Upload 2 files

app.py

@@ -0,0 +1,182 @@
+import gradio as gr
+import pandas as pd
+import plotly.express as px
+import requests
+from bs4 import BeautifulSoup
+import csv
+from datetime import datetime
+import calendar
+
+color_map = {
+    "Shek Pik": "blue",
+    "Quarry Bay": "red"
+}
+
+def get_end_date_from_month(month_str):
+    try:
+        dt = datetime.strptime(month_str, "%Y-%m")
+    except ValueError:
+        raise ValueError("Invalid format. Please use YYYY-MM (e.g., '2023-07')")
+    last_day = calendar.monthrange(dt.year, dt.month)[1]
+    return dt.year, dt.month, f"{dt.year}-{dt.month:02d}-{last_day:02d}"
+
+def fetch_measured_data(station_name, endtime, period="30"):
+    station_codes = {"Quarry Bay": "quar", "Shek Pik": "shek"}
+    code = station_codes.get(station_name)
+    if not code:
+        raise ValueError(f"Invalid station name: {station_name}")
+    if len(endtime) == 10:
+        endtime_full = endtime + " 23:59:59"
+    else:
+        endtime_full = endtime
+    url = f"https://www.ioc-sealevelmonitoring.org/bgraph.php?code={code}&output=tab&period={period}&endtime={endtime_full}"
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+    except requests.RequestException as e:
+        raise RuntimeError(f"Error fetching data: {e}")
+    soup = BeautifulSoup(response.text, 'html.parser')
+    table = soup.find('table')
+    if not table:
+        raise ValueError(f"No data table found in HTML for station {station_name} at {endtime_full}")
+    rows = table.find_all('tr')
+    data = [[col.get_text(strip=True) for col in row.find_all(['td', 'th'])] for row in rows]
+    output_csv = f"{code}_tide_data.csv"
+    with open(output_csv, 'w', newline='', encoding='utf-8') as f:
+        writer = csv.writer(f)
+        writer.writerows(data)
+    return output_csv
+
+def load_measured_csv(file_path, station_name):
+    df = pd.read_csv(file_path)
+    df.columns = df.columns.str.strip()
+    df['Time (UTC)'] = pd.to_datetime(df['Time (UTC)'], errors='coerce')
+    df = df.dropna(subset=['Time (UTC)'])
+    df['Time (UTC+8)'] = df['Time (UTC)'].dt.tz_localize('UTC').dt.tz_convert('Asia/Hong_Kong')
+    df['Station'] = station_name
+    return df[['Time (UTC+8)', 'flt(m)', 'Station']].rename(columns={'flt(m)': 'Measured'})
+
+def fetch_hko_tide_data(url, station_name, year):
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+    except requests.RequestException:
+        return None
+    soup = BeautifulSoup(response.text, 'html.parser')
+    rows = soup.find_all('tr')[1:]
+    data = []
+    for row in rows:
+        cols = [td.get_text(strip=True) for td in row.find_all(['td', 'th'])]
+        if len(cols) >= 26:
+            mm, dd = cols[0], cols[1]
+            for hour in range(24):
+                tide_str = cols[hour + 2]
+                if tide_str == '':
+                    continue
+                try:
+                    tide = float(tide_str)
+                    dt = datetime(year, int(mm), int(dd), hour)
+                    data.append({'Datetime': dt, 'Tide Height (m)': tide, 'Station': station_name})
+                except ValueError:
+                    continue
+    return pd.DataFrame(data)
+
+def tide_analysis_for_month_gradio(month_str):
+    logs = []
+
+    if not month_str:
+        return "Please enter a month in YYYY-MM format.", None, None, None
+
+    try:
+        logs.append(f"Parsing input month: {month_str}")
+        year, month, end_date = get_end_date_from_month(month_str)
+        logs.append(f"End date calculated: {end_date}")
+
+        # Fetch measured data
+        logs.append("Fetching measured data for Shek Pik...")
+        file_shek = fetch_measured_data("Shek Pik", end_date)
+        logs.append("Fetching measured data for Quarry Bay...")
+        file_quar = fetch_measured_data("Quarry Bay", end_date)
+
+        logs.append("Loading and processing measured CSV data...")
+        df_shek = load_measured_csv(file_shek, "Shek Pik")
+        df_quar = load_measured_csv(file_quar, "Quarry Bay")
+        df_measured = pd.concat([df_shek, df_quar], ignore_index=True)
+        min_time = df_measured['Time (UTC+8)'].min()
+        max_time = df_measured['Time (UTC+8)'].max()
+        logs.append(f"Measured data range: {min_time} to {max_time}")
+
+        # Fetch predicted tide data
+        logs.append("Fetching predicted tide data from HKO...")
+        url_quar = f"https://www.hko.gov.hk/tide/QUBtextPH{year}.htm"
+        url_shek = f"https://www.hko.gov.hk/tide/SPWtextPH{year}.htm"
+        df_pred_quar = fetch_hko_tide_data(url_quar, "Quarry Bay", year)
+        df_pred_shek = fetch_hko_tide_data(url_shek, "Shek Pik", year)
+
+        if df_pred_quar is None or df_pred_shek is None:
+            logs.append("Failed to fetch predicted tide data.")
+            return "\n".join(logs), None, None, None
+
+        logs.append("Processing predicted tide data...")
+        df_pred = pd.concat([df_pred_quar, df_pred_shek], ignore_index=True)
+        df_pred['Time (UTC+8)'] = pd.to_datetime(df_pred['Datetime']).dt.tz_localize('Asia/Hong_Kong')
+        df_pred = df_pred.rename(columns={'Tide Height (m)': 'Predicted'})
+        df_pred = df_pred[(df_pred['Time (UTC+8)'] >= min_time) & (df_pred['Time (UTC+8)'] <= max_time)]
+
+        logs.append("Generating plot for predicted tide...")
+        fig_pred = px.line(df_pred, x='Time (UTC+8)', y='Predicted', color='Station',
+                           title='Predicted Tide',
+                           labels={'Predicted': 'Tide Height (m)', 'Time (UTC+8)': 'Time (UTC+8)'},
+                           color_discrete_map=color_map)
+        fig_pred.update_traces(mode='lines+markers')
+
+        logs.append("Generating plot for measured tide...")
+        fig_meas = px.line(df_measured, x='Time (UTC+8)', y='Measured', color='Station',
+                           title='Measured Tide',
+                           labels={'Measured': 'Tide Height (m)', 'Time (UTC+8)': 'Time (UTC+8)'},
+                           color_discrete_map=color_map)
+        fig_meas.update_traces(mode='lines+markers')
+
+        logs.append("Calculating and plotting residuals...")
+        df_merged = pd.merge(df_measured, df_pred[['Time (UTC+8)', 'Predicted', 'Station']],
+                             on=['Time (UTC+8)', 'Station'], how='inner')
+        df_merged['Residual'] = df_merged['Measured'] - df_merged['Predicted']
+        fig_resid = px.line(df_merged, x='Time (UTC+8)', y='Residual', color='Station',
+                            title='Tide Residuals (Measured - Predicted)',
+                            labels={'Residual': 'Residual (m)', 'Time (UTC+8)': 'Time (UTC+8)'},
+                            color_discrete_map=color_map)
+        fig_resid.update_traces(mode='lines+markers')
+
+        logs.append("Analysis completed successfully.")
+        return "\n".join(logs), fig_pred, fig_meas, fig_resid
+
+    except Exception as e:
+        logs.append(f"Error during processing: {e}")
+        return "\n".join(logs), None, None, None
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## Tide Time Series Analysis by Month")
+
+    # --- First Row: Controls ---
+    with gr.Row():
+        month_input = gr.Textbox(label="Enter Month (YYYY-MM)", placeholder="e.g. 2023-07")
+        run_btn = gr.Button("Run Analysis")
+
+    # --- Second Row: Plot Area ---
+    with gr.Row():
+        with gr.Column():
+            with gr.Row():
+                plot_meas = gr.Plot(label="Measured Tide")
+                plot_resid = gr.Plot(label="Residuals")
+            with gr.Row():
+                plot_pred = gr.Plot(label="Predicted Tide")
+                status_output = gr.Textbox(label="Status / Error", interactive=False, lines=1)
+
+    run_btn.click(fn=tide_analysis_for_month_gradio,
+                  inputs=month_input,
+                  outputs=[status_output, plot_pred, plot_meas, plot_resid])
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,110 @@
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.15
+aiosignal==1.4.0
+annotated-types==0.7.0
+anyio==4.10.0
+appnope==0.1.4
+asttokens==3.0.0
+async-timeout==5.0.1
+attrs==25.3.0
+backcall==0.2.0
+beautifulsoup4==4.13.4
+bleach==6.2.0
+Brotli==1.1.0
+cachetools==6.1.0
+certifi==2025.8.3
+charset-normalizer==3.4.2
+click==8.2.1
+decorator==5.2.1
+defusedxml==0.7.1
+docopt==0.6.2
+exceptiongroup==1.3.0
+executing==2.2.0
+fastapi==0.116.1
+fastjsonschema==2.21.1
+ffmpy==0.6.1
+filelock==3.18.0
+frozenlist==1.7.0
+fsspec==2025.7.0
+gradio==5.40.0
+gradio_client==1.11.0
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.34.3
+idna==3.10
+ipython==8.12.3
+jedi==0.19.2
+Jinja2==3.1.6
+jsonschema==4.25.0
+jsonschema-specifications==2025.4.1
+jupyter_client==8.6.3
+jupyter_core==5.8.1
+jupyterlab_pygments==0.3.0
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mistune==3.1.3
+multidict==6.6.3
+narwhals==2.0.1
+nbclient==0.10.2
+nbconvert==7.16.6
+nbformat==5.10.4
+numpy==2.2.6
+orjson==3.11.1
+packaging==25.0
+pandas==2.3.1
+pandocfilters==1.5.1
+parso==0.8.4
+pexpect==4.9.0
+pickleshare==0.7.5
+pillow==11.3.0
+pipreqs==0.5.0
+platformdirs==4.3.8
+plotly==6.2.0
+prompt_toolkit==3.0.51
+propcache==0.3.2
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==27.0.1
+referencing==0.36.2
+requests==2.32.4
+rich==14.1.0
+rpds-py==0.26.0
+ruff==0.12.7
+safehttpx==0.1.6
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.7
+stack-data==0.6.3
+starlette==0.47.2
+tinycss2==1.4.0
+tomlkit==0.13.3
+tornado==6.5.1
+tqdm==4.67.1
+traitlets==5.14.3
+typer==0.16.0
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.35.0
+wcwidth==0.2.13
+webencodings==0.5.1
+websockets==15.0.1
+yarg==0.1.9
+yarl==1.20.1