import sys

sys.path.append('../..')
from textgen import GptModel


def generate_prompt(instruction):
  return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:{instruction}\n\n### Response:"""


model = GptModel("llama", "decapoda-research/llama-7b-hf", peft_name="ziqingyang/chinese-alpaca-lora-7b")
predict_sentence = generate_prompt("问：用一句话描述地球为什么是独一无二的。\n答：")
r = model.predict([predict_sentence])
print(r)  # ['地球是唯一一颗拥有生命的行星。']

import argparse
from loguru import logger
import sys

sys.path.append('../..')
from textgen.seq2seq.conv_seq2seq_model import ConvSeq2SeqModel


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--train_file', default='../data/zh_dialog.tsv', type=str, help='Training data file')
    parser.add_argument('--do_train', action='store_true', help='Whether to run training.')
    parser.add_argument('--do_predict', action='store_true', help='Whether to run predict.')
    parser.add_argument('--output_dir', default='./outputs/convseq2seq_zh/', type=str, help='Model output directory')
    parser.add_argument('--max_seq_length', default=50, type=int, help='Max sequence length')
    parser.add_argument('--num_epochs', default=200, type=int, help='Number of training epochs')
    parser.add_argument('--batch_size', default=32, type=int, help='Batch size')
    args = parser.parse_args()
    logger.info(args)

    if args.do_train:
        logger.info('Loading data...')
        model = ConvSeq2SeqModel(epochs=args.num_epochs, batch_size=args.batch_size,
                                 model_dir=args.output_dir, max_length=args.max_seq_length)
        model.train_model(args.train_file)
        print(model.eval_model(args.train_file))

    if args.do_predict:
        model = ConvSeq2SeqModel(epochs=args.num_epochs, batch_size=args.batch_size,
                                 model_dir=args.output_dir, max_length=args.max_seq_length)
        sentences = ["什么是ai", "你是什么类型的计算机", "你知道热力学吗"]
        print("inputs:", sentences)
        print('outputs:', model.predict(sentences))


if __name__ == '__main__':
    main()

import argparse
from loguru import logger
import pandas as pd
import sys

sys.path.append('../..')
from textgen.t5 import T5Model


def load_data(file_path):
    data = []
    with open(file_path, 'r', encoding='utf-8') as f:
        for line in f:
            line = line.strip('\n')
            terms = line.split('\t')
            if len(terms) == 2:
                data.append(['QA', terms[0], terms[1]])
            else:
                logger.warning(f'line error: {line}')
    return data


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--train_file', default='../data/zh_dialog.tsv', type=str, help='Training data file')
    parser.add_argument('--model_type', default='t5', type=str, help='Transformers model type')
    parser.add_argument('--model_name', default='Langboat/mengzi-t5-base', type=str, help='Transformers model or path')
    parser.add_argument('--do_train', action='store_true', help='Whether to run training.')
    parser.add_argument('--do_predict', action='store_true', help='Whether to run predict.')
    parser.add_argument('--output_dir', default='./outputs/mengzi_t5_zh/', type=str, help='Model output directory')
    parser.add_argument('--max_seq_length', default=50, type=int, help='Max sequence length')
    parser.add_argument('--num_epochs', default=10, type=int, help='Number of training epochs')
    parser.add_argument('--batch_size', default=32, type=int, help='Batch size')
    args = parser.parse_args()
    logger.info(args)

    if args.do_train:
        logger.info('Loading data...')
        # train_data: Pandas DataFrame containing the 3 columns - `prefix`, `input_text`, `target_text`.
        #   - `prefix`: A string indicating the task to perform. (E.g. `"question"`, `"stsb"`)
        #   - `input_text`: The input text. `prefix` is prepended to form the full input. (<prefix>: <input_text>)
        #   - `target_text`: The target sequence
        train_data = load_data(args.train_file)
        logger.debug('train_data: {}'.format(train_data[:10]))
        train_df = pd.DataFrame(train_data, columns=["prefix", "input_text", "target_text"])

        eval_data = load_data(args.train_file)[:10]
        eval_df = pd.DataFrame(eval_data, columns=["prefix", "input_text", "target_text"])

        model_args = {
            "reprocess_input_data": True,
            "overwrite_output_dir": True,
            "max_seq_length": args.max_seq_length,
            "train_batch_size": args.batch_size,
            "num_train_epochs": args.num_epochs,
            "save_eval_checkpoints": False,
            "save_model_every_epoch": False,
            "evaluate_generated_text": True,
            "evaluate_during_training": True,
            "evaluate_during_training_verbose": True,
            "use_multiprocessing": True,
            "save_best_model": True,
            "output_dir": args.output_dir,
            "use_early_stopping": True,
        }
        # model_type: t5  model_name: Langboat/mengzi-t5-base
        model = T5Model(args.model_type, args.model_name, args=model_args)

        def count_matches(labels, preds):
            logger.debug(f"labels: {labels[:10]}")
            logger.debug(f"preds: {preds[:10]}")
            match = sum([1 if label == pred else 0 for label, pred in zip(labels, preds)])
            logger.debug(f"match: {match}")
            return match

        model.train_model(train_df, eval_data=eval_df, matches=count_matches)
        print(model.eval_model(eval_df, matches=count_matches))

    if args.do_predict:
        model = T5Model(args.model_type, args.output_dir)
        sentences = ["什么是ai", "你是什么类型的计算机", "你知道热力学吗"]
        print("inputs:", sentences)
        print("outputs:", model.predict(sentences))


if __name__ == '__main__':
    main()

import sys

sys.path.append('..')
from textgen.augment import TextAugment

if __name__ == '__main__':
    docs = ['主要研究机器学习、深度学习、计算机视觉、智能对话系统相关内容',
            '晚上肚子好难受',
            '你会武功吗，我不会',
            '组装标题质量受限于广告主自提物料的片段质量，且表达丰富度有限',
            ]
    m = TextAugment(sentence_list=docs)
    a = docs[0]
    print(a)

    b = m.augment(a, aug_ops='random-0.2')
    print('random-0.2:', b)

    b = m.augment(a, aug_ops='insert-0.2')
    print('insert-0.2:', b)

    b = m.augment(a, aug_ops='delete-0.2')
    print('delete-0.2:', b)

    b = m.augment(a, aug_ops='tfidf-0.2')
    print('tfidf-0.2:', b)

    b = m.augment(a, aug_ops='mix-0.2')
    print('mix-0.2:', b)

import os
import sys

sys.path.append('..')
from textgen.unsup_generation import TglsModel, load_list

pwd_path = os.path.abspath(os.path.dirname(__file__))

samples = load_list(os.path.join(pwd_path, './data/ecommerce_comments.txt'))
docs_text = [
    ["挺好的，速度很快，也很实惠，不知效果如何",
     "产品没得说，买了以后就降价，心情不美丽。",
     "刚收到，包装很完整，不错",
     "发货速度很快，物流也不错，同一时间买的两个东东，一个先到一个还在路上。这个水水很喜欢，不过盖子真的开了。盖不牢了现在。",
     "包装的很好，是正品",
     "被种草兰蔻粉水三百元一大瓶囤货，希望是正品好用，收到的时候用保鲜膜包裹得严严实实，只敢买考拉自营的护肤品",
     ],
    ['很温和，清洗的也很干净，不油腻，很不错，会考虑回购，第一次考拉买护肤品，满意',
     '这款卸妆油我会无限回购的。即使我是油痘皮，也不会闷痘，同时在脸部按摩时，还能解决白头的脂肪粒的问题。用清水洗完脸后，非常的清爽。',
     '自从用了fancl之后就不用其他卸妆了，卸的舒服又干净',
     '买贵了，大润发才卖79。9。',
     ],
    samples
]
m = TglsModel(docs_text)
r = m.generate(samples[:500])
print('size:', len(r))
for review in r:
    print('\t' + review)