fixe

Dockerfile

@@ -0,0 +1,20 @@
+# Use an official Python image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy requirements.txt into the container
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the entire application into the container
+COPY . .
+
+# Expose the port the app runs on
+EXPOSE 7860
+
+# Run the FastAPI application with Uvicorn
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--reload"]

app.py

@@ -0,0 +1,79 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import joblib
+import numpy as np
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Load the trained Gradient Boosting model
+model = joblib.load('gradient_boosting_model.pkl')
+
+# Define the input data schema
+class PredictionInput(BaseModel):
+    age: int
+    job: str
+    marital: str
+    education: str
+    default: str
+    balance: float
+    housing: str
+    loan: str
+    contact: str
+    day: int
+    month: str
+    duration: float
+    campaign: int
+    pdays: int
+    previous: int
+    poutcome: str
+
+# Define the mapping for categorical variables (if encoded)
+categorical_mapping = {
+    "job": ['admin.', 'technician', 'blue-collar', 'management', 'retired', 'services', 'self-employed', 'entrepreneur', 'unemployed', 'housemaid', 'student', 'unknown'],
+    "marital": ['married', 'single', 'divorced'],
+    "education": ['secondary', 'tertiary', 'primary', 'unknown'],
+    "default": ['no', 'yes'],
+    "housing": ['no', 'yes'],
+    "loan": ['no', 'yes'],
+    "contact": ['unknown', 'telephone', 'cellular'],
+    "month": ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec'],
+    "poutcome": ['unknown', 'other', 'failure', 'success']
+}
+
+# Utility function to preprocess the input data
+def preprocess_input(data: PredictionInput):
+    # Convert input data to a feature array
+    features = [
+        data.age,
+        categorical_mapping['job'].index(data.job),
+        categorical_mapping['marital'].index(data.marital),
+        categorical_mapping['education'].index(data.education),
+        categorical_mapping['default'].index(data.default),
+        data.balance,
+        categorical_mapping['housing'].index(data.housing),
+        categorical_mapping['loan'].index(data.loan),
+        categorical_mapping['contact'].index(data.contact),
+        data.day,
+        categorical_mapping['month'].index(data.month),
+        data.duration,
+        data.campaign,
+        data.pdays,
+        data.previous,
+        categorical_mapping['poutcome'].index(data.poutcome),
+    ]
+    return np.array([features])
+
+# Define a POST endpoint for predictions
+@app.post("/predict")
+async def predict(data: PredictionInput):
+    # Preprocess the input
+    input_data = preprocess_input(data)
+    
+    # Make a prediction
+    prediction = model.predict(input_data)
+    
+    # Convert prediction to "yes"/"no"
+    response = "yes" if prediction[0] == 1 else "no"
+    
+    return {"prediction": response}

gradient_boosting_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39cd8c31dfbb53a3936302ace105f40b5f5462cc78fe7007ae7eaf07b1c9611
+size 1287324

requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.95.2
+uvicorn==0.22.0
+scikit-learn==1.3.0
+joblib==1.3.2
+numpy==1.24.3
+pandas==2.0.3