
    def open(self, fpath, *args, **kwargs):
        if not os.path.isabs(fpath):
            fpath = os.path.join(self.data_folder, fpath)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
154 155
        return open(fpath, *args, **kwargs)

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
156 157
    def serve(self, debug=True, **kwargs):
        utils.easy(plugin_list=[self, ], plugin_folder=None, debug=debug, **kwargs)
158

159

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
160
# For backwards compatibility
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
161 162 163
SenpyPlugin = Plugin


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
164 165 166 167
class Analysis(Plugin):
    '''
    A subclass of Plugin that analyses text and provides an annotation.
    '''
168

169
    def analyse(self, *args, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
170
        raise NotImplementedError(
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
171
            'Your plugin should implement either analyse or analyse_entry')
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
172 173 174 175 176 177 178 179

    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)
        """
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
180
        text = entry['nif:isString']
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
181 182 183 184 185
        params = copy.copy(parameters)
        params['input'] = text
        results = self.analyse(**params)
        for i in results.entries:
            yield i
186

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
187 188 189
    def analyse_entries(self, entries, parameters):
        for entry in entries:
            logger.debug('Analysing entry with plugin {}: {}'.format(self, entry))
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
190 191 192 193 194 195 196 197 198 199 200 201 202
            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)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
203

204

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
205 206 207 208 209 210 211 212
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.
    '''
213
    pass
214

215

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
216 217 218 219 220 221 222
ConversionPlugin = Conversion


class SentimentPlugin(Analysis, models.SentimentPlugin):
    '''
    Sentiment plugins provide sentiment annotation (using Marl)
    '''
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
223 224
    minPolarityValue = 0
    maxPolarityValue = 1
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
225

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
226 227
    def test_case(self, case):
        if 'polarity' in case:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
228
            expected = case.get('expected', {})
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
229 230 231 232 233 234 235 236 237 238 239 240 241
            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
242 243
    minEmotionValue = 0
    maxEmotionValue = 1
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
244 245


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
246 247 248 249
class EmotionConversion(Conversion):
    '''
    A subclass of Conversion that converts emotion annotations using different models
    '''
250
    pass
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
251 252


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
253 254 255
EmotionConversionPlugin = EmotionConversion


256 257 258 259 260 261 262
class Box(AnalysisPlugin):
    '''
    Black box plugins delegate analysis to a function.
    The flow is like so:

    .. code-block::

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
263
                   entry --> input() --> predict_one() --> output() --> entry'
264 265 266 267 268 269 270 271 272 273 274 275 276 277 278


    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

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
279
    def predict_one(self, input):
280 281 282 283 284
        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)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
285
            results = self.predict_one(input=input)
286 287
            yield self.output(output=results, entry=entry, params=params)

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
288 289 290 291
    def fit(self, X=None, y=None):
        return self

    def transform(self, X):
292
        return [self.predict_one(x) for x in X]
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
293 294 295 296 297 298 299 300 301 302 303 304 305

    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

306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351

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
352 353 354 355 356 357 358 359
    @property
    def mappings(self):
        return self._mappings

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

360 361 362 363 364 365 366 367
    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)


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
368 369 370
class ShelfMixin(object):
    @property
    def sh(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
371
        if not hasattr(self, '_sh') or self._sh is None:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
372
            self._sh = {}
373
            if os.path.isfile(self.shelf_file):
374
                try:
375
                    with self.open(self.shelf_file, 'rb') as p:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
376
                        self._sh = pickle.load(p)
377
                except (IndexError, EOFError, pickle.UnpicklingError):
378 379 380
                    logger.warning('{} has a corrupted shelf file!'.format(self.id))
                    if not self.get('force_shelf', False):
                        raise
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
381 382 383 384
        return self._sh

    @sh.deleter
    def sh(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
385 386
        if os.path.isfile(self.shelf_file):
            os.remove(self.shelf_file)
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
387
            del self._sh
388
        self.save()
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
389

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
390 391 392 393
    @sh.setter
    def sh(self, value):
        self._sh = value

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
394 395
    @property
    def shelf_file(self):
396 397 398 399 400 401 402
        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
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
403

404
    def save(self):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
405
        logger.debug('saving pickle')
406
        if hasattr(self, '_sh') and self._sh is not None:
407
            with self.open(self.shelf_file, 'wb') as f:
408
                pickle.dump(self._sh, f)
409 410 411 412 413 414 415 416


def pfilter(plugins, **kwargs):
    """ Filter plugins by different criteria """
    if isinstance(plugins, models.Plugins):
        plugins = plugins.plugins
    elif isinstance(plugins, dict):
        plugins = plugins.values()
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
417
    ptype = kwargs.pop('plugin_type', Plugin)
418 419 420
    logger.debug('#' * 100)
    logger.debug('ptype {}'.format(ptype))
    if ptype:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
421 422
        if isinstance(ptype, PluginMeta):
            ptype = ptype.__name__
423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443
        try:
            ptype = ptype[0].upper() + ptype[1:]
            pclass = globals()[ptype]
            logger.debug('Class: {}'.format(pclass))
            candidates = filter(lambda x: isinstance(x, pclass),
                                plugins)
        except KeyError:
            raise models.Error('{} is not a valid type'.format(ptype))
    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
444
    return candidates
445 446


447 448 449
def load_module(name, root=None):
    if root:
        sys.path.append(root)
450
    tmp = importlib.import_module(name)
451 452
    if root:
        sys.path.remove(root)
453 454 455
    return tmp


456
def _log_subprocess_output(process):
457 458 459 460 461 462 463
    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):
464
    installed = False
465 466 467
    for info in plugins:
        requirements = info.get('requirements', [])
        if requirements:
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
468
            pip_args = [sys.executable, '-m', 'pip', 'install']
469 470 471 472 473 474
            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)
475
            _log_subprocess_output(process)
476
            exitcode = process.wait()
477
            installed = True
478 479
            if exitcode != 0:
                raise models.Error("Dependencies not properly installed")
480
    return installed
481 482


483 484
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
485 486


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519
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


def from_path(fpath, **kwargs):
    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)
        yield from_info(info, **kwargs)


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


def from_info(info, root=None, **kwargs):
    if any(x not in info for x in ('module',)):
520
        raise ValueError('Plugin info is not valid: {}'.format(info))
521 522
    module = info["module"]

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
523 524 525 526
    if not root and '_path' in info:
        root = os.path.dirname(info['_path'])

    return one_from_module(module, root=root, info=info, **kwargs)
527 528


529
def parse_plugin_info(fpath):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
530
    logger.debug("Parsing plugin info: {}".format(fpath))
531 532
    with open(fpath, 'r') as f:
        info = yaml.load(f)
533
    info['_path'] = fpath
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
534
    return info
535 536


J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
537
def from_module(module, **kwargs):
538

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
539 540 541 542 543 544
    if inspect.ismodule(module):
        res = _from_loaded_module(module, **kwargs)
    else:
        res = _from_module_name(module, **kwargs)
    for p in res:
        yield p
545

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589

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


def _from_module_name(module, root, info=None, install=True, **kwargs):
    try:
        module = load_module(module, root)
    except ImportError:
        if not install or not info:
            raise
        install_deps(info)
        module = load_module(module, root)
    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
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
590 591 592


def evaluate(plugins, datasets, **kwargs):
J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
593 594 595
    if not GSITK_AVAILABLE:
        raise Exception('GSITK is not available. Install it to use this function.')

J. Fernando Sánchez's avatar
J. Fernando Sánchez committed
596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636
    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