Upload folder using huggingface_hub

DockerFile

@@ -0,0 +1,23 @@
+#Create base image with Python 3.9 installed
+from PYTHON:3.9
+
+#Setting working directory
+WORKDIR \app 
+
+#Copying files from current directory on the host to the container
+COPY..
+
+#Installing requirements from requirements.txt 
+RUN pip install -r requirements.txt
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME = /home/user \
+  PATH = /home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+#Making streamlit app to run locally on port 8501 and make it access externally
+CMD ["streamlit","run","app.py","--server.port=8501","--server.address=0.0.0.0","--server.enableXsrfProtection = False"]

app.py

@@ -0,0 +1,43 @@
+import streamlit as st
+import pandas as pd
+from huggingface_hub import hf_hub_download
+import joblib
+
+#Download the model from model hub
+model_path = hf_hub_download(repo_id="Shalyn/PredictiveMaintanence-model",filename="engine_condition_model_v1.joblib")
+
+#loading the model
+model = joblib.load(model_path)
+
+#Building Streamlit app UI
+st.title("Predictive Maintanence Prediction Tool")
+st.write("This tool helps to forecast potential failures in vehicles before they occur.")
+st.write("Kindly enter the vehicle sensor values to predict if the vehicle needs maintanence.")
+
+#collect user input
+Engine_RPM = st.number_input("Engine_RPM(The number of revolutions per minute (RPM) of the engine, indicating engine speed. It is defined in Revolutions per Minute (RPM))")
+Lub_Oil_Pressure = st.number_input("Lub_Oil_Pressure (The pressure of the lubricating oil in the engine, essential for reducing friction and wear. It is defined in bar or kilopascals (kPa))")
+Fuel_Pressure = st.number_input("Fuel_Pressure (The pressure at which fuel is supplied to the engine, critical for proper combustion. It is defined in bar or kilopascals (kPa))")
+Coolant_Pressure = st.number_input("Coolant_Pressure (The pressure of the engine coolant, affecting engine temperature regulation. It is defined in bar or kilopascals (kPa) )")
+Lub_Oil_Temperature = st.number_input("Lub_Oil_Temperature (The temperature of the lubricating oil, which impacts viscosity and engine performance. It is defined in degrees Celsius (°C) )")
+Coolant_Temperature = st.number_input("Coolant_Temperature (The temperature of the engine coolant, crucial for preventing overheating. It is defined in degrees Celsius (°C))")
+
+#Converting the inputs to match training datarow
+input_data = pd.DataFrame([{
+    'Engine rpm': Engine_RPM,
+    'Lub oil pressure': Lub_Oil_Pressure,
+    'Fuel pressure': Fuel_Pressure,
+    'Coolant pressure': Coolant_Pressure,
+    'lub oil temp' : Lub_Oil_Temperature,
+    'Coolant temp': Coolant_Temperature
+}])
+
+#setting up classification threshold
+classification_threshold = 0.45
+
+#Creating prediction button
+if st.button("Predict"):
+  prediction_prob = model.predict_proba(input_data)[0,1]
+  prediction = (prediction_prob>classification_threshold).astype(int)
+  result = "Off/False/Active" if prediction == 0 else "On/True/Faulty"
+  st.write(f"Based on the given input the vehicle is {result}")

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+huggingface_hub==0.32.6
+streamlit==1.43.2
+joblib==1.5.1
+scikit-learn
+xgboost==2.1.4
+mlflow==3.0.1