🙇♂️
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
y = readability_scores | |
N = len(y) | |
x = [i+1 for i in range(N)] | |
width = 1/1.5 | |
mini = min(readability_scores) | |
maxi = max(readability_scores) | |
pylab.title("Readability Comparison of text") | |
pylab.xlabel("Book") |
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
import sys | |
import time | |
import glob | |
import codecs | |
import matplotlib.pyplot as plt | |
import requests | |
# Books present | |
books = sorted(glob.glob("data/harrypotter/*.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
from happytransformer import HappyGeneration, GENTrainArgs | |
gpt_neo = HappyGeneration("GPT-Neo", "EleutherAI/gpt-neo-125M") | |
train_args = GENTrainArgs(num_train_epochs=1, learning_rate=2e-05, batch_size=2) | |
gpt_neo.train("train.txt", args=train_args) |
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
from happytransformer import GENSettings | |
top_k_sampling_settings = GENSettings(do_sample=True, top_k=50, max_length=30, min_length=10) | |
output_top_k_sampling = gpt_neo.generate_text("Iphone ", args=top_k_sampling_settings) | |
print (output_top_k_sampling.text) | |
# iphones are very good for keeping track of calls |
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
from happytransformer import HappyGeneration | |
gpt_neo = HappyGeneration(model_type="GPT-NEO", model_name="EleutherAI/gpt-neo-125M") | |
print (gpt_neo) |
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
from transformers import AutoModelForQuestionAnswering, AutoTokenizer | |
from transformers_interpret import QuestionAnsweringExplainer | |
tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad") | |
model = AutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad") | |
qa_explainer = QuestionAnsweringExplainer( | |
model, | |
tokenizer, | |
) |
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
from transformers_interpret import SequenceClassificationExplainer | |
sample_text = """A very classy nice restaurant. A warm welcoming, followed by an excellent service, with a lot of attention to details on order to please you.""" | |
multiclass_explainer = SequenceClassificationExplainer(model=model, tokenizer=tokenizer) | |
word_attributions = multiclass_explainer(text=sample_text) | |
print (word_attributions) |
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
from transformers import AutoModelForSequenceClassification, AutoTokenizer | |
tokenizer = AutoTokenizer.from_pretrained("sampathkethineedi/industry-classification") | |
model = AutoModelForSequenceClassification.from_pretrained( | |
"sampathkethineedi/industry-classification" | |
) | |
print (tokenizer, model) |
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
""" | |
@author: Prakhar Mishra | |
""" | |
import streamlit as st | |
from easynmt import EasyNMT | |
model = EasyNMT('opus-mt') | |
LANGS = [('en', 'es'), ('en', 'fr'), ('en', 'de'), ('en', 'ar'), ('en', 'tr'), ('en', 'ko')] |
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
class TrieNode: | |
def __init__(self): | |
self.child = {} | |
self.last = False |
NewerOlder