Upload 2 files

app.py.py

@@ -0,0 +1,421 @@
+from datetime import date, timedelta
+
+import altair as alt
+import pandas as pd
+import streamlit as st
+from geopy.extra.rate_limiter import RateLimiter
+from geopy.geocoders import Nominatim
+
+st.set_page_config(
+    page_title="Weather dashboard",
+    page_icon=":material/thermostat:",
+    layout="wide",
+)
+
+# ---------------------------------------------------------------------------
+# Constants
+# ---------------------------------------------------------------------------
+TIME_RANGES = ["1M", "3M", "6M", "1Y", "YTD", "All"]
+VARIABLES = ["Temperature", "Wind speed", "Wind gusts", "Precipitation"]
+VAR_COLS = {
+    "Temperature": "temperature_2m",
+    "Wind speed": "windspeed_10m",
+    "Wind gusts": "windgusts_10m",
+    "Precipitation": "precipitation",
+}
+VAR_UNITS = {
+    "Temperature": "F",
+    "Wind speed": "mph",
+    "Wind gusts": "mph",
+    "Precipitation": "in",
+}
+
+
+# ---------------------------------------------------------------------------
+# Data helpers
+# ---------------------------------------------------------------------------
+@st.cache_data(show_spinner=False)
+def geocode(address: str) -> tuple[float, float]:
+    """Return (lat, lon) for *address*, trying Census first then Nominatim."""
+    try:
+        address2 = address.replace(" ", "+").replace(",", "%2C")
+        url = (
+            "https://geocoding.geo.census.gov/geocoder/locations/onelineaddress"
+            f"?address={address2}&benchmark=2020&format=json"
+        )
+        df = pd.read_json(url)
+        coords = df.iloc[:1, 0][0][0]["coordinates"]
+        return coords["y"], coords["x"]
+    except Exception:
+        geolocator = Nominatim(user_agent="WeatherDashboard")
+        geocode_fn = RateLimiter(geolocator.geocode, min_delay_seconds=1)
+        location = geocode_fn(address)
+        if location is None:
+            raise ValueError(f"Could not geocode: {address}")
+        return location.latitude, location.longitude
+
+
+@st.cache_data(show_spinner=False, ttl=900)
+def get_weather_data(
+    lat: float, lon: float, start_date: str, end_date: str
+) -> pd.DataFrame:
+    """Fetch hourly weather from Open-Meteo archive API."""
+    url = (
+        f"https://archive-api.open-meteo.com/v1/archive"
+        f"?latitude={lat}&longitude={lon}"
+        f"&start_date={start_date}&end_date={end_date}"
+        f"&hourly=temperature_2m,precipitation,windspeed_10m,windgusts_10m"
+        f"&models=best_match"
+        f"&temperature_unit=fahrenheit&windspeed_unit=mph&precipitation_unit=inch"
+    )
+    raw = pd.read_json(url).reset_index()
+    data = pd.DataFrame({c["index"]: c["hourly"] for _, c in raw.iterrows()})
+    data["time"] = pd.to_datetime(data["time"])
+    data = data.dropna(subset=["temperature_2m"])
+    return data
+
+
+def aggregate_daily(df: pd.DataFrame) -> pd.DataFrame:
+    """Compute daily aggregates from hourly data."""
+    df = df.copy()
+    df["date"] = df["time"].dt.date
+    agg = df.groupby("date").agg(
+        temperature_2m_min=("temperature_2m", "min"),
+        temperature_2m_mean=("temperature_2m", "mean"),
+        temperature_2m_max=("temperature_2m", "max"),
+        precipitation_sum=("precipitation", "sum"),
+        windspeed_10m_min=("windspeed_10m", "min"),
+        windspeed_10m_mean=("windspeed_10m", "mean"),
+        windspeed_10m_max=("windspeed_10m", "max"),
+        windgusts_10m_min=("windgusts_10m", "min"),
+        windgusts_10m_mean=("windgusts_10m", "mean"),
+        windgusts_10m_max=("windgusts_10m", "max"),
+    )
+    agg.index = pd.to_datetime(agg.index)
+    agg.index.name = "date"
+    return agg
+
+
+def filter_by_time_range(
+    df: pd.DataFrame, x_col: str, time_range: str
+) -> pd.DataFrame:
+    """Filter dataframe by a preset time range."""
+    if time_range == "All" or df.empty:
+        return df
+    df = df.copy()
+    df[x_col] = pd.to_datetime(df[x_col])
+    max_date = df[x_col].max()
+    if time_range == "1M":
+        min_date = max_date - timedelta(days=30)
+    elif time_range == "3M":
+        min_date = max_date - timedelta(days=90)
+    elif time_range == "6M":
+        min_date = max_date - timedelta(days=180)
+    elif time_range == "1Y":
+        min_date = max_date - timedelta(days=365)
+    elif time_range == "YTD":
+        min_date = pd.Timestamp(date(max_date.year, 1, 1))
+    else:
+        return df
+    return df[df[x_col] >= min_date]
+
+
+@st.cache_data
+def to_csv(df: pd.DataFrame) -> bytes:
+    return df.to_csv(index=True).encode("utf-8")
+
+
+# ---------------------------------------------------------------------------
+# Sidebar
+# ---------------------------------------------------------------------------
+with st.sidebar:
+    st.header("Settings")
+
+    address = st.text_input(
+        "Address",
+        value="1000 Main St, Cincinnati, OH 45202",
+        placeholder="Enter an address...",
+    )
+    col_s, col_e = st.columns(2)
+    with col_s:
+        start_date = st.date_input("Start date", pd.Timestamp(2024, 1, 1))
+    with col_e:
+        end_date = st.date_input("End date", pd.Timestamp(2025, 11, 10))
+
+    variable = st.selectbox("Variable", VARIABLES, index=2)
+
+    st.caption("Data from Open-Meteo archive API")
+
+# ---------------------------------------------------------------------------
+# Geocode + fetch
+# ---------------------------------------------------------------------------
+try:
+    lat, lon = geocode(address)
+except Exception:
+    st.error(
+        "Could not find that address. Please check the spelling and try again.",
+        icon=":material/error:",
+    )
+    st.stop()
+
+start_str = start_date.strftime("%Y-%m-%d")
+end_str = end_date.strftime("%Y-%m-%d")
+
+with st.spinner("Fetching weather data..."):
+    try:
+        hourly = get_weather_data(lat, lon, start_str, end_str)
+    except Exception as exc:
+        st.error(f"Failed to fetch weather data: {exc}", icon=":material/error:")
+        st.stop()
+
+daily = aggregate_daily(hourly)
+
+# ---------------------------------------------------------------------------
+# Header
+# ---------------------------------------------------------------------------
+col_var = VAR_COLS[variable]
+unit = VAR_UNITS[variable]
+
+st.markdown("# :material/thermostat: Weather dashboard")
+st.caption(f"{address}  ({lat:.4f}, {lon:.4f})")
+
+# ---------------------------------------------------------------------------
+# KPI metrics row
+# ---------------------------------------------------------------------------
+if variable == "Precipitation":
+    total_precip = daily["precipitation_sum"].sum()
+    avg_daily = daily["precipitation_sum"].mean()
+    max_daily = daily["precipitation_sum"].max()
+    dry_days = int((daily["precipitation_sum"] < 0.01).sum())
+
+    k1, k2, k3, k4 = st.columns(4)
+    k1.metric("Total precipitation", f"{total_precip:.1f} {unit}", border=True)
+    k2.metric("Avg daily", f"{avg_daily:.2f} {unit}", border=True)
+    k3.metric("Max daily", f"{max_daily:.2f} {unit}", border=True)
+    k4.metric("Dry days", f"{dry_days:,}", border=True)
+else:
+    mean_col = f"{col_var}_mean"
+    min_col = f"{col_var}_min"
+    max_col = f"{col_var}_max"
+
+    overall_mean = daily[mean_col].mean()
+    overall_min = daily[min_col].min()
+    overall_max = daily[max_col].max()
+
+    k1, k2, k3, k4 = st.columns(4)
+    k1.metric(
+        f"Avg {variable.lower()}",
+        f"{overall_mean:.1f} {unit}",
+        border=True,
+    )
+    k2.metric(f"Min {variable.lower()}", f"{overall_min:.1f} {unit}", border=True)
+    k3.metric(f"Max {variable.lower()}", f"{overall_max:.1f} {unit}", border=True)
+    k4.metric("Days of data", f"{len(daily):,}", border=True)
+
+# ---------------------------------------------------------------------------
+# Filters row
+# ---------------------------------------------------------------------------
+with st.popover("Filters", icon=":material/filter_list:"):
+    time_range = st.segmented_control("Time range", TIME_RANGES, default="All")
+    agg_mode = st.segmented_control(
+        "Aggregation", ["Hourly", "Daily"], default="Daily"
+    )
+    if variable != "Precipitation":
+        show_range = st.toggle("Show min/max range", value=True)
+    else:
+        show_range = False
+
+# ---------------------------------------------------------------------------
+# Build filtered data
+# ---------------------------------------------------------------------------
+if agg_mode == "Hourly":
+    chart_df = hourly[["time", col_var]].copy()
+    chart_df = filter_by_time_range(chart_df, "time", time_range)
+    x_field = "time"
+else:
+    chart_df = daily.reset_index().copy()
+    chart_df = filter_by_time_range(chart_df, "date", time_range)
+    x_field = "date"
+
+# ---------------------------------------------------------------------------
+# Main charts row
+# ---------------------------------------------------------------------------
+col1, col2 = st.columns([3, 1])
+
+with col1:
+    with st.container(border=True):
+        st.markdown(f"**{variable} over time**")
+
+        if agg_mode == "Hourly":
+            chart = (
+                alt.Chart(chart_df)
+                .mark_line(strokeWidth=1.5)
+                .encode(
+                    x=alt.X("time:T", title="Date"),
+                    y=alt.Y(f"{col_var}:Q", title=f"{variable} ({unit})"),
+                    tooltip=[
+                        alt.Tooltip("time:T", title="Time"),
+                        alt.Tooltip(f"{col_var}:Q", title=variable, format=".1f"),
+                    ],
+                )
+                .properties(height=380)
+            )
+            st.altair_chart(chart, use_container_width=True)
+
+        elif variable == "Precipitation":
+            chart = (
+                alt.Chart(chart_df)
+                .mark_bar(color="#4B9CD3")
+                .encode(
+                    x=alt.X("date:T", title="Date"),
+                    y=alt.Y("precipitation_sum:Q", title=f"Daily total ({unit})"),
+                    tooltip=[
+                        alt.Tooltip("date:T", title="Date"),
+                        alt.Tooltip(
+                            "precipitation_sum:Q",
+                            title="Precipitation",
+                            format=".2f",
+                        ),
+                    ],
+                )
+                .properties(height=380)
+            )
+            st.altair_chart(chart, use_container_width=True)
+
+        else:
+            mean_c = f"{col_var}_mean"
+            min_c = f"{col_var}_min"
+            max_c = f"{col_var}_max"
+
+            line = (
+                alt.Chart(chart_df)
+                .mark_line(strokeWidth=2)
+                .encode(
+                    x=alt.X("date:T", title="Date"),
+                    y=alt.Y(f"{mean_c}:Q", title=f"{variable} ({unit})"),
+                    tooltip=[
+                        alt.Tooltip("date:T", title="Date"),
+                        alt.Tooltip(f"{min_c}:Q", title="Min", format=".1f"),
+                        alt.Tooltip(f"{mean_c}:Q", title="Mean", format=".1f"),
+                        alt.Tooltip(f"{max_c}:Q", title="Max", format=".1f"),
+                    ],
+                )
+            )
+
+            if show_range:
+                band = (
+                    alt.Chart(chart_df)
+                    .mark_area(opacity=0.15)
+                    .encode(
+                        x=alt.X("date:T"),
+                        y=alt.Y(f"{min_c}:Q"),
+                        y2=alt.Y2(f"{max_c}:Q"),
+                    )
+                )
+                chart = (band + line).properties(height=380)
+            else:
+                chart = line.properties(height=380)
+
+            st.altair_chart(chart, use_container_width=True)
+
+with col2:
+    with st.container(border=True):
+        st.markdown("**Monthly summary**")
+
+        monthly = hourly.copy()
+        monthly["month"] = monthly["time"].dt.to_period("M").astype(str)
+
+        if variable == "Precipitation":
+            monthly_agg = (
+                monthly.groupby("month")["precipitation"].sum().reset_index()
+            )
+            monthly_agg.columns = ["month", "value"]
+        else:
+            monthly_agg = monthly.groupby("month")[col_var].mean().reset_index()
+            monthly_agg.columns = ["month", "value"]
+
+        bar = (
+            alt.Chart(monthly_agg)
+            .mark_bar()
+            .encode(
+                x=alt.X("month:O", title="Month", axis=alt.Axis(labelAngle=-45)),
+                y=alt.Y(
+                    "value:Q",
+                    title=f"{'Total' if variable == 'Precipitation' else 'Avg'} ({unit})",
+                ),
+                tooltip=[
+                    alt.Tooltip("month:O", title="Month"),
+                    alt.Tooltip("value:Q", title=variable, format=".1f"),
+                ],
+            )
+            .properties(height=380)
+        )
+        st.altair_chart(bar, use_container_width=True)
+
+# ---------------------------------------------------------------------------
+# Bottom section: distribution + data table
+# ---------------------------------------------------------------------------
+col_left, col_right = st.columns(2)
+
+with col_left:
+    with st.container(border=True):
+        st.markdown("**Distribution**")
+
+        if agg_mode == "Hourly":
+            hist_data = chart_df[col_var].dropna()
+        else:
+            if variable == "Precipitation":
+                hist_data = chart_df["precipitation_sum"].dropna()
+            else:
+                hist_data = chart_df[f"{col_var}_mean"].dropna()
+
+        hist_df = pd.DataFrame({"value": hist_data})
+        hist = (
+            alt.Chart(hist_df)
+            .mark_bar()
+            .encode(
+                x=alt.X(
+                    "value:Q",
+                    bin=alt.Bin(maxbins=40),
+                    title=f"{variable} ({unit})",
+                ),
+                y=alt.Y("count()", title="Frequency"),
+                tooltip=[
+                    alt.Tooltip(
+                        "value:Q", bin=alt.Bin(maxbins=40), title=variable
+                    ),
+                    alt.Tooltip("count()", title="Count"),
+                ],
+            )
+            .properties(height=280)
+        )
+        st.altair_chart(hist, use_container_width=True)
+
+with col_right:
+    with st.container(border=True):
+        st.markdown("**Raw data**")
+
+        display_df = chart_df.copy()
+
+        st.dataframe(
+            display_df,
+            height=280,
+            hide_index=True,
+            column_config={
+                "date": st.column_config.DateColumn(
+                    "Date", format="MMM DD, YYYY"
+                ),
+                "time": st.column_config.DatetimeColumn(
+                    "Time", format="MMM DD, YYYY HH:mm"
+                ),
+            },
+        )
+
+        csv = to_csv(display_df)
+        st.download_button(
+            label="Download CSV",
+            data=csv,
+            file_name=f"weather_{start_str}_to_{end_str}.csv",
+            mime="text/csv",
+            icon=":material/download:",
+        )

requirements.txt

@@ -1,3 +1,4 @@
-altair
-pandas
-streamlit
+altair>=5.2.0
+geopy>=2.4.0
+pandas>=2.0.0
+streamlit>=1.45.0