Spaces:
Sleeping
Sleeping
File size: 11,564 Bytes
6a34fd4 ee40bd7 6a34fd4 debb3aa c343cc3 6a34fd4 1922da0 c343cc3 ee40bd7 c343cc3 5c72fe4 c343cc3 ee40bd7 c343cc3 5c72fe4 c343cc3 5c72fe4 ee40bd7 5e7e944 ee40bd7 445302e debb3aa 5fdf2ba debb3aa ee40bd7 debb3aa c343cc3 3821b59 c343cc3 debb3aa 6a34fd4 1922da0 c343cc3 1922da0 6a34fd4 bffd338 6a34fd4 bffd338 1922da0 5c72fe4 c343cc3 1922da0 bffd338 3821b59 6a34fd4 debb3aa 6a34fd4 ee40bd7 c343cc3 1922da0 6a34fd4 bffd338 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 |
import gradio as gr
from huggingface_hub import hf_hub_download
import pickle
from gradio import Progress
import numpy as np
import subprocess
import shutil
import matplotlib.pyplot as plt
from sklearn.metrics import roc_curve, auc
import pandas as pd
# Define the function to process the input file and model selection
def process_file(file,label,info,model_name,inc_slider,progress=Progress(track_tqdm=True)):
# progress = gr.Progress(track_tqdm=True)
progress(0, desc="Starting the processing")
with open(file.name, 'r') as f:
content = f.read()
saved_test_dataset = "train.txt"
saved_test_label = "train_label.txt"
saved_train_info="train_info.txt"
# Save the uploaded file content to a specified location
shutil.copyfile(file.name, saved_test_dataset)
shutil.copyfile(label.name, saved_test_label)
shutil.copyfile(info.name, saved_train_info)
# Load the test_info file and the graduation rate file
test_info = pd.read_csv('train_info.txt', sep=',', header=None, engine='python')
grad_rate_data = pd.DataFrame(pd.read_pickle('school_grduation_rate.pkl'),columns=['school_number','grad_rate']) # Load the grad_rate data
# Step 1: Extract unique school numbers from test_info
unique_schools = test_info[0].unique()
# Step 2: Filter the grad_rate_data using the unique school numbers
schools = grad_rate_data[grad_rate_data['school_number'].isin(unique_schools)]
# Define a threshold for high and low graduation rates (adjust as needed)
grad_rate_threshold = 0.9
# Step 4: Divide schools into high and low graduation rate groups
high_grad_schools = schools[schools['grad_rate'] >= grad_rate_threshold]['school_number'].unique()
low_grad_schools = schools[schools['grad_rate'] < grad_rate_threshold]['school_number'].unique()
# Step 5: Sample percentage of schools from each group
high_sample = pd.Series(high_grad_schools).sample(frac=inc_slider/100, random_state=1).tolist()
low_sample = pd.Series(low_grad_schools).sample(frac=inc_slider/100, random_state=1).tolist()
# Step 6: Combine the sampled schools
random_schools = high_sample + low_sample
# Step 7: Get indices for the sampled schools
indices = test_info[test_info[0].isin(random_schools)].index.tolist()
# Load the test file and select rows based on indices
test = pd.read_csv('train.txt', sep=',', header=None, engine='python')
selected_rows_df2 = test.loc[indices]
# Save the selected rows to a file
selected_rows_df2.to_csv('selected_rows.txt', sep='\t', index=False, header=False, quoting=3, escapechar=' ')
# For demonstration purposes, we'll just return the content with the selected model name
if(model_name=="High Graduated Schools"):
finetune_task="highGRschool10"
elif(model_name== "Low Graduated Schools" ):
finetune_task="highGRschool10"
elif(model_name=="Full Set"):
finetune_task="highGRschool10"
else:
finetune_task=None
# print(checkpoint)
progress(0.1, desc="Files created and saved")
# if (inc_val<5):
# model_name="highGRschool10"
# elif(inc_val>=5 & inc_val<10):
# model_name="highGRschool10"
# else:
# model_name="highGRschool10"
progress(0.2, desc="Executing models")
subprocess.run([
"python", "new_test_saved_finetuned_model.py",
"-workspace_name", "ratio_proportion_change3_2223/sch_largest_100-coded",
"-finetune_task", "highGRschool10",
"-test_dataset_path","../../../../selected_rows.txt",
# "-test_label_path","../../../../train_label.txt",
"-finetuned_bert_classifier_checkpoint",
"ratio_proportion_change3_2223/sch_largest_100-coded/output/highGRschool10/bert_fine_tuned.model.ep42",
"-e",str(1),
"-b",str(1000)
])
progress(0.6,desc="Model execution completed")
result = {}
with open("result.txt", 'r') as file:
for line in file:
key, value = line.strip().split(': ', 1)
# print(type(key))
if key=='epoch':
result[key]=value
else:
result[key]=float(value)
# Create a plot
with open("roc_data.pkl", "rb") as f:
fpr, tpr, _ = pickle.load(f)
roc_auc = auc(fpr, tpr)
fig, ax = plt.subplots()
ax.plot(fpr, tpr, color='blue', lw=2, label=f'ROC curve (area = {roc_auc:.2f})')
ax.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
ax.set(xlabel='False Positive Rate', ylabel='True Positive Rate', title=f'ROC Curve: {model_name}')
ax.legend(loc="lower right")
ax.grid()
# Save plot to a file
plot_path = "plot.png"
fig.savefig(plot_path)
plt.close(fig)
progress(1.0)
# Prepare text output
text_output = f"Model: {model_name}\nResult:\n{result}"
# Prepare text output with HTML formatting
text_output = f"""
Model: {model_name}\n
Result Summary:\n
-----------------\n
Precision: {result['precisions']:.2f}\n
Recall: {result['recalls']:.2f}\n
Time Taken: {result['time_taken_from_start']:.2f} seconds\n
Total Schools in test: {len(unique_schools):.4f}\n
Total Schools taken: {len(random_schools):.4f}\n
High grad schools: {len(high_sample):.4f}\n
Low grad schools: {len(low_sample):.4f}\n
-----------------\n
Note: The ROC Curve is also displayed for the evaluation.
"""
return text_output,plot_path
# List of models for the dropdown menu
models = ["High Graduated Schools", "Low Graduated Schools", "Full Set"]
# Create the Gradio interface
with gr.Blocks(css="""
body {
background-color: #1e1e1e!important;
font-family: 'Arial', sans-serif;
color: #f5f5f5!important;;
}
.gradio-container {
max-width: 850px!important;
margin: 0 auto!important;;
padding: 20px!important;;
background-color: #292929!important;
border-radius: 10px;
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.2);
}
.gradio-container-4-44-0 .prose h1 {
font-size: var(--text-xxl);
color: #ffffff!important;
}
#title {
color: white!important;
font-size: 2.3em;
font-weight: bold;
text-align: center!important;
margin-bottom: 20px;
}
.description {
text-align: center;
font-size: 1.1em;
color: #bfbfbf;
margin-bottom: 30px;
}
.file-box {
max-width: 180px;
padding: 5px;
background-color: #444!important;
border: 1px solid #666!important;
border-radius: 6px;
height: 80px!important;;
margin: 0 auto!important;;
text-align: center;
color: transparent;
}
.file-box span {
color: #f5f5f5!important;
font-size: 1em;
line-height: 45px; /* Vertically center text */
}
.dropdown-menu {
max-width: 220px;
margin: 0 auto!important;
background-color: #444!important;
color:#444!important;
border-radius: 6px;
padding: 8px;
font-size: 1.1em;
border: 1px solid #666;
}
.button {
background-color: #4CAF50!important;
color: white!important;
font-size: 1.1em;
padding: 10px 25px;
border-radius: 6px;
cursor: pointer;
transition: background-color 0.2s ease-in-out;
}
.button:hover {
background-color: #45a049!important;
}
.output-text {
background-color: #333!important;
padding: 12px;
border-radius: 8px;
border: 1px solid #666;
font-size: 1.1em;
}
.footer {
text-align: center;
margin-top: 50px;
font-size: 0.9em;
color: #b0b0b0;
}
.svelte-12ioyct .wrap {
display: none !important;
}
.file-label-text {
display: none !important;
}
div.svelte-sfqy0y {
display: flex;
flex-direction: inherit;
flex-wrap: wrap;
gap: var(--form-gap-width);
box-shadow: var(--block-shadow);
border: var(--block-border-width) solid var(--border-color-primary);
border-radius: var(--block-radius);
background: #1f2937!important;
overflow-y: hidden;
}
.block.svelte-12cmxck {
position: relative;
margin: 0;
box-shadow: var(--block-shadow);
border-width: var(--block-border-width);
border-color: var(--block-border-color);
border-radius: var(--block-radius);
background: #1f2937!important;
width: 100%;
line-height: var(--line-sm);
}
.svelte-12ioyct .wrap {
display: none !important;
}
.file-label-text {
display: none !important;
}
input[aria-label="file upload"] {
display: none !important;
}
gradio-app .gradio-container.gradio-container-4-44-0 .contain .file-box span {
font-size: 1em;
line-height: 45px;
color: #1f2937 !important;
}
.wrap.svelte-12ioyct {
display: flex;
flex-direction: column;
justify-content: center;
align-items: center;
min-height: var(--size-60);
color: #1f2937 !important;
line-height: var(--line-md);
height: 100%;
padding-top: var(--size-3);
text-align: center;
margin: auto var(--spacing-lg);
}
span.svelte-1gfkn6j:not(.has-info) {
margin-bottom: var(--spacing-lg);
color: white!important;
}
label.float.svelte-1b6s6s {
position: relative!important;
top: var(--block-label-margin);
left: var(--block-label-margin);
}
label.svelte-1b6s6s {
display: inline-flex;
align-items: center;
z-index: var(--layer-2);
box-shadow: var(--block-label-shadow);
border: var(--block-label-border-width) solid var(--border-color-primary);
border-top: none;
border-left: none;
border-radius: var(--block-label-radius);
background: rgb(120 151 180)!important;
padding: var(--block-label-padding);
pointer-events: none;
color: #1f2937!important;
font-weight: var(--block-label-text-weight);
font-size: var(--block-label-text-size);
line-height: var(--line-sm);
}
.file.svelte-18wv37q.svelte-18wv37q {
display: block!important;
width: var(--size-full);
}
tbody.svelte-18wv37q>tr.svelte-18wv37q:nth-child(odd) {
background: ##7897b4!important;
color: white;
background: #aca7b2;
}
.gradio-container-4-31-4 .prose h1, .gradio-container-4-31-4 .prose h2, .gradio-container-4-31-4 .prose h3, .gradio-container-4-31-4 .prose h4, .gradio-container-4-31-4 .prose h5 {
color: white;
""") as demo:
gr.Markdown("<h1 id='title'>ASTRA</h1>", elem_id="title")
gr.Markdown("<p class='description'>Upload a .txt file and select a model from the dropdown menu.</p>")
with gr.Row():
file_input = gr.File(label="Upload a test file", file_types=['.txt'], elem_classes="file-box")
label_input = gr.File(label="Upload test labels", file_types=['.txt'], elem_classes="file-box")
info_input = gr.File(label="Upload test info", file_types=['.txt'], elem_classes="file-box")
model_dropdown = gr.Dropdown(choices=models, label="Select Finetune Task", elem_classes="dropdown-menu")
increment_slider = gr.Slider(minimum=1, maximum=100, step=1, label="Schools Percentage", value=1)
with gr.Row():
output_text = gr.Textbox(label="Output Text")
output_image = gr.Image(label="Output Plot")
btn = gr.Button("Submit")
btn.click(fn=process_file, inputs=[file_input,label_input,info_input,model_dropdown,increment_slider], outputs=[output_text,output_image])
# Launch the app
demo.launch() |