rsplot 0.2.1__tar.gz → 0.2.3__tar.gz

{rsplot-0.2.1 → rsplot-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rsplot
-Version: 0.2.1
+Version: 0.2.3
 Summary: CLI tool for plotting Remote Sensing data, designed for Agent.
 Project-URL: Repository, https://git.lug.ustc.edu.cn/yaoyhu/rsplot
 Project-URL: GitHub, https://github.com/yaoyhu/rsplot
@@ -279,6 +279,9 @@ rsplot raster 合肥 20260115 -p no2 -o ./logs/hcho/raster_city_jiujiang_hcho.pn
 # Plot a 30-day TROPOMI window mean.
 rsplot raster 安徽 20260131 -p hcho --days 30 -o hcho_anhui_202601.png
 
+# Plot a TROPOMI ozone-profile tropospheric column raster.
+rsplot raster 安徽 20260227 -p o3pr -o o3pr_anhui_20260227.png
+
 # Plot an explicit TROPOMI date range.
 rsplot raster 长三角 20260101-20260131 -p no2 -o no2_yrd_202601.png
 

{rsplot-0.2.1 → rsplot-0.2.3}/README.md

@@ -52,6 +52,9 @@ rsplot raster 合肥 20260115 -p no2 -o ./logs/hcho/raster_city_jiujiang_hcho.pn
 # Plot a 30-day TROPOMI window mean.
 rsplot raster 安徽 20260131 -p hcho --days 30 -o hcho_anhui_202601.png
 
+# Plot a TROPOMI ozone-profile tropospheric column raster.
+rsplot raster 安徽 20260227 -p o3pr -o o3pr_anhui_20260227.png
+
 # Plot an explicit TROPOMI date range.
 rsplot raster 长三角 20260101-20260131 -p no2 -o no2_yrd_202601.png
 

{rsplot-0.2.1 → rsplot-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "rsplot"
-version = "0.2.1"
+version = "0.2.3"
 description = "CLI tool for plotting Remote Sensing data, designed for Agent."
 authors = [
     { name = "Yaoyao Hu", email = "yaoyhu@mail.ustc.edu.cn" },

{rsplot-0.2.1 → rsplot-0.2.3}/src/rsplot/cli.py

@@ -86,7 +86,7 @@ def raster(
         "o3",
         "--product",
         "-p",
-        help="产品类型: no2 / o3 / hcho",
+        help="产品类型: no2 / o3 / o3pr / hcho",
     ),
     days: int | None = typer.Option(
         None,
@@ -98,8 +98,8 @@ def raster(
         None,
         "--n-min",
         help=(
-            "窗口模式下每像元最少有效天数。默认: NO2/O3=max(3, 天数//2), "
-            "HCHO=max(3, ceil(天数*0.25))"
+            "窗口模式下每像元最少有效天数。默认: NO2/O3/O3PR="
+            "max(3, 天数//2), HCHO=max(3, ceil(天数*0.25))"
         ),
     ),
     level: str | None = typer.Option(
@@ -205,12 +205,25 @@ def raster(
 
     # --- 3. Merge params (level defaults + CLI overrides) ---
     params = info.params
-    use_res = res if res is not None else params.res
     use_dpi = dpi if dpi is not None else cfg.dpi
     prod_info = get_product_info(product)
+    product_defaults = prod_info.defaults_for_level(info.level)
+    use_res = (
+        res
+        if res is not None
+        else product_defaults.res
+        if product_defaults.res is not None
+        else params.res
+    )
     use_cmap = cmap if cmap is not None else prod_info.cmap
     use_qa = qa if qa is not None else cfg.qa_threshold
-    use_smooth = smooth if smooth is not None else params.smooth_sigma
+    use_smooth = (
+        smooth
+        if smooth is not None
+        else product_defaults.smooth_sigma
+        if product_defaults.smooth_sigma is not None
+        else params.smooth_sigma
+    )
 
     if basemap is not None:
         use_basemap: bool | None = basemap.lower() == "satellite"
@@ -496,6 +509,7 @@ def station(
     console.print(f"[bold]解析区域:[/bold] {region}")
     info = resolve_region(region, cfg, level_override=level)
     console.print(f"  → [green]{info.name}[/green] (级别: {info.level})")
+    params = info.params
 
     # --- 4. Read station data ---
     use_data_dir = (
@@ -589,6 +603,7 @@ def station(
 _PRODUCT_STATION_PAIR: dict[str, str] = {
     "no2": "NO2",
     "o3": "O3",
+    "o3pr": "O3",
 }
 
 
@@ -607,7 +622,7 @@ def overlay(
         "o3",
         "--product",
         "-p",
-        help="卫星产品类型: no2 / o3",
+        help="卫星产品类型: no2 / o3 / o3pr / hcho",
     ),
     # --- station variable ---
     var: str | None = typer.Option(
@@ -713,12 +728,25 @@ def overlay(
 
     # --- 5. Merge params ---
     params = info.params
-    use_res = res if res is not None else params.res
     use_dpi = dpi if dpi is not None else cfg.dpi
     prod_info = get_product_info(product)
+    product_defaults = prod_info.defaults_for_level(info.level)
+    use_res = (
+        res
+        if res is not None
+        else product_defaults.res
+        if product_defaults.res is not None
+        else params.res
+    )
     use_cmap = cmap if cmap is not None else prod_info.cmap
     use_qa = qa if qa is not None else cfg.qa_threshold
-    use_smooth = smooth if smooth is not None else params.smooth_sigma
+    use_smooth = (
+        smooth
+        if smooth is not None
+        else product_defaults.smooth_sigma
+        if product_defaults.smooth_sigma is not None
+        else params.smooth_sigma
+    )
 
     if basemap is not None:
         use_basemap: bool | None = basemap.lower() == "satellite"
@@ -891,7 +919,7 @@ def recent(
         "o3",
         "--product",
         "-p",
-        help="source=raster 时的产品: no2 / o3 / hcho",
+        help="source=raster 时的产品: no2 / o3 / o3pr / hcho",
     ),
     var: str = typer.Option(
         "AQI",
@@ -970,7 +998,14 @@ def recent(
 
     if use_source == "raster":
         prod_info = get_product_info(product)
-        use_res = res if res is not None else info.params.res
+        product_defaults = prod_info.defaults_for_level(info.level)
+        use_res = (
+            res
+            if res is not None
+            else product_defaults.res
+            if product_defaults.res is not None
+            else info.params.res
+        )
         use_qa = qa if qa is not None else cfg.qa_threshold
         use_data_dir = (
             data_dir if data_dir is not None else cfg.get_data_dir(product)

{rsplot-0.2.1 → rsplot-0.2.3}/src/rsplot/config.py

@@ -24,6 +24,7 @@ else:
 DEFAULT_DATA_DIRS: dict[str, str] = {
     "no2": "/satellite/exports2/yaoyhu/NO2",
     "o3": "/satellite/exports2/yaoyhu/O3",
+    "o3pr": "/satellite/exports2/yaoyhu/O3PR",
     "hcho": "/satellite/exports2/yaoyhu/HCHO",
     "guokong": "/home/zzgsg/data/guokong_combine",
 }

{rsplot-0.2.1 → rsplot-0.2.3}/src/rsplot/readers/__init__.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import math
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 
 import numpy as np
 
@@ -11,10 +11,19 @@ from rsplot.readers.base import BaseReader
 from rsplot.readers.tropomi_hcho import TropomiHCHOReader
 from rsplot.readers.tropomi_no2 import TropomiNO2Reader
 from rsplot.readers.tropomi_o3 import TropomiO3Reader
+from rsplot.readers.tropomi_o3pr import TropomiO3PRReader
 
 HCHO_CMAP = "rsplot_hcho"
 
 
+@dataclass
+class ProductPlotDefaults:
+    """Optional per-product plotting defaults by administrative level."""
+
+    res: float | None = None
+    smooth_sigma: float | None = None
+
+
 @dataclass
 class ProductInfo:
     """Per-product metadata: reader class, display settings, auto-range config."""
@@ -25,6 +34,13 @@ class ProductInfo:
     vmin: float | None  # None = auto from data percentiles
     vmax: float | None
     min_range: float  # minimum vmax-vmin to avoid exaggerating small differences
+    level_defaults: dict[str, ProductPlotDefaults] = field(
+        default_factory=dict
+    )
+
+    def defaults_for_level(self, level: str) -> ProductPlotDefaults:
+        """Return product-specific defaults for an administrative level."""
+        return self.level_defaults.get(level, ProductPlotDefaults())
 
 
 PRODUCT_REGISTRY: dict[str, ProductInfo] = {
@@ -44,6 +60,24 @@ PRODUCT_REGISTRY: dict[str, ProductInfo] = {
         vmax=None,
         min_range=30.0,
     ),
+    "o3pr": ProductInfo(
+        reader_cls=TropomiO3PRReader,
+        colorbar_label="O3 Tropospheric Column from Profile (DU)",
+        cmap="YlOrRd",
+        vmin=None,
+        vmax=None,
+        min_range=5.0,
+        level_defaults={
+            # O3__PR is a coarse 30x30 km profile product. These defaults
+            # keep map pixels close to the native sampling while still using
+            # modest smoothing for display.
+            "country": ProductPlotDefaults(res=0.25, smooth_sigma=1.0),
+            "key_region": ProductPlotDefaults(res=0.15, smooth_sigma=1.2),
+            "province": ProductPlotDefaults(res=0.1, smooth_sigma=1.5),
+            "city": ProductPlotDefaults(res=0.075, smooth_sigma=1.5),
+            "county": ProductPlotDefaults(res=0.05, smooth_sigma=2.0),
+        },
+    ),
     "hcho": ProductInfo(
         reader_cls=TropomiHCHOReader,
         colorbar_label="HCHO VCD (x10^15 molec/cm2)",

rsplot-0.2.3/src/rsplot/readers/tropomi_o3pr.py

@@ -0,0 +1,103 @@
+"""TROPOMI O3 profile tropospheric-column reader.
+
+Reads ``S5P_*_L2__O3__PR`` ozone profile products and uses the provided
+``ozone_tropospheric_column`` variable directly. Values are converted from
+``mol m-2`` to DU.
+"""
+
+from __future__ import annotations
+
+import glob
+import os
+
+import numpy as np
+from rich.progress import track
+
+from rsplot.readers.base import (
+    BaseReader,
+    SwathData,
+    read_tropomi_product_arrays,
+)
+
+VALUE_NAME = "ozone_tropospheric_column"
+
+# mol/m2 -> DU, from the product attribute
+# multiplication_factor_to_convert_to_DU = 2241.15
+UNIT_CONVERSION = 2241.15
+
+
+class TropomiO3PRReader(BaseReader):
+    """Reader for TROPOMI L2 O3 profile tropospheric-column files."""
+
+    def read(
+        self,
+        data_dir: str,
+        date: str,
+        extent: tuple[float, float, float, float],
+        qa_threshold: float = 0.5,
+    ) -> SwathData:
+        patterns = [
+            os.path.join(data_dir, f"S5P_*_L2__O3__PR_{date}T*.nc"),
+            os.path.join(data_dir, f"S5P_*_L2__O3__PR_{date}T*.nc.zip"),
+        ]
+        files: list[str] = []
+        for p in patterns:
+            files.extend(glob.glob(p))
+        files = sorted(set(files))
+        if not files:
+            raise FileNotFoundError(
+                f"未找到匹配文件:\n  "
+                + "\n  ".join(patterns)
+                + "\n请检查 --data-dir 和 --date 参数。"
+            )
+
+        lon_min, lon_max, lat_min, lat_max = extent
+        all_lon, all_lat, all_o3 = [], [], []
+        broken = 0
+        broken_examples: list[str] = []
+
+        for f in track(files, description="[cyan]读取 O3PR 轨道..."):
+            try:
+                lon, lat, o3, qa = read_tropomi_product_arrays(f, VALUE_NAME)
+            except (OSError, ValueError, KeyError) as e:
+                broken += 1
+                if len(broken_examples) < 3:
+                    broken_examples.append(
+                        f"{os.path.basename(f)}: {str(e).splitlines()[0]}"
+                    )
+                continue
+
+            mask = (
+                (qa > qa_threshold)
+                & (lon >= lon_min)
+                & (lon <= lon_max)
+                & (lat >= lat_min)
+                & (lat <= lat_max)
+                & np.isfinite(o3)
+                & (o3 < 1e30)
+            )
+            if mask.sum() > 0:
+                all_lon.append(lon[mask])
+                all_lat.append(lat[mask])
+                all_o3.append(o3[mask] * UNIT_CONVERSION)
+
+        if not all_lon:
+            broken_msg = (
+                "\n损坏/不可读示例:\n  " + "\n  ".join(broken_examples)
+                if broken_examples
+                else ""
+            )
+            raise ValueError(
+                f"{date} 当天 O3PR 无有效数据覆盖目标区域 {extent}。\n"
+                f"共扫描 {len(files)} 个文件，损坏 {broken} 个。"
+                f"{broken_msg}"
+            )
+
+        return SwathData(
+            lon=np.concatenate(all_lon),
+            lat=np.concatenate(all_lat),
+            values=np.concatenate(all_o3),
+            n_pixels=sum(len(a) for a in all_lon),
+            n_files=len(files),
+            n_broken=broken,
+        )

{rsplot-0.2.1 → rsplot-0.2.3}/src/rsplot/results.py

@@ -187,21 +187,31 @@ def _attribute_stations_to_cities(
     lon: np.ndarray, lat: np.ndarray, cities_gdf: gpd.GeoDataFrame
 ) -> np.ndarray:
     """Return city name for each (lon, lat); empty string if none contain it."""
+    return _attribute_stations_to_areas(lon, lat, cities_gdf)
+
+
+def _attribute_stations_to_areas(
+    lon: np.ndarray,
+    lat: np.ndarray,
+    areas_gdf: gpd.GeoDataFrame,
+    name_field: str = "name",
+) -> np.ndarray:
+    """Return containing admin-unit name for each (lon, lat)."""
     from shapely.geometry import Point
 
-    sindex = cities_gdf.sindex
+    sindex = areas_gdf.sindex
     out = np.empty(len(lon), dtype=object)
     for i, (x, y) in enumerate(zip(lon, lat)):
         if not (np.isfinite(x) and np.isfinite(y)):
             out[i] = ""
             continue
         pt = Point(float(x), float(y))
-        city = ""
+        area = ""
         for idx in sindex.intersection((x, y, x, y)):
-            if cities_gdf.iloc[idx].geometry.contains(pt):
-                city = cities_gdf.iloc[idx]["name"]
+            if areas_gdf.iloc[idx].geometry.contains(pt):
+                area = areas_gdf.iloc[idx][name_field]
                 break
-        out[i] = city
+        out[i] = area
     return out
 
 
@@ -220,6 +230,46 @@ def _aqi_distribution(vals: np.ndarray) -> dict[str, int]:
     return dist
 
 
+def _station_admin_level(region: RegionInfo) -> str | None:
+    if region.level == "country":
+        return "province"
+    if region.level == "key_region":
+        return "city"
+    if region.level == "province":
+        municipalities = {"北京市", "天津市", "上海市", "重庆市"}
+        return "county" if region.name in municipalities else "city"
+    if region.level == "city":
+        return "county"
+    return None
+
+
+def _top_station_entries(
+    *,
+    vals: np.ndarray,
+    ids: np.ndarray,
+    lons: np.ndarray,
+    lats: np.ndarray,
+    area_names: np.ndarray | None,
+    admin_level: str | None,
+    limit: int = 10,
+) -> list[dict[str, Any]]:
+    top_stations: list[dict[str, Any]] = []
+    for i in np.argsort(vals)[::-1][:limit]:
+        entry: dict[str, Any] = {
+            "id": str(ids[i]),
+            "value": _round(vals[i]),
+            "lon": round(float(lons[i]), 3),
+            "lat": round(float(lats[i]), 3),
+        }
+        if area_names is not None:
+            entry["admin_level"] = admin_level
+            entry["admin_name"] = area_names[i] or None
+            # Backward-compatible alias for older consumers.
+            entry["city"] = area_names[i] or None
+        top_stations.append(entry)
+    return top_stations
+
+
 def build_station_result(
     *,
     region: RegionInfo,
@@ -235,6 +285,12 @@ def build_station_result(
     lons = data.lon[valid]
     lats = data.lat[valid]
     ids = np.asarray(data.id)[valid]
+    admin_gdf = (
+        region.sub_boundary_gdf
+        if region.sub_boundary_gdf is not None and len(region.sub_boundary_gdf) > 0
+        else cities_gdf
+    )
+    admin_level = _station_admin_level(region)
 
     result: dict[str, Any] = {
         "command": "station",
@@ -253,9 +309,25 @@ def build_station_result(
         "stats": _basic_stats(vals),
     }
 
-    station_cities = None
-    if cities_gdf is not None and len(cities_gdf) > 0 and len(vals) > 0:
-        station_cities = _attribute_stations_to_cities(lons, lats, cities_gdf)
+    station_areas = None
+    if admin_gdf is not None and len(admin_gdf) > 0 and len(vals) > 0:
+        station_areas = _attribute_stations_to_areas(
+            lons, lats, admin_gdf, region.sub_name_field
+        )
+
+    if len(vals) > 0:
+        result["top_stations"] = _top_station_entries(
+            vals=vals,
+            ids=ids,
+            lons=lons,
+            lats=lats,
+            area_names=station_areas,
+            admin_level=admin_level,
+            limit=10,
+        )
+        result["top_station_ids"] = [
+            entry["id"] for entry in result["top_stations"]
+        ]
 
     # Exceedance summary
     if threshold is not None and len(vals) > 0:
@@ -272,8 +344,11 @@ def build_station_result(
                 "lon": round(float(lons[i]), 3),
                 "lat": round(float(lats[i]), 3),
             }
-            if station_cities is not None:
-                entry["city"] = station_cities[i] or None
+            if station_areas is not None:
+                entry["admin_level"] = admin_level
+                entry["admin_name"] = station_areas[i] or None
+                # Backward-compatible alias for older consumers.
+                entry["city"] = station_areas[i] or None
             top_stations.append(entry)
             if len(top_stations) >= 10:
                 break
@@ -287,11 +362,11 @@ def build_station_result(
     if data.var_name == "AQI" and len(vals) > 0:
         result["aqi_distribution"] = _aqi_distribution(vals)
 
-    # Per-city ranking
-    if station_cities is not None and len(vals) > 0:
+    # Per-admin-unit ranking, exposed under the legacy city_ranking key.
+    if station_areas is not None and len(vals) > 0:
         acc: dict[str, dict[str, Any]] = {}
         for i in range(len(vals)):
-            c = station_cities[i]
+            c = station_areas[i]
             if not c:
                 continue
             s = acc.setdefault(c, {"values": [], "n_exceed": 0})
@@ -303,6 +378,9 @@ def build_station_result(
             arr = np.asarray(s["values"])
             ranking.append(
                 {
+                    "name": city,
+                    "admin_level": admin_level,
+                    # Backward-compatible alias for older consumers.
                     "city": city,
                     "n_valid": len(arr),
                     "mean": _round(np.mean(arr)),