initial

.gitignore

@@ -0,0 +1,12 @@
+*.idea/
+
+# Ignore venv directory
+venv/
+
+__pycache__/
+
+Models/
+
+checkpoints/
+
+result.txt

README.md

@@ -1,13 +1,12 @@
 ---
-title: LTBoost
-emoji: 🐢
-colorFrom: purple
+title: AI Project
+emoji: 🐨
+colorFrom: red
 colorTo: indigo
 sdk: gradio
-sdk_version: 4.44.0
+sdk_version: 4.28.3
 app_file: app.py
 pinned: false
-license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,336 @@
+import os
+import gradio as gr
+import matplotlib.pyplot as plt
+
+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
+    if not dataset_choice :
+        return gr.update(minimum=1, maximum=10, step=1, value=reset_value)
+    if dataset_choice in ['Electricity', 'Traffic']:
+        num_variable_range = (1,10,1)
+    elif dataset_choice in ['ETTh1', 'ETTh2', 'ETTm1', 'ETTm2', 'National_illness']:
+        num_variable_range = (1,7,1)
+    elif dataset_choice == "Weather":
+        num_variable_range = (1,21,1)
+    elif dataset_choice == "Exchange":
+        num_variable_range = (1,8,1)
+    return gr.update(minimum=num_variable_range[0], maximum=num_variable_range[1], step=num_variable_range[2],
+                     value=reset_value)
+def update_time_horizon(dataset_choice):
+    if dataset_choice == "National_illness":
+        choices = [24, 36, 48, 60]
+    else:
+        choices = [96, 192, 336, 720]
+
+    #default value = maximum choice
+    default_value = max(choices)
+
+    return gr.update(choices=choices, value=default_value)
+
+def update_starting_point(model_choice, dataset_choice, time_horizon):
+    reset_value = 0
+    starting_point_range = (0, 300, 20)  # Standardwert
+    if not model_choice or not dataset_choice or not time_horizon:
+        return gr.update(minimum=0, maximum=300, step=20, value = reset_value)
+
+    if model_choice == "NLinear":
+        if dataset_choice == "Electricity":
+            if time_horizon == 96:
+                starting_point_range = (0, 160, 20)
+            elif time_horizon in [192, 336, 720]:
+                starting_point_range = (0, 140, 20)
+        elif dataset_choice == "ETTh1":
+            if time_horizon in [96, 192]:
+                starting_point_range = (0, 80, 20)
+            else:
+                starting_point_range = (0, 60, 20)
+        elif dataset_choice == "ETTh2":
+            if time_horizon in [96, 192]:
+                starting_point_range = (0, 80, 20)
+            else:
+                starting_point_range = (0, 60, 20)
+        elif dataset_choice == "Traffic":
+            if time_horizon in [96, 192]:
+                starting_point_range = (0, 100, 20)
+            else:
+                starting_point_range = (0, 80, 20)
+        elif dataset_choice == "Weather":
+            if time_horizon in [96, 192]:
+                starting_point_range = (0, 320, 20)
+            else:
+                starting_point_range = (0, 300, 20)
+        elif dataset_choice == "Exchange":
+            if time_horizon in [96, 192]:
+                starting_point_range = (0,40,20)
+            else:
+                starting_point_range = (0, 20, 20)
+        elif dataset_choice == "National_illness":
+            starting_point_range = (0, 0, 0)
+        elif dataset_choice == "ETTm2":
+            if time_horizon == 720:
+                starting_point_range = (0, 320, 20)
+            else:
+                starting_point_range = (0,340,20)
+        elif dataset_choice == "ETTm1":
+            if time_horizon == 720:
+                starting_point_range = (0, 320, 20)
+            else:
+                starting_point_range = (0,340,20)
+    else:
+        if dataset_choice == "National_illness":
+            if time_horizon == 24:
+                starting_point_range = (0, 160, 20)
+            elif time_horizon in [36, 48]:
+                starting_point_range = (0, 140, 20)
+            elif time_horizon == 60:
+                starting_point_range = (0, 120, 20)
+        elif dataset_choice == "Electricity":
+            starting_point_range = (0,4320, 720)
+        elif dataset_choice in ["ETTh1", "ETTh2"]:
+            if time_horizon == 96:
+                starting_point_range = (0, 2700, 100)
+            elif time_horizon == 192:
+                starting_point_range = (0, 2600, 100)
+            elif time_horizon == 336:
+                starting_point_range = (0, 2300, 100)
+            elif time_horizon == 720:
+                starting_point_range = (0, 2100, 100)
+        elif dataset_choice in ["ETTm1", "ETTm2"]:
+            starting_point_range = (0,10800, 720)
+        elif dataset_choice == "Exchange":
+            if time_horizon == 96:
+                starting_point_range = (0, 1300, 100)
+            elif time_horizon == 192:
+                starting_point_range = (0, 1100, 100)
+            elif time_horizon == 336:
+                starting_point_range = (0, 1000, 100)
+            elif time_horizon == 720:
+                starting_point_range = (0, 700, 100)
+        elif dataset_choice == "Traffic":
+            if time_horizon == 96:
+                starting_point_range = (0, 3300, 100)
+            elif time_horizon == 192:
+                starting_point_range = (0, 3200, 100)
+            elif time_horizon == 336:
+                starting_point_range = (0, 3000, 100)
+            elif time_horizon == 720:
+                starting_point_range = (0, 2100, 100)
+        elif dataset_choice == "Weather":
+            starting_point_range = (0, 9360, 720)
+        else:
+            starting_point_range = (0, 300, 20)
+    return gr.update(minimum = starting_point_range[0], maximum = starting_point_range[1], step = starting_point_range[2], value = reset_value)
+
+
+
+def find_csv_file(dataset_choice, time_horizon, look_back_window):
+    dir = "Models/LTBoost"
+    for root, dirs, files in os.walk(dir):
+        for dir_name in dirs:
+            if dataset_choice.lower() in dir_name.lower():
+                full_dir_path = os.path.join(root, dir_name)
+                for file_name in os.listdir(full_dir_path):
+                    if f"pl_{time_horizon}" in file_name:
+                        csv_file_path = os.path.join(full_dir_path, file_name)
+                        if os.path.exists(csv_file_path):
+                            return csv_file_path
+    return None
+
+def plot_forecast_vs_ground_truth(df_forecast, df_ground_truth, dataset_choice, model_choice, lookback_window,time_horizon, starting_point, num_variable):
+    plt.figure(figsize=(12, 6))
+
+    plt.plot(df_ground_truth, label='Forecast')
+    plt.plot(df_forecast, label='Ground Truth')
+    # Marking the transition between look-back window and forecast horizon
+    transition_point = lookback_window
+    plt.axvline(x=transition_point, color='black', linestyle='-')
+    plt.title(f'Forecast vs Ground Truth for {dataset_choice} using {model_choice} Model')
+    #plt.xlabel('Time')
+    #plt.ylabel('Value')
+    plt.legend()
+    plt.grid(True)
+    # Create directory path based on dataset name, lookback window, and time horizon
+    save_dir = f"results_ltboost/{dataset_choice}_sl{lookback_window}_pl{time_horizon}/{num_variable}"
+    os.makedirs(save_dir, exist_ok=True)  # Ensure directory exists, create if not
+
+    # Save the plot as PNG file
+    path = os.path.join(save_dir, f"img_{starting_point}.png")
+    plt.savefig(path)
+
+    plt.close()
+    return path
+
+def find_image_path(dataset_choice, model_choice, time_horizon, look_back_window, starting_point):
+    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
+    return None
+
+def find_image_path_LTBoost(dataset_choice, time_horizon, look_back_window, starting_point, num_variable):
+    directory = "results_ltboost"
+    for root, dirs, files in os.walk(directory):
+        for dir_name in dirs:
+            # Check if the folder name contains the desired dataset, time horizon, and look-back window
+            if (dataset_choice.lower() in dir_name.lower() and
+                    f"pl{time_horizon}" in dir_name and
+                    f"sl{look_back_window}" in dir_name):
+
+                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"img_{starting_point}.png")
+
+                    if os.path.exists(image_path):
+                        return image_path
+
+    return None
+
+
+def perform_forecasting(dataset_choice, model_choice, time_horizon, starting_point, num_variable):
+    if model_choice == "NLinear":
+        if dataset_choice == "National_illness":
+            look_back_window = 104
+        else:
+            look_back_window = 336
+    else:
+        if dataset_choice == "National_illness":
+            look_back_window = 104
+        elif dataset_choice == "Exchange" or dataset_choice == "ETTh1":
+            look_back_window = 336
+        else:
+            look_back_window = 720
+
+    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)
+        if img:
+            return img
+        else:
+            return "No image found"
+
+    elif model_choice == "LTBoost":
+        # check if already have a png image
+        img = find_image_path_LTBoost(dataset_choice, time_horizon, look_back_window, starting_point, num_variable)
+        if img:
+            return img
+        else:
+            return "Image not found"
+
+
+
+
+def main():
+    theme = gr.themes.Base(
+        primary_hue="blue",
+        secondary_hue="blue",
+        neutral_hue="gray"
+    )
+    theme.set(
+        body_background_fill="*primary_50",
+        body_background_fill_dark="*checkbox_background_color_focus",
+        body_text_color_dark="white",
+        body_text_color="*neutral_800",
+        background_fill_secondary_dark="*checkbox_border_color_hover",
+        block_background_fill="*background_fill_primary",
+        block_background_fill_dark="*neutral_800",
+        block_border_color_dark="*primary_100",
+        block_border_width_dark="4px",
+        block_border_width="4px",
+        block_border_color="*secondary_200"
+    )
+    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>
+               """)
+        with gr.Row():
+            with gr.Column():
+                dataset_choice = gr.Dropdown(
+                    ["Electricity", "Traffic", "Weather", "Exchange", "National_illness", "ETTh1", "ETTh2", "ETTm1", "ETTm2"],
+                    label="Dataset Choice"
+                )
+                model_choice = gr.Dropdown(["NLinear", "LTBoost"], label="Model Choice", value= "LTBoost")
+                time_horizon = gr.Dropdown([96, 192, 336, 720], label="Time Horizon")
+                starting_point = gr.Slider(minimum=0, maximum=300, step=20, label="Starting Point", value= 0)
+                num_variable = gr.Slider(minimum=1,maximum=10,step=1,label="Variable")
+
+                input_components = [dataset_choice, model_choice, time_horizon, starting_point, num_variable]
+
+                dataset_choice.change(update_time_horizon, inputs=dataset_choice, outputs=time_horizon)
+
+                dataset_choice.change(update_starting_point, inputs=[model_choice, dataset_choice, time_horizon],
+                                      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)
+
+                gr.ClearButton(input_components)
+
+            with gr.Column():
+                # Automatically update the output image whenever any input component changes
+                output_png = gr.Image(label="Forecast Results")
+                for component in input_components:
+                    component.change(perform_forecasting, inputs=input_components, outputs=output_png)
+        with gr.Row():
+            with gr.Column():
+                gr.Markdown("Examples for the user input:")
+                gr.Examples([
+                    ['ETTh1', 'NLinear', 720, 0],
+
+                    ['ETTh2', 'NLinear', 720, 0],
+
+                    ['ETTm1', 'NLinear', 720, 0],
+
+                    ['ETTm2', 'NLinear', 720, 0],
+
+                    ['Weather', 'NLinear', 720, 0],
+
+                    ['Traffic', 'NLinear', 720, 0],
+
+                    ['Electricity', 'NLinear', 720, 0],
+
+                    ['ETTh1', 'LTBoost', 720, 0],
+
+                    ['ETTh2', 'LTBoost', 720, 0],
+
+                    ['ETTm1', 'LTBoost', 720, 0],
+
+                    ['ETTm2', 'LTBoost', 720, 0],
+
+                    ['Weather', 'LTBoost', 720, 0],
+
+                    ['Traffic', 'LTBoost', 720, 0],
+
+                    ['Electricity', 'LTBoost', 720, 0],
+
+                            ],
+
+                            inputs=input_components)
+
+
+
+    demo.launch()
+
+if __name__ == "__main__":
+    main()
+

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+torch
+sklearn
+pandas
+matplotlib.pyplot
+os
+numpy