Spaces:
Sleeping
Sleeping
File size: 12,681 Bytes
a7bac1c | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 | """
Ashley Wu
Main application
"""
import gradio as gr
import utils
import insights
import data_processor as dp
import visualizations as vis
def create_gradio_interface():
"""
Create a Gradio interface for the mosaic generator.
"""
# Create Gradio interface
with gr.Blocks(title="Buisiness Dashboard") as demo:
gr.Markdown("# 🎨 Buisiness Dashboard")
gr.Markdown("Upload a csv or txt file (in the format of a csv file)!")
with gr.Tab("Data Upload"):
# File upload and preview
with gr.Row():
file_input = gr.File(
label="Upload CSV File",
file_types=[".csv", ".txt"],
type="filepath"
)
file_upload_textbox = gr.Textbox(
label="CSV Quick Data",
lines=25
)
with gr.Row():
output = gr.Dataframe(
label="CSV Data - Edit or Delete Rows",
interactive=True
)
"""Download button"""
with gr.Row():
download_btn = gr.DownloadButton(
label="Download Modified CSV",
visible=True
)
with gr.Tab("Filter & Explore"):
# Interactive filtering
with gr.Row():
with gr.Column():
column_dropdown = gr.Dropdown(
label="Select Column to Filter",
choices=[],
interactive=True
)
with gr.Row():
apply_button = gr.Button("Apply Filter")
row_count = gr.Number(
label="Rows in dataframe",
visible=True,
interactive=False
)
max_num_textbox = gr.Number(
label="Set max value of column",
visible = False
)
min_num_textbox = gr.Number(
label="Set min value of column",
visible = False
)
category_multiselect = gr.Dropdown(
label="Select elements you want to filter out",
choices=[],
multiselect=True,
interactive=True,
visible=False
)
with gr.Column():
with gr.Row():
max_date_textbox = gr.Textbox(
label="Set max date of the column (YYYY-MM-DD)",
visible = False
)
min_date_textbox = gr.Textbox(
label="Set min date of column (YYYY-MM-DD)",
visible = False
)
submit_dates = gr.Button("Submit Dates")
with gr.Row():
preview_df = gr.Dataframe(
label="Preview of filtered dataframe",
interactive=False
)
with gr.Tab("Statistics"):
# Summary statistics and profiling
with gr.Column():
numerical_data = gr.Dataframe(
label="Numerical Column Statistics",
interactive=False
)
categorical_data = gr.Dataframe(
label="Categorical Column Statistics",
interactive=False
)
correlation_matrix= gr.Dataframe(
label="Correlation matrix of dataframe",
interactive=False
)
with gr.Tab("Visualizations"):
# Charts and graphs
with gr.Column():
time_series = gr.Plot(
label="Time Series"
)
with gr.Row():
x_time = gr.Dropdown(
label = "X axis column",
choices=[],
interactive=True,
)
y_time = gr.Dropdown(
label ="Y axis column",
choices=[],
interactive=True,
)
generate_time = gr.Button("Generate Time Series Graph")
#Histogram
with gr.Column():
histogram = gr.Plot(
label="Histogram"
)
with gr.Row():
hist_col = gr.Dropdown(
label = "Histogram variable",
choices=[],
interactive=True,
)
hist_bin = gr.Slider(
label ="Bins",
maximum=1,
minimum=0,
step=1,
interactive=True,
)
generate_hist = gr.Button("Generate Graph")
#Bar chart
with gr.Column():
bar_chart = gr.Plot(
label="Bar chart"
)
with gr.Row():
bar_x = gr.Dropdown(
label = "X axis variable",
choices=[],
interactive=True,
)
bar_y = gr.Dropdown(
label ="Y axis variable",
choices=[],
interactive=True,
)
with gr.Column():
gr.Markdown("Count does not require a column in the Y axis")
agg_method = gr.Dropdown(
label ="How you want categories to be aggregated",
choices=['sum', 'mean', 'median', 'count'],
interactive=True,
)
generate_bar = gr.Button("Generate Graph")
#Scatter plot
with gr.Column():
scatter_plot = gr.Plot(
label="Scatter plot"
)
with gr.Row():
scatter_x = gr.Dropdown(
label = "X axis variable",
choices=[],
interactive=True,
)
scatter_y = gr.Dropdown(
label ="Y axis variable",
choices=[],
interactive=True,
)
generate_scatter = gr.Button("Generate Graph")
download_plots = gr.DownloadButton(
label="Download all graphs",
visible=True
)
with gr.Tab("Insights"):
# Automated insights
max_min_df = gr.DataFrame(
label='Data Insights',
interactive=False
)
std_df = gr.DataFrame(
label='Standard Devation of Values',
interactive=False
)
var_df = gr.DataFrame(
label='Variance of Values',
interactive=False
)
# Connect the upload to the processing function
file_input.change(
fn=dp.process_csv,
inputs=file_input,
outputs=[output, file_upload_textbox]
)
"""Quick Info"""
#Automatically update statistics calculations when dataframe is modified
output.change(
fn=insights.calculate_stats,
inputs=output,
outputs=[numerical_data, categorical_data]
)
output.change(
fn=insights.correlation_matrix,
inputs=output,
outputs=correlation_matrix
)
"""Filter Elements"""
# update the dropdown menu whenever the dataframe is changed
output.change(
fn=utils.update_dropdown,
inputs=output,
outputs=column_dropdown
)
# Create visibility changes when item in dropdown is selected
column_dropdown.change(
fn=utils.update_filter_block,
inputs=[output, column_dropdown],
outputs=[max_num_textbox, min_num_textbox, category_multiselect, max_date_textbox, min_date_textbox]
)
max_num_textbox.change(
fn=dp.set_max,
inputs=[max_num_textbox, output, column_dropdown],
outputs=[preview_df]
)
min_num_textbox.change(
fn=dp.set_min,
inputs=[min_num_textbox, output, column_dropdown],
outputs=[preview_df]
)
column_dropdown.change(
fn=utils.populate_categories,
inputs=[output, column_dropdown],
outputs=[category_multiselect]
)
category_multiselect.change(
fn=dp.set_categories,
inputs=[category_multiselect, output, column_dropdown],
outputs=[preview_df]
)
preview_df.change(
fn=utils.count_rows,
inputs=preview_df,
outputs=row_count
)
submit_dates.click(
fn=dp.submit_dates,
inputs=[output, max_date_textbox, min_date_textbox, column_dropdown],
outputs=preview_df
)
apply_button.click(
fn=utils.apply_filter,
inputs=preview_df,
outputs=output
)
"""Visualization Elements"""
dropdown_pairs = [
(x_time, y_time),
(bar_x, bar_y),
(scatter_x, scatter_y)
]
for drop_x, drop_y in dropdown_pairs:
output.change(
fn=utils.update_dropdown,
inputs=output,
outputs=drop_x
)
output.change(
fn=utils.update_dropdown,
inputs=output,
outputs=drop_y
)
output.change(
fn=utils.update_dropdown,
inputs=output,
outputs=hist_col
)
hist_col.change(
fn=utils.change_slider,
inputs=[output, hist_col],
outputs=hist_bin
)
button_plot_pairs = [(generate_time, time_series, vis.time_series, x_time, y_time), (generate_hist, histogram, vis.histogram, hist_col, hist_bin), (generate_scatter, scatter_plot, vis.scatter, scatter_x, scatter_y)]
for button, plot, graph_func, x, y in button_plot_pairs:
button.click(
fn=graph_func,
inputs=[output, x, y],
outputs=plot
)
generate_bar.click(
fn=vis.bar_chart,
inputs=[output, bar_x, bar_y, agg_method],
outputs=bar_chart
)
download_plots.click(
fn=utils.download_chats,
inputs=[bar_chart, time_series, histogram, scatter_plot]
)
"""Insight Generation"""
output.change(
fn=insights.max_min_df,
inputs=output,
outputs=max_min_df
)
output.change(
fn=insights.std,
inputs=output,
outputs=std_df
)
output.change(
fn=insights.var,
inputs=output,
outputs=var_df
)
# Connect the download button to save function
output.change(
fn=dp.save_csv,
inputs=output,
outputs=download_btn
)
return demo
if __name__ == "__main__":
# Create and launch the Gradio interface
ui = create_gradio_interface()
ui.launch() |