Upload folder using huggingface_hub
Browse files- Dockerfile +0 -1
- app.py +1 -6
Dockerfile
CHANGED
|
@@ -21,4 +21,3 @@ EXPOSE 8501
|
|
| 21 |
|
| 22 |
# Command to run the Streamlit application
|
| 23 |
CMD ["streamlit", "run", "app.py", "--server.port", "8501", "--server.address", "0.0.0.0"]
|
| 24 |
-
|
|
|
|
| 21 |
|
| 22 |
# Command to run the Streamlit application
|
| 23 |
CMD ["streamlit", "run", "app.py", "--server.port", "8501", "--server.address", "0.0.0.0"]
|
|
|
app.py
CHANGED
|
@@ -8,21 +8,16 @@ model = joblib.load("D:/Machine_Learning_Neural_Nets_Course/SuperKart/backend_fi
|
|
| 8 |
# @sapp.get('/')
|
| 9 |
# def home():
|
| 10 |
# return "Welcome to the Supermarket Product Price Predictor!"
|
| 11 |
-
|
| 12 |
-
|
| 13 |
# Define an endpoint
|
| 14 |
##@app.post('/v1/price')
|
| 15 |
-
@sapp.
|
| 16 |
def predict_price():
|
| 17 |
# Get JSON data from the request
|
| 18 |
input_json = request.get_json()
|
| 19 |
-
|
| 20 |
# Convert the extracted data into a DataFrame
|
| 21 |
input_data = pd.DataFrame([input_json])
|
| 22 |
-
|
| 23 |
# Make a churn prediction using the trained model
|
| 24 |
prediction = model.predict(input_data)
|
| 25 |
-
|
| 26 |
# Return the prediction as a JSON response
|
| 27 |
return jsonify({'Price': prediction})
|
| 28 |
|
|
|
|
| 8 |
# @sapp.get('/')
|
| 9 |
# def home():
|
| 10 |
# return "Welcome to the Supermarket Product Price Predictor!"
|
|
|
|
|
|
|
| 11 |
# Define an endpoint
|
| 12 |
##@app.post('/v1/price')
|
| 13 |
+
@sapp.post('/price')
|
| 14 |
def predict_price():
|
| 15 |
# Get JSON data from the request
|
| 16 |
input_json = request.get_json()
|
|
|
|
| 17 |
# Convert the extracted data into a DataFrame
|
| 18 |
input_data = pd.DataFrame([input_json])
|
|
|
|
| 19 |
# Make a churn prediction using the trained model
|
| 20 |
prediction = model.predict(input_data)
|
|
|
|
| 21 |
# Return the prediction as a JSON response
|
| 22 |
return jsonify({'Price': prediction})
|
| 23 |
|