new plots

app.py

@@ -1,106 +1,131 @@
 import gradio as gr
-import hopsworks
 import pandas as pd
 import matplotlib.pyplot as plt
-import os
+import tempfile
+import hopsworks
 from xgboost import XGBRegressor
+from datetime import datetime, timedelta
 
-# IMPORTANT: HuggingFace builds need non-interactive backend
-import matplotlib
-matplotlib.use("Agg")
+from airquality.util import plot_air_quality_forecast
 
-FEATURE_COLUMNS = [
-    "temperature_2m_mean",
-    "precipitation_sum",
-    "wind_speed_10m_max",
-    "wind_direction_10m_dominant"
-]
 
+# -------------------------
+# HOPSWORKS LOGIN + MODEL LOAD
+# -------------------------
 def load_resources():
-    """Connect to Hopsworks, load model + feature view."""
     project = hopsworks.login()
-
     fs = project.get_feature_store()
+
+    # Load Feature View
+    fv = fs.get_feature_view(
+        name="air_quality_fv",
+        version=1
+    )
+    fv.init_batch_scoring(1)
+
+    # Load Weather Feature Group (for future predictions)
+    weather_fg = fs.get_feature_group("weather", 1)
+
+    # Load Model from Registry
     mr = project.get_model_registry()
+    model_obj = mr.get_model("air_quality_xgboost_model", version=1)
+    model_dir = model_obj.download()
 
-    # Load model
-    model_meta = mr.get_model("air_quality_xgboost_model", version=1)
-    model_dir = model_meta.download()
     model = XGBRegressor()
     model.load_model(model_dir + "/model.json")
 
-    # Load feature view
-    fv = fs.get_feature_view("air_quality_fv", version=1)
+    return model, fv, weather_fg, project
 
-    return model, fv
 
-# Load on startup
-model, feature_view = load_resources()
+model, feature_view, weather_fg, project = load_resources()
 
+
+# -------------------------
+# FORECAST LOGIC (NEXT 7 DAYS)
+# -------------------------
 def generate_forecast():
-    """Fetch latest feature data, generate PM25 forecast plot."""
-    df = feature_view.get_batch_data()
+    today = datetime.utcnow().date()
+    future_dates = [(today + timedelta(days=i)).strftime("%Y-%m-%d") for i in range(1, 8)]
+
+    df_future = weather_fg.read()
+    df_future["date"] = pd.to_datetime(df_future["date"]).dt.date
+
+    preds = []
+    for d in future_dates:
+        dt = datetime.strptime(d, "%Y-%m-%d").date()
+        row = df_future[df_future["date"] == dt]
+
+        if len(row) == 0:
+            continue
+
+        input_features = row.drop(columns=["date", "city"])
+        pm25_pred = model.predict(input_features)[0]
+
+        preds.append({"date": d, "predicted_pm25": pm25_pred})
 
-    # Convert timestamp to datetime
-    df["date"] = pd.to_datetime(df["date"], unit="us")
+    if len(preds) == 0:
+        return None
 
-    # Predict PM2.5
-    df["predicted_pm25"] = model.predict(df[FEATURE_COLUMNS])
+    df_preds = pd.DataFrame(preds)
 
-    # Plot forecast
-    plt.figure(figsize=(10, 4))
-    plt.plot(df["date"], df["predicted_pm25"], marker="o")
-    plt.title("PM2.5 Forecast (Next Days)")
-    plt.xlabel("Date")
-    plt.ylabel("Predicted PM2.5")
-    plt.grid(True)
-    plt.tight_layout()
-    plt.savefig("forecast.png")
-    plt.close()
+    # Save plot
+    tmp_path = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
+    plot_air_quality_forecast("linkoping", "hamngatan-10", df_preds, tmp_path, hindcast=False)
 
-    return "forecast.png"
+    return tmp_path
 
+
+# -------------------------
+# HINDCAST LOGIC (LAST 7 DAYS)
+# -------------------------
 def generate_hindcast():
-    """Generate hindcast accuracy plot (past days)."""
-    df = feature_view.get_batch_data()
-    df["date"] = pd.to_datetime(df["date"], unit="us")
-    df["predicted_pm25"] = model.predict(df[FEATURE_COLUMNS])
-
-    # For hindcast: show difference between predicted & actual (most recent available data)
-    # NOTE: Your data may not include true pm25 for recent dates; 
-    # we'll plot model signal only.
-
-    plt.figure(figsize=(10, 4))
-    plt.plot(df["date"], df["predicted_pm25"], label="Predicted", marker="o")
-    plt.title("PM2.5 Hindcast (Recent Days)")
-    plt.xlabel("Date")
-    plt.ylabel("PM2.5")
-    plt.grid(True)
-    plt.legend()
-    plt.tight_layout()
-    plt.savefig("hindcast.png")
-    plt.close()
-
-    return "hindcast.png"
-
-
-def run_dashboard():
-    forecast_img = generate_forecast()
-    hindcast_img = generate_hindcast()
-    return forecast_img, hindcast_img
-
-
-with gr.Blocks() as demo:
-    gr.Markdown("# 🌤️ PM2.5 Air Quality Dashboard")
-    gr.Markdown("Powered by Hopsworks Feature Store + XGBoost Model")
-
-    btn = gr.Button("Generate Forecast")
-    output_forecast = gr.Image(label="Forecast (Next Days)")
-    output_hindcast = gr.Image(label="Hindcast (Past Days)")
-
-    btn.click(
-        run_dashboard,
-        outputs=[output_forecast, output_hindcast]
+    # Read actual + predicted from Feature View
+    features_df, labels_df = feature_view.training_data(
+        start_time=datetime.utcnow().date() - timedelta(days=7),
+        end_time=datetime.utcnow().date(),
+        statistics_config=False
     )
 
-demo.launch()
+    features_df["date"] = pd.to_datetime(features_df["date"]).dt.date
+    labels_df["pm25"] = labels_df["pm25"]
+
+    df = features_df.copy()
+    df["pm25"] = labels_df["pm25"]
+
+    # Predict using model
+    df["predicted_pm25"] = model.predict(
+        df[["temperature_2m_mean", "precipitation_sum", "wind_speed_10m_max", "wind_direction_10m_dominant"]]
+    )
+
+    # Keep last 7 days
+    df = df.sort_values("date").tail(7)
+
+    # Save plot
+    tmp_path = tempfile.NamedTemporaryFile(suffix=".png", delete=False).name
+    plot_air_quality_forecast("linkoping", "hamngatan-10", df, tmp_path, hindcast=True)
+
+    return tmp_path
+
+
+# -------------------------
+# GRADIO UI
+# -------------------------
+def run_dashboard(_):
+    forecast_plot = generate_forecast()
+    hindcast_plot = generate_hindcast()
+
+    return forecast_plot, hindcast_plot
+
+
+iface = gr.Interface(
+    fn=run_dashboard,
+    inputs=gr.Button("Generate Dashboard"),
+    outputs=[
+        gr.Image(label="PM2.5 Forecast (Next 7 Days)"),
+        gr.Image(label="PM2.5 Hindcast (Past 7 Days)")
+    ],
+    title="Air Quality Forecast Dashboard",
+    description="Forecast and Hindcast PM2.5 for Linköping using XGBoost + Hopsworks",
+)
+
+iface.launch()