add trend data visualization

pages/HF_Dataset.py

@@ -2,6 +2,11 @@ import streamlit as st
 import pandas as pd
 from huggingface_hub import hf_hub_download
 import os
+import pydeck as pdk
+from datetime import datetime
+
+# Set the Streamlit layout to wide
+st.set_page_config(layout="wide")
 
 # Set your Hugging Face token from environment variable
 hf_token = os.getenv("pegelonline_dataset_read_only")
@@ -10,19 +15,106 @@ if hf_token is None:
     st.error("Hugging Face token not found. Please set the HF_TOKEN environment variable.")
 else:
     # Download the dataset file
-    dataset_path = hf_hub_download(
+    dataset_path_stations = hf_hub_download(
         repo_id="DSSG-Wasserwacht/pegelonline-dataset",
         filename="processed/stations.parquet",
         repo_type="dataset",
         use_auth_token=hf_token
     )
+    dataset_path_water_level = hf_hub_download(
+        repo_id="DSSG-Wasserwacht/pegelonline-dataset",
+        filename="processed/current_water_level.parquet",
+        repo_type="dataset",
+        use_auth_token=hf_token
+    )
+    dataset_path_timeseries = hf_hub_download(
+        repo_id="DSSG-Wasserwacht/pegelonline-dataset",
+        filename="processed/timeseries.parquet",
+        repo_type="dataset",
+        use_auth_token=hf_token
+    )
 
     # Load the dataset
-    df = pd.read_parquet(dataset_path)
+    df_stations = pd.read_parquet(dataset_path_stations)
+    df_water_level = pd.read_parquet(dataset_path_water_level)
+    df_timeseries = pd.read_parquet(dataset_path_timeseries).groupby("uuid").mean("value").round(1).reset_index().rename(columns={"value": "mean_value"})
+    df = df_stations.merge(df_water_level, how="left", on="uuid")
+    df = df.merge(df_timeseries, how="left", on="uuid")
+
+    # Format the timestamp nicely
+    df["formatted_timestamp"] = df["timestamp"].apply(
+        lambda x: datetime.fromisoformat(x).strftime("%Y-%m-%d %H:%M:%S") if pd.notna(x) else None
+        )
+
+    # Add arrows based on the result of mean_value - value
+    def add_arrow(row):
+        if pd.isna(row["value"]):
+            return None
+        difference = row["mean_value"] - row["value"]
+        if abs(difference) <= 0.01 * row["mean_value"]:
+            return "➡️"
+        elif difference > 0:
+            return "⬇️"
+        else:
+            return "⬆️"
+
+    df["arrow"] = df.apply(add_arrow, axis=1)
+
+    # Add traffic light column
+    def add_traffic_light(row):
+        if pd.isna(row["value"]):
+            return None
+        difference = abs(row["mean_value"] - row["value"])
+        if difference > 0.15 * row["mean_value"]:
+            return "🔴"
+        elif difference > 0.10 * row["mean_value"]:
+            return "🟡"
+        else:
+            return "🟢"
+
+    df["traffic_light"] = df.apply(add_traffic_light, axis=1)
+
+    # Define a color mapping for the traffic lights
+    color_mapping = {
+        "🟢": [0, 255, 0, 140],  # Green
+        "🟡": [255, 255, 0, 140],  # Yellow
+        "🔴": [255, 0, 0, 140],   # Red
+        None: [128, 128, 128, 140]  # Grey for None
+    }
+
+    # Map the traffic_light column to colors
+    df["color"] = df["traffic_light"].map(color_mapping)
 
     # Streamlit app
     st.title("Pegelonline Dataset Viewer")
     st.write("This app displays data from the Pegelonline dataset.")
 
+    # PyDeck Layer für Kartenanzeige
+    layer = pdk.Layer(
+        "ScatterplotLayer",
+        data=df,
+        get_position=["longitude", "latitude"],
+        get_radius=2000,
+        get_color="color",
+        pickable=True,
+    )
+
+    # Deck.gl Map
+    view_state = pdk.ViewState(
+        latitude=df["latitude"].mean(),
+        longitude=df["longitude"].mean(),
+        zoom=6,
+        pitch=0,
+    )
+    r = pdk.Deck(
+        layers=[layer], 
+        initial_view_state=view_state, 
+        tooltip={"text": "{shortname}, {value} cm, {mean_value} cm,\n {arrow} {traffic_light} {formatted_timestamp}"}
+    )
+    st.pydeck_chart(r)
+
+    # Rohdaten anzeigen
+    st.write("### Rohdaten der Pegelstationen")
+    
     # Display the dataframe
-    st.dataframe(df)
+    st.dataframe(df[["shortname", "km", "value", "mean_value", "arrow", "traffic_light", "formatted_timestamp"]])