Hugging Face's logo

Spaces:
LivanArzuaga
/
Testcase
Sleeping

App Files Community
LArzuaga commited on
Commit
a8d020d
路
1 Parent(s): e3503ad

Comit1

Browse files
Files changed (4) hide show
  1. Dockerfile +12 -0
  2. main.py +98 -0
  3. mejor_modelo_score_febrero_25.pkl +3 -0
  4. requirements.txt +8 -0
Dockerfile ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.9-slim
2
+
3
+ WORKDIR /app
4
+
5
+ COPY requirements.txt .
6
+ RUN pip install --no-cache-dir -r requirements.txt
7
+
8
+ COPY . .
9
+
10
+ EXPOSE 7860
11
+
12
+ CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
main.py ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from fastapi import FastAPI, File, UploadFile, Response
2
+ from fastapi.responses import HTMLResponse
3
+ import pandas as pd
4
+ import numpy as np
5
+ import pickle
6
+ from io import BytesIO
7
+
8
+ app = FastAPI()
9
+
10
+ # Cargar modelo y datos est谩ticos al iniciar la aplicaci贸n
11
+ model1 = None
12
+ df1 = None
13
+
14
+ @app.on_event("startup")
15
+ def load_assets():
16
+ global model1, df1
17
+ with open('mejor_modelo_score_febrero_25.pkl', 'rb') as f:
18
+ model1 = pickle.load(f)
19
+ df1 = pd.read_excel('df1.xlsx')
20
+
21
+ @app.get("/", response_class=HTMLResponse)
22
+ def read_root():
23
+ return """
24
+ <html>
25
+ <head>
26
+ <title>API de Predicci贸n</title>
27
+ <style>
28
+ body {
29
+ font-family: Arial, sans-serif;
30
+ margin: 40px;
31
+ background-color: #f0f2f5;
32
+ }
33
+ .container {
34
+ max-width: 800px;
35
+ margin: 0 auto;
36
+ padding: 20px;
37
+ background-color: white;
38
+ border-radius: 8px;
39
+ box-shadow: 0 2px 4px rgba(0,0,0,0.1);
40
+ }
41
+ h1 {
42
+ color: #1a73e8;
43
+ border-bottom: 2px solid #1a73e8;
44
+ padding-bottom: 10px;
45
+ }
46
+ p {
47
+ line-height: 1.6;
48
+ color: #333;
49
+ }
50
+ </style>
51
+ </head>
52
+ <body>
53
+ <div class="container">
54
+ <h1>API Funcional 馃殌</h1>
55
+ <p>Bienvenido al sistema de predicci贸n de riesgo.</p>
56
+ <p>Usa el endpoint <code>/model_predict</code> via POST con un archivo XLSX para obtener predicciones.</p>
57
+ <p>Estado del servicio: <span style="color: green; font-weight: bold;">Operativo</span></p>
58
+ </div>
59
+ </body>
60
+ </html>
61
+ """
62
+
63
+ @app.post("/model_predict")
64
+ async def model_predict(file: UploadFile = File(...)):
65
+ content = await file.read()
66
+ data = pd.read_excel(BytesIO(content))
67
+
68
+ predacierta = model1.predict_proba(data)
69
+ predacierta = [p[1] for p in predacierta]
70
+ prediccion_acierta = pd.Series(predacierta, name='prob_90')
71
+
72
+ prediccionrf = pd.concat([df1, prediccion_acierta], axis=1)
73
+
74
+ risk_class = []
75
+ for row in prediccionrf['prob_90']:
76
+ if row > 0.1000039:
77
+ risk_class.append('Extremo')
78
+ elif row > 0.0500117:
79
+ risk_class.append('Muy Alto')
80
+ elif row > 0.0200018:
81
+ risk_class.append('Alto')
82
+ elif row > 0.0060008:
83
+ risk_class.append('Moderado')
84
+ elif row > 0.0020001:
85
+ risk_class.append('Bajo')
86
+ else:
87
+ risk_class.append('Muy Bajo')
88
+
89
+ prediccionrf['risk_class'] = risk_class
90
+ prediccionrf['Score'] = 99.9 - prediccionrf['prob_90'] * 100
91
+
92
+ csv_data = prediccionrf.to_csv(index=False)
93
+
94
+ return Response(
95
+ content=csv_data,
96
+ media_type="text/csv",
97
+ headers={"Content-Disposition": "attachment; filename=predicciones.csv"}
98
+ )
mejor_modelo_score_febrero_25.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c00143b64821c61cd590a9bf44532f5ac449b7079cb21643a6d8740f3e9ed5
3
+ size 123313
requirements.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ fastapi>=0.68.0
2
+ pandas>=1.3.0
3
+ numpy==1.24.3
4
+ catboost
5
+ scikit-learn>=1.0.0
6
+ openpyxl>=3.0.0
7
+ python-multipart>=0.0.5
8
+ uvicorn>=0.15.0