这是用于酒店评论（例如正面或负面）的情感分析代码示例。我使用 pandas、transformers、datasets、turkish_lm_tuner 库。首先，我认为路径名称（C:\Users\Ata Onur

这是用于酒店评论（例如正面或负面）的情感分析代码示例。我使用了 pandas、transformers、datasets 和 turkish_lm_tuner 库。首先，我认为路径名称（C:\Users\Ata Onur Özdemir，所以是“Ö”字母）和我已更改，但它没有修复，输出给出相同的错误。其次，我在输出文件夹中创建了 init .py，但这种方式给出了相同的错误。而且我在环境变量中定义了路径，但相同的错误再次出现。我搜索了 google 和 ，但我找不到任何方法，我尝试了很多方法，但我没有找到。请帮助我 :) 我搜索了 google 和 ，但我找不到任何方法，我尝试了很多方法，但我没有找到。请帮助我 :)

import os
import pandas as pd
from transformers import AutoTokenizer
from datasets import Dataset
from turkish_lm_tuner import TrainerForClassification, EvaluatorForClassification

# Load the data
data = pd.read_csv('../Emotion_Detection/Hotel_readablee.csv')

# Define the output directory
output_dir = 'C:\\Users\\Ata Onur Özdemir\\PycharmProjects\\Emotion_Detection\\output'

# Check if the output directory exists
if os.path.exists(output_dir):
    # Check the contents of the directory
    print(f"Contents of {output_dir} directory:")
    print(os.listdir(output_dir))
    
    # Rename the directory
    new_output_dir = output_dir + "_old"
    os.rename(output_dir, new_output_dir)
    print(f"{output_dir} directory has been renamed to {new_output_dir}.")
    
    # Create a new output directory
    os.makedirs(output_dir)
    print(f"New {output_dir} directory created.")
else:
    # If the directory does not exist, create it
    os.makedirs(output_dir)
    print(f"{output_dir} directory created.")

# Initialize the tokenizer
model_name = "boun-tabi-LMG/TURNA"
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the CustomDatasetProcessor class and other necessary steps
class CustomDatasetProcessor:
    def __init__(self, tokenizer, max_input_length):
        self.tokenizer = tokenizer
        self.max_input_length = max_input_length

    def load_and_preprocess_data(self, data):
        dataset = Dataset.from_pandas(data)

        def preprocess_function(examples):
            # Convert each review text to string type
            positive_reviews = [str(review) for review in examples['Positive_Review_Tr']]
            negative_reviews = [str(review) for review in examples['Negative_Review_Tr']]

            # Use the tokenizer correctly
            tokenized_reviews = self.tokenizer(
                positive_reviews,
                negative_reviews,
                truncation=True,
                padding='max_length',
                max_length=self.max_input_length,
                return_tensors='pt'  # Return PyTorch tensors
            )

            return tokenized_reviews

        tokenized_dataset = dataset.map(preprocess_function, batched=True)
        return tokenized_dataset

# Initialize the dataset processor
dataset_processor = CustomDatasetProcessor(tokenizer, max_input_length=2048)

# Split the data into training, validation, and test sets
train_data = data.sample(frac=0.8, random_state=42)
remaining_data = data.drop(train_data.index)
validation_data = remaining_data.sample(frac=0.5, random_state=42)
test_data = remaining_data.drop(validation_data.index)

# Preprocess the datasets
train_dataset = dataset_processor.load_and_preprocess_data(train_data)
eval_dataset = dataset_processor.load_and_preprocess_data(validation_data)
test_dataset = dataset_processor.load_and_preprocess_data(test_data)

# Training parameters
training_params = {
    'num_train_epochs': 10,
    'per_device_train_batch_size': 4,
    'per_device_eval_batch_size': 4,
    'output_dir': output_dir,
    'evaluation_strategy': 'epoch',
    'save_strategy': 'epoch',
}

# Optimizer parameters
optimizer_params = {
    'optimizer_type': 'adafactor',
    'scheduler': False,
}

# Test parameters
test_params = {
    'per_device_eval_batch_size': 4,
    'output_dir': output_dir,
}

num_labels = 4  # Assuming you are performing binary classification

# Initialize TrainerForClassification
model_trainer = TrainerForClassification(
    model_name=model_name,
    num_labels=num_labels,
    task='classification',
    optimizer_params=optimizer_params,
    training_params=training_params,
    model_save_path="hotel_reviews_classification_model",
    test_params=test_params
)

# Train and evaluate the model
trainer, model = model_trainer.train_and_evaluate(train_dataset, eval_dataset, test_dataset)

# Save the trained model and tokenizer
model.save_pretrained("hotel_reviews_classification_model")
tokenizer.save_pretrained("hotel_reviews_classification_model")

# Evaluate the model using EvaluatorForClassification
evaluator = EvaluatorForClassification(
    model_save_path="hotel_reviews_classification_model",
    model_name=model_name,
    task='classification',
    test_params=test_params,
    num_labels=num_labels
)

# Evaluate the model on the test dataset
results = evaluator.evaluate_model(test_dataset)

# Convert the results to a DataFrame
results_df = pd.DataFrame(results)

# Save the results to a new CSV file
results_df.to_csv('evaluation_results.csv', index=False)
print("Evaluation results saved to evaluation_results.csv.")

# Check the current working directory
print("Current Working Directory:", os.getcwd())

系统出现此错误：

Traceback (most recent call last):
  File "C:\Users\Ata Onur Özdemir\PycharmProjects\Emotion_Detection\main.py", line 101, in <module>
    trainer, model = model_trainer.train_and_evaluate(train_dataset, eval_dataset, test_dataset)
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\turkish_lm_tuner\trainer.py", line 195, in train_and_evaluate
    trainer.train()
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\transformers\trainer.py", line 1885, in train
    return inner_training_loop(
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\transformers\trainer.py", line 2147, in _inner_training_loop
    self.control = self.callback_handler.on_train_begin(args, self.state, self.control)
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\transformers\trainer_callback.py", line 454, in on_train_begin
    return self.call_event("on_train_begin", args, state, control)
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\transformers\trainer_callback.py", line 498, in call_event
    result = getattr(callback, event)(
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\transformers\integrations\integration_utils.py", line 629, in on_train_begin
    self._init_summary_writer(args, log_dir)
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\transformers\integrations\integration_utils.py", line 615, in _init_summary_writer
    self.tb_writer = self._SummaryWriter(log_dir=log_dir)
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\torch\utils\tensorboard\writer.py", line 249, in __init__
    self._get_file_writer()
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\torch\utils\tensorboard\writer.py", line 281, in _get_file_writer
    self.file_writer = FileWriter(
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\torch\utils\tensorboard\writer.py", line 75, in __init__
    self.event_writer = EventFileWriter(
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\tensorboard\summary\writer\event_file_writer.py", line 72, in __init__
    tf.io.gfile.makedirs(logdir)
  File "C:\Users\Ata Onur Özdemir\venv\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 513, in recursive_create_dir_v2
    _pywrap_file_io.RecursivelyCreateDir(compat.path_to_bytes(path))
tensorflow.python.framework.errors_impl.FailedPreconditionError: C:\Users\Ata Onur Özdemir\PycharmProjects\Emotion_Detection\output is not a directory

D:\TEMP>tree PycharmProjects文件夹路径列表卷序列号为 A544-D3FBD:\TEMP\PYCHARMPROJECTS路径无效 - \TEMP\PYCHARMPROJECTS不存在子文件夹

以下是我测试过的内容：function testRounding() { var order = { size1：0.07529999999999999，size2：0.07529999999999999 }; order.size1 = order.size1.roundDecimal(4); order.size2.roundDecimal(...

以下是我测试过的内容：

function testRounding() {
  var order = { size1: 0.07529999999999999, size2: 0.07529999999999999 };
  order.size1 = order.size1.roundDecimal(4);
  order.size2.roundDecimal(4);
  Logger.log(order.size1); //outputs 0.0753
  Logger.log(order.size2); //outputs 0.07529999999999999 but desired output is 0.0753
}

Number.prototype.roundDecimal = function (place) {
  var mult = 1;
  for (var i = 1; i < place; i++) {
    mult = mult * 10;
  }
  return Math.round(this * 10 * mult) / (10 * mult);
}

我从记录器输出中可以看到该方法有效，但不会更改它所应用的对象，除非像我对 size1 所做的那样故意覆盖它。我宁愿不必这样做，而是让我对 size2 使用的语法实际上修改 size2 的值。

我怎么做？

我正在尝试运行使用 llama 的 FinGPT_forecaster 的示例代码。有关使用 llama 的此财务 GPT 的示例代码和信息可在此处找到：https://github.com/AI4Finance-Found...

我正在尝试运行使用 llama 的 FinGPT_forecaster 的示例代码。有关使用 llama 的此财务 GPT 的示例代码和信息可在此处找到： https://github.com/AI4Finance-Foundation/FinGPT/tree/master/fingpt/FinGPT_Forecaster

我在 Meta 注册并创建了一个 Huggingface 账户。我在 Huggingface 上生成了代币，并将其嵌入到下面的代码中。

我稍微修改了代码，使其包含我的令牌，因此代码如下所示（为了保护隐私，此处将令牌指定为 xxx）

from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch


base_model = AutoModelForCausalLM.from_pretrained(
    'meta-llama/Llama-2-7b-chat-hf',
    trust_remote_code=True,
    device_map="auto",
    torch_dtype=torch.float16,
    token='xxx' # optional if you have enough VRAM
)

tokenizer = AutoTokenizer.from_pretrained('meta-llama/Llama-2-7b-chat-hf',token='xxx')
print("hi")
model = PeftModel.from_pretrained(base_model, 'FinGPT/fingpt-forecaster_dow30_llama2-7b_lora',token='xxx')
print("hi2")
model = model.eval()

运行时，线路出现停顿， model = PeftModel... 我多次收到以下消息：

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Some parameters are on the meta device device because they were offloaded to the cpu and disk.
hi

C:\Users\xxx\AppData\Roaming\Python\Python311\site-packages\torch\nn\modules\module.py:2047: UserWarning: for base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass `assign=True` to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
  warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '

然后我收到消息：

Traceback (most recent call last):

  File c:\ProgramData\Anaconda3\Lib\site-packages\spyder_kernels\py3compat.py:356 in compat_exec
    exec(code, globals, locals)

  File c:\users\xxx\downloads\fingpt20240715.py:23
    model = PeftModel.from_pretrained(base_model, 'FinGPT/fingpt-forecaster_dow30_llama2-7b_lora',token='xxx')

  File ~\AppData\Roaming\Python\Python311\site-packages\peft\peft_model.py:430 in from_pretrained
    model.load_adapter(model_id, adapter_name, is_trainable=is_trainable, **kwargs)

  File ~\AppData\Roaming\Python\Python311\site-packages\peft\peft_model.py:1022 in load_adapter
    self._update_offload(offload_index, adapters_weights)

  File ~\AppData\Roaming\Python\Python311\site-packages\peft\peft_model.py:908 in _update_offload
    safe_module = dict(self.named_modules())[extended_prefix]

KeyError: 'base_model.model.model.model.embed_tokens'

有什么建议吗？提前谢谢。

数字是不可变的（谢天谢地），所以如果不创建其他类型，你就无法做到这一点。另外，不要扩展内置原型——这是一种不好的做法，可能会与语言的未来扩展相冲突，并导致整个程序出现怪异现象，比如全局可变状态，甚至更糟。最好的办法是编写一个独立函数

@Luuk 我控制了所有路径，它们都是有效目录。代码是创建文件夹，但它不读取自己的文件夹，我无法理解这个错误的含义，我已经搜索解决方案 3-4 天了。

@Luuk 是的，但我需要解决方案，因为这是我的实习项目，我必须解决这个问题，这就是我无法关闭这个问题的原因。

我创建了 该问题的 最小可重现示例

import os

output_dir = 'D:\\TEMP\\PhycharmProjects\\Emotion_Detection\\output'

if not os.path.exists(output_dir):
    os.makedirs(output_dir)
    print(f"{output_dir} created!")
elif not os.path.isdir(output_dir):
    print(f"{output_dir} NOT created!")
    raise NotADirectoryError(f"{output_dir} is not a directory")

运行此代码将产生以下输出：

D:\TEMP>python testdir.py
D:\TEMP\PhycharmProjects\Emotion_Detection\output created!

我甚至仔细检查了一遍（虽然没有必要，但是……）

D:\TEMP>tree PhycharmProjects
Folder PATH listing for volume HDD
Volume serial number is D46B-804B
D:\TEMP\PHYCHARMPROJECTS
Emotion_Detection
    output