Spaces:
Runtime error
Runtime error
Upload testSampleCode.py with huggingface_hub
Browse files- testSampleCode.py +67 -0
testSampleCode.py
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
from sklearn.model_selection import train_test_split
|
3 |
+
|
4 |
+
dataFromCsv = pd.read_csv('test.csv')
|
5 |
+
|
6 |
+
text = dataFromCsv['text'].tolist()
|
7 |
+
label = dataFromCsv['label'].tolist()
|
8 |
+
|
9 |
+
print(text)
|
10 |
+
print(label)
|
11 |
+
|
12 |
+
sorted_lable = sorted((dataFromCsv['label']).unique())
|
13 |
+
print(sorted_lable)
|
14 |
+
|
15 |
+
|
16 |
+
lableList = {label: i for i, label in enumerate(sorted_lable)}
|
17 |
+
dataFromCsv['label'] = dataFromCsv['label'].map(lableList)
|
18 |
+
|
19 |
+
print("label list = ",lableList)
|
20 |
+
print("from csv file label = ",dataFromCsv['label'])
|
21 |
+
|
22 |
+
|
23 |
+
|
24 |
+
# Split the dataset
|
25 |
+
train_df, test_df = train_test_split(dataFromCsv, test_size=0.2, random_state=42)
|
26 |
+
print("Training Set:")
|
27 |
+
print(train_df)
|
28 |
+
print("\nTesting Set:")
|
29 |
+
print(test_df)
|
30 |
+
|
31 |
+
lableList = { 0: "lastmonth", 1: "nextweek", 2: "sevendays", 3: "today", 4: "yesterday" }
|
32 |
+
|
33 |
+
print("After = ", lableList[4])
|
34 |
+
print("label items = ", lableList.items())
|
35 |
+
|
36 |
+
#test of dataset
|
37 |
+
# from torch.utils.data import Dataset
|
38 |
+
# import torch
|
39 |
+
|
40 |
+
# class IntentDataset(Dataset):
|
41 |
+
# def __init__(self, encodings, labels):
|
42 |
+
# self.encodings = encodings
|
43 |
+
# self.labels = labels
|
44 |
+
|
45 |
+
# def __getitem__(self, idx):
|
46 |
+
# item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
|
47 |
+
# label = self.labels[idx]
|
48 |
+
# item['labels'] = torch.tensor(self.labels[idx])
|
49 |
+
|
50 |
+
# return item
|
51 |
+
|
52 |
+
# def __len__(self):
|
53 |
+
# return len(self.labels)
|
54 |
+
|
55 |
+
# # Sample data
|
56 |
+
# encodings = {
|
57 |
+
# 'input_ids': [[101, 102, 103], [104, 105, 106], [107, 108, 109]],
|
58 |
+
# 'attention_mask': [[1, 1, 1], [1, 1, 1], [1, 1, 1]]
|
59 |
+
# }
|
60 |
+
# labels = [0, 1, 0]
|
61 |
+
|
62 |
+
# dataset = IntentDataset(encodings, labels)
|
63 |
+
# dataset_length = len(dataset)
|
64 |
+
# print(f"The dataset contains {dataset_length} items. {dataset.labels}")
|
65 |
+
|
66 |
+
# dataset_show = dataset[2]
|
67 |
+
# print(dataset_show)
|