class Factory(object):
def __init__(self, config):
self.config = config
self.analyzer = Analyzer(self.config)
self.classify = Classify(config)
@staticmethod
def get_all_column_data(file):
"""
Combine all column data into a single feature matrix
:param file:
:return:
"""
# Get all the feature matrices
title_matrix, response_vector = f.analyze_column_data(file, 'title')
abstract_matrix, response_vector = f.analyze_column_data(
file, 'abstract')
claims_matrix, response_vector = f.analyze_column_data(file, 'claims')
# Get them all together
feature_matrix = hstack([title_matrix, abstract_matrix])
feature_matrix = hstack([feature_matrix, claims_matrix])
return feature_matrix, response_vector
def analyze_column_data(self, filename, column_name):
"""
Create the feature model and matrix for the abstract column
:param filename:
:return:
"""
self.analyzer.load_patent_data(filename)
self.analyzer.extract_data(column_name)
n_grams = 1
self.analyzer.extract_features(n_grams, column_name)
return self.analyzer.feature_matrix, self.analyzer.response
def compute_heuristics(self, filename, column_name):
"""
Figure out what words make up the groups in the shit
:param filename:
:return:
"""
self.analyze_column_data(filename, column_name)
self.analyzer.heuristics(column_name)
def full_train(self):
"""
GET THE CLASSIFIER TRAINED
:return:
"""
# self.classify.feature_selection()
self.classify.classifier_selection()
# self.classify.optimize_classifier()
self.classify.train()
self.classify.save_classifier()
def evaluate(self, title, abstract, claims):
"""
Predict group of a single entry
:param abstract:
:return:
"""
self.analyzer.load_model('title')
title_vector = self.analyzer.transform([title])
self.analyzer.load_model('abstract')
abstract_vector = self.analyzer.transform([abstract])
self.analyzer.load_model('claims')
claims_vector = self.analyzer.transform([claims])
feature_vector = hstack([title_vector, abstract_vector])
feature_vector = hstack([feature_vector, claims_vector])
return feature_vector
def predict(self, feature_vector):
"""
Predict class based on feature vector input
:param feature_vector:
:return:
"""
group = self.classify.predict(feature_vector)
return group
#-*- coding:utf-8 -*-
from classify import Classify
import numpy as np
import sys
reload(sys)
sys.setdefaultencoding("utf8")
if __name__ == "__main__":
X_train = np.array([
u"我想听张学友的歌", u"周杰伦的龙卷风", u"鹿晗有什么歌好听", u"姚明打篮球好厉害", u"张继科会打乒乓球",
u"詹姆士是体育明星"
])
Y_train = np.array([1, 1, 1, 2, 2, 2])
Test_data = [u"我想听薛之谦的演员", "邓亚萍是体育明星", "刘翔是体育明星"]
Model = Classify()
Model.load_W2V_Model("word2vec.model")
Model.train(X_train, Y_train)
Model.predict(Test_data)
Model.save_NBmodel("NB.model")
del Model
NBmodel_test = Classify()
NBmodel_test.load_NBmodel("NB.model")
NBmodel_test.predict(Test_data)
del NBmodel_test
