files upload

dockerfile

@@ -0,0 +1,22 @@
+#specifing the docker image
+FROM python:3.9-slim
+
+#setting working directory where my app code is in.
+WORKDIR /app
+
+#copying requirements file from project woekdir to docker dir
+COPY requirements.txt .
+
+RUN pip install  -r requirements.txt
+
+#copying the entire project code to the container
+COPY app.py .
+
+#copying the model to the docker dir
+COPY key_comp key_comp
+
+#specfying the port that my fastapi is in
+EXPOSE 8000
+
+# Run the FastAPI application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

main.py

@@ -0,0 +1,61 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import uvicorn
+import pandas as pd
+import joblib
+
+app = FastAPI()
+
+
+#Load your saved model and components
+def load_model():
+  num_imputer = joblib.load('numerical_imputer.joblib')
+  scaler = joblib.load('scaler.joblib')
+  model = joblib.load('sepsis_model.joblib')
+  return num_imputer, scaler, model
+
+#Create a class for taking inputs
+class UserInput(BaseModel):
+    PRG: int
+    PL: int
+    PR: int
+    SK: int
+    TS: int
+    M11: float
+    BD2: float
+    Age: int
+    Insurance:int
+
+@app.get('/')
+async def index():
+    return {"Sepsis API": "Sepsis Prediction"}
+
+#get data and make predictions
+@app.post('/predict/')
+async def predict(UserInput: UserInput):
+
+  data = {
+           'PRG': UserInput.PRG, 
+           'PL': UserInput.PL,
+           'PR': UserInput.PR,
+           'SK': UserInput.SK,
+           'TS': UserInput.TS,
+           'M11': UserInput.M11,
+           'BD2': UserInput.BD2,
+           'Age': UserInput.Age,
+           'Insurance': UserInput.Insurance,
+                }
+  df = pd.DataFrame(data, index=[0])
+  num_col =  [ 'PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age','Insurance']
+  num_imputer, scaler, model = load_model()
+     #Scale numerical colums
+  scaled_col = scaler.transform(df[num_col])
+  df2 = pd.DataFrame(scaled_col)                  
+  prediction = model.predict(df2).tolist()
+
+  if (prediction[0] == 1):
+    result = "Positive Sepsis"
+  else:
+    result = "Negative Sepsis"
+
+  return{"result":result}

numerical_imputer.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43c1f7b7b8b97db860ddf4ddf83741bc781d08b5b0f610ffd2cecc4d8655143
+size 580

requirements.txt

@@ -0,0 +1,6 @@
+pytest
+scikit-learn
+fastapi[all]
+pydantic
+pandas
+joblib

scaler.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fe6ca76b5671f97668579d398794900497b324d65a21435abdb89222346a1d
+size 665

sepsis_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfbe6ecd57f0bc5f1ec468216f837130436b0f1dea23fe5eba5fb1016ff3a92d
+size 1783