-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
21 changed files
with
1,280 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,37 @@ | ||
Metadata-Version: 1.1 | ||
Name: Manteia | ||
Version: 0.0.10 | ||
Summary: deep learning,NLP,classification,text,bert,distilbert,albert,xlnet,roberta,gpt2 | ||
Home-page: https://github.com/ym001/Manteia | ||
Author: Yves Mercadier | ||
Author-email: manteia.ym001@gmail.com | ||
License: UNKNOWN | ||
Description: Manteia - proclaim the good word | ||
================================================================ | ||
|
||
This module proclaims the good word. May they | ||
regain total freedom of artificial thought towards a new age | ||
reminiscent. | ||
|
||
You can install it with pip: | ||
|
||
pip install Manteia | ||
|
||
Example of use: | ||
|
||
>>> from Manteia.Classification import Classification | ||
>>> # Initializing a list of texts,labels | ||
>>> documents=['a text','text b'] | ||
>>> labels=['a','b'] | ||
>>> Classification(documents,labels) | ||
|
||
This code is licensed under MIT. | ||
|
||
Platform: UNKNOWN | ||
Classifier: Programming Language :: Python | ||
Classifier: Development Status :: 1 - Planning | ||
Classifier: License :: OSI Approved :: MIT License | ||
Classifier: Natural Language :: English | ||
Classifier: Operating System :: OS Independent | ||
Classifier: Programming Language :: Python :: 3.6 | ||
Classifier: Topic :: Communications |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,18 @@ | ||
MANIFEST.in | ||
README.md | ||
setup.cfg | ||
setup.py | ||
Manteia/Classification.py | ||
Manteia/Generation.py | ||
Manteia/Model.py | ||
Manteia/Preprocess.py | ||
Manteia/Statistic.py | ||
Manteia/Task.py | ||
Manteia/Visualisation.py | ||
Manteia/__init__.py | ||
Manteia.egg-info/PKG-INFO | ||
Manteia.egg-info/SOURCES.txt | ||
Manteia.egg-info/dependency_links.txt | ||
Manteia.egg-info/entry_points.txt | ||
Manteia.egg-info/requires.txt | ||
Manteia.egg-info/top_level.txt |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,5 @@ | ||
[console_scripts] | ||
Manteia-classification = Manteia.Manteia:makeClassification | ||
Manteia-data = Manteia.Manteia:readData | ||
Manteia-test = Manteia.Manteia:testManteia | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
matplotlib==3.2.1 | ||
transformers==2.8.0 | ||
pandas==1.0.3 | ||
torch==1.5.0 | ||
nltk==3.4.5 | ||
numpy==1.18.1 | ||
scikit_learn==0.22.2.post1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1 @@ | ||
Manteia |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,70 @@ | ||
|
||
import numpy as np | ||
import random | ||
import pandas as pd | ||
import sklearn | ||
from sklearn.model_selection import train_test_split,KFold | ||
import time | ||
import datetime | ||
import gc | ||
############ | ||
from .Model import * | ||
from .Preprocess import Preprocess | ||
|
||
class Classification: | ||
r""" | ||
This is the class to classify text in categorie a NLP task. | ||
Args: | ||
model_name (:obj:`string`, optional, defaults to 'bert'): | ||
give the name of a model. | ||
documents (:obj:`list`, optional, defaults to None): | ||
A list of documents. | ||
labels (:obj:`float`, optional, defaults to None): | ||
A list of labels. | ||
Example:: | ||
from Manteia.Classification import Classification | ||
# Initializing a list of texts,labels | ||
documents=['a text','text b'] | ||
labels=['a','b'] | ||
Classification(documents,labels) | ||
Attributes: | ||
""" | ||
def __init__(self,model_name ='bert',documents = None,labels = None): | ||
self.MAX_SEQ_LEN = 64 | ||
self.model_name = model_name | ||
|
||
if documents!=None and labels!=None: | ||
pp = Preprocess(documents,labels) | ||
self.list_labels = pp.list_labels | ||
self.model = Model(num_labels=len(pp.list_labels)) | ||
self.model.load() | ||
|
||
train_text, validation_text, train_labels, validation_labels = train_test_split(pp.documents, pp.labels, random_state=2018, test_size=0.1) | ||
|
||
train_ids,train_masks = encode_text(train_text,self.model.tokenizer,self.MAX_SEQ_LEN) | ||
validation_ids,validation_masks = encode_text(validation_text,self.model.tokenizer,self.MAX_SEQ_LEN) | ||
train_labels = encode_label(train_labels,pp.list_labels) | ||
validation_labels = encode_label(validation_labels,pp.list_labels) | ||
|
||
dt_train = Create_DataLoader_train(train_ids,train_masks,train_labels) | ||
dt_validation = Create_DataLoader_train(validation_ids,validation_masks,validation_labels) | ||
|
||
self.model.configuration(dt_train) | ||
self.model.fit(dt_train,dt_validation) | ||
def test(self): | ||
return "Classification Mantéïa." | ||
|
||
def predict(self,documents): | ||
inputs,masks = encode_text(documents,self.model.tokenizer) | ||
predict_inputs = totensors(inputs) | ||
predict_masks = totensors(masks) | ||
dt = Create_DataLoader_predict(predict_inputs,predict_masks) | ||
prediction = self.model.predict(dt) | ||
prediction = decode_label(prediction,self.list_labels) | ||
return prediction | ||
|
||
|
||
|
||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,58 @@ | ||
|
||
import numpy as np | ||
import random | ||
import pandas as pd | ||
import sklearn | ||
from sklearn.model_selection import train_test_split,KFold | ||
import time | ||
import datetime | ||
import gc | ||
############ | ||
from .Model import * | ||
from .Preprocess import Preprocess | ||
|
||
class Generation: | ||
r""" | ||
This is the class to gnerate text in categorie a NLP task. | ||
Args: | ||
model_name (:obj:`string`, optional, defaults to 'bert'): | ||
give the name of a model. | ||
documents (:obj:`list`, optional, defaults to None): | ||
A list of documents. | ||
labels (:obj:`float`, optional, defaults to None): | ||
A list of labels. | ||
Example:: | ||
from Manteia.Classification import Classification | ||
# Initializing a list of texts,labels | ||
documents=['a text','text b'] | ||
labels=['a','b'] | ||
Classification(documents,labels) | ||
Attributes: | ||
""" | ||
def __init__(self,model_name ='gpt2-medium',documents = None,labels = None): | ||
|
||
|
||
model = Model(model_name =model_name) | ||
model.load() | ||
text_loader = Create_DataLoader_generation(documents) | ||
model.BATCH_SIZE = 16 | ||
model.EPOCHS = 10 | ||
model.LEARNING_RATE = 3e-5 | ||
model.WARMUP_STEPS = 500 | ||
model.MAX_SEQ_LEN = 400 | ||
|
||
model.fit_generation(text_loader) | ||
|
||
output = model.predict_generation('joke') | ||
output_text = decode_text(output,model.tokenizer) | ||
print(output_text) | ||
|
||
|
||
def test(self): | ||
return "Generation Mantéïa." | ||
|
||
|
||
|
||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,72 @@ | ||
#!/usr/bin/env python | ||
# -*- coding: utf-8 -*- | ||
# | ||
# core.py | ||
# | ||
# Copyright 2020 Yves <yves@mercadier> | ||
# | ||
# This program is free software; you can redistribute it and/or modify | ||
# it under the terms of the GNU General Public License as published by | ||
# the Free Software Foundation; either version 2 of the License, or | ||
# (at your option) any later version. | ||
# | ||
# This program is distributed in the hope that it will be useful, | ||
# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
# GNU General Public License for more details. | ||
# | ||
# You should have received a copy of the GNU General Public License | ||
# along with this program; if not, write to the Free Software | ||
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, | ||
# MA 02110-1301, USA. | ||
# | ||
# | ||
|
||
""" | ||
This module proclaims the good word. May they | ||
regain total freedom of artificial thought towards a new age | ||
reminiscent. | ||
You can install it with pip: | ||
pip install Manteia | ||
Example of use: | ||
>>> from Manteia import testManteia | ||
>>> testManteia () | ||
This code is licensed under MIT. | ||
""" | ||
__all__ = ['testManteia','testData','testClassification'] | ||
|
||
from .Preprocess import Preprocess | ||
from .Classification import Classification | ||
from .Statistic import Statistic | ||
from .Visualisation import Visualisation | ||
from .Model import Model | ||
|
||
class Manteia: | ||
def __init__(self,documents=None,labels=None,task='classification'): | ||
if documents!=None: | ||
self.data=Data(documents,labels) | ||
if task=='classification': | ||
self.classification=Classification(data=self.data) | ||
def testManteia(): | ||
return "Hello, Mantéïa is alive." | ||
|
||
def testManteia(): | ||
print ("Hello, Mantéïa is alive.") | ||
|
||
def testData(): | ||
documents=[' ,;:123test car','test houses'] | ||
labels=['1','0'] | ||
mant=Data(documents,labels) | ||
print(mant.data.list_labels) | ||
print(mant.data.get_df()) | ||
|
||
def testClassification(): | ||
documents=['test car','test house'] | ||
labels=['1','0'] | ||
mant=Classification(documents,labels) | ||
|
Oops, something went wrong.