Upload folder using huggingface_hub
Browse files- app.py +5 -5
- requirements.txt +1 -0
app.py
CHANGED
|
@@ -8,7 +8,7 @@ model_path = hf_hub_download(repo_id="sandtemp01/ml-fail-pred-model-hf", filenam
|
|
| 8 |
model = joblib.load(model_path)
|
| 9 |
|
| 10 |
# Streamlit UI for Machine Failure Prediction
|
| 11 |
-
st.title("Machine Failure Prediction App")
|
| 12 |
st.write("""
|
| 13 |
This application predicts the likelihood of a machine failing based on its operational parameters.
|
| 14 |
Please enter the sensor and configuration data below to get a prediction.
|
|
@@ -24,11 +24,11 @@ tool_wear = st.number_input("Tool Wear (min)", min_value=0, max_value=300, value
|
|
| 24 |
|
| 25 |
# Assemble input into DataFrame
|
| 26 |
input_data = pd.DataFrame([{
|
| 27 |
-
'
|
| 28 |
-
'
|
| 29 |
-
'
|
| 30 |
'Torque': torque,
|
| 31 |
-
'
|
| 32 |
'Type': Type
|
| 33 |
}])
|
| 34 |
|
|
|
|
| 8 |
model = joblib.load(model_path)
|
| 9 |
|
| 10 |
# Streamlit UI for Machine Failure Prediction
|
| 11 |
+
st.title("Machine Failure Prediction App-CD")
|
| 12 |
st.write("""
|
| 13 |
This application predicts the likelihood of a machine failing based on its operational parameters.
|
| 14 |
Please enter the sensor and configuration data below to get a prediction.
|
|
|
|
| 24 |
|
| 25 |
# Assemble input into DataFrame
|
| 26 |
input_data = pd.DataFrame([{
|
| 27 |
+
'Air_temperature': air_temp,
|
| 28 |
+
'Process_temperature': process_temp,
|
| 29 |
+
'Rotational_speed': rot_speed,
|
| 30 |
'Torque': torque,
|
| 31 |
+
'Tool_wear': tool_wear,
|
| 32 |
'Type': Type
|
| 33 |
}])
|
| 34 |
|
requirements.txt
CHANGED
|
@@ -4,3 +4,4 @@ streamlit==1.43.2
|
|
| 4 |
joblib==1.5.1
|
| 5 |
scikit-learn==1.6.0
|
| 6 |
xgboost==2.1.4
|
|
|
|
|
|
| 4 |
joblib==1.5.1
|
| 5 |
scikit-learn==1.6.0
|
| 6 |
xgboost==2.1.4
|
| 7 |
+
mlflow==3.0.1
|