Add application file

.gitignore

@@ -0,0 +1 @@
+/venv_api

Dockerfile

@@ -0,0 +1,12 @@
+FROM Python:3.11
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]
+

main.py

@@ -0,0 +1,94 @@
+from fastapi import FastAPI,HTTPException
+from typing import Literal,List
+import uvicorn
+from pydantic import BaseModel
+import pandas as pd
+import os
+import pickle
+
+# setup
+SRC = os.path.abspath('./SRC/Assets')
+
+# Load the pipeline using pickle
+pipeline_path = os.path.join(SRC, 'pipeline.pkl')
+with open(pipeline_path, 'rb') as file:
+    pipeline = pickle.load(file)
+
+# Load the encoder using pickle
+model_path = os.path.join(SRC, 'rfc_model.pkl')
+with open(model_path, 'rb') as file:
+    model = pickle.load(file)
+
+app = FastAPI(
+    title= 'Income Classification FastAPI',
+    description='A FastAPI service to classify individuals based on income level using a trained machine learning model.',
+    version= '1.0.0'
+)
+
+class IncomePredictionInput(BaseModel):
+    age:                   int
+    gender:                str
+    education:             str
+    worker_class:          str
+    marital_status:        str
+    race:                  str
+    is_hispanic:           str
+    employment_commitment: str
+    employment_stat:       int
+    wage_per_hour:         int
+    working_week_per_year: int
+    industry_code:         int
+    industry_code_main:    str
+    occupation_code:       int
+    occupation_code_main:  str
+    total_employed:        int
+    household_summary:     str
+    vet_benefit:           int
+    tax_status:            str
+    gains:                 int
+    losses:                int
+    stocks_status:         int
+    citizenship:           str
+    importance_of_record:  float
+
+   
+class IncomePredictionOutput(BaseModel):
+    income_prediction: str
+    prediction_probability: float
+
+
+# get
+@app.get('/')
+def home():
+    return {
+        'message': 'Income Classification FastAPI',
+        'description': 'FastAPI service to classify individuals based on income level.',
+        'instruction': 'Click here (/docs) to access API documentation and test endpoints.'
+    }
+   
+
+# post
+@app.post('/classify', response_model=IncomePredictionOutput)
+def income_classification(income: IncomePredictionInput):
+    try:
+        # Convert input data to DataFrame
+        input_df = pd.DataFrame([dict(income)])
+
+        # Preprocess the input data through the pipeline
+        input_df_transformed = pipeline.transform(input_df)
+
+        # Make predictions
+        prediction = model.predict(input_df_transformed)
+        probability = model.predict_proba(input_df_transformed).max(axis=1)[0]
+
+        prediction_result = "Above Limit" if prediction[0] == 1 else "Below Limit"
+        return {"income_prediction": prediction_result, "prediction_probability": probability}
+
+    except Exception as e:
+        error_detail = str(e)
+        raise HTTPException(status_code=500, detail=f"Error during classification: {error_detail}")
+
+
+if __name__ == '__main__':
+    uvicorn.run('main:app', reload=True)
+    

requirements.txt

@@ -0,0 +1,37 @@
+annotated-types==0.6.0
+anyio==4.2.0
+certifi==2023.11.17
+click==8.1.7
+colorama==0.4.6
+dnspython==2.4.2
+email-validator==2.1.0.post1
+fastapi==0.108.0
+h11==0.14.0
+httpcore==1.0.2
+httptools==0.6.1
+httpx==0.26.0
+idna==3.6
+itsdangerous==2.1.2
+Jinja2==3.1.2
+MarkupSafe==2.1.3
+numpy==1.26.3
+orjson==3.9.10
+pandas==2.1.4
+pydantic==2.5.3
+pydantic-extra-types==2.4.0
+pydantic-settings==2.1.0
+pydantic_core==2.14.6
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+six==1.16.0
+sniffio==1.3.0
+starlette==0.32.0.post1
+typing_extensions==4.9.0
+tzdata==2023.4
+ujson==5.9.0
+uvicorn==0.25.0
+watchfiles==0.21.0
+websockets==12.0