fix starting point and nlinear

.gitignore

@@ -1,10 +1,13 @@
 *.idea/
 
 # Ignore venv directory
-venv/
+.venv/
 
 __pycache__/
 
+Models/
+
+Dataset/
 
 checkpoints/
 

README.md

@@ -1,12 +1,12 @@
 ---
-title: AI Project
-emoji: 🐨
-colorFrom: red
-colorTo: indigo
+title: LTBoost
+emoji: 📈
+colorFrom: purple
+colorTo: yellow
 sdk: gradio
-sdk_version: 4.28.3
+sdk_version: 4.44.0
 app_file: app.py
-pinned: false
+pinned: true
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,12 +1,7 @@
-import os
 import gradio as gr
 import matplotlib.pyplot as plt
+import os
 
-def toggle_num_variable_visibility(model_choice):
-    if model_choice == "LTBoost":
-        return gr.update(visible=True)
-    else:
-        return gr.update(visible=False)
 
 def update_num_variable(dataset_choice):
     reset_value = 1
@@ -130,7 +125,7 @@ def update_starting_point(model_choice, dataset_choice, time_horizon):
 
 
 def find_csv_file(dataset_choice, time_horizon, look_back_window):
-    dir = "Models/LTBoost"
+    dir = "../../../Desktop/Project/Models/LTBoost"
     for root, dirs, files in os.walk(dir):
         for dir_name in dirs:
             if dataset_choice.lower() in dir_name.lower():
@@ -166,14 +161,16 @@ def plot_forecast_vs_ground_truth(df_forecast, df_ground_truth, dataset_choice,
     plt.close()
     return path
 
-def find_image_path(dataset_choice, model_choice, time_horizon, look_back_window, starting_point):
+def find_image_path(dataset_choice, model_choice, time_horizon, look_back_window, starting_point, num_variable):
     directory = "results_nlinear"
     for root, dirs, files in os.walk(directory):
         for dir_name in dirs:
             if dataset_choice.lower() in dir_name.lower() and model_choice in dir_name and f"pl{time_horizon}" in dir_name and f"sl{look_back_window}" in dir_name:
-                image_path = os.path.join(root, dir_name, f"{starting_point}.png")
-                if os.path.exists(image_path):
-                    return image_path
+                variable_dir = os.path.join(root, dir_name, str(num_variable))
+                if os.path.exists(variable_dir):
+                    image_path = os.path.join(variable_dir, f"{starting_point}.png")
+                    if os.path.exists(image_path):
+                        return image_path
     return None
 
 def find_image_path_LTBoost(dataset_choice, time_horizon, look_back_window, starting_point, num_variable):
@@ -212,7 +209,7 @@ def perform_forecasting(dataset_choice, model_choice, time_horizon, starting_poi
 
     if model_choice == "NLinear":
         # check if already have a png image
-        img = find_image_path(dataset_choice, model_choice, time_horizon, look_back_window, starting_point)
+        img = find_image_path(dataset_choice, model_choice, time_horizon, look_back_window, starting_point, num_variable)
         if img:
             return img
         else:
@@ -250,16 +247,24 @@ def main():
     )
     with gr.Blocks(theme=theme) as demo:
         gr.Markdown("""
-        <h1 style="text-align: center;">Time Series Forecasting DEMO</h1>
-        <div style="letter-spacing: 1px; line-height: 1.5;">This is the AI demo with the use of Hugging Face platform with Gradio library interface.
-           Users have the ability to choose between the dataset, model, time horizon, and starting point. <br>
-           Options: <br>
-                  - Dataset Choice: 9 LTSF datasets <br>
-                  - Model choice: NLinear or LTBoost <br>
-                  - Time horizon: {96, 192, 336, 720} (depends on the dataset)<br>
-                  - Starting point: {0, 20, 40 ... 300}<br>
-            Number of figures for each of the dataset depends on the dataset_trainset length and the model we choose<br></div>
-               """)
+            <h1 style="text-align: center; font-size: 1.5em;">LTBoost</h1>
+            <div style="font-size: 16px; letter-spacing: 1.2px; line-height: 1.8; text-align: justify;">
+                LTBoost long term time series forecasting (LTSF) demonstrator.<br>
+                <strong>LTBoost repository:</strong> <a href="LTBoost" target="_blank">https://github.com/hubtru/LTBoost</a><br>
+                You can choose between the dataset, model, time horizon, and starting point. <br>
+                <strong>Options:</strong> <br>
+                <ul>
+                    <li><strong>Datasets:</strong> Electricity, Exchange Rate, Traffic, Weather, ILI, 4 ETTs</li>
+                    <li><strong>Models:</strong> LTBoost or NLinear</li>
+                    <li><strong>Time horizon:</strong> {96, 192, 336, 720} (different for ILI)</li>
+                    <li><strong>Starting point:</strong> {0, ..., end}</li>
+                    <li><strong>Variate:</strong> 10 last variates (including the OT which is always the last)</li>
+                </ul>
+                Number of figures for each of the dataset depends on the dataset_trainset length and the starting_point_resolution (offset).<br>
+                Due to the high number of the figures the starting_point_resolution has been limited to {20, 100, 720}.<br>
+            </div>
+            """)
+
         with gr.Row():
             with gr.Column():
                 dataset_choice = gr.Dropdown(
@@ -279,7 +284,6 @@ def main():
                                       outputs=starting_point)
                 model_choice.change(update_starting_point, inputs=[model_choice, dataset_choice, time_horizon],
                                     outputs=starting_point)
-                model_choice.change(fn=toggle_num_variable_visibility, inputs=model_choice, outputs=num_variable)
                 time_horizon.change(update_starting_point, inputs=[model_choice, dataset_choice, time_horizon],
                                       outputs=starting_point)
                 dataset_choice.change(update_num_variable, inputs = dataset_choice, outputs = num_variable)

requirements.txt

@@ -1,6 +1,6 @@
 gradio
 torch
 scikit-learn
-pandas
 matplotlib
+pandas
 numpy