Create app.py

app.py

@@ -0,0 +1,101 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from datetime import datetime
+import joblib
+
+# Load the trained Random Forest model
+rf_model = joblib.load('rf_model.joblib')
+
+# Load encoders
+le_jobtitle = joblib.load('le_jobtitle.joblib')
+le_location = joblib.load('le_location.joblib')
+le_season = joblib.load('le_season.joblib')
+
+# Load scaler
+scaler = joblib.load('scaler.joblib')
+
+# Load target encoding mapping for Hospital
+hospital_target_mapping = joblib.load('hospital_target_mapping.joblib')
+
+# Load lists for dropdown menus
+job_titles = joblib.load('job_titles.joblib')
+locations = joblib.load('locations.joblib')
+hospitals = joblib.load('hospitals.joblib')
+
+# Streamlit app
+st.title('Hourly Pay Rate Prediction')
+
+st.write("""
+This application predicts the **Hourly Pay Rate** based on:
+- Job Title
+- Location
+- Hospital
+- Contract Start Date
+- Contract End Date
+""")
+
+# User inputs
+job_title = st.selectbox('Job Title', sorted(job_titles))
+location = st.selectbox('Location', sorted(locations))
+hospital = st.selectbox('Hospital', sorted(hospitals))
+contract_start_date = st.date_input('Contract Start Date', datetime.today())
+contract_end_date = st.date_input('Contract End Date', datetime.today())
+
+# Validate contract dates
+if contract_end_date < contract_start_date:
+    st.error('Contract End Date must be after Contract Start Date.')
+    st.stop()
+
+# Feature Engineering
+contract_duration = (contract_end_date - contract_start_date).days
+start_month = contract_start_date.month
+start_year = contract_start_date.year
+
+def get_season(month):
+    if month in [12, 1, 2]:
+        return 'Winter'
+    elif month in [3, 4, 5]:
+        return 'Spring'
+    elif month in [6, 7, 8]:
+        return 'Summer'
+    else:
+        return 'Fall'
+
+season = get_season(start_month)
+
+job_title_encoded = le_jobtitle.transform([job_title])[0]
+location_encoded = le_location.transform([location])[0]
+season_encoded = le_season.transform([season])[0]
+
+# For 'HospitalEncoded_RF', use the target encoding mapping
+average_hourly_rate = np.mean(list(hospital_target_mapping.values()))
+hospital_encoded_rf = hospital_target_mapping.get(hospital, average_hourly_rate)
+
+# Prepare numerical features
+numerical_features = ['ContractDuration', 'StartMonth', 'StartYear']
+numerical_values = np.array([[contract_duration, start_month, start_year]])
+numerical_values_scaled = scaler.transform(numerical_values)
+
+input_data = pd.DataFrame({
+    'JobTitleEncoded': [job_title_encoded],
+    'LocationEncoded': [location_encoded],
+    'HospitalEncoded_RF': [hospital_encoded_rf],
+    'SeasonEncoded': [season_encoded],
+    'ContractDuration': [numerical_values_scaled[0][0]],
+    'StartMonth': [numerical_values_scaled[0][1]],
+    'StartYear': [numerical_values_scaled[0][2]],
+})
+
+features_rf = [
+    'JobTitleEncoded',
+    'LocationEncoded',
+    'HospitalEncoded_RF',
+    'SeasonEncoded',
+    'ContractDuration',
+    'StartMonth',
+    'StartYear'
+]
+
+prediction = rf_model.predict(input_data[features_rf])
+st.write(f"## Predicted Hourly Pay Rate: ${prediction[0]:.2f}")