Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
@@ -1,173 +1,94 @@
|
|
1 |
import os
|
2 |
-
import nltk
|
3 |
import csv
|
4 |
import logging
|
5 |
-
from tqdm import tqdm
|
6 |
import gradio as gr
|
7 |
-
|
8 |
-
from
|
9 |
-
import
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
13 |
|
14 |
-
#
|
15 |
-
nltk.download('
|
|
|
16 |
|
17 |
-
#
|
18 |
-
|
19 |
-
|
20 |
-
MODELS = ["bert-base-uncased", "gpt2", "roberta-base", "distilbert-base-uncased", "albert-base-v2"] # Corrected model identifier
|
21 |
|
22 |
-
#
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
|
|
|
|
28 |
|
29 |
-
#
|
30 |
-
def
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
word_means[model_name] = output[0].mean().item()
|
40 |
-
except Exception as e:
|
41 |
-
logging.error(f"Error processing word {word} with model {model_name}: {e}")
|
42 |
-
word_means[model_name] = None
|
43 |
-
means[word] = word_means
|
44 |
-
return {"tokenizer": tokens, "words": words, "meaning": means}
|
45 |
|
46 |
-
|
47 |
-
|
48 |
-
|
|
|
|
|
49 |
writer.writeheader()
|
50 |
-
for word in data
|
51 |
-
writer.writerow({
|
52 |
-
"word": word,
|
53 |
-
"meanings": str(data['meaning'][word])
|
54 |
-
})
|
55 |
-
|
56 |
-
def train_dataset():
|
57 |
-
text = "Your long text goes here..."
|
58 |
-
data = process_text(text)
|
59 |
-
save_to_csv(data)
|
60 |
-
logging.info("Dataset processed and saved to CSV.")
|
61 |
-
|
62 |
-
def generate_report():
|
63 |
-
with open('app.log', 'r') as log_file:
|
64 |
-
log_content = log_file.read()
|
65 |
-
return log_content
|
66 |
-
|
67 |
-
def get_uptime():
|
68 |
-
uptime = time.strftime('%H:%M:%S', time.gmtime(time.time() - start_time))
|
69 |
-
return f"Uptime: {uptime}"
|
70 |
|
71 |
-
#
|
72 |
-
def
|
73 |
-
|
74 |
-
|
75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
-
#
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
}
|
84 |
-
#title {
|
85 |
-
text-align: center;
|
86 |
-
margin-bottom: 20px;
|
87 |
-
}
|
88 |
-
#input_text, #output_text, #log_output, #commit_input, #username_input, #metadata_input, #uptime_text {
|
89 |
-
width: 100%;
|
90 |
-
max-width: 600px;
|
91 |
-
margin: 10px 0;
|
92 |
-
}
|
93 |
-
#generate_button, #report_button, #save_settings_button {
|
94 |
-
width: 100%;
|
95 |
-
max-width: 200px;
|
96 |
-
margin: 10px 0;
|
97 |
-
}
|
98 |
-
#settings_container {
|
99 |
-
margin-top: 20px;
|
100 |
-
}
|
101 |
-
</style>
|
102 |
-
"""
|
103 |
|
104 |
-
|
|
|
105 |
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
with gr.Row():
|
111 |
-
input_text = gr.Textbox(label="Input Text", placeholder="Enter your text here...", elem_id="input_text")
|
112 |
-
output_text = gr.Textbox(label="Output", placeholder="Output will appear here...", elem_id="output_text")
|
113 |
-
generate_button = gr.Button("Generate", elem_id="generate_button")
|
114 |
-
generate_button.click(fn=generate_all, inputs=input_text, outputs=output_text)
|
115 |
-
|
116 |
-
with gr.Tab("Logs"):
|
117 |
-
with gr.Row():
|
118 |
-
log_output = gr.Textbox(label="Logs", placeholder="Logs will appear here...", elem_id="log_output")
|
119 |
-
report_button = gr.Button("Report using Logs", elem_id="report_button")
|
120 |
-
report_button.click(fn=generate_report, outputs=log_output)
|
121 |
-
|
122 |
-
with gr.Tab("Settings"):
|
123 |
-
with gr.Row():
|
124 |
-
commit_input = gr.Textbox(label="Commit", placeholder="Enter commit message", elem_id="commit_input")
|
125 |
-
username_input = gr.Textbox(label="Username", placeholder="Enter your username", elem_id="username_input")
|
126 |
-
metadata_input = gr.Textbox(label="Metadata", placeholder="Enter metadata", elem_id="metadata_input")
|
127 |
-
uptime_text = gr.Textbox(label="Uptime", placeholder="Uptime will appear here...", elem_id="uptime_text", interactive=False)
|
128 |
-
save_settings_button = gr.Button("Save Settings", elem_id="save_settings_button")
|
129 |
-
|
130 |
-
save_settings_button.click(
|
131 |
-
fn=lambda commit, username, metadata: f"Settings saved: {commit}, {username}, {metadata}",
|
132 |
-
inputs=[commit_input, username_input, metadata_input],
|
133 |
-
outputs=[uptime_text] # Reusing uptime_text for output to show settings saved message
|
134 |
-
)
|
135 |
-
|
136 |
-
# Update uptime every 10 seconds
|
137 |
-
def update_uptime():
|
138 |
-
return get_uptime()
|
139 |
-
|
140 |
-
gr.Every(10, fn=update_uptime, outputs=uptime_text)
|
141 |
|
142 |
-
#
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
logging.info("Dataset pushed to HuggingFace.")
|
154 |
-
except Exception as e:
|
155 |
-
logging.error(f"Error uploading to HuggingFace: {e}")
|
156 |
-
try:
|
157 |
-
# Log the error to a separate errors repo
|
158 |
-
errors_repo = "katsukiai/errors"
|
159 |
-
api.create_repo(repo_id=errors_repo, private=False, exist_ok=True)
|
160 |
-
with open('upload_error.log', 'w') as error_file:
|
161 |
-
error_file.write(f"Error uploading to HuggingFace: {e}\n")
|
162 |
-
upload_file(
|
163 |
-
path_or_fileobj="upload_error.log",
|
164 |
-
path_in_repo="upload_error.log",
|
165 |
-
repo_id=errors_repo
|
166 |
-
)
|
167 |
-
logging.info("Error log pushed to HuggingFace errors repo.")
|
168 |
-
except Exception as e2:
|
169 |
-
logging.error(f"Failed to log error to HuggingFace errors repo: {e2}")
|
170 |
|
|
|
171 |
if __name__ == "__main__":
|
172 |
-
|
173 |
-
run_and_push()
|
|
|
1 |
import os
|
|
|
2 |
import csv
|
3 |
import logging
|
|
|
4 |
import gradio as gr
|
5 |
+
import nltk
|
6 |
+
from datasets import Dataset, DatasetDict, DatasetInfo, Features, Value, ClassLabel
|
7 |
+
from huggingface_hub import HfApi, Repository, create_repo
|
8 |
+
from tqdm import tqdm
|
9 |
+
from nltk.tokenize import word_tokenize
|
10 |
+
from nltk.corpus import wordnet as wn
|
11 |
+
import random
|
12 |
+
import string
|
13 |
|
14 |
+
# Ensure necessary NLTK resources are downloaded
|
15 |
+
nltk.download('punkt')
|
16 |
+
nltk.download('wordnet')
|
17 |
|
18 |
+
# Set up logging
|
19 |
+
logging.basicConfig(level=logging.INFO)
|
20 |
+
logger = logging.getLogger(__name__)
|
|
|
21 |
|
22 |
+
# Function to generate random words
|
23 |
+
def generate_random_words(num_words=100):
|
24 |
+
words = []
|
25 |
+
for _ in range(num_words):
|
26 |
+
word_length = random.randint(3, 10)
|
27 |
+
word = ''.join(random.choices(string.ascii_lowercase, k=word_length))
|
28 |
+
words.append(word)
|
29 |
+
return words
|
30 |
|
31 |
+
# Function to get meanings of words using NLTK WordNet
|
32 |
+
def get_word_meanings(words):
|
33 |
+
meanings = {}
|
34 |
+
for word in words:
|
35 |
+
synsets = wn.synsets(word)
|
36 |
+
if synsets:
|
37 |
+
meanings[word] = synsets[0].definition()
|
38 |
+
else:
|
39 |
+
meanings[word] = "No definition found."
|
40 |
+
return meanings
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
|
42 |
+
# Function to convert data to CSV format
|
43 |
+
def convert_to_csv(data, filename='dataset.csv'):
|
44 |
+
fieldnames = ['word', 'meaning']
|
45 |
+
with open(filename, mode='w', newline='', encoding='utf-8') as file:
|
46 |
+
writer = csv.DictWriter(file, fieldnames=fieldnames)
|
47 |
writer.writeheader()
|
48 |
+
for word, meaning in data.items():
|
49 |
+
writer.writerow({'word': word, 'meaning': meaning})
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
|
51 |
+
# Function to create and push dataset to Hugging Face
|
52 |
+
def create_and_push_dataset(csv_file='dataset.csv', repo_name='DeepFocus-X3'):
|
53 |
+
# Create a new dataset repository on Hugging Face
|
54 |
+
create_repo(repo_name, exist_ok=True)
|
55 |
+
api = HfApi()
|
56 |
+
api.upload_file(
|
57 |
+
path_or_fileobj=csv_file,
|
58 |
+
path_in_repo=csv_file,
|
59 |
+
repo_id=repo_name,
|
60 |
+
repo_type='dataset'
|
61 |
+
)
|
62 |
+
logger.info(f"Dataset {repo_name} created and file {csv_file} uploaded.")
|
63 |
|
64 |
+
# Gradio interface functions
|
65 |
+
def generate_words_interface():
|
66 |
+
num_words = random.randint(50, 200)
|
67 |
+
words = generate_random_words(num_words)
|
68 |
+
meanings = get_word_meanings(words)
|
69 |
+
convert_to_csv(meanings)
|
70 |
+
return f"Generated {num_words} random words and saved to dataset.csv."
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
|
72 |
+
def about_interface():
|
73 |
+
return "This is a dataset generation tool that creates a dataset of random words and their meanings, then uploads it to Hugging Face."
|
74 |
|
75 |
+
def logs_interface():
|
76 |
+
with open('dataset_generation.log', 'r') as file:
|
77 |
+
logs = file.read()
|
78 |
+
return logs
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
79 |
|
80 |
+
# Gradio app setup
|
81 |
+
with gr.Blocks() as demo:
|
82 |
+
with gr.Tabs():
|
83 |
+
with gr.Tab("About"):
|
84 |
+
about_text = gr.Markdown(about_interface)
|
85 |
+
with gr.Tab("Generate"):
|
86 |
+
generate_button = gr.Button("Generate Dataset")
|
87 |
+
generate_output = gr.Textbox()
|
88 |
+
generate_button.click(generate_words_interface, outputs=generate_output)
|
89 |
+
with gr.Tab("Logs"):
|
90 |
+
logs_output = gr.Textbox(value=logs_interface(), interactive=False)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
|
92 |
+
# Run the Gradio app
|
93 |
if __name__ == "__main__":
|
94 |
+
demo.launch()
|
|