adding application

main.py

@@ -0,0 +1,89 @@
+# For app development
+from fastapi import FastAPI, File, UploadFile
+from typing import Annotated
+from fastapi import FastAPI, Form, Depends
+# Import the Response class from fastapi
+from fastapi import Response
+import pandas as pd
+import uvicorn
+from pydantic import BaseModel
+# For data frame
+import pandas as pd
+# For loading pipeline
+import joblib
+# For controlling warnings
+import warnings
+warnings.filterwarnings('ignore')
+# For system functions
+from io import BytesIO
+import os
+
+# Pieline loading
+with open("..\\..\\data\\catboost_pipeline_4.job", "rb") as f:
+    pipe = joblib.load(f) 
+print(pipe)
+
+# instantiating fastAPI object
+app = FastAPI( title = "Machine Learning Classification API for predicting \
+              Income limit as Above Limit / Below Limit") 
+  
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    try:
+        content = await file.read() 
+        df = pd.read_csv(BytesIO(content)) 
+        
+        columns = ['age', 'gender', 'education', 'class', 'marital_status', 'race',
+       'is_hispanic', 'employment_commitment', 'employment_stat',
+       'wage_per_hour', 'working_week_per_year', 'industry_code',
+       'industry_code_main', 'occupation_code', 'occupation_code_main',
+       'total_employed', 'household_stat', 'household_summary', 'vet_benefit',
+       'tax_status', 'gains', 'losses', 'stocks_status', 'citizenship',
+       'mig_year', 'country_of_birth_own', 'country_of_birth_father',
+       'country_of_birth_mother', 'importance_of_record']
+
+        # Copying neccesary columns
+
+        id = df["ID"].copy()
+        print(id)
+
+        df = df[ columns ].copy()
+        print(df)
+
+        # Renaming column class
+        df.rename(columns={'class': 'class_'}, inplace=True)
+
+        # Predicting...
+        output = pipe.predict_proba(df)
+        print(output)
+               
+        df["predicted_label"] = output.argmax(axis = -1)
+        mapping = {0: "Below Limit", 1: "Above Limit"}
+        df["predicted_label"] = [mapping[x] for x in df["predicted_label"]]
+        print(df["predicted_label"])
+
+        # Calculating confidence score
+        confidence_score = output.max(axis= -1)
+        df["confidence_score"] = f"{round( ( confidence_score[0] * 100 ) , 2) }%"
+
+        # Create a dataframe with a column named 'id'
+        df_final = pd.DataFrame(id, columns=['ID'])
+        print(df_final)
+
+        df_final["predicted_label"] = df["predicted_label"]
+        df_final["confidence_score"] = df["confidence_score"]
+        print(df_final)
+
+        print("****************")
+
+        # Convert the dataframe to a CSV string
+        df_csv = df_final.to_csv(index=False)
+
+        # Return the CSV string with the response class
+        return Response(content=df_csv, media_type="text/csv")
+    
+    except Exception as e:
+        return {"error": str(e)} # return an error message if something goes wrong
+
+if __name__ == "__main__":
+    uvicorn.run("main:app" , reload = True)