final version

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 data/NECRIF_and_PRISM_merged.csv filter=lfs diff=lfs merge=lfs -text
 data/PRISM.pkl filter=lfs diff=lfs merge=lfs -text
+data/2024_11_7_total_return_sample.pkl filter=lfs diff=lfs merge=lfs -text

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----
+MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw
+TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh
+cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4
+WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu
+ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY
+MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc
+h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+
+0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U
+A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW
+T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH
+B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC
+B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv
+KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn
+OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn
+jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw
+qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI
+rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV
+HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq
+hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL
+ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ
+3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK
+NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5
+ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur
+TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC
+jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc
+oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq
+4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA
+mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d
+emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc=
+-----END CERTIFICATE-----

.gradio/flagged/dataset1.csv

@@ -0,0 +1,2 @@
+Select CBSA Area,Predicted Total Return for 2025 (Quarters),timestamp
+AL-Birmingham-Hoover,,2024-11-05 12:18:07.477425

app.py

@@ -1,53 +1,118 @@
-# Import required libraries
 import gradio as gr
 import numpy as np
+import pandas as pd
 import pickle
 from tensorflow.keras.models import load_model
 from sklearn.preprocessing import MinMaxScaler
+import matplotlib.pyplot as plt
+from io import BytesIO
+from PIL import Image
+import json
 
-# Load the model and scaler
 model = load_model('models/new_merged_weather_financial_q_l4q_l24q.keras')
 scaler = MinMaxScaler()
 
-# Load the dataset from the pickle file
 with open('data/PRISM.pkl', 'rb') as f:
     data = pickle.load(f)
 
-# Process the data as before
-features = data.drop(columns=['Date', 'CBSA_Name', 'Id', 'iname', 'type', 'Cluster', 'region', 'division', 'state', 'msa'])
+data = data.sort_values(by=['YYYYQ', 'CBSA_Name'])
+
+features = data.drop(
+    columns=['Date', 'CBSA_Name', 'Id', 'iname', 'type', 'Cluster', 'region', 'division', 'state', 'msa'])
 scaler.fit(features)
 
-def predict_future(cbsa_name):
-    # Filter data for the selected CBSA
+
+def get_actual_values_2015_2023(cbsa_name):
+    with open('data/2024_11_7_total_return_sample.pkl', 'rb') as f:
+        cbsa_filtered_data = pickle.load(f)
+
+    cbsa_data = cbsa_filtered_data[cbsa_filtered_data['CBSA_Name'] == cbsa_name]
+    cbsa_data = cbsa_data.sort_values(by='YYYYQ')
+    cbsa_data['YYYYQ'] = cbsa_data['YYYYQ'].astype(str).str.strip()
+
+    actual_values = cbsa_data[(cbsa_data['YYYYQ'].str[:4].astype(int) >= 2015) &
+                              (cbsa_data['YYYYQ'].str[:4].astype(int) <= 2023)]['tret'].values
+
+    return actual_values
+
+
+def predict_and_plot(cbsa_name):
     cbsa_data = data[data['CBSA_Name'] == cbsa_name]
-    cbsa_features = cbsa_data.drop(
-        columns=['Date', 'CBSA_Name', 'Id', 'iname', 'type', 'Cluster', 'region', 'division', 'state', 'msa'])
+    cbsa_data = cbsa_data.sort_values(by='YYYYQ')
+    cbsa_data['YYYYQ'] = cbsa_data['YYYYQ'].astype(str).str.strip()
+
+    actual_values = get_actual_values_2015_2023(cbsa_name)
 
-    # Scale the features
+    cbsa_features = cbsa_data.drop(
+        columns=['Date', 'CBSA_Name', 'Id', 'iname', 'type', 'Cluster', 'region', 'division', 'state', 'msa']
+    )
     cbsa_scaled_features = scaler.transform(cbsa_features)
 
-    # Prepare the input sequence
-    num_steps = 24
+    num_steps = min(len(cbsa_scaled_features), 24)
     latest_sequence = cbsa_scaled_features[-num_steps:].reshape(1, num_steps, cbsa_scaled_features.shape[1])
-
-    # Generate predictions for the next 4 quarters
     future_predictions = []
-    for _ in range(4):
+
+    for _ in range(44):  # Ensure predictions cover from 2015 Q1 to 2025 Q4
         predicted_value = model.predict(latest_sequence)[0, 0]
-        future_predictions.append(predicted_value)
+        future_predictions.append(float(predicted_value))  # Convert to native float type
         latest_sequence = np.roll(latest_sequence, -1, axis=1)
         latest_sequence[0, -1, -1] = predicted_value
 
-    return {f"2025 Q{i + 1}": pred for i, pred in enumerate(future_predictions)}
+    combined_values = np.array(future_predictions)
+
+    years_quarters = [f"{year} Q{quarter}" for year in range(2015, 2026) for quarter in range(1, 5)]
+    years_quarters = years_quarters[:len(combined_values)]
+
+    predicted_json = []
+    for i, value in enumerate(combined_values[len(actual_values):]):
+        year, quarter = years_quarters[len(actual_values) + i].split()
+        predicted_json.append({"Year": int(year), "Quarter": quarter, "Value": round(value, 3)})
+
+    json_output = {
+        "CBSA": cbsa_name,
+        "Label": "Total Return",
+        "Predicted": predicted_json
+    }
+
+    plt.figure(figsize=(14, 6))
+    plt.plot(years_quarters[:len(actual_values)], actual_values, label="Actual (2015-2023)", marker='o', color='blue')
+    plt.plot(years_quarters, combined_values, label="Predicted (2015-2025)", linestyle='--', color='orange')
+
+    plt.title(f'Total Return Prediction for {cbsa_name} (2015-2025)')
+    plt.xlabel('Quarter')
+    plt.ylabel('Total Return')
+    plt.xticks(rotation=45)
+    plt.legend()
+
+    buf = BytesIO()
+    plt.savefig(buf, format='png')
+    buf.seek(0)
+    img = Image.open(buf)
+    img_array = np.array(img)
+
+    return img_array, json.dumps(json_output, indent=2)
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            cbsa_dropdown = gr.Dropdown(choices=data['CBSA_Name'].unique().tolist(), label="Select CBSA Area")
+            predict_button = gr.Button("Submit")
+        with gr.Column():
+            gr.Markdown("""
+            **Total Return**: Total return is a measure of the performance of an asset or investment over a specific period, defined as the sum of **Income Return** and **Asset Return**. 
+
+            - **Income Return**: The net income generated by a property, calculated as rental income minus operating and capital expenditures.
+            - **Asset Return**: The appreciation in the market value of a property from purchase to sale.
+
+            **CBSA (Core-Based Statistical Area)**: Represents a geographical area defined by the Office of Management and Budget, typically used for statistical purposes in the U.S. It consists of counties and county equivalents centered around an urban center with a high degree of social and economic integration.
+            """)
+    with gr.Row():
+        with gr.Column():
+            output_image = gr.Image(type="numpy", label="Actual vs Predicted Total Return (2015-2025)")
+        with gr.Column():
+            json_display = gr.JSON(label="Prediction JSON Output")
 
-# Set CBSA options
-cbsa_options = data['CBSA_Name'].unique().tolist()
-iface = gr.Interface(
-    fn=predict_future,
-    inputs=gr.Dropdown(choices=cbsa_options, label="Select CBSA Area"),
-    outputs=gr.JSON(label="Predicted Total Return for 2025 (Quarters)"),
-    title="CBSA Total Return Predictor",
-    description="Select a CBSA to get predicted total returns for the upcoming year."
-)
+    predict_button.click(fn=predict_and_plot, inputs=cbsa_dropdown, outputs=[output_image, json_display])
 
-iface.launch()
+demo.launch()

data/2024_11_7_total_return_sample.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0043164c3837ad6e8d742088852919f908a1514ea980e7bd3c8aaee260c7b4e
+size 3905447

requirements.txt

@@ -3,3 +3,4 @@ tensorflow
 pandas
 numpy
 scikit-learn
+matplotlib