Spaces:
Sleeping
Sleeping
Upload folder using huggingface_hub
Browse files- Dockerfile +7 -21
- app.py +88 -0
- requirements.txt +3 -3
Dockerfile
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
-
FROM python:3.
|
| 2 |
-
|
| 3 |
-
WORKDIR /app
|
| 4 |
-
|
| 5 |
-
RUN
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
software-properties-common \
|
| 9 |
-
git \
|
| 10 |
-
&& rm -rf /var/lib/apt/lists/*
|
| 11 |
-
|
| 12 |
-
COPY requirements.txt ./
|
| 13 |
-
COPY src/ ./src/
|
| 14 |
-
|
| 15 |
-
RUN pip3 install -r requirements.txt
|
| 16 |
-
|
| 17 |
-
EXPOSE 8501
|
| 18 |
-
|
| 19 |
-
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
|
| 20 |
-
|
| 21 |
-
ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
|
|
|
|
| 1 |
+
FROM python:3.11-slim
|
| 2 |
+
|
| 3 |
+
WORKDIR /app
|
| 4 |
+
COPY . .
|
| 5 |
+
RUN pip install --no-cache-dir -r requirements.txt
|
| 6 |
+
|
| 7 |
+
CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
app.py
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
import streamlit as st
|
| 3 |
+
import pandas as pd
|
| 4 |
+
import requests
|
| 5 |
+
|
| 6 |
+
# Configure backend URL (defaults to your Space). You can override in the UI.
|
| 7 |
+
DEFAULT_BACKEND_URL = "https://12ongo-backendproject.hf.space"
|
| 8 |
+
backend_url = st.text_input(
|
| 9 |
+
"Backend URL",
|
| 10 |
+
value=st.secrets.get("BACKEND_URL", DEFAULT_BACKEND_URL),
|
| 11 |
+
help="Override if needed (e.g., local http://127.0.0.1:5000)",
|
| 12 |
+
)
|
| 13 |
+
|
| 14 |
+
st.title("SuperKart Sales Prediction")
|
| 15 |
+
|
| 16 |
+
st.subheader("Online Prediction")
|
| 17 |
+
|
| 18 |
+
# Input widgets
|
| 19 |
+
product_weight = st.number_input("Product Weight", min_value=0.0, value=10.0, step=0.1)
|
| 20 |
+
product_sugar_content = st.selectbox(
|
| 21 |
+
"Product Sugar Content",
|
| 22 |
+
["low sugar", "regular", "no sugar"],
|
| 23 |
+
)
|
| 24 |
+
product_allocated_area = st.number_input("Product Allocated Area", min_value=0.0, value=0.15, step=0.01)
|
| 25 |
+
product_type = st.selectbox(
|
| 26 |
+
"Product Type",
|
| 27 |
+
[
|
| 28 |
+
"meat",
|
| 29 |
+
"snack foods",
|
| 30 |
+
"hard drinks",
|
| 31 |
+
"dairy",
|
| 32 |
+
"canned",
|
| 33 |
+
"soft drinks",
|
| 34 |
+
"health and hygiene",
|
| 35 |
+
"baking goods",
|
| 36 |
+
"bread",
|
| 37 |
+
"breakfast",
|
| 38 |
+
"frozen foods",
|
| 39 |
+
"fruits and vegetables",
|
| 40 |
+
"household",
|
| 41 |
+
"seafood",
|
| 42 |
+
"starchy foods",
|
| 43 |
+
"others",
|
| 44 |
+
],
|
| 45 |
+
)
|
| 46 |
+
product_mrp = st.number_input("Product MRP", min_value=0.0, value=99.0, step=0.5)
|
| 47 |
+
store_before_2005 = st.checkbox("Store Established Before 2005?", value=True)
|
| 48 |
+
store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
|
| 49 |
+
store_city_type = st.selectbox("Store City Type", ["Tier 1", "Tier 2", "Tier 3"])
|
| 50 |
+
store_type = st.selectbox(
|
| 51 |
+
"Store Type",
|
| 52 |
+
["Departmental Store", "Supermarket Type 1", "Supermarket Type 2", "Food Mart"],
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
if st.button("Predict Sales"):
|
| 56 |
+
payload = {
|
| 57 |
+
"Product_Weight": product_weight,
|
| 58 |
+
"Product_Sugar_Content": product_sugar_content,
|
| 59 |
+
"Product_Allocated_Area": product_allocated_area,
|
| 60 |
+
"Product_Type": product_type,
|
| 61 |
+
"Product_MRP": product_mrp,
|
| 62 |
+
"Store_Establishment_Year_Before_2005": bool(store_before_2005),
|
| 63 |
+
"Store_Size": store_size,
|
| 64 |
+
"Store_Location_City_Type": store_city_type,
|
| 65 |
+
"Store_Type": store_type,
|
| 66 |
+
}
|
| 67 |
+
try:
|
| 68 |
+
resp = requests.post(f"{backend_url}/v1/sales", json=payload, timeout=30)
|
| 69 |
+
if resp.status_code == 200:
|
| 70 |
+
st.success(f"Predicted Sales: {resp.json().get('Predicted_Sales')}")
|
| 71 |
+
else:
|
| 72 |
+
st.error(f"Error {resp.status_code}: {resp.text}")
|
| 73 |
+
except Exception as e:
|
| 74 |
+
st.error(f"Request failed: {e}")
|
| 75 |
+
|
| 76 |
+
st.subheader("Batch Prediction")
|
| 77 |
+
uploaded_file = st.file_uploader("Upload CSV (same schema as training features)", type=["csv"])
|
| 78 |
+
if uploaded_file is not None:
|
| 79 |
+
if st.button("Predict Batch"):
|
| 80 |
+
try:
|
| 81 |
+
files = {"file": uploaded_file}
|
| 82 |
+
resp = requests.post(f"{backend_url}/v1/salesbatch", files=files, timeout=60)
|
| 83 |
+
if resp.status_code == 200:
|
| 84 |
+
st.write(pd.DataFrame({"Predicted_Sales": resp.json().get("Predicted_Sales", [])}))
|
| 85 |
+
else:
|
| 86 |
+
st.error(f"Error {resp.status_code}: {resp.text}")
|
| 87 |
+
except Exception as e:
|
| 88 |
+
st.error(f"Batch request failed: {e}")
|
requirements.txt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
streamlit
|
|
|
|
| 1 |
+
pandas==2.2.2
|
| 2 |
+
requests==2.32.3
|
| 3 |
+
streamlit==1.43.2
|