Classification

class Manteia.Classification.Classification(model=None, documents_train=[], labels_train=[], documents_test=[], labels_test=[], process_classif=False, verbose=True)

This is the class to classify text in categorie a NLP task.

Args:

model_name (string, optional, defaults to ‘bert’):

give the name of a model.

documents (list, optional, defaults to None):

A list of documents.

labels (float, optional, defaults to None):

A list of labels.

Example 1:

from Manteia.Classification import Classification 
from Manteia.Model import Model 

documents = ['What should you do before criticizing Pac-Man? WAKA WAKA WAKA mile in his shoe.'
,'What did Arnold Schwarzenegger say at the abortion clinic? Hasta last vista, baby.',]

labels = ['funny','not funny']

model = Model(model_name ='roberta')
cl=Classification(model,documents,labels,process_classif=True)

>>>Training complete!
load_model()

Example 3:

from Manteia.Classification import Classification 
from Manteia.Preprocess import list_labels 

documents = ['What should you do before criticizing Pac-Man? WAKA WAKA WAKA mile in his shoe.'
,'What did Arnold Schwarzenegger say at the abortion clinic? Hasta last vista, baby.',]

labels = ['funny','not funny']

cl=Classification(documents_train = documents,labels_train = labels)
cl.list_labels     = list_labels(labels)
cl.load_model()
cl.model.devices()
print(cl.predict(documents[:2]))
>>>['funny', 'funny']
predict(documents)

This is the description of the predict function.

Args:

documents (list, optional, defaults to None):

A list of documents (str).

Example 5:

from Manteia.Classification import Classification 
from Manteia.Model import Model 

documents = ['What should you do before criticizing Pac-Man? WAKA WAKA WAKA mile in his shoe.'
,'What did Arnold Schwarzenegger say at the abortion clinic? Hasta last vista, baby.',]

labels = ['funny','not funny']

model = Model(model_name ='roberta')
cl=Classification(model,documents,labels,process_classif=True)
print(cl.predict(documents[:2]))

>>>['funny', 'funny']
process()

Example 2:

from Manteia.Classification import Classification 
from Manteia.Preprocess import list_labels 
from Manteia.Model import Model 

documents = ['What should you do before criticizing Pac-Man? WAKA WAKA WAKA mile in his shoe.'
,'What did Arnold Schwarzenegger say at the abortion clinic? Hasta last vista, baby.',]

labels = ['funny','not funny']

model = Model(model_name ='roberta')
cl=Classification(model,documents,labels)
cl.list_labels     = list_labels(labels)
cl.process()
print(cl.predict(documents[:2]))
>>>['funny', 'funny']
process_text()

This is the description of the process_text function.

Example 4:

from Manteia.Classification import Classification 
from Manteia.Preprocess import list_labels 

documents = ['What should you do before criticizing Pac-Man? WAKA WAKA WAKA mile in his shoe.'
,'What did Arnold Schwarzenegger say at the abortion clinic? Hasta last vista, baby.',]

labels = ['funny','not funny']

cl=Classification(documents_train = documents,labels_train = labels)
cl.list_labels     = list_labels(labels)
cl.load_model()
dt_train ,dt_validation=cl.process_text()
cl.model.configuration(dt_train)
cl.model.fit(dt_train,dt_validation)

>>>Training complete!

A complete example

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
     from Manteia.Classification import Classification
     from Manteia.Preprocess import Preprocess
     from Manteia.Dataset import Dataset

     def main(args):

             ds             = Dataset('20newsgroups')
             documents      = ds.documents_train
             labels         = ds.labels_train
             pp             = Preprocess(documents=documents,labels=labels,nb_sample=500)
             documents      = pp.documents
             labels         = pp.labels
             cl             = Classification(documents_train=documents,labels_train=labels)
             cl.list_labels = pp.list_labels

             cl.load_model()
             dt_train ,dt_validation = cl.process_text()
             cl.model.configuration(dt_train)
             cl.model.fit(dt_train,dt_validation)

             print(cl.predict(documents[:5]))

             return 0

     if __name__ == '__main__':
             import sys
             sys.exit(main(sys.argv))