File size: 4,561 Bytes
ae7fe37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
# --- IMPORTS ---

import torch
from datasets import Dataset
from transformers import Trainer, TrainingArguments, DataCollatorWithPadding
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import re
import nltk
from nltk.corpus import stopwords
nltk.download('stopwords')
stopwords = set(stopwords.words('english'))

# -------------------------

# --- INPUT ---

input_list = [""" WRITE HERE YOUR FIRST ESSAY """,
              """ WRITE HERE YOUR SECOND ESSAY """]

# -------------

# --- USEFUL FUNCTIONS ----


def clean_text(text):
    """
    This funtion get's rid of nonalphabetical characters, stopwords and lower cases the text.

    Args:
    text (str): The text to be cleaned

    Returns:
    text (str): The cleaned text

    Example:
    df['text'] = df['text'].apply(clean_text)
    """
    text = re.sub(r'[^a-zA-Z]', ' ', text)
    text = text.lower()
    words = text.split()
    text = [word for word in words if not word in stopwords]
    text = ' '.join(words)
    return text


def tokenize_function(dataframe):
    """
    This funtion tokenizes the 'text' field of the dataframe.

    Args:
    dataframe (pandas.DataFrame): The dataframe to be tokenized

    Returns:
    dataframe (pandas.DataFrame): The tokenized dataframe

    Example and output:
    train_dataset_token = train_dataset.map(tokenize_function, batched=True)
    """
    return tokenizer(dataframe["text"], truncation=True)


def compute_metrics(eval_pred):
    """
    This funtion computes the accuracy, precision, recall and f1 score of the model.

    It'is passed to the trainer and it outputs when evaluating the model.

    Args:
    eval_pred (tuple): The predictions and labels of the model

    Returns:
    dict: The accuracy, precision, recall and f1 score of the model

    Example:
    >>> trainer.evaluate()
    {
        'accuracy': accuracy,
        'precision': precision,
        'recall': recall,
        'f1': f1
    }
    """
    predictions, labels = eval_pred
    predictions = predictions.argmax(axis=-1)
    accuracy = accuracy_score(labels, predictions)
    precision, recall, f1, _ = precision_recall_fscore_support(
        labels, predictions, average='binary')
    return {
        'accuracy': accuracy,
        'precision': precision,
        'recall': recall,
        'f1': f1
    }

# -------------------------

# --- LOADING THE MODEL ---


# Load the initial tokenizer and model to set the number of labels its going to classify as 2
checkpoint = "diegovelilla/EssAI"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForSequenceClassification.from_pretrained(checkpoint)

# -------------------------

# --- DATA PREPROCESSING ---

n_input = len(input_list)

# Now we convert the input to a dataset
df = pd.DataFrame({'text': input_list})


# Get rid of nonalphatetical characters, stopwords and we lower case it.
df['text'] = df['text'].apply(clean_text)

# We convert the pandas dataframe into hugging face datasets and tokenize both of them
ds = Dataset.from_pandas(df)
ds_token = ds.map(tokenize_function, batched=True)

# Drop columns that are not necessary and set the dataset format to pytorch tensors
ds_token = ds_token.remove_columns(["text", "token_type_ids"])
ds_token.set_format(type='torch', columns=['input_ids', 'attention_mask'])

# -------------------------

# --- INSTANTIATING TRAINER ----

# We instantiate a DataCollatorWithPadding in order to pad the inputs in batches while training
data_collator = DataCollatorWithPadding(tokenizer=tokenizer)

# Create the training arguments
training_args = TrainingArguments(".")

# Create the trainer
trainer = Trainer(
    model,
    training_args,
    eval_dataset=ds_token,
    data_collator=data_collator,
    tokenizer=tokenizer,
    compute_metrics=compute_metrics
)

# -------------------------

# --- PREDICT ---

# We predict and then format the output
predictions = trainer.predict(ds_token)
predictions = torch.from_numpy(predictions.predictions)
predictions = torch.nn.functional.softmax(predictions, dim=-1)

print('\n\n')
for i in range(n_input):
    index = torch.argmax(predictions[i])
    print(f'{i+1}: HUMAN {round(predictions[i][0].item() * 100, 2)}% of confidence.') if index == 0 else print(
        f'{i+1}: AI {round(predictions[i][1].item() * 100, 2)}% of confidence.')

# -------------------------