def compare_model():
index = Index()
models = [Vectoriel(index, SimpleWeighter(index), normalized=True),
Vectoriel(index, BasicWeighter(index), normalized=True),
Vectoriel(index, ThirdWeighter(index), normalized=False),
Vectoriel(index, FourthWeighter(index), normalized=False),
Okapi(index),
LanguageModel(index, .7),
HITS(index, seeds=3, k=5),
PageRank(index, seeds=3, k=5)
]
names = ['Vectoriel1', 'Vectoriel2','Vectoriel3','Vectoriel4','Okapi', 'Language', 'HITS', 'PageRank']
models_scores = compare_models(names, models)
fig = plt.figure(figsize=(10,8))
colors=iter(cm.hot(np.linspace(0,.7,len(names))))
x = [s['AveragePrecision']['mean'] for s in scores.values()]
plt.xticks(x, scores.keys())
plt.bar(x, models_scores.values(), alpha=.4, color=c)
# for n, s in models_scores.items():
# color = next(colors)
# y = s['PrecisionRecall']['mean']
# x = list(range(len(y)))
# plt.plot(x, y, color=color, label=n)
# plt.legend()
plt.savefig('plot/models_comparison_precision_eval.png')
class FeaturerVectoriel1(Featurer):
def __init__(self, index):
super(FeaturerVectoriel1, self).__init__(index)
self.model = Vectoriel(index, SimpleWeighter(index), normalized=True)
self.features = {}
def get_query_scores(self, query):
ranks = self.model.getRanking(query.getText())
return [(d, r / float(self.documents_count)) for (d, r) in ranks]
def get_features(self, idDoc, query):
queryId = query.getId()
if queryId not in self.features.keys():
self.features[queryId] = self.get_query_scores(query)
return [s for (d, s) in self.features[queryId] if d == idDoc][0]
def __init__(self, index):
super(FeaturerVectoriel1, self).__init__(index)
self.model = Vectoriel(index, SimpleWeighter(index), normalized=True)
self.features = {}
def __init__(self, index):
super(FeaturerVectoriel4, self).__init__(index)
self.model = Vectoriel(index, FourthWeighter(index), normalized=False)
self.features = {}