anta-database 0.3.0__tar.gz → 0.3.2__tar.gz

{anta_database-0.3.0 → anta_database-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anta_database
-Version: 0.3.0
+Version: 0.3.2
 Summary: SQLite database for the AntArchitecture Community Data
 Author: Antoine Hermant
 Author-email: antoine.hermant@etik.com
@@ -20,12 +20,14 @@ License-File: LICENSE
 Requires-Dist: pandas
 Requires-Dist: geopandas
 Requires-Dist: xarray
+Requires-Dist: h5netcdf
 Requires-Dist: h5py
 Requires-Dist: pyproj
 Requires-Dist: scipy
 Requires-Dist: matplotlib
 Requires-Dist: colormaps
 Requires-Dist: tqdm
+Requires-Dist: pyshp
 Dynamic: license-file
 
 <h1 align="center">

{anta_database-0.3.0 → anta_database-0.3.2}/anta_database/database/database.py

@@ -5,6 +5,7 @@ import numpy as np
 import xarray as xr
 import h5py
 from typing import Union, List, Dict, Tuple, Optional, Generator
+from tqdm import tqdm
 
 from anta_database.plotting.plotting import Plotting
 
@@ -17,6 +18,7 @@ class Database:
         self._plotting = None
         self._max_displayed_flight_ids = max_displayed_flight_ids
         self._include_BM = include_BEDMAP
+        self._disable_tqdm = os.getenv("JUPYTER_BOOK_BUILD", False)
         self._excluded = {
             'dataset': [],
             'institute': [],
@@ -710,6 +712,7 @@ class Database:
         metadata: Union[None, Dict, 'MetadataResult'] = None,
         data_dir: Optional[str] = None,
         downscale_factor: Optional[str] = None,
+        disable_tqdm: bool = False,
     ) -> Generator[Tuple[pd.DataFrame, Dict]]:
         """
         Generates xarray Datasets from HDF5 files, one at a time, with lazy loading.
@@ -737,7 +740,7 @@ class Database:
         file_paths = self._get_file_paths_from_metadata(metadata=md)
         file_paths = np.unique(file_paths) # Be carefull as many pointers point to the same file
 
-        for file_path in file_paths:
+        for file_path in tqdm(file_paths, desc='Generating dataframes', total=len(file_paths), unit='file', disable=disable_tqdm):
             full_path = os.path.join(data_dir, file_path)
             file_md = self._get_file_metadata(file_path)
             ds = h5py.File(full_path, 'r')
@@ -759,7 +762,8 @@ class Database:
                         df[int(age)] = ds[var][::downscale_factor, irh_index]
 
                 else:
-                    df[var] = ds[var][::downscale_factor]
+                    if var in ds.keys():
+                        df[var] = ds[var][::downscale_factor]
 
             metadata = {
                 'dataset': file_md['dataset'],

{anta_database-0.3.0 → anta_database-0.3.2}/anta_database/plotting/plotting.py

@@ -1,10 +1,12 @@
 import os
 import h5py
 import pandas as pd
-import geopandas as gpd
 import numpy as np
 import matplotlib.pyplot as plt
 from matplotlib.colors import BoundaryNorm, ListedColormap, LinearSegmentedColormap
+import shapefile
+from matplotlib.patches import Polygon
+from matplotlib.collections import PatchCollection
 from matplotlib import patheffects as path_effects
 import colormaps as cmaps
 from contextlib import contextmanager
@@ -22,6 +24,7 @@ class Plotting:
         self._site_coords_path = files('anta_database.data').joinpath('site-coords.pkl')
         self._imbie_path = files('anta_database.data').joinpath('ANT_Basins_IMBIE2_v1.6.shp')
         self._center_coords = files('anta_database.data').joinpath('centeroid_coords_basins.shp')
+        self._disable_tqdm = os.getenv("JUPYTER_BOOK_BUILD", False)
 
     def _pre_plot_check(self,
                         metadata: Union[None, Dict, 'MetadataResult'] = None
@@ -206,7 +209,7 @@ class Plotting:
             downscale_factor: Optional[int] = None,
             title: Optional[str] = None,
             xlim: tuple = (None, None),
-            ylim: tuple = (3000, None),
+            ylim: tuple = (3500, 0),
             scale_factor: float = 1.0,
             marker_size: Optional[float] = 2,
             latex: bool = False,
@@ -274,10 +277,7 @@ class Plotting:
 
         total_traces = len(metadata['flight_id'])
 
-        if latex:
-            from matplotlib import rc
-            rc('font', **{'family': 'serif', 'serif': ['Computer Modern']})
-            rc('text', usetex=True)
+        # if latex:
 
         if not self._pre_plot_check(metadata):
             return
@@ -325,7 +325,7 @@ class Plotting:
             colors.update(bedmap_colors)
 
             flight_ids = metadata['flight_id']
-            for dataset in tqdm(datasets, desc="Plotting", total=len(datasets), unit='dataset'):
+            for dataset in tqdm(datasets, desc="Plotting", total=len(datasets), unit='dataset', disable=self._disable_tqdm):
                 metadata_impl = self._db.query(dataset=dataset, flight_id=flight_ids, retain_query=False)
                 file_paths = self._db._get_file_paths_from_metadata(metadata_impl)
                 file_paths = np.unique(file_paths)
@@ -363,7 +363,7 @@ class Plotting:
             colors = {dataset: cmap(i) for i, dataset in zip(color_indices, institutes)}
 
             flight_ids = metadata['flight_id']
-            for institute in tqdm(institutes, desc="Plotting", total=len(institutes), unit='institute'):
+            for institute in tqdm(institutes, desc="Plotting", total=len(institutes), unit='institute', disable=self._disable_tqdm):
                 metadata_impl = self._db.query(institute=institute, flight_id=flight_ids, retain_query=False)
                 file_paths = self._db._get_file_paths_from_metadata(metadata_impl)
                 file_paths = np.unique(file_paths)
@@ -398,7 +398,7 @@ class Plotting:
 
 
             all_dfs = []
-            for ds, _ in tqdm(self._db.data_generator(metadata, downscale_factor=downscale_factor), desc="Plotting", total=total_traces, unit='trace'):
+            for ds, _ in tqdm(self._db.data_generator(metadata, downscale_factor=downscale_factor, disable_tqdm=True), desc="Plotting", total=total_traces, unit='trace', disable=self._disable_tqdm):
                 all_dfs.append(ds)
             df = pd.concat(all_dfs)
 
@@ -474,6 +474,7 @@ class Plotting:
 
             elif var in ['IRH_DEPTH', 'IRH_FRAC_DEPTH']:
                 if var == 'IRH_DEPTH':
+                    label = f'IRH Depth [m]'
                     if cmap == None:
                         cmap = cmaps.torch_r
                     extend = 'both'
@@ -556,7 +557,7 @@ class Plotting:
 
             datasets = list(metadata['dataset'])
             flight_ids = metadata['flight_id']
-            for flight_id in tqdm(flight_ids, desc="Plotting", total=len(flight_ids), unit='flight_id'):
+            for flight_id in tqdm(flight_ids, desc="Plotting", total=len(flight_ids), unit='flight_id', disable=self._disable_tqdm):
                 metadata_impl = self._db.query(flight_id=flight_id, retain_query=False)
                 file_paths = self._db._get_file_paths_from_metadata(metadata_impl)
                 file_paths = np.unique(file_paths)
@@ -576,14 +577,14 @@ class Plotting:
         # --- Format Figure ---
         print('Formatting ...')
 
-        x0, x1 = ax.get_xlim() if xlim == (None, None) else xlim
-        y0, y1 = ax.get_ylim() if ylim == (None, None) else ylim
-        x_extent = x1 - x0
-        y_extent = y1 - y0
-        aspect_ratio = y_extent / x_extent
         ax.set_xlim(*xlim)
         ax.set_ylim(*ylim)
         if color_by != 'transect':
+            x0, x1 = ax.get_xlim() if xlim == (None, None) else xlim
+            y0, y1 = ax.get_ylim() if ylim == (None, None) else ylim
+            x_extent = x1 - x0
+            y_extent = y1 - y0
+            aspect_ratio = y_extent / x_extent
             ax.set_xlabel('x [km]')
             ax.set_ylabel('y [km]')
             ax.set_aspect('equal')
@@ -616,17 +617,55 @@ class Plotting:
 
         # --- Plot IMBIE basins ---
         if basins and color_by != 'transect':
-            basins = gpd.read_file(self._imbie_path)
-            basins.geometry = basins.geometry.scale(xfact=0.001, yfact=0.001, origin=(0, 0))
-            basins.plot(ax=ax, color='none', edgecolor='black', linewidth=0.5)
-            center_coords = gpd.read_file(self._center_coords)
-            center_coords.geometry = center_coords.geometry.scale(xfact=0.001, yfact=0.001, origin=(0, 0))
-            center_coords['x'] = center_coords['geometry'].x
-            center_coords['y'] = center_coords['geometry'].y
-            for x, y, sub in zip(center_coords['x'], center_coords['y'], center_coords['Subregion']):
-                ax.text(x, y, sub, fontsize=12, color='k', ha='center',
-                        path_effects=[path_effects.withStroke(linewidth=5, foreground=(1,1,1,0.7))]
-                        )
+            sf_basins = shapefile.Reader(self._imbie_path)
+            basin_patches = []
+
+            for shape_rec in sf_basins.shapeRecords():
+                shp = shape_rec.shape
+                pts = shp.points
+                parts = list(shp.parts) + [len(pts)]  # add sentinel end index
+
+                # build one polygon per part
+                for i in range(len(parts) - 1):
+                    start, end = parts[i], parts[i + 1]
+                    ring = pts[start:end]
+
+                    # scale coordinates
+                    scaled = [(x * 0.001, y * 0.001) for x, y in ring]
+
+                    poly = Polygon(scaled, closed=True, fill=False)
+                    basin_patches.append(poly)
+
+            pc = PatchCollection(
+                basin_patches,
+                facecolor='none',
+                edgecolor='black',
+                linewidth=0.5,
+            )
+            ax.add_collection(pc)
+
+            # ---- CENTERS: read + scale + label ----
+            sf_centers = shapefile.Reader(self._center_coords)
+
+            # find the field index for "Subregion" in the DBF
+            fields = sf_centers.fields[1:]  # first is DeletionFlag
+            field_names = [f[0] for f in fields]
+            sub_idx = field_names.index('Subregion')
+
+            for shape_rec in sf_centers.shapeRecords():
+                # assuming center_coords are points
+                x_raw, y_raw = shape_rec.shape.points[0]
+                x = x_raw * 0.001
+                y = y_raw * 0.001
+                sub = shape_rec.record[sub_idx]
+
+                if x0 <= x <= x1 and y0 <= y <= y1:
+                    ax.text(
+                        x, y, sub, fontsize=12, color='k', ha='center',
+                        path_effects=[path_effects.withStroke(
+                            linewidth=5, foreground=(1, 1, 1, 0.7)
+                        )]
+                    )
         # --- Plot ice core sites ---
         if stations and color_by != 'transect':
             site_coords = pd.read_pickle(self._site_coords_path)

{anta_database-0.3.0 → anta_database-0.3.2}/anta_database.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anta_database
-Version: 0.3.0
+Version: 0.3.2
 Summary: SQLite database for the AntArchitecture Community Data
 Author: Antoine Hermant
 Author-email: antoine.hermant@etik.com
@@ -20,12 +20,14 @@ License-File: LICENSE
 Requires-Dist: pandas
 Requires-Dist: geopandas
 Requires-Dist: xarray
+Requires-Dist: h5netcdf
 Requires-Dist: h5py
 Requires-Dist: pyproj
 Requires-Dist: scipy
 Requires-Dist: matplotlib
 Requires-Dist: colormaps
 Requires-Dist: tqdm
+Requires-Dist: pyshp
 Dynamic: license-file
 
 <h1 align="center">

{anta_database-0.3.0 → anta_database-0.3.2}/anta_database.egg-info/requires.txt

@@ -1,9 +1,11 @@
 pandas
 geopandas
 xarray
+h5netcdf
 h5py
 pyproj
 scipy
 matplotlib
 colormaps
 tqdm
+pyshp

{anta_database-0.3.0 → anta_database-0.3.2}/pyproject.toml

@@ -18,12 +18,14 @@ dependencies = [
   "pandas",
   "geopandas",
   "xarray",
+  "h5netcdf",
   "h5py",
   "pyproj",
   "scipy",
   "matplotlib",
   "colormaps",
   "tqdm",
+  "pyshp",
 ]
 
 keywords = ["isochrones", "database", "IRH", "radar"]