def __init__(self, basePath, stockName, Retrain):
'''
Constructor
:type self:
'''
if (basePath == None):
self.basePath = self.basePath
else:
self.basePath = basePath
self.stockName = stockName
serializationFile = open(
os.path.join(self.basePath, 'StockToClassifier.bin'), 'rb')
self.StockToClassifier = pickle.load(serializationFile)
#import pdb; pdb.set_trace()
self.usedClassifier = self.StockToClassifier[self.stockName]
# Start the DatasetBuilder
#-------------------------
# Configurations file xml of the dataset builder
configFileDatasetBuilder = os.path.join(self.basePath,
"DatasetBuilder",
"Configurations",
"Configurations.xml")
# The serialization file to save the dataset
datasetSerializationFile = os.path.join(self.basePath,
"DatasetBuilder", "Output",
"dataset.bin")
if Retrain == False:
# The XLSX file name for train set
xlsxTrainFileName = os.path.join(self.basePath, "DatasetBuilder",
"Input", "train")
# Initialize the DatasetBuilder from serialization file
datasetBuilder = DatasetBuilder(configFileDatasetBuilder, [],
datasetSerializationFile)
datasetBuilder.trainSet = datasetBuilder.GetDatasetFromXLSXFile(
xlsxTrainFileName)
self.RunLanguageModel(self.usedClassifier, datasetBuilder.trainSet)
trainFeaturesExtractor = self.RunFeatureExtractor(
self.usedClassifier, datasetBuilder.trainSet)
self.Train(self.usedClassifier, trainFeaturesExtractor, True)
else:
# Initialize the DatasetBuilder from serialization file
datasetBuilder = DatasetBuilder(configFileDatasetBuilder, [],
datasetSerializationFile)
def init_dicts():
configFileDatasetBuilder = os.path.join('DatasetBuilder','Configurations','Configurations.xml')
datasetSerializationFile = os.path.join('DatasetBuilder','Output', 'dataset.bin')
xlsxTrainFileName = os.path.join('DatasetBuilder','Input','sentiment')
datasetBuilder = DatasetBuilder(configFileDatasetBuilder, [], datasetSerializationFile)
datasetBuilder.trainSet = datasetBuilder.GetSentimentDatasetFromXLSXFile(xlsxTrainFileName).values()
words_dict = {'negative':[], 'positive': [], 'neutral': []}
for item in datasetBuilder.trainSet:
words_dict[item['label']] += item['words']
for k in words_dict:
words_dict[k] = list(set(words_dict[k]))
return words_dict
datasetSerializationFile)
# Load the dataset
#datasetBuilder.LoadDataset()
# Update the labels
'''
numFiles = 50
for i in range(numFiles):
print('Updating labels from file ' + xlsxManualLabelsFileName + "_" + str(i + 1) + '...')
datasetBuilder.UpdateManualLabelsFromXLSXFile(xlsxManualLabelsFileName + "_" + str(i + 1), (i + 1)) # This should be done separately when dataset is manually labeled
# Form or load the train/test sets
datasetBuilder.SplitTrainTest()
'''
datasetBuilder.trainSet = datasetBuilder.GetDatasetFromXLSXFile(
xlsxTrainFileName)
# Set the dataset to the train set so that the language model is built from train tweets only
datasetBuilder.dataSet = datasetBuilder.GetDatasetFromXLSXFile(
xlsxTrainFileName)
datasetBuilder.testSet = datasetBuilder.GetDatasetFromXLSXFile(
xlsxTestFileName)
#datasetBuilder.dataSet.extend(datasetBuilder.GetDatasetFromXLSXFile(xlsxTestFileName))
#datasetBuilder.trainSet.extend(datasetBuilder.GetDatasetFromXLSXFile(xlsxTestFileName))
# Configurations file xml of the language model
configFileLanguageModel = ".\\LanguageModel\\Configurations\\Configurations.xml"
langModelLogFile = ".\\LanguageModel\\Output\\language_model.txt"
langModelTxtLoadFile = ".\\LanguageModel\\Output\\language_model_stocks_mix.txt"
stopWordsFileName = ".\\LanguageModel\\Input\\stop_words.txt"
linksDBFile = ".\\LanguageModel\\Output\\links_database.txt"
# The serialization file to save the model
def __init__(self):
'''
Constructor
:type self:
'''
# Start the DatasetBuilder
#-------------------------
# Configurations file xml of the dataset builder
configFileDatasetBuilder = os.path.join('DatasetBuilder','Configurations','Configurations.xml')
# The serialization file to save the dataset
datasetSerializationFile = os.path.join('DatasetBuilder','Output', 'dataset.bin')
# The XLSX file name for train set
xlsxTrainFileName = os.path.join('DatasetBuilder','Input','train')
# Initialize the DatasetBuilder from serialization file
datasetBuilder = DatasetBuilder(configFileDatasetBuilder, [], datasetSerializationFile)
datasetBuilder.trainSet = datasetBuilder.GetDatasetFromXLSXFile(xlsxTrainFileName)
# Configurations file xml of the language model
configFileLanguageModel_lexicon = os.path.join('LanguageModel', 'Configurations', 'Configurations-lexicon.xml')
configFileLanguageModel_Tasi = os.path.join('LanguageModel', 'Configurations', 'Configurations-Tasi.xml')
stopWordsFileName = os.path.join('LanguageModel', 'Input', 'stop_words.txt')
linksDBFile = os.path.join('LanguageModel', 'Output', 'links_database.txt')
# The serialization file to save the model
languageModelSerializationFile = os.path.join('LanguageModel', 'Output', 'language_model.bin')
# Start the LanguageModel:
# Initialize the LanguageModel_Lexicon
self.languageModel_lexicon = LanguageModel(configFileLanguageModel_lexicon, stopWordsFileName, languageModelSerializationFile, linksDBFile, datasetBuilder.trainSet)
self.languageModel_lexicon.BuildLanguageModel()
# Initialize the LanguageModel_Tasi
self.languageModel_Tasi = LanguageModel(configFileLanguageModel_Tasi, stopWordsFileName, languageModelSerializationFile, linksDBFile, datasetBuilder.trainSet)
self.languageModel_Tasi.BuildLanguageModel()
# Configurations file xml of the features extractor
configFileFeaturesExtractor_Lexicon = os.path.join('FeaturesExtractor', 'Configurations', 'Configurations-lexicon.xml')
configFileFeaturesExtractor_Tasi = os.path.join('FeaturesExtractor', 'Configurations', 'Configurations-Tasi.xml')
# The serialization file to save the features
trainFeaturesSerializationFile = os.path.join('FeaturesExtractor', 'Output', 'train_features.bin')
trainLabelsSerializationFile = os.path.join('FeaturesExtractor', 'Output', 'train_labels.bin')
# Start the FeaturesExtractor:
#-----------------------------
# Initialize the FeaturesExtractor _ Lexicon
trainFeaturesExtractor_Lexicon = FeaturesExtractor(configFileFeaturesExtractor_Lexicon, trainFeaturesSerializationFile, trainLabelsSerializationFile, self.languageModel_lexicon, datasetBuilder.trainSet)
trainFeaturesExtractor_Lexicon.ExtractNumTfFeatures()
# Initialize the FeaturesExtractor _ Tasi
trainFeaturesExtractor_Tasi = FeaturesExtractor(configFileFeaturesExtractor_Tasi, trainFeaturesSerializationFile, trainLabelsSerializationFile, self.languageModel_Tasi, datasetBuilder.trainSet)
trainFeaturesExtractor_Tasi.ExtractNumTfFeatures()
# The serialization file to save the features
configFileClassifier_Lexicon = os.path.join('Classifier', 'Configurations', 'Configurations-lexicon.xml')
configFileClassifier_Tasi = os.path.join('Classifier', 'Configurations', 'Configurations-Tasi.xml')
modelSerializationFile = os.path.join('Classifier', 'Output', 'classifier_model.bin')
# Start the Classifier:
#---------------------
print(trainFeaturesExtractor_Tasi.labels[:4])
print([i['label'] for i in trainFeaturesExtractor_Lexicon.dataSet[:4]])
self.classifier_Lexicon = Classifier(configFileClassifier_Lexicon, modelSerializationFile, trainFeaturesExtractor_Lexicon.features, trainFeaturesExtractor_Lexicon.labels, [], [])
self.classifier_Tasi = Classifier(configFileClassifier_Tasi, modelSerializationFile, trainFeaturesExtractor_Tasi.features,
trainFeaturesExtractor_Tasi.labels, [],[])
# Train
self.classifier_Lexicon.Train()
self.classifier_Tasi.Train()
def init(cls, save_path, use_backend=True, pre_stocks=None):
'''
Constructor
:type self:
'''
global stocks
if pre_stocks:
stocks = pre_stocks
for stock in stocks:
print('Buildind model for %s' % stock)
stock_model = {}
# Start the DatasetBuilder
#-------------------------
# Configurations file xml of the dataset builder
configFileDatasetBuilder = os.path.join('DatasetBuilder',
'Configurations',
'Configurations.xml')
# The serialization file to save the dataset
datasetSerializationFile = os.path.join('DatasetBuilder', 'Output',
'dataset.bin')
# The XLSX file name for train set
xlsxTrainFileName = os.path.join('DatasetBuilder', 'Input',
'train')
# Initialize the DatasetBuilder from serialization file
datasetBuilder = DatasetBuilder(configFileDatasetBuilder, [],
datasetSerializationFile)
if use_backend:
datasetBuilder.trainSet = datasetBuilder.GetDatasetFromBackend(
stock)
else:
datasetBuilder.trainSet = datasetBuilder.GetDatasetFromXLSXFile(
xlsxTrainFileName, stock)
if len(datasetBuilder.trainSet) < NMIN_SET:
print("Not enough data: ", len(datasetBuilder.trainSet))
continue
datasetBuilder.trainSet = datasetBuilder.trainSet[NVALID:]
# Configurations file xml of the language model
configFileLanguageModel_lexicon = os.path.join(
'LanguageModel', 'Configurations', 'Configurations-Tasi.xml')
stopWordsFileName = os.path.join('LanguageModel', 'Input',
'stop_words.txt')
linksDBFile = os.path.join('LanguageModel', 'Output',
'links_database.txt')
# The serialization file to save the model
languageModelSerializationFile = os.path.join(
'LanguageModel', 'Output', 'language_model.bin')
# Start the LanguageModel:
# Initialize the LanguageModel_Lexicon
stock_model['languageModel_lexicon'] = LanguageModel(
configFileLanguageModel_lexicon, stopWordsFileName,
languageModelSerializationFile, linksDBFile,
datasetBuilder.trainSet)
stock_model['languageModel_lexicon'].BuildLanguageModel()
# Configurations file xml of the features extractor
configFileFeaturesExtractor_Lexicon = os.path.join(
'FeaturesExtractor', 'Configurations',
'Configurations-Tasi.xml')
# The serialization file to save the features
trainFeaturesSerializationFile = os.path.join(
'FeaturesExtractor', 'Output', 'train_features.bin')
trainLabelsSerializationFile = os.path.join(
'FeaturesExtractor', 'Output', 'train_labels.bin')
# Start the FeaturesExtractor:
#-----------------------------
# Initialize the FeaturesExtractor _ Lexicon
trainFeaturesExtractor_Lexicon = FeaturesExtractor(
configFileFeaturesExtractor_Lexicon,
trainFeaturesSerializationFile, trainLabelsSerializationFile,
stock_model['languageModel_lexicon'], datasetBuilder.trainSet)
trainFeaturesExtractor_Lexicon.ExtractNumTfFeatures(sparse=True)
#print(trainFeaturesExtractor_Lexicon.features[0])
# The serialization file to save the features
configFileClassifier_Lexicon = os.path.join(
'Classifier', 'Configurations', 'Configurations-Tasi.xml')
modelSerializationFile = os.path.join('Classifier', 'Output',
'classifier_model.bin')
# Start the Classifier:
#---------------------
stock_model['classifier_Lexicon'] = Classifier(
configFileClassifier_Lexicon, modelSerializationFile,
trainFeaturesExtractor_Lexicon.sparse_features,
trainFeaturesExtractor_Lexicon.labels, [], [])
#stock_model['classifier_Lexicon'] = Classifier(configFileClassifier_Lexicon, modelSerializationFile, trainFeaturesExtractor_Lexicon.features, trainFeaturesExtractor_Lexicon.labels, [], [])
#print(trainFeaturesExtractor_Lexicon.labels[:4])
#print([i['label'] for i in trainFeaturesExtractor_Lexicon.dataSet[:4]])
# Train
stock_model['classifier_Lexicon'].Train()
stock_model['training_samples'] = len(datasetBuilder.trainSet)
cls.save(save_path, stock, stock_model)
print("----------------------------------------------------")