Upload app.py with huggingface_hub
Browse files
app.py
CHANGED
|
@@ -6,20 +6,33 @@ import gradio as gr
|
|
| 6 |
import joblib
|
| 7 |
import pandas as pd
|
| 8 |
from huggingface_hub import hf_hub_download
|
|
|
|
| 9 |
|
| 10 |
-
|
| 11 |
-
model_path = hf_hub_download(
|
| 12 |
-
repo_id="niru-nny/house-price-prediction",
|
| 13 |
-
filename="house_price_model.joblib"
|
| 14 |
-
)
|
| 15 |
-
pipeline_path = hf_hub_download(
|
| 16 |
-
repo_id="niru-nny/house-price-prediction",
|
| 17 |
-
filename="preprocessing_pipeline.joblib"
|
| 18 |
-
)
|
| 19 |
|
| 20 |
-
#
|
| 21 |
-
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
def predict_price(longitude, latitude, housing_median_age, total_rooms,
|
| 25 |
total_bedrooms, population, households, median_income,
|
|
|
|
| 6 |
import joblib
|
| 7 |
import pandas as pd
|
| 8 |
from huggingface_hub import hf_hub_download
|
| 9 |
+
import os
|
| 10 |
|
| 11 |
+
print("🔄 Downloading model files...")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
+
# Download model files
|
| 14 |
+
try:
|
| 15 |
+
model_path = hf_hub_download(
|
| 16 |
+
repo_id="niru-nny/house-price-prediction",
|
| 17 |
+
filename="house_price_model.joblib"
|
| 18 |
+
)
|
| 19 |
+
print(f"✅ Model downloaded: {model_path}")
|
| 20 |
+
|
| 21 |
+
pipeline_path = hf_hub_download(
|
| 22 |
+
repo_id="niru-nny/house-price-prediction",
|
| 23 |
+
filename="preprocessing_pipeline.joblib"
|
| 24 |
+
)
|
| 25 |
+
print(f"✅ Pipeline downloaded: {pipeline_path}")
|
| 26 |
+
|
| 27 |
+
# Load model and pipeline
|
| 28 |
+
print("🔄 Loading model and pipeline...")
|
| 29 |
+
model = joblib.load(model_path)
|
| 30 |
+
pipeline = joblib.load(pipeline_path)
|
| 31 |
+
print("✅ Model and pipeline loaded successfully!")
|
| 32 |
+
|
| 33 |
+
except Exception as e:
|
| 34 |
+
print(f"❌ Error loading model: {e}")
|
| 35 |
+
raise
|
| 36 |
|
| 37 |
def predict_price(longitude, latitude, housing_median_age, total_rooms,
|
| 38 |
total_bedrooms, population, households, median_income,
|