Hugging Face's logo

Spaces:
fantix
/
demographic-33k-alpha
Sleeping

App Files Community
fbellomo commited on
Commit
4f0134c
·
verified ·
1 Parent(s): bb5cfed

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1121 -69
app.py CHANGED
@@ -1,34 +1,432 @@
 
 
 
 
1
  import gradio as gr
2
  import pandas as pd
 
3
 
4
  available_datasets = [
5
- "Demographic",
6
- "Health",
7
- "Financial",
8
- "Social",
9
- "Economic",
10
- "Political",
 
 
11
  ]
12
 
13
- default_dataset = "Demographic"
14
 
15
  available_attributes = [
16
- "Income",
17
  "Age",
 
 
18
  "Marital Status",
19
- "Education",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  ]
21
 
22
- default_attributes = ["Income", "Age"]
 
 
 
 
 
 
 
 
23
 
24
- available_model_versions = ["Demographic Base"]
25
 
26
- default_model_version = "Demographic Base"
 
 
 
27
 
28
- def generate_code_example(dataset, attributes, model_version):
29
- attributes_with_types = ", ".join([f"fantix.type.{attr.upper().replace(' ', '_')}" for attr in attributes])
30
- prediction_columns = ", ".join([f'"{attr}"' for attr in attributes])
31
-
32
  code = f"""
33
  import fantix
34
  import pandas as pd
@@ -55,53 +453,716 @@ response = client.predict(
55
  fantix.type.MARITAL_SATUS,
56
  fantix.type.EDUCATION,
57
  ],
58
- attribute_to_predict=[{attributes_with_types}],
59
- model_version='{model_version},
 
 
60
  )
61
  """
62
  return code.strip()
63
 
64
- def load_dataset(dataset, model_version):
65
- return pd.DataFrame(
66
- {
67
- "Name": ["John", "Doe", "Jane", "Smith"],
68
- "Age": [25, 30, 35, 40],
69
- "Income": [50000, 60000, 70000, 80000],
70
- "Marital Status": ["Single", "Married", "Single", "Married"],
71
- "Education": ["High School", "Bachelor", "Master", "PhD"],
72
- }
73
- )
74
 
 
 
75
 
76
- def predict(dataset, attributes, access_token, model_version):
77
- if not access_token:
78
- raise gr.Error(
79
- "Access token missing or invalid. Please ensure you have a valid access token."
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  )
81
 
82
- prediction_message = "200 predictions made in 2.5 seconds."
83
- prediction_results = pd.DataFrame(
84
- {
85
- "Name": ["John", "Doe", "Jane", "Smith"],
86
- "Predicted Value": [25000, 30000, 35000, 40000],
87
- }
88
- )
89
- return prediction_message, prediction_results
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
 
 
 
 
 
 
 
 
 
 
91
 
92
- def load_dataset_and_predict(dataset, attributes, access_token, model_version):
93
- loaded_data = load_dataset(dataset, model_version)
94
- code_example = generate_code_example(dataset, attributes, model_version)
 
 
 
95
 
96
  if access_token:
97
  prediction_message, prediction_results = predict(
98
- dataset, attributes, access_token, model_version
99
  )
 
 
100
  else:
101
  prediction_message = "No access token provided, prediction skipped."
102
- prediction_results = None
103
 
104
- return loaded_data, prediction_message, prediction_results, code_example
105
 
106
 
107
  interface_theme = gr.themes.Default()
@@ -114,13 +1175,6 @@ with gr.Blocks(theme=interface_theme) as demo:
114
  placeholder="Enter your access token here.",
115
  )
116
 
117
- gr.Markdown("### Model")
118
- model_version = gr.Dropdown(
119
- choices=available_model_versions,
120
- label="Model Version",
121
- value=default_model_version,
122
- )
123
-
124
  with gr.Row():
125
  with gr.Column():
126
  gr.Markdown("### Select Dataset and Attributes")
@@ -140,37 +1194,35 @@ with gr.Blocks(theme=interface_theme) as demo:
140
 
141
  gr.Markdown("### Dataset Preview")
142
  dataset_preview = gr.Dataframe()
 
143
 
144
  with gr.Accordion("Code Example", open=False):
145
  code_example = gr.Code(language="python")
146
-
147
- predict_button = gr.Button("Predict Attributes")
148
 
149
- gr.Markdown("### Prediction Results")
150
- prediction_preview = gr.Dataframe()
151
- prediction_label = gr.Markdown("")
152
 
153
  selected_dataset.change(
 
 
 
 
 
 
154
  fn=generate_code_example,
155
- inputs=[selected_dataset, selected_attributes, model_version],
156
  outputs=code_example,
157
  )
158
 
159
  predict_button.click(
160
- fn=predict,
161
- inputs=[selected_dataset, selected_attributes, access_token, model_version],
162
- outputs=[prediction_label, prediction_preview],
163
- )
164
- predict_button.click(
165
- fn=generate_code_example,
166
- inputs=[selected_dataset, selected_attributes, model_version],
167
- outputs=code_example,
168
  )
169
 
170
  demo.load(
171
  fn=load_dataset_and_predict,
172
- inputs=[selected_dataset, selected_attributes, access_token, model_version],
173
- outputs=[dataset_preview, prediction_label, prediction_preview, code_example],
174
  )
175
 
176
  demo.launch()
 
1
+ # @title Define the application
2
+
3
+ import time
4
+
5
  import gradio as gr
6
  import pandas as pd
7
+ import requests
8
 
9
  available_datasets = [
10
+ "Demographics",
11
+ "DoorDash Customer Segmentation",
12
+ "Personal Care and Lifestyle Category Propensity",
13
+ "Quick Service Restaurant (QSR) Propensity",
14
+ "Technology Brand Propensity",
15
+ "Uber Customer Segmentation",
16
+ "Walgreens Customer Segmentation",
17
+ "Walmart Customer Segmentation",
18
  ]
19
 
20
+ default_dataset = "Demographics"
21
 
22
  available_attributes = [
 
23
  "Age",
24
+ "Gender",
25
+ "Household Income",
26
  "Marital Status",
27
+ "Occupation",
28
+ "Political Affiliation And Voting",
29
+ "Brand Propensity 365 Retail Markets",
30
+ "Brand Propensity 7 Eleven",
31
+ "Brand Propensity Affirm",
32
+ "Brand Propensity Afterpay",
33
+ "Brand Propensity Albert",
34
+ "Brand Propensity Amazon",
35
+ "Brand Propensity Amazon Prime Video",
36
+ "Brand Propensity Apple",
37
+ "Brand Propensity Bp",
38
+ "Brand Propensity Betmgm",
39
+ "Brand Propensity Brigit",
40
+ "Brand Propensity Burger King",
41
+ "Brand Propensity Cvs",
42
+ "Brand Propensity Chevron",
43
+ "Brand Propensity Chick Fil A",
44
+ "Brand Propensity Chumba Casino",
45
+ "Brand Propensity Circle K",
46
+ "Brand Propensity Cleo Ai",
47
+ "Brand Propensity Dave",
48
+ "Brand Propensity Dollar General",
49
+ "Brand Propensity Dollar Tree",
50
+ "Brand Propensity Doordash",
51
+ "Brand Propensity Draftkings",
52
+ "Brand Propensity Dunkin",
53
+ "Brand Propensity Earnin",
54
+ "Brand Propensity Empower",
55
+ "Brand Propensity Family Dollar",
56
+ "Brand Propensity Fanduel",
57
+ "Brand Propensity Fanduel Sportsbook",
58
+ "Brand Propensity Floatme",
59
+ "Brand Propensity Klarna",
60
+ "Brand Propensity Klover App",
61
+ "Brand Propensity Kroger",
62
+ "Brand Propensity Lyft",
63
+ "Brand Propensity Mcdonalds",
64
+ "Brand Propensity Moneylion",
65
+ "Brand Propensity Netflix",
66
+ "Brand Propensity Publix",
67
+ "Brand Propensity Quiktrip",
68
+ "Brand Propensity Sezzle",
69
+ "Brand Propensity Shell",
70
+ "Brand Propensity Sony Playstation",
71
+ "Brand Propensity Speedway",
72
+ "Brand Propensity Starbucks",
73
+ "Brand Propensity Sunoco",
74
+ "Brand Propensity T Mobile",
75
+ "Brand Propensity Taco Bell",
76
+ "Brand Propensity Target",
77
+ "Brand Propensity Uber",
78
+ "Brand Propensity Uber Eats",
79
+ "Brand Propensity Walgreens",
80
+ "Brand Propensity Walmart",
81
+ "Brand Propensity Wawa",
82
+ "Brand Propensity Wendys",
83
+ "Brand Propensity Zip Co",
84
+ "Recency 365 Retail Markets",
85
+ "Recency 7 Eleven",
86
+ "Recency Affirm",
87
+ "Recency Afterpay",
88
+ "Recency Albert",
89
+ "Recency Amazon",
90
+ "Recency Amazon Prime Video",
91
+ "Recency Apple",
92
+ "Recency Bp",
93
+ "Recency Betmgm",
94
+ "Recency Brigit",
95
+ "Recency Burger King",
96
+ "Recency Cvs",
97
+ "Recency Chevron",
98
+ "Recency Chick Fil A",
99
+ "Recency Chumba Casino",
100
+ "Recency Circle K",
101
+ "Recency Cleo Ai",
102
+ "Recency Dave",
103
+ "Recency Dollar General",
104
+ "Recency Dollar Tree",
105
+ "Recency Doordash",
106
+ "Recency Draftkings",
107
+ "Recency Dunkin",
108
+ "Recency Earnin",
109
+ "Recency Empower",
110
+ "Recency Family Dollar",
111
+ "Recency Fanduel",
112
+ "Recency Fanduel Sportsbook",
113
+ "Recency Floatme",
114
+ "Recency Klarna",
115
+ "Recency Klover App",
116
+ "Recency Kroger",
117
+ "Recency Lyft",
118
+ "Recency Mcdonalds",
119
+ "Recency Moneylion",
120
+ "Recency Netflix",
121
+ "Recency Publix",
122
+ "Recency Quiktrip",
123
+ "Recency Sezzle",
124
+ "Recency Shell",
125
+ "Recency Sony Playstation",
126
+ "Recency Speedway",
127
+ "Recency Starbucks",
128
+ "Recency Sunoco",
129
+ "Recency T Mobile",
130
+ "Recency Taco Bell",
131
+ "Recency Target",
132
+ "Recency Uber",
133
+ "Recency Uber Eats",
134
+ "Recency Walgreens",
135
+ "Recency Walmart",
136
+ "Recency Wawa",
137
+ "Recency Wendys",
138
+ "Recency Zip Co",
139
+ "Monetary 365 Retail Markets",
140
+ "Monetary 7 Eleven",
141
+ "Monetary Affirm",
142
+ "Monetary Afterpay",
143
+ "Monetary Albert",
144
+ "Monetary Amazon",
145
+ "Monetary Amazon Prime Video",
146
+ "Monetary Apple",
147
+ "Monetary Bp",
148
+ "Monetary Betmgm",
149
+ "Monetary Brigit",
150
+ "Monetary Burger King",
151
+ "Monetary Cvs",
152
+ "Monetary Chevron",
153
+ "Monetary Chick Fil A",
154
+ "Monetary Chumba Casino",
155
+ "Monetary Circle K",
156
+ "Monetary Cleo Ai",
157
+ "Monetary Dave",
158
+ "Monetary Dollar General",
159
+ "Monetary Dollar Tree",
160
+ "Monetary Doordash",
161
+ "Monetary Draftkings",
162
+ "Monetary Dunkin",
163
+ "Monetary Earnin",
164
+ "Monetary Empower",
165
+ "Monetary Family Dollar",
166
+ "Monetary Fanduel",
167
+ "Monetary Fanduel Sportsbook",
168
+ "Monetary Floatme",
169
+ "Monetary Klarna",
170
+ "Monetary Klover App",
171
+ "Monetary Kroger",
172
+ "Monetary Lyft",
173
+ "Monetary Mcdonalds",
174
+ "Monetary Moneylion",
175
+ "Monetary Netflix",
176
+ "Monetary Publix",
177
+ "Monetary Quiktrip",
178
+ "Monetary Sezzle",
179
+ "Monetary Shell",
180
+ "Monetary Sony Playstation",
181
+ "Monetary Speedway",
182
+ "Monetary Starbucks",
183
+ "Monetary Sunoco",
184
+ "Monetary T Mobile",
185
+ "Monetary Taco Bell",
186
+ "Monetary Target",
187
+ "Monetary Uber",
188
+ "Monetary Uber Eats",
189
+ "Monetary Walgreens",
190
+ "Monetary Walmart",
191
+ "Monetary Wawa",
192
+ "Monetary Wendys",
193
+ "Monetary Zip Co",
194
+ "Frequency 365 Retail Markets",
195
+ "Frequency 7 Eleven",
196
+ "Frequency Affirm",
197
+ "Frequency Afterpay",
198
+ "Frequency Albert",
199
+ "Frequency Amazon",
200
+ "Frequency Amazon Prime Video",
201
+ "Frequency Apple",
202
+ "Frequency Bp",
203
+ "Frequency Betmgm",
204
+ "Frequency Brigit",
205
+ "Frequency Burger King",
206
+ "Frequency Cvs",
207
+ "Frequency Chevron",
208
+ "Frequency Chick Fil A",
209
+ "Frequency Chumba Casino",
210
+ "Frequency Circle K",
211
+ "Frequency Cleo Ai",
212
+ "Frequency Dave",
213
+ "Frequency Dollar General",
214
+ "Frequency Dollar Tree",
215
+ "Frequency Doordash",
216
+ "Frequency Draftkings",
217
+ "Frequency Dunkin",
218
+ "Frequency Earnin",
219
+ "Frequency Empower",
220
+ "Frequency Family Dollar",
221
+ "Frequency Fanduel",
222
+ "Frequency Fanduel Sportsbook",
223
+ "Frequency Floatme",
224
+ "Frequency Klarna",
225
+ "Frequency Klover App",
226
+ "Frequency Kroger",
227
+ "Frequency Lyft",
228
+ "Frequency Mcdonalds",
229
+ "Frequency Moneylion",
230
+ "Frequency Netflix",
231
+ "Frequency Publix",
232
+ "Frequency Quiktrip",
233
+ "Frequency Sezzle",
234
+ "Frequency Shell",
235
+ "Frequency Sony Playstation",
236
+ "Frequency Speedway",
237
+ "Frequency Starbucks",
238
+ "Frequency Sunoco",
239
+ "Frequency T Mobile",
240
+ "Frequency Taco Bell",
241
+ "Frequency Target",
242
+ "Frequency Uber",
243
+ "Frequency Uber Eats",
244
+ "Frequency Walgreens",
245
+ "Frequency Walmart",
246
+ "Frequency Wawa",
247
+ "Frequency Wendys",
248
+ "Frequency Zip Co",
249
+ "Category Propensity Atm",
250
+ "Category Propensity Airlines And Aviation Services",
251
+ "Category Propensity Arts And Crafts",
252
+ "Category Propensity Arts And Entertainment",
253
+ "Category Propensity Automotive",
254
+ "Category Propensity Beauty Products",
255
+ "Category Propensity Billpay",
256
+ "Category Propensity Bookstores",
257
+ "Category Propensity Business Services",
258
+ "Category Propensity Car Service",
259
+ "Category Propensity Clothing And Accessories",
260
+ "Category Propensity Computers And Electronics",
261
+ "Category Propensity Convenience Stores",
262
+ "Category Propensity Credit",
263
+ "Category Propensity Credit Card",
264
+ "Category Propensity Debit",
265
+ "Category Propensity Department Stores",
266
+ "Category Propensity Deposit",
267
+ "Category Propensity Digital Purchase",
268
+ "Category Propensity Discount Stores",
269
+ "Category Propensity Education",
270
+ "Category Propensity Entertainment",
271
+ "Category Propensity Financial",
272
+ "Category Propensity Food And Beverage",
273
+ "Category Propensity Food And Beverage Store",
274
+ "Category Propensity Gas Stations",
275
+ "Category Propensity Gift And Novelty",
276
+ "Category Propensity Government Departments And Agencies",
277
+ "Category Propensity Gyms And Fitness Centers",
278
+ "Category Propensity Healthcare Services",
279
+ "Category Propensity Insufficient Funds",
280
+ "Category Propensity Insurance",
281
+ "Category Propensity Jewelry And Watches",
282
+ "Category Propensity Keep The Change Savings Program",
283
+ "Category Propensity Lodging",
284
+ "Category Propensity Organizations And Associations",
285
+ "Category Propensity Overdraft",
286
+ "Category Propensity Parking",
287
+ "Category Propensity Personal Care",
288
+ "Category Propensity Pharmacies",
289
+ "Category Propensity Public Transportation Services",
290
+ "Category Propensity Religious",
291
+ "Category Propensity Rent",
292
+ "Category Propensity Restaurants",
293
+ "Category Propensity Shipping And Freight",
294
+ "Category Propensity Sporting Goods",
295
+ "Category Propensity Subscription",
296
+ "Category Propensity Supermarkets And Groceries",
297
+ "Category Propensity Taxi",
298
+ "Category Propensity Telecommunication Services",
299
+ "Category Propensity Third Party",
300
+ "Category Propensity Utilities",
301
+ "Category Propensity Withdrawal",
302
+ "LTV 365 Retail Markets",
303
+ "LTV 7 Eleven",
304
+ "LTV Affirm",
305
+ "LTV Afterpay",
306
+ "LTV Albert",
307
+ "LTV Amazon",
308
+ "LTV Amazon Prime Video",
309
+ "LTV Apple",
310
+ "LTV Bp",
311
+ "LTV Betmgm",
312
+ "LTV Brigit",
313
+ "LTV Burger King",
314
+ "LTV Cvs",
315
+ "LTV Chevron",
316
+ "LTV Chick Fil A",
317
+ "LTV Chumba Casino",
318
+ "LTV Circle K",
319
+ "LTV Cleo Ai",
320
+ "LTV Dave",
321
+ "LTV Dollar General",
322
+ "LTV Dollar Tree",
323
+ "LTV Doordash",
324
+ "LTV Draftkings",
325
+ "LTV Dunkin",
326
+ "LTV Earnin",
327
+ "LTV Empower",
328
+ "LTV Family Dollar",
329
+ "LTV Fanduel",
330
+ "LTV Fanduel Sportsbook",
331
+ "LTV Floatme",
332
+ "LTV Klarna",
333
+ "LTV Klover App",
334
+ "LTV Kroger",
335
+ "LTV Lyft",
336
+ "LTV Mcdonalds",
337
+ "LTV Moneylion",
338
+ "LTV Netflix",
339
+ "LTV Publix",
340
+ "LTV Quiktrip",
341
+ "LTV Sezzle",
342
+ "LTV Shell",
343
+ "LTV Sony Playstation",
344
+ "LTV Speedway",
345
+ "LTV Starbucks",
346
+ "LTV Sunoco",
347
+ "LTV T Mobile",
348
+ "LTV Taco Bell",
349
+ "LTV Target",
350
+ "LTV Uber",
351
+ "LTV Uber Eats",
352
+ "LTV Walgreens",
353
+ "LTV Walmart",
354
+ "LTV Wawa",
355
+ "LTV Wendys",
356
+ "LTV Zip Co",
357
+ "Share Wallet 365 Retail Markets",
358
+ "Share Wallet 7 Eleven",
359
+ "Share Wallet Affirm",
360
+ "Share Wallet Afterpay",
361
+ "Share Wallet Albert",
362
+ "Share Wallet Amazon",
363
+ "Share Wallet Amazon Prime Video",
364
+ "Share Wallet Apple",
365
+ "Share Wallet Bp",
366
+ "Share Wallet Betmgm",
367
+ "Share Wallet Brigit",
368
+ "Share Wallet Burger King",
369
+ "Share Wallet Cvs",
370
+ "Share Wallet Chevron",
371
+ "Share Wallet Chick Fil A",
372
+ "Share Wallet Chumba Casino",
373
+ "Share Wallet Circle K",
374
+ "Share Wallet Cleo Ai",
375
+ "Share Wallet Dave",
376
+ "Share Wallet Dollar General",
377
+ "Share Wallet Dollar Tree",
378
+ "Share Wallet Doordash",
379
+ "Share Wallet Draftkings",
380
+ "Share Wallet Dunkin",
381
+ "Share Wallet Earnin",
382
+ "Share Wallet Empower",
383
+ "Share Wallet Family Dollar",
384
+ "Share Wallet Fanduel",
385
+ "Share Wallet Fanduel Sportsbook",
386
+ "Share Wallet Floatme",
387
+ "Share Wallet Klarna",
388
+ "Share Wallet Klover App",
389
+ "Share Wallet Kroger",
390
+ "Share Wallet Lyft",
391
+ "Share Wallet Mcdonalds",
392
+ "Share Wallet Moneylion",
393
+ "Share Wallet Netflix",
394
+ "Share Wallet Publix",
395
+ "Share Wallet Quiktrip",
396
+ "Share Wallet Sezzle",
397
+ "Share Wallet Shell",
398
+ "Share Wallet Sony Playstation",
399
+ "Share Wallet Speedway",
400
+ "Share Wallet Starbucks",
401
+ "Share Wallet Sunoco",
402
+ "Share Wallet T Mobile",
403
+ "Share Wallet Taco Bell",
404
+ "Share Wallet Target",
405
+ "Share Wallet Uber",
406
+ "Share Wallet Uber Eats",
407
+ "Share Wallet Walgreens",
408
+ "Share Wallet Walmart",
409
+ "Share Wallet Wawa",
410
+ "Share Wallet Wendys",
411
+ "Share Wallet Zip Co",
412
  ]
413
 
414
+ default_attributes = [
415
+ "Brand Propensity 365 Retail Markets",
416
+ "Brand Propensity 7 Eleven",
417
+ "Brand Propensity Affirm",
418
+ "Brand Propensity Afterpay",
419
+ "Brand Propensity Albert",
420
+ "Brand Propensity Amazon",
421
+ "Brand Propensity Amazon Prime Video",
422
+ ]
423
 
 
424
 
425
+ def generate_code_example(attributes):
426
+ attributes_with_types = ", \n".join(
427
+ [f"\t\tfantix.type.{attr.upper().replace(' ', '_')}" for attr in attributes]
428
+ )
429
 
 
 
 
 
430
  code = f"""
431
  import fantix
432
  import pandas as pd
 
453
  fantix.type.MARITAL_SATUS,
454
  fantix.type.EDUCATION,
455
  ],
456
+ attribute_to_predict=[
457
+ {attributes_with_types}
458
+ ],
459
+ model_version="demographic-33k-alpha",
460
  )
461
  """
462
  return code.strip()
463
 
 
 
 
 
 
 
 
 
 
 
464
 
465
+ def load_dataset(dataset):
466
+ formated_dataset_name = dataset.lower().replace(" ", "_")
467
 
468
+ print(f"Loading dataset: {formated_dataset_name}")
469
+
470
+ if formated_dataset_name == "demographics":
471
+ return pd.DataFrame(
472
+ {
473
+ "age": [
474
+ "65-74",
475
+ "25-34",
476
+ "65-74",
477
+ "65-74",
478
+ "65-74",
479
+ "75+",
480
+ "55-64",
481
+ "75+",
482
+ "65-74",
483
+ "25-34",
484
+ "25-34",
485
+ "75+",
486
+ "55-64",
487
+ "65-74",
488
+ "65-74",
489
+ "75+",
490
+ "75+",
491
+ "55-64",
492
+ "35-44",
493
+ ],
494
+ "gender": [
495
+ "female",
496
+ "male",
497
+ "female",
498
+ "female",
499
+ "female",
500
+ "female",
501
+ "male",
502
+ "female",
503
+ "male",
504
+ "female",
505
+ "female",
506
+ "female",
507
+ "male",
508
+ "female",
509
+ "male",
510
+ "male",
511
+ "female",
512
+ "female",
513
+ "male",
514
+ ],
515
+ "occupation": [
516
+ "professional_or_technical",
517
+ "business_owner",
518
+ "management",
519
+ "management",
520
+ "clerical_service_worker",
521
+ "retired",
522
+ "business_owner",
523
+ "management",
524
+ "business_owner",
525
+ "business_owner",
526
+ "management",
527
+ "professional_or_technical",
528
+ "management",
529
+ "business_owner",
530
+ "contractors",
531
+ "retired",
532
+ "professional_or_technical",
533
+ "business_owner",
534
+ "contractors",
535
+ ],
536
+ "household_income": [
537
+ "$75k-$99k",
538
+ "$100k-$149k",
539
+ "$30k-$39k",
540
+ "$75k-$99k",
541
+ "$20k-$29k",
542
+ "$30k-$39k",
543
+ "$20k-$29k",
544
+ "$75k-$99k",
545
+ "$40k-$49k",
546
+ "$100k-$149k",
547
+ "$100k-$149k",
548
+ "$100k-$149k",
549
+ "$100k-$149k",
550
+ "$50k-$74k",
551
+ "$30k-$39k",
552
+ "$40k-$49k",
553
+ "$50k-$74k",
554
+ "$100k-$149k",
555
+ "$20k-$29k",
556
+ ],
557
+ }
558
+ )
559
+ elif formated_dataset_name == "doordash_customer_segmentation":
560
+ return pd.DataFrame(
561
+ {
562
+ "monetary_doordash": [
563
+ 1,
564
+ 3,
565
+ 2,
566
+ 2,
567
+ 1,
568
+ 1,
569
+ 1,
570
+ 2,
571
+ 4,
572
+ 4,
573
+ 2,
574
+ 2,
575
+ 2,
576
+ 1,
577
+ 1,
578
+ 4,
579
+ 4,
580
+ 1,
581
+ 1,
582
+ ],
583
+ "frequency_doordash": [
584
+ 1,
585
+ 1,
586
+ 1,
587
+ 1,
588
+ 1,
589
+ 1,
590
+ 1,
591
+ 1,
592
+ 1,
593
+ 1,
594
+ 1,
595
+ 1,
596
+ 1,
597
+ 1,
598
+ 1,
599
+ 4,
600
+ 4,
601
+ 1,
602
+ 1,
603
+ ],
604
+ "recency_doorDash": [
605
+ 4,
606
+ 1,
607
+ 3,
608
+ 3,
609
+ 2,
610
+ 1,
611
+ 3,
612
+ 5,
613
+ 5,
614
+ 5,
615
+ 5,
616
+ 5,
617
+ 5,
618
+ 4,
619
+ 1,
620
+ 1,
621
+ 1,
622
+ 2,
623
+ 2,
624
+ ],
625
+ }
626
+ )
627
+ elif formated_dataset_name == "personal_care_and_lifestyle_category_propensity":
628
+ return pd.DataFrame(
629
+ {
630
+ "category_propensity_beauty_products": [
631
+ 3,
632
+ 3,
633
+ 1,
634
+ 1,
635
+ 1,
636
+ 1,
637
+ 1,
638
+ 1,
639
+ 1,
640
+ 1,
641
+ 1,
642
+ 1,
643
+ 1,
644
+ 1,
645
+ 1,
646
+ 1,
647
+ 2,
648
+ 2,
649
+ 2,
650
+ ],
651
+ "category_propensity_personal_care": [
652
+ 2,
653
+ 2,
654
+ 2,
655
+ 2,
656
+ 2,
657
+ 2,
658
+ 2,
659
+ 2,
660
+ 1,
661
+ 1,
662
+ 1,
663
+ 1,
664
+ 1,
665
+ 1,
666
+ 1,
667
+ 1,
668
+ 2,
669
+ 2,
670
+ 2,
671
+ ],
672
+ "category_propensity_gyms_and_fitness_centers": [
673
+ 3,
674
+ 3,
675
+ 1,
676
+ 1,
677
+ 1,
678
+ 1,
679
+ 1,
680
+ 1,
681
+ 1,
682
+ 1,
683
+ 1,
684
+ 1,
685
+ 1,
686
+ 1,
687
+ 1,
688
+ 1,
689
+ 1,
690
+ 1,
691
+ 1,
692
+ ],
693
+ "category_propensity_pharmacies": [
694
+ 4,
695
+ 4,
696
+ 1,
697
+ 1,
698
+ 1,
699
+ 1,
700
+ 1,
701
+ 1,
702
+ 1,
703
+ 1,
704
+ 1,
705
+ 1,
706
+ 1,
707
+ 1,
708
+ 1,
709
+ 1,
710
+ 4,
711
+ 4,
712
+ 4,
713
+ ],
714
+ }
715
  )
716
 
717
+ elif formated_dataset_name == "quick_service_restaurant_(qsr)_propensity":
718
+ return pd.DataFrame(
719
+ {
720
+ "brand_propensity_burger_king": [
721
+ 2,
722
+ 2,
723
+ 2,
724
+ 2,
725
+ 2,
726
+ 2,
727
+ 1,
728
+ 1,
729
+ 1,
730
+ 1,
731
+ 1,
732
+ 1,
733
+ 3,
734
+ 3,
735
+ 3,
736
+ 3,
737
+ 1,
738
+ 1,
739
+ 1,
740
+ ],
741
+ "brand_propensity_chick_fil_a": [
742
+ 1,
743
+ 1,
744
+ 1,
745
+ 1,
746
+ 1,
747
+ 1,
748
+ 1,
749
+ 1,
750
+ 1,
751
+ 1,
752
+ 1,
753
+ 1,
754
+ 2,
755
+ 2,
756
+ 2,
757
+ 2,
758
+ 4,
759
+ 5,
760
+ 5,
761
+ ],
762
+ "brand_propensity_mcdonalds": [
763
+ 2,
764
+ 2,
765
+ 2,
766
+ 2,
767
+ 2,
768
+ 2,
769
+ 1,
770
+ 1,
771
+ 1,
772
+ 1,
773
+ 1,
774
+ 1,
775
+ 2,
776
+ 2,
777
+ 2,
778
+ 2,
779
+ 1,
780
+ 4,
781
+ 4,
782
+ ],
783
+ "brand_propensity_taco_bell": [
784
+ 2,
785
+ 2,
786
+ 2,
787
+ 2,
788
+ 2,
789
+ 2,
790
+ 1,
791
+ 1,
792
+ 1,
793
+ 1,
794
+ 1,
795
+ 1,
796
+ 5,
797
+ 5,
798
+ 5,
799
+ 5,
800
+ 2,
801
+ 1,
802
+ 1,
803
+ ],
804
+ }
805
+ )
806
+
807
+ elif formated_dataset_name == "technology_brand_propensity":
808
+ return pd.DataFrame(
809
+ {
810
+ "brand_propensity_apple": [
811
+ 4,
812
+ 4,
813
+ 4,
814
+ 2,
815
+ 2,
816
+ 2,
817
+ 2,
818
+ 2,
819
+ 2,
820
+ 5,
821
+ 5,
822
+ 5,
823
+ 5,
824
+ 5,
825
+ 5,
826
+ 5,
827
+ 5,
828
+ 2,
829
+ 2,
830
+ ],
831
+ "brand_propensity_amazon": [
832
+ 2,
833
+ 2,
834
+ 2,
835
+ 1,
836
+ 1,
837
+ 1,
838
+ 1,
839
+ 1,
840
+ 1,
841
+ 2,
842
+ 2,
843
+ 2,
844
+ 2,
845
+ 2,
846
+ 2,
847
+ 2,
848
+ 2,
849
+ 1,
850
+ 1,
851
+ ],
852
+ "brand_propensity_sony_playstation": [
853
+ 2,
854
+ 2,
855
+ 2,
856
+ 3,
857
+ 3,
858
+ 3,
859
+ 3,
860
+ 3,
861
+ 5,
862
+ 2,
863
+ 2,
864
+ 2,
865
+ 2,
866
+ 2,
867
+ 2,
868
+ 2,
869
+ 2,
870
+ 1,
871
+ 1,
872
+ ],
873
+ "brand_propensity_netflix": [
874
+ 2,
875
+ 2,
876
+ 2,
877
+ 3,
878
+ 3,
879
+ 3,
880
+ 3,
881
+ 3,
882
+ 2,
883
+ 2,
884
+ 2,
885
+ 2,
886
+ 2,
887
+ 2,
888
+ 2,
889
+ 2,
890
+ 2,
891
+ 2,
892
+ 2,
893
+ ],
894
+ }
895
+ )
896
+ elif formated_dataset_name == "uber_customer_segmentation":
897
+ return pd.DataFrame(
898
+ {
899
+ "monetary_uber": [
900
+ 2,
901
+ 2,
902
+ 5,
903
+ 1,
904
+ 1,
905
+ 1,
906
+ 1,
907
+ 1,
908
+ 1,
909
+ 1,
910
+ 1,
911
+ 1,
912
+ 1,
913
+ 1,
914
+ 1,
915
+ 1,
916
+ 1,
917
+ 1,
918
+ 2,
919
+ ],
920
+ "frequency_uber": [
921
+ 2,
922
+ 2,
923
+ 5,
924
+ 1,
925
+ 1,
926
+ 1,
927
+ 1,
928
+ 1,
929
+ 1,
930
+ 1,
931
+ 1,
932
+ 1,
933
+ 1,
934
+ 1,
935
+ 1,
936
+ 1,
937
+ 1,
938
+ 1,
939
+ 2,
940
+ ],
941
+ "recency_uber": [
942
+ 5,
943
+ 5,
944
+ 1,
945
+ 4,
946
+ 1,
947
+ 4,
948
+ 1,
949
+ 1,
950
+ 5,
951
+ 5,
952
+ 3,
953
+ 3,
954
+ 3,
955
+ 2,
956
+ 3,
957
+ 2,
958
+ 3,
959
+ 1,
960
+ 4,
961
+ ],
962
+ }
963
+ )
964
+ elif formated_dataset_name == "walgreens_customer_segmentation":
965
+ return pd.DataFrame(
966
+ {
967
+ "monetary_walgreens": [
968
+ 4,
969
+ 3,
970
+ 2,
971
+ 2,
972
+ 3,
973
+ 3,
974
+ 1,
975
+ 2,
976
+ 1,
977
+ 1,
978
+ 2,
979
+ 2,
980
+ 2,
981
+ 2,
982
+ 2,
983
+ 2,
984
+ 2,
985
+ 2,
986
+ 1,
987
+ ],
988
+ "frequency_walgreens": [
989
+ 4,
990
+ 2,
991
+ 1,
992
+ 1,
993
+ 1,
994
+ 1,
995
+ 1,
996
+ 1,
997
+ 1,
998
+ 1,
999
+ 2,
1000
+ 1,
1001
+ 1,
1002
+ 5,
1003
+ 5,
1004
+ 5,
1005
+ 5,
1006
+ 5,
1007
+ 1,
1008
+ ],
1009
+ "recency_walgreens": [
1010
+ 1,
1011
+ 4,
1012
+ 4,
1013
+ 4,
1014
+ 5,
1015
+ 5,
1016
+ 5,
1017
+ 1,
1018
+ 4,
1019
+ 4,
1020
+ 1,
1021
+ 3,
1022
+ 3,
1023
+ 1,
1024
+ 1,
1025
+ 1,
1026
+ 1,
1027
+ 1,
1028
+ 4,
1029
+ ],
1030
+ }
1031
+ )
1032
+ elif formated_dataset_name == "walmart_customer_segmentation":
1033
+ return pd.DataFrame(
1034
+ {
1035
+ "monetary_walmart": [
1036
+ 1,
1037
+ 1,
1038
+ 1,
1039
+ 3,
1040
+ 3,
1041
+ 1,
1042
+ 1,
1043
+ 1,
1044
+ 1,
1045
+ 1,
1046
+ 1,
1047
+ 1,
1048
+ 1,
1049
+ 1,
1050
+ 1,
1051
+ 1,
1052
+ 1,
1053
+ 1,
1054
+ 1,
1055
+ ],
1056
+ "frequency_walmart": [
1057
+ 1,
1058
+ 1,
1059
+ 1,
1060
+ 1,
1061
+ 1,
1062
+ 2,
1063
+ 2,
1064
+ 1,
1065
+ 1,
1066
+ 1,
1067
+ 1,
1068
+ 1,
1069
+ 1,
1070
+ 1,
1071
+ 1,
1072
+ 1,
1073
+ 1,
1074
+ 1,
1075
+ 1,
1076
+ ],
1077
+ "recency_walmart": [
1078
+ 1,
1079
+ 1,
1080
+ 1,
1081
+ 3,
1082
+ 2,
1083
+ 2,
1084
+ 2,
1085
+ 1,
1086
+ 3,
1087
+ 3,
1088
+ 3,
1089
+ 5,
1090
+ 5,
1091
+ 5,
1092
+ 5,
1093
+ 5,
1094
+ 4,
1095
+ 1,
1096
+ 2,
1097
+ ],
1098
+ }
1099
+ )
1100
+ else:
1101
+ return pd.DataFrame()
1102
+
1103
+
1104
+ def predict(dataset, attributes, access_token):
1105
+ """
1106
+ Makes a prediction using an external API call and calculates the performance.
1107
+
1108
+ Parameters:
1109
+ - dataset (list of dict): The input data for prediction.
1110
+ - attributes (list): The attributes to predict.
1111
+ - access_token (str): The access token for API authentication.
1112
+
1113
+ Returns:
1114
+ - tuple: A message about the prediction, prediction results as a DataFrame,
1115
+ and the number of predictions made in the given time frame.
1116
+ """
1117
+ api_url = "https://rb3mw988lz88cvpz.us-east-1.aws.endpoints.huggingface.cloud"
1118
+ headers = {
1119
+ "Accept": "application/json",
1120
+ "Authorization": f"Bearer {access_token}",
1121
+ "Content-Type": "application/json"
1122
+ }
1123
+
1124
+ payload = {
1125
+ "inputs": [
1126
+ {
1127
+ "input_data": dataset.to_dict(orient="records"),
1128
+ "attributes_to_predict": [
1129
+ attribute.lower().replace(" ", "_") for attribute in attributes
1130
+ ],
1131
+ }
1132
+ ],
1133
+ }
1134
+
1135
+ start_time = time.time()
1136
+ response = requests.post(api_url, headers=headers, json=payload)
1137
+ end_time = time.time()
1138
 
1139
+ elapsed_time = end_time - start_time
1140
+
1141
+ if response.status_code == 200:
1142
+ prediction_results = pd.DataFrame(response.json())
1143
+ predictions_count = len(prediction_results)
1144
+ prediction_message = f"{predictions_count} predictions made in {elapsed_time:.2f} seconds."
1145
+ else:
1146
+ prediction_message = "Failed to make predictions."
1147
+ prediction_results = pd.DataFrame([])
1148
 
1149
+ return prediction_message, prediction_results
1150
+
1151
+ def load_dataset_and_predict(dataset, attributes, access_token):
1152
+ loaded_data = load_dataset(dataset)
1153
+
1154
+ code_example = generate_code_example(attributes)
1155
 
1156
  if access_token:
1157
  prediction_message, prediction_results = predict(
1158
+ loaded_data, attributes, access_token
1159
  )
1160
+
1161
+ return prediction_results, prediction_message, code_example
1162
  else:
1163
  prediction_message = "No access token provided, prediction skipped."
 
1164
 
1165
+ return loaded_data, prediction_message, code_example
1166
 
1167
 
1168
  interface_theme = gr.themes.Default()
 
1175
  placeholder="Enter your access token here.",
1176
  )
1177
 
 
 
 
 
 
 
 
1178
  with gr.Row():
1179
  with gr.Column():
1180
  gr.Markdown("### Select Dataset and Attributes")
 
1194
 
1195
  gr.Markdown("### Dataset Preview")
1196
  dataset_preview = gr.Dataframe()
1197
+ prediction_label = gr.Markdown("")
1198
 
1199
  with gr.Accordion("Code Example", open=False):
1200
  code_example = gr.Code(language="python")
 
 
1201
 
1202
+ predict_button = gr.Button("Predict Attributes")
 
 
1203
 
1204
  selected_dataset.change(
1205
+ fn=load_dataset,
1206
+ inputs=[selected_dataset],
1207
+ outputs=dataset_preview,
1208
+ )
1209
+
1210
+ selected_attributes.change(
1211
  fn=generate_code_example,
1212
+ inputs=[selected_attributes],
1213
  outputs=code_example,
1214
  )
1215
 
1216
  predict_button.click(
1217
+ fn=load_dataset_and_predict,
1218
+ inputs=[selected_dataset, selected_attributes, access_token],
1219
+ outputs=[dataset_preview, prediction_label, code_example],
 
 
 
 
 
1220
  )
1221
 
1222
  demo.load(
1223
  fn=load_dataset_and_predict,
1224
+ inputs=[selected_dataset, selected_attributes, access_token],
1225
+ outputs=[dataset_preview, prediction_label, code_example],
1226
  )
1227
 
1228
  demo.launch()