Spaces:
Runtime error
Runtime error
File size: 4,865 Bytes
4f607de |
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 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from datasets import load_dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from datasets import Dataset, load_metric
from sklearn.model_selection import train_test_split
from source.services.predicting_effective_arguments.train.model import TransformersSequenceClassifier
class CFG:
TARGET = 'discourse_effectiveness'
TEXT = "discourse_text"
MODEL_CHECKPOINT = "distilbert-base-uncased"
MODEL_OUTPUT_DIR ='source/services/predicting_effective_arguments/model/hf_textclassification/predicting_effective_arguments_distilbert'
model_name="debertav3base"
learning_rate=1.5e-5
weight_decay=0.02
hidden_dropout_prob=0.007
attention_probs_dropout_prob=0.007
num_train_epochs=10
n_splits=4
batch_size=12
random_seed=42
save_steps=100
max_length=512
def seed_everything(seed: int):
import random, os
import numpy as np
import torch
random.seed(seed)
os.environ['PYTHONHASHSEED'] = str(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = True
def prepare_input_text(df, sep_token):
df['inputs'] = df.discourse_type.str.lower() + ' ' + sep_token + ' ' + df.discourse_text.str.lower()
return df
if __name__ == '__main__':
config = CFG()
tokenizer = AutoTokenizer.from_pretrained(config.MODEL_CHECKPOINT)
data = pd.read_csv("data/raw_data/train.csv")[:100]
label_names = list(data[config.TARGET].unique())
#score_df = pd.read_csv("data/raw_data/test.csv")
"""
data[TARGET].value_counts(ascending=True).plot.barh()
plt.title("Frequency of Classes")
plt.show()
data['discourse_type'].value_counts(ascending=True).plot.barh()
plt.title("Frequency of discourse_type")
plt.show()
data["Words Per text"] = data[TEXT].str.split().apply(len)
data.boxplot("Words Per text", by=TARGET, grid=False, showfliers=False,
color="black")
plt.suptitle("")
plt.xlabel("")
plt.show()
"""
train_size = 0.7
valid_size = 0.2
test_size = 0.1
# First split: Separate out the training set
train_df, temp_df = train_test_split(data, test_size=1 - train_size, random_state=5600)
# Second split: Separate out the validation and test sets
valid_df, test_df = train_test_split(temp_df, test_size=test_size / (test_size + valid_size), random_state=5600)
train_df = prepare_input_text(train_df, sep_token=tokenizer.sep_token)
valid_df = prepare_input_text(valid_df, sep_token=tokenizer.sep_token)
test_df = prepare_input_text(test_df, sep_token=tokenizer.sep_token)
train_dataset = Dataset.from_pandas(train_df[['inputs', config.TARGET]]).rename_column(config.TARGET, 'label').class_encode_column("label")
val_dataset = Dataset.from_pandas(valid_df[['inputs', config.TARGET]]).rename_column(config.TARGET, 'label').class_encode_column("label")
test_dataset = Dataset.from_pandas(test_df[['inputs', config.TARGET]]).rename_column(config.TARGET, 'label').class_encode_column("label")
id2label = {i: label for i, label in enumerate(label_names)}
label2id = {v: k for k, v in id2label.items()}
seqClassifer = TransformersSequenceClassifier(model_output_dir=config.MODEL_OUTPUT_DIR,
tokenizer=tokenizer,
model_checkpoint="distilbert-base-uncased",
num_labels=3,
id2label=id2label,
label2id=label2id)
train_tok_dataset = seqClassifer.tokenize_dataset(dataset=train_dataset)
val_tok_dataset = seqClassifer.tokenize_dataset(dataset=val_dataset)
test_tok_dataset = seqClassifer.tokenize_dataset(dataset=test_dataset)
seqClassifer.train(train_dataset=train_tok_dataset, eval_dataset=val_tok_dataset, epochs=1, batch_size=16)
y_test_pred = seqClassifer.predict_argmax_logit(test_tok_dataset)
seqClassifer.plot_confusion_matrix(y_preds=y_test_pred, y_true=test_dataset['label'], label_names=label_names)
y_pred = seqClassifer.predict_pipeline(model_checkpoint=config.MODEL_OUTPUT_DIR, test_list=test_df['inputs'].tolist())
#hidden = train_tok_dataset.map(seqClassifer.extract_hidden_states,
# batched=True,
# fn_kwargs={'tokenizer': AutoTokenizer.from_pretrained(config.MODEL_OUTPUT_DIR),
# 'model': AutoModelForSequenceClassification.from_pretrained(config.MODEL_OUTPUT_DIR)})
pass
|