Spaces:
Runtime error
Runtime error
File size: 4,701 Bytes
baecba5 6d47c20 e332268 baecba5 6d47c20 bfa58d3 cb31cda baecba5 6d47c20 c60eaaf 24dcd2b 6d47c20 c60eaaf 6d47c20 afe376b 6d47c20 1789ff2 6d47c20 cb31cda 6d47c20 e332268 24dcd2b 6d47c20 afe376b 6d47c20 24dcd2b 6d47c20 afe376b 6d47c20 |
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 |
import gradio as gr
import pandas as pd
from realtabformer import REaLTabFormer
from scipy.io import arff
rtf_model = REaLTabFormer(
model_type="tabular",
epochs=50,
gradient_accumulation_steps=4)
def generate_data(file, num_samples):
if '.arff' in file.name:
data = arff.loadarff(open(file.name,'rt'))
df = pd.DataFrame(data[0])
elif '.csv' in file.name:
df = pd.read_csv(file.name)
rtf_model.fit(df)
# Generate synthetic data
samples = rtf_model.sample(n_samples=num_samples)
return samples
css = """
.gradio-container {
font-family: 'IBM Plex Sans', sans-serif;
}
.gr-button {
color: white;
border-color: black;
background: black;
}
input[type='range'] {
accent-color: black;
}
.dark input[type='range'] {
accent-color: #dfdfdf;
}
.container {
max-width: 430px;
margin: auto;
padding-top: 1.5rem;
}
#gallery {
min-height: 22rem;
margin-bottom: 15px;
margin-left: auto;
margin-right: auto;
border-bottom-right-radius: .5rem !important;
border-bottom-left-radius: .5rem !important;
}
#gallery>div>.h-full {
min-height: 20rem;
}
.details:hover {
text-decoration: underline;
}
.gr-button {
white-space: nowrap;
}
.gr-button:focus {
border-color: rgb(147 197 253 / var(--tw-border-opacity));
outline: none;
box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
--tw-border-opacity: 1;
--tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
--tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
--tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
--tw-ring-opacity: .5;
}
#advanced-btn {
font-size: .7rem !important;
line-height: 19px;
margin-top: 12px;
margin-bottom: 12px;
padding: 2px 8px;
border-radius: 14px !important;
}
#advanced-options {
display: none;
margin-bottom: 20px;
}
.footer {
margin-bottom: 45px;
margin-top: 35px;
text-align: center;
border-bottom: 1px solid #e5e5e5;
}
.footer>p {
font-size: .8rem;
display: inline-block;
padding: 0 10px;
transform: translateY(10px);
background: white;
}
.dark .footer {
border-color: #303030;
}
.dark .footer>p {
background: #0b0f19;
}
"""
with gr.Blocks(css = css) as demo:
gr.Markdown("""
## REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers
""")
gr.HTML('''
<p style="margin-bottom: 10px; font-size: 94%">
This is an unofficial demo for REaLTabFormer that can be used to generate synthetic data from single tabular data using GPT. The demo is based on the <a href='https://github.com/avsolatorio/REaLTabFormer' style='text-decoration: underline;' target='_blank'> Github </a> implementation provided by the authors.
</p>
''')
with gr.Column():
#gr.Markdown(""" ### Record audio """)
# with gr.Tab("Record Audio"):
# audio_input_r = gr.Audio(label = 'Record Audio Input',source="microphone",type="filepath")
# transcribe_audio_r = gr.Button('Transcribe')
with gr.Tab("Upload Data as File"):
data_input_u = gr.File(label = 'Upload Data File', file_types=["text", ".json", ".csv", ".arff"])
num_samples = gr.Slider(label="Number of Samples", minimum=5, maximum=100, value=5, step=10)
generate_data_btn = gr.Button('Generate Synthetic Data')
with gr.Row():
#data_sample = gr.Dataframe(label = "Original Data")
data_output = gr.Dataframe(label = "Synthetic Data")
generate_data_btn.click(generate_data, inputs = [data_input_u,num_samples], outputs = [data_output])
examples = gr.Examples(examples=[['diabetes.arff',5]],inputs = [data_input_u,num_samples], outputs = [data_output], cache_examples = True, fn = generate_data)
demo.launch() |