Updates

app.py

@@ -4,15 +4,15 @@ import pickle
 import os
 
 # Load the model and encoder
-SIC = os.path.abspath('.')
-pipeline_path = os.path.join(SIC, 'rfc_pipeline.pkl')
-encoder_path = os.path.join(SIC, 'encoder.pkl')
+SRC = os.path.abspath('.')
+pipeline_path = os.path.join(SRC, 'pipeline.pkl')
+model_path = os.path.join(SRC, 'rfc_model.pkl')
 
 with open(pipeline_path, 'rb') as file:
-    model = pickle.load(file)
+    pipeline = pickle.load(file)
 
-with open(encoder_path, 'rb') as file:
-    encoder = pickle.load(file)
+with open(model_path, 'rb') as file:
+    model = pickle.load(file)
 
 # Sidebar for navigation
 st.sidebar.title("Navigation")
@@ -98,9 +98,12 @@ if options == "Prediction":
             'citizenship', 'importance_of_record'
         ])
 
+        # Preprocess the input data through the pipeline before making predictions
+        input_data_transformed = pipeline.transform(input_data)
+
         # Predict and display results
-        prediction = model.predict(input_data)
-        probability = model.predict_proba(input_data).max(axis=1)[0]
+        prediction = model.predict(input_data_transformed)
+        probability = model.predict_proba(input_data_transformed).max(axis=1)[0]
         result = "Above Limit" if prediction[0] == 1 else "Below Limit"
         st.success(f'Income Level Prediction: {result}')
         st.info(f'Prediction Probability: {probability:.2f}')
@@ -119,8 +122,8 @@ elif options == "Model Information":
         - **Training Data:** 
           - Our model is trained on comprehensive census data, encompassing a wide range of features such as age, education, marital status, race, occupation, and more. This rich dataset ensures a nuanced understanding of the socio-economic factors influencing income levels.
 
-        - **Accuracy:** 92%
-          - With an accuracy of 92%, our model stands as a reliable predictor, demonstrating its effectiveness in understanding and categorizing income levels.
+        - **Accuracy:** 94%
+          - With an accuracy of 94%, our model stands as a reliable predictor, demonstrating its effectiveness in understanding and categorizing income levels.
 
         - **What It Aims to Solve:**
           - **Economic Research:** Assists in socio-economic studies, understanding income distribution, and identifying key factors influencing income levels.
@@ -135,7 +138,6 @@ elif options == "Model Information":
 
 
 # Feedback Page
-
 elif options == "Feedback":
     st.title("Feedback")
     st.write("We value your feedback! Please let us know your thoughts about the model and interface.")

encoder.pkl → pipeline.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98baac762b1becb7d5b699f21576a27ebe7555a83826444f23d540dcfc7d01d1
-size 270
+oid sha256:dd28c23cc70beba35906a28c1b6937630ffb3bb4a7c5e8cb8276f66a33eb60e4
+size 4811

requirements.txt

@@ -1,3 +1,3 @@
-streamlit
-pandas
-scikit-learn==1.3.0 
+streamlit==1.29.0
+pandas==2.1.4
+scikit-learn==1.3.2 

rfc_pipeline.pkl → rfc_model.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6be7713061b3b93f04b7e4c3239216dc6f51b4b18ead0b60fce19c0cbe594e
-size 223631035
+oid sha256:cd6ad029aa941d54353a585b399b77c15380a06cfa80a2c81faf9697effe0aac
+size 267723561