diff --git a/.gitignore b/.gitignore
index 899420baaa77403d6a89810a59df6da7aac7014b..15908f0b552af20b6b2d4ed9da19266c589d6d4e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,10 +1,13 @@
*.idea/
# Ignore venv directory
-venv/
+.venv/
__pycache__/
+Models/
+
+Dataset/
checkpoints/
diff --git a/README.md b/README.md
index 804a6a59fec4cb8124472c15558ee7d2934fa455..6d2387871607598782b367286b8a67bea807cbb6 100644
--- a/README.md
+++ b/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
diff --git a/app.py b/app.py
index 355e8725fdcdfbafa8a00915d69ac4c78f876bea..070e42b5428d48d1cf47e9548b8daa29d0b726da 100644
--- a/app.py
+++ b/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("""
- Time Series Forecasting DEMO
- 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.
- Options:
- - Dataset Choice: 9 LTSF datasets
- - Model choice: NLinear or LTBoost
- - Time horizon: {96, 192, 336, 720} (depends on the dataset)
- - Starting point: {0, 20, 40 ... 300}
- Number of figures for each of the dataset depends on the dataset_trainset length and the model we choose
- """)
+ LTBoost
+
+ LTBoost long term time series forecasting (LTSF) demonstrator.
+
LTBoost repository: https://github.com/hubtru/LTBoost
+ You can choose between the dataset, model, time horizon, and starting point.
+
Options:
+
+ - Datasets: Electricity, Exchange Rate, Traffic, Weather, ILI, 4 ETTs
+ - Models: LTBoost or NLinear
+ - Time horizon: {96, 192, 336, 720} (different for ILI)
+ - Starting point: {0, ..., end}
+ - Variate: 10 last variates (including the OT which is always the last)
+
+ Number of figures for each of the dataset depends on the dataset_trainset length and the starting_point_resolution (offset).
+ Due to the high number of the figures the starting_point_resolution has been limited to {20, 100, 720}.
+