Upload 5 files

Dockerfile

@@ -0,0 +1,23 @@
+# pull python base image
+FROM python:3.10
+
+COPY requirements.txt requirements.txt
+
+# update pip
+RUN pip install --upgrade pip
+
+# install dependencies
+RUN pip install -r requirements.txt
+
+RUN useradd -m -u 1000 myuser
+
+USER myuser
+
+# copy application files
+COPY --chown=myuser . .
+
+# expose port for application
+EXPOSE 8001
+
+# start fastapi application
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,106 @@
+from fastapi import FastAPI, Request, Response
+
+import gradio
+import joblib
+from xgboost import XGBClassifier
+import pandas as pd
+import numpy as np
+
+from sklearn.metrics import f1_score, precision_score, recall_score
+import prometheus_client as prom
+
+app = FastAPI()
+
+username = "runaksh"
+repo_name = "Patientsurvival-model"
+repo_path = username+ '/' + repo_name
+sentiment_model = pipeline(model= repo_path)
+
+import pandas as pd
+
+test_data = pd.read_csv("test_data.csv")
+
+f1_metric = prom.Gauge('sentiment_f1_score', 'F1 score for random 100 test samples')
+precision_metric = prom.Gauge('sentiment_precision_score', 'Precision score for random 100 test samples')
+recall_metric = prom.Gauge('sentiment_recall_score', 'Recall score for random 100 test samples')
+
+
+# Function for response generation
+# Load your trained model
+xgb_model_loaded = joblib.load("xgboost-model.pkl")
+
+def bol_to_int(bol):
+  if bol==True:
+    return 1
+  else:
+    return 0
+
+# Function for prediction
+def predict_death_event(feature1, feature2, feature3,feature4, feature5, feature6, feature7, feature8, feature9, feature10, feature11, feature12):
+    data = {'age' : [feature1], 'anaemia' : [bol_to_int(feature2)],
+            'creatinine_phosphokinase' : [feature3],
+            'diabetes' : [bol_to_int(feature4)],
+            'ejection_fraction' : [feature5],
+            'high_blood_pressure' : [bol_to_int(feature6)],
+            'platelets' : [feature7],
+            'serum_creatinine' : [feature8],
+            'serum_sodium' : [feature9],
+            'sex' : [bol_to_int(feature10)],
+            'smoking' : [bol_to_int(feature11)],
+            'time' : [feature12]}
+    df = pd.DataFrame(data)
+    y_pred = xgb_model_loaded.predict(df)[0]
+    return y_pred
+
+# Function for updating metrics
+def update_metrics():
+    test = test_data.sample(100)
+    test_text = test['Text'].values
+    test_pred = sentiment_model(list(test_text))
+    pred_labels = [int(pred['label'].split("_")[1]) for pred in test_pred]
+    f1 = f1_score(test['labels'], pred_labels).round(3)
+    precision = precision_score(test['labels'], pred_labels).round(3)
+    recall = recall_score(test['labels'], pred_labels).round(3)
+    
+    f1_metric.set(f1)
+    precision_metric.set(precision)
+    recall_metric.set(recall)
+
+
+@app.get("/metrics")
+async def get_metrics():
+    update_metrics()
+    return Response(media_type="text/plain", content= prom.generate_latest())
+
+
+# Gradio interface to generate UI link
+# Gradio interface to generate UI link
+title = "Patient Survival Prediction"
+description = "Predict survival of patient with heart failure, given their clinical record"
+
+iface = gradio.Interface(fn = predict_death_event,
+                         inputs=[
+                            gradio.components.Slider(30, 100, step=1, label= 'age'),
+                            gradio.components.Radio(["0","1"], label= 'anaemia'),
+                            gradio.components.Slider(1, 10000, step=1, label= 'creatinine_phosphokinase'),
+                            gradio.components.Radio(["0","1"], label= 'diabetes'),
+                            gradio.components.Slider(1, 100, step=1, label= 'ejection_fraction'),
+                            gradio.components.Radio(["0","1"], label= 'high_blood_pressure'),
+                            gradio.components.Number(label= 'platelets'),
+                            gradio.components.Slider(0.1, 10.0, step=0.1, label= 'serum_creatinine'),
+                            gradio.components.Slider(100, 150, step=1, label= 'serum_sodium'),
+                            gradio.components.Radio(["0","1"], label= 'sex'),
+                            gradio.components.Radio(["0","1"], label= 'smoking'),
+                            gradio.components.Slider(1, 300, step=1, label= 'time')],
+                         outputs = [gradio.components.Textbox (label ='DeathEvent')],
+                         title = title,
+                         description = description)
+
+app = gradio.mount_gradio_app(app, iface, path="/")
+
+#iface.launch(server_name = "0.0.0.0", server_port = 8001) # Ref. for parameters: https://www.gradio.app/docs/interface
+
+if __name__ == "__main__":
+    # Use this for debugging purposes only
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8001)

requirements.txt

@@ -0,0 +1,14 @@
+torch
+gradio
+joblib
+numpy
+pandas
+xgboost
+
+uvicorn
+fastapi
+python-multipart
+pydantic
+
+scikit-learn
+prometheus-client

test_data.csv

@@ -0,0 +1,91 @@
+age,anaemia,creatinine_phosphokinase,diabetes,ejection_fraction,high_blood_pressure,platelets,serum_creatinine,serum_sodium,sex,smoking,time,DEATH_EVENT
+70,0,161,0,25,0,244000,1.2,142,0,0,66,1
+53,1,270,1,35,0,227000,2.15,145,1,0,105,0
+60,1,588,1,60,0,194000,1.1,142,0,0,33,1
+53,1,1280.25,0,60,1,249000,0.7,138,1,1,106,0
+65,0,118,0,50,0,194000,1.1,145,1,1,200,0
+70,0,93,0,35,0,185000,1.1,134,1,1,208,0
+50,0,482,1,30,0,329000,0.9,132,0,0,109,0
+60,1,96,1,60,1,271000,0.7,136,0,0,94,0
+65,1,68,1,60,1,304000,0.8,140,1,0,79,0
+60,0,68,0,20,0,119000,2.15,127,1,1,64,1
+90,1,47,0,40,1,204000,2.1,132,1,1,8,1
+90,1,337,0,38,0,390000,0.9,144,0,0,256,0
+65,1,59,1,60,0,172000,0.9,137,0,0,107,0
+60,0,1280.25,1,25,0,365000,2.1,144,0,0,172,1
+70,0,69,0,40,0,293000,1.7,136,0,0,75,0
+65,1,335,0,35,1,235000,0.8,136,0,0,120,0
+60,0,253,0,35,0,279000,1.7,140,1,0,250,0
+61,1,84,0,40,1,229000,0.9,141,0,0,110,0
+75,1,81,0,38,1,368000,2.15,131,1,1,10,1
+63,1,103,1,35,0,179000,0.9,136,1,1,270,0
+40,0,244,0,45,1,275000,0.9,140,0,0,174,0
+70,1,125,0,25,1,237000,1,140,0,0,15,1
+49,1,69,0,50,0,132000,1,140,0,0,147,0
+75,0,582,1,30,1,263358.03,1.83,134,0,0,23,1
+73,1,231,1,30,0,160000,1.18,142,1,1,180,0
+65,0,157,0,65,0,263358.03,1.5,138,0,0,10,1
+60,1,315,1,60,0,440000,1.1,131,1,1,10,1
+66,1,72,0,40,1,242000,1.2,134,1,0,121,0
+53,0,63,1,60,0,368000,0.8,135,1,0,22,0
+45,0,1280.25,0,38,0,140000,1.4,140,1,1,280,0
+42,0,102,1,40,0,237000,1.2,140,1,0,74,0
+50,0,115,0,45,1,184000,0.9,134,1,1,118,0
+55,0,748,0,45,0,263000,1.3,137,1,0,88,0
+70,0,97,0,60,1,220000,0.9,138,1,0,186,0
+53,1,91,0,20,1,418000,1.4,139,0,0,43,1
+60,0,582,0,40,0,217000,2.15,134,1,0,96,1
+60,1,154,0,25,0,210000,1.7,135,1,0,82,1
+44,0,582,1,30,1,263358.03,1.6,130,1,1,244,0
+55,1,180,0,45,0,263358.03,1.18,137,1,1,211,0
+63,1,122,1,60,0,267000,1.2,145,1,0,147,0
+58,1,57,0,25,0,189000,1.3,132,1,1,205,0
+58,1,200,1,60,0,300000,0.8,137,0,0,104,0
+64,0,143,0,25,0,246000,2.15,135,1,0,214,0
+85,0,129,0,60,0,306000,1.2,132,1,1,90,1
+78,1,64,0,40,0,277000,0.7,137,1,1,187,0
+52,0,190,1,38,0,382000,1,140,1,1,258,0
+70,0,1202,0,50,1,358000,0.9,141,0,0,196,0
+80,1,123,0,35,1,388000,2.15,133,1,1,10,1
+95,1,112,0,40,1,196000,1,138,0,0,24,1
+63,1,1280.25,0,45,0,76000,0.7,137,1,0,186,0
+67,0,213,0,38,0,215000,1.2,133,0,0,245,0
+58,1,60,0,38,0,153000,2.15,134,1,0,26,1
+60,0,235,1,38,0,329000,2.15,142,0,0,30,1
+59,1,129,0,45,1,362000,1.1,139,1,1,121,0
+78,0,224,0,50,0,440000,1.4,138,1,1,192,0
+70,0,571,1,45,1,185000,1.2,139,1,1,33,1
+65,1,113,1,60,1,203000,0.9,140,0,0,94,0
+50,0,582,1,38,0,310000,1.9,135,1,1,35,1
+55,0,1199,0,20,0,263358.03,1.83,134,1,1,241,1
+62,0,281,1,35,0,221000,1,136,0,0,108,0
+45,1,66,1,25,0,233000,0.8,135,1,0,230,0
+46,1,291,0,35,0,348000,0.9,140,0,0,109,0
+64,0,1280.25,0,60,0,242000,1,137,1,0,113,0
+55,1,1280.25,0,35,1,141000,1,140,1,0,206,0
+95,1,371,0,30,0,440000,2,132,1,0,50,1
+65,1,305,0,25,0,298000,1.1,141,1,0,87,0
+50,1,121,1,40,0,260000,0.7,130,1,0,175,0
+60,1,260,1,38,0,255000,2.15,132,0,1,45,1
+65,0,198,1,35,1,281000,0.9,137,1,1,146,0
+80,0,582,1,35,0,350000,2.1,134,1,0,174,0
+55,0,835,0,40,0,279000,0.7,140,1,1,147,0
+50,0,196,0,45,0,395000,1.6,136,1,1,285,0
+50,0,582,0,50,0,153000,0.6,134,0,0,172,1
+62,0,30,1,60,1,244000,0.9,139,1,0,117,0
+51,0,1280.25,0,25,1,271000,0.9,130,1,0,38,1
+69,0,1280.25,0,40,0,105000,1,135,1,1,147,0
+70,1,143,0,60,0,351000,1.3,137,0,0,90,1
+65,1,135,0,35,1,290000,0.8,134,1,0,194,0
+50,1,582,1,20,1,279000,1,134,0,0,186,0
+53,0,207,1,40,0,223000,1.2,130,0,0,214,0
+60,1,156,1,25,1,318000,1.2,137,0,0,85,0
+45,0,1280.25,1,60,0,440000,0.8,138,0,0,278,0
+85,0,212,0,38,0,186000,0.9,136,1,0,187,0
+55,0,60,0,35,0,228000,1.2,135,1,1,90,0
+47,0,582,0,25,0,130000,0.8,134,1,0,201,0
+72,1,328,0,30,1,440000,1.7,138,0,1,88,1
+70,1,171,0,60,1,176000,1.1,145,1,1,146,0
+75,1,203,1,38,1,283000,0.6,131,1,1,74,0
+50,1,111,0,20,0,210000,1.9,137,1,0,7,1
+73,0,582,0,20,0,263358.03,1.83,134,1,0,198,1

xgboost-model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c0d2599174830ec5a9052af2a416a00ef52c7e61b44844bf32c833cdb6de7f
+size 189168