anta-database 0.3.1__tar.gz → 0.3.3__tar.gz

{anta_database-0.3.1 → anta_database-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anta_database
-Version: 0.3.1
+Version: 0.3.3
 Summary: SQLite database for the AntArchitecture Community Data
 Author: Antoine Hermant
 Author-email: antoine.hermant@etik.com
@@ -27,6 +27,7 @@ Requires-Dist: scipy
 Requires-Dist: matplotlib
 Requires-Dist: colormaps
 Requires-Dist: tqdm
+Requires-Dist: pyshp
 Dynamic: license-file
 
 <h1 align="center">

{anta_database-0.3.1 → anta_database-0.3.3}/anta_database/compiling/compile.py

@@ -863,6 +863,8 @@ class CompileDatabase:
                             max_depth[i] = depth_slice[max_idx]
                             age_max_depth[i] = ds.IRH_AGE.values[max_idx]
 
+                    age_max_depth = np.abs(age_max_depth)
+                    max_depth = np.abs(max_depth)
                     flight_id = ds.attrs["flight ID"]
                     acq_year = ds.attrs["acquisition year"]
                     project = ds.attrs["project"]
@@ -872,10 +874,10 @@ class CompileDatabase:
                     df = gpd.GeoDataFrame({
                         "geometry": [Point(x, y) for x, y in zip(ds.PSX.values, ds.PSY.values)],
                         "irh_num": N.astype('int16'),
-                        "max_age": age_max_depth.astype('int16'),
+                        "max_age": age_max_depth.astype('int32'),
                         "max_depth": max_depth.astype('int16'),
-                        "flight_id": [flight_id] * len(N),
-                        "doi_data": [doi_data] * len(N),
+                        # "flight_id": [flight_id] * len(N),
+                        # "doi_data": [doi_data] * len(N),
                     }, crs="EPSG:3031")
 
                     all_dfs.append(df)

{anta_database-0.3.1 → anta_database-0.3.3}/anta_database/compiling/reconnect.py

@@ -43,7 +43,7 @@ class Reconnect:
 
 
     def process(self, df_connect: pd.DataFrame, tree, file_path: str):
-        data_dir = self._db.db_dir
+        data_dir = self._db._db_dir
         full_path = os.path.join(data_dir, file_path)
         with h5py.File(full_path, 'a') as f:
             with xr.open_dataset(f, engine='h5netcdf') as ds:

{anta_database-0.3.1 → anta_database-0.3.3}/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': [],
@@ -90,11 +92,13 @@ class Database:
             LEFT JOIN
                 variables v ON dv.variable_id = v.id
             LEFT JOIN
-                dataset_ages da ON d.id = da.dataset_id
+                dataset_ages da ON d.id = da.dataset_id AND v.name = 'IRH_DEPTH'
             LEFT JOIN
                 ages a ON da.age_id = a.id
             LEFT JOIN
-                regions r ON da.region_id = r.id
+                dataset_regions dr ON d.id = dr.dataset_id
+            LEFT JOIN
+                regions r ON dr.region_id = r.id
         '''
         conditions = []
         params = []
@@ -413,21 +417,21 @@ class Database:
         Helper method to build the SQL query and parameters for filtering.
         Returns the query string and parameters list.
         """
-        select_clause = 's.name AS dataset, \
+        select_clause = "s.name AS dataset, \
                         s.citation, \
                         s.DOI_dataset, \
                         s.DOI_publication, \
                         institutes_list.institutes, \
                         projects_list.projects, \
                         d.acq_year, \
-                        a.age, \
-                        a.age_unc, \
+                        CASE WHEN v.name = 'IRH_DEPTH' THEN a.age ELSE NULL END AS age, \
+                        CASE WHEN v.name = 'IRH_DEPTH' THEN a.age_unc ELSE NULL END AS age_unc, \
                         v.name AS var, \
                         d.flight_id, \
                         r.region, \
                         r.IMBIE_basin, \
                         radar_instruments_list.radar_instruments \
-        '
+        "
         query = f'''
             SELECT {select_clause}
             FROM
@@ -472,11 +476,13 @@ class Database:
             LEFT JOIN
                 variables v ON dv.variable_id = v.id
             LEFT JOIN
-                dataset_ages da ON d.id = da.dataset_id
+                dataset_ages da ON d.id = da.dataset_id AND v.name = 'IRH_DEPTH'
             LEFT JOIN
                 ages a ON da.age_id = a.id
             LEFT JOIN
-                regions r ON da.region_id = r.id
+                dataset_regions dr ON d.id = dr.dataset_id
+            LEFT JOIN
+                regions r ON dr.region_id = r.id
         '''
         conditions = []
         params = []
@@ -534,21 +540,21 @@ class Database:
               retain_query: Optional[bool] = True,
               ) -> 'MetadataResult':
 
-        select_clause = 's.name AS dataset, \
+        select_clause = "s.name AS dataset, \
                         s.citation, \
                         s.DOI_dataset, \
                         s.DOI_publication, \
                         institutes_list.institutes, \
                         projects_list.projects, \
                         d.acq_year, \
-                        a.age, \
-                        a.age_unc, \
+                        CASE WHEN v.name = 'IRH_DEPTH' THEN a.age ELSE NULL END AS age, \
+                        CASE WHEN v.name = 'IRH_DEPTH' THEN a.age_unc ELSE NULL END AS age_unc, \
                         v.name AS var, \
                         d.flight_id, \
                         r.region, \
                         r.IMBIE_basin, \
                         radar_instruments_list.radar_instruments \
-        '
+        "
         query, params = self._build_query_and_params(age, var, dataset, institute, project, acquisition_year, flight_id, region, IMBIE_basin, radar_instrument, select_clause)
 
         conn = sqlite3.connect(self._file_db_path)
@@ -684,18 +690,18 @@ class Database:
 
     def get_files(
         self,
-        metadata: Union[None, Dict, 'MetadataResult'] = None,
-        data_dir: Union[None, str] = None,
+        metadata: Optional[Union[None, Dict, 'MetadataResult']] = None,
+        data_dir: Optional[Union[None, str]] = None,
     ):
 
         md = metadata or self._md
         if not md:
-            print('Please provide metadata of the files you want to generate the data from. Exiting...')
+            print('Please provide metadata of the files you want to generate the data from.')
             return
 
         data_dir = data_dir or self._db_dir
         if not data_dir:
-            print('No data directory provided. Exiting...')
+            print('No data directory provided.')
             return
 
         file_paths = self._get_file_paths_from_metadata(metadata=md)
@@ -710,6 +716,7 @@ 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 +744,7 @@ 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')

{anta_database-0.3.1 → anta_database-0.3.3}/anta_database/indexing/index_database.py

@@ -126,11 +126,9 @@ class IndexDatabase:
             CREATE TABLE IF NOT EXISTS dataset_ages (
                 dataset_id INTEGER,
                 age_id INTEGER,
-                region_id INTEGER,
                 FOREIGN KEY (dataset_id) REFERENCES datasets (id),
                 FOREIGN KEY (age_id) REFERENCES ages (id),
-                FOREIGN KEY (region_id) REFERENCES regions (id),
-                PRIMARY KEY (dataset_id, age_id, region_id)
+                PRIMARY KEY (dataset_id, age_id)
                 )
             ''')
 
@@ -164,6 +162,16 @@ class IndexDatabase:
                 )
             ''')
 
+        cursor.execute('''
+            CREATE TABLE IF NOT EXISTS dataset_regions (
+                dataset_id INTEGER,
+                region_id INTEGER,
+                FOREIGN KEY (dataset_id) REFERENCES datasets (id),
+                FOREIGN KEY (region_id) REFERENCES regions (id),
+                PRIMARY KEY (dataset_id, region_id)
+                )
+            ''')
+
         for f in tqdm(h5_files, desc="Indexing files"):
             _, file_name = os.path.split(f)
 
@@ -281,7 +289,7 @@ class IndexDatabase:
             # Insert variables
             var_list = ['ICE_THK', 'SURF_ELEV', 'BED_ELEV', 'BASAL_UNIT', 'IRH_NUM', 'IRH_DEPTH']
             for var in var_list:
-                if var in ds_vars or var == 'IRH_DEPTH':
+                if var in ds_vars:
                     cursor.execute('INSERT OR IGNORE INTO variables (name) VALUES (?)', (var,))
                     var_id = cursor.execute('SELECT id FROM variables WHERE name = ?', (var,)).fetchone()[0]
                     cursor.execute('''
@@ -294,13 +302,18 @@ class IndexDatabase:
                 for age, age_unc in age_uncs.iterrows():
                     cursor.execute('INSERT OR IGNORE INTO ages (age, age_unc) VALUES (?, ?)', (str(age), str(age_unc['age_unc'])))
                     age_id = cursor.execute('SELECT id FROM ages WHERE age = ? AND age_unc = ?', (str(age), str(age_unc['age_unc']))).fetchone()[0]
-                    for basin, region in basin_mapping.items():
-                        cursor.execute('INSERT OR IGNORE INTO regions (region, IMBIE_basin) VALUES (?, ?)', (region, basin))
-                        region_id = cursor.execute('SELECT id FROM regions WHERE region = ? AND IMBIE_basin = ?', (region, basin)).fetchone()[0]
-                        cursor.execute('''
-                            INSERT OR IGNORE INTO dataset_ages (dataset_id, age_id, region_id)
-                            VALUES (?, ?, ?)
-                        ''', (dataset_row_id, age_id, region_id))
+                    cursor.execute('''
+                        INSERT OR IGNORE INTO dataset_ages (dataset_id, age_id)
+                        VALUES (?, ?)
+                    ''', (dataset_row_id, age_id))
+
+            for basin, region in basin_mapping.items():
+                cursor.execute('INSERT OR IGNORE INTO regions (region, IMBIE_basin) VALUES (?, ?)', (region, basin))
+                region_id = cursor.execute('SELECT id FROM regions WHERE region = ? AND IMBIE_basin = ?', (region, basin)).fetchone()[0]
+                cursor.execute('''
+                    INSERT OR IGNORE INTO dataset_regions (dataset_id, region_id)
+                    VALUES (?, ?)
+                ''', (dataset_row_id, region_id))
 
         conn.commit()
         conn.close()

{anta_database-0.3.1 → anta_database-0.3.3}/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
@@ -61,11 +64,12 @@ class Plotting:
             metadata: Union[None, Dict, 'MetadataResult'] = None,
             downscale_factor: Optional[int] = None,
             title: Optional[str] = None,
-            xlim: tuple = (None, None),
-            ylim: tuple = (None, None),
+            xlim: Optional[tuple] = (None, None),
+            ylim: Optional[tuple] = (None, None),
+            vmin: Optional[float] = None,
+            vmax: Optional[float] = None,
             scale_factor: float = 1.0,
             marker_size: Optional[float] = 0.5,
-            latex: bool = False,
             cmap: Optional['LinearSegmentedColormap'] = None,
             grounding_line: Optional[bool] = True,
             basins: Optional[bool] = True,
@@ -83,8 +87,9 @@ class Plotting:
             title=title,
             xlim=xlim,
             ylim=ylim,
+            vmin=vmin,
+            vmax=vmax,
             scale_factor=scale_factor,
-            latex=latex,
             cmap=cmap,
             grounding_line=grounding_line,
             basins=basins,
@@ -97,11 +102,12 @@ class Plotting:
             metadata: Union[None, Dict, 'MetadataResult'] = None,
             downscale_factor: Optional[int] = None,
             title: Optional[str] = None,
-            xlim: tuple = (None, None),
-            ylim: tuple = (None, None),
+            xlim: Optional[tuple] = (None, None),
+            ylim: Optional[tuple] = (None, None),
+            vmin: Optional[float] = None,
+            vmax: Optional[float] = None,
             scale_factor: float = 1.0,
             marker_size: Optional[float] = 0.1,
-            latex: bool = False,
             cmap: Optional['LinearSegmentedColormap'] = None,
             grounding_line: Optional[bool] = True,
             basins: Optional[bool] = True,
@@ -119,8 +125,9 @@ class Plotting:
             title=title,
             xlim=xlim,
             ylim=ylim,
+            vmin=vmin,
+            vmax=vmax,
             scale_factor=scale_factor,
-            latex=latex,
             cmap=cmap,
             grounding_line=grounding_line,
             basins=basins,
@@ -133,11 +140,12 @@ class Plotting:
             metadata: Union[None, Dict, 'MetadataResult'] = None,
             downscale_factor: Optional[int] = None,
             title: Optional[str] = None,
-            xlim: tuple = (None, None),
-            ylim: tuple = (None, None),
+            xlim: Optional[tuple] = (None, None),
+            ylim: Optional[tuple] = (None, None),
+            vmin: Optional[float] = None,
+            vmax: Optional[float] = None,
             scale_factor: float = 1.0,
             marker_size: Optional[float] = 0.1,
-            latex: bool = False,
             cmap: Optional['LinearSegmentedColormap'] = None,
             grounding_line: Optional[bool] = True,
             basins: Optional[bool] = True,
@@ -156,7 +164,8 @@ class Plotting:
             title=title,
             xlim=xlim,
             ylim=ylim,
-            latex=latex,
+            vmin=vmin,
+            vmax=vmax,
             cmap=cmap,
             grounding_line=grounding_line,
             basins=basins,
@@ -169,11 +178,12 @@ class Plotting:
             metadata: Union[None, Dict, 'MetadataResult'] = None,
             downscale_factor: Optional[int] = None,
             title: Optional[str] = None,
-            xlim: tuple = (None, None),
-            ylim: tuple = (None, None),
+            xlim: Optional[tuple] = (None, None),
+            ylim: Optional[tuple] = (None, None),
+            vmin: Optional[float] = None,
+            vmax: Optional[float] = None,
             scale_factor: float = 1.0,
             marker_size: Optional[float] = 0.3,
-            latex: bool = False,
             cmap: Optional['LinearSegmentedColormap'] = None,
             grounding_line: Optional[bool] = True,
             basins: Optional[bool] = True,
@@ -190,9 +200,10 @@ class Plotting:
             title=title,
             xlim=xlim,
             ylim=ylim,
+            vmin=vmin,
+            vmax=vmax,
             scale_factor=scale_factor,
             marker_size=marker_size,
-            latex=latex,
             cmap=cmap,
             grounding_line=grounding_line,
             basins=basins,
@@ -200,16 +211,16 @@ class Plotting:
             save=save,
         )
 
-    def transect(
+    def transect_1D(
             self,
             metadata: Union[None, Dict, 'MetadataResult'] = None,
+            elevation: Optional[bool] = False,
             downscale_factor: Optional[int] = None,
             title: Optional[str] = None,
-            xlim: tuple = (None, None),
-            ylim: tuple = (3500, 0),
+            xlim: Optional[tuple] = (None, None),
+            ylim: Optional[tuple] = (None, None),
             scale_factor: float = 1.0,
             marker_size: Optional[float] = 2,
-            latex: bool = False,
             cmap: Optional['LinearSegmentedColormap'] = None,
             grounding_line: Optional[bool] = True,
             basins: Optional[bool] = True,
@@ -220,7 +231,8 @@ class Plotting:
         Plot the color-coded values of the given variable on Antarcitic map
         """
         self._base_plot(
-            color_by='transect',
+            color_by='transect_1D',
+            elevation=elevation,
             metadata=metadata,
             downscale_factor=downscale_factor,
             title=title,
@@ -228,7 +240,6 @@ class Plotting:
             ylim=ylim,
             scale_factor=scale_factor,
             marker_size=marker_size,
-            latex=latex,
             cmap=cmap,
             grounding_line=grounding_line,
             basins=basins,
@@ -247,22 +258,24 @@ class Plotting:
                 plt.close()
 
     def _base_plot(
-        self,
-        metadata: Union[None, Dict, 'MetadataResult'] = None,
-        downscale_factor: Optional[int] = None,
-        title: Optional[str] = None,
-        xlim: tuple = (None, None),
-        ylim: tuple = (None, None),
-        scale_factor: float = 1.0,
-        marker_size: Optional[float] = 0.1,
-        latex: bool = False,
-        save: Optional[str] = None,
-        color_by: str = 'dataset',  # 'dataset', 'flight_id', 'depth', 'density'
-        cmap: Optional['LinearSegmentedColormap'] = None,
-        grounding_line: Optional[bool] = True,
-        basins: Optional[bool] = True,
-        stations: Optional[bool] = True,
-        ncol: Optional[int] = None,
+            self,
+            metadata: Union[None, Dict, 'MetadataResult'] = None,
+            elevation: Optional[bool] = False,
+            downscale_factor: Optional[int] = None,
+            title: Optional[str] = None,
+            xlim: Optional[tuple] = (None, None),
+            ylim: Optional[tuple] = (None, None),
+            vmin: Optional[float] = None,
+            vmax: Optional[float] = None,
+            scale_factor: float = 1.0,
+            marker_size: Optional[float] = 0.1,
+            save: Optional[str] = None,
+            color_by: str = 'dataset',  # 'dataset', 'flight_id', 'depth', 'density'
+            cmap: Optional['LinearSegmentedColormap'] = None,
+            grounding_line: Optional[bool] = True,
+            basins: Optional[bool] = True,
+            stations: Optional[bool] = True,
+            ncol: Optional[int] = None,
     ) -> None:
         # --- Setup ---
         if metadata is None:
@@ -274,11 +287,6 @@ 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 not self._pre_plot_check(metadata):
             return
 
@@ -292,7 +300,7 @@ class Plotting:
         if basins:
             grounding_line = False
         # --- Plot Grounding Line ---
-        if True and color_by != 'transect': # FIXME
+        if True and color_by != 'transect_1D': # FIXME
             gl = pd.read_pickle(self._gl_path)
             ax.plot(gl.x/1000, gl.y/1000, linewidth=1, color='k')
 
@@ -302,8 +310,6 @@ class Plotting:
         values = None
         label = None
         extend = None
-        vmin = 0
-        vmax = 10
 
         if color_by == 'dataset':
             if not title:
@@ -325,7 +331,7 @@ 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 +369,7 @@ 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 +404,7 @@ 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)
 
@@ -442,43 +448,42 @@ class Plotting:
                     if cmap == None:
                         cmap = cmaps.bukavu
                     extend = 'both'
-                    vmin = -1000
-                    vmax = 1000
+                    if not vmin: vmin = -1000
+                    if not vmax: vmax = 1000
                     if not title:
                         title = f'AntADatabase Bed Elevation'
                 elif var == 'ICE_THK':
                     if cmap == None:
                         cmap = cmaps.torch_r
                     extend = 'max'
-                    vmin = 0
-                    vmax = 4000
+                    if not vmin: vmin = 0
+                    if not vmax: vmax = 4000
                     if not title:
                         title = f'AntADatabase Ice Thickness'
                 elif var == 'SURF_ELEV':
                     if cmap == None:
                         cmap = cmaps.torch_r
                     extend = 'max'
-                    vmin = 2000
-                    vmax = 4000
+                    if not vmin: vmin = 2000
+                    if not vmax: vmax = 4000
                     if not title:
                         title = f'AntADatabase Surface Elevation'
                 elif var == 'BASAL_UNIT':
                     if cmap == None:
                         cmap = cmaps.torch_r
                     extend = 'both'
-                    vmin = 2000
-                    vmax = 4000
+                    if not vmin: vmin = 2000
+                    if not vmax: vmax = 400
                     if not title:
                         title = f'AntADatabase Basal Unit'
                 scatter = plt.scatter(df['PSX']/1000, df['PSY']/1000, c=df[var], cmap=cmap, s=marker_size, vmin=vmin, vmax=vmax, linewidths=0, rasterized=True)
 
             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'
-                    vmin = None
-                    vmax = None
                     age = list(metadata['age'])
                     if not title:
                         title = f'AntADatabase IRH Depth'
@@ -492,8 +497,6 @@ class Plotting:
                     if cmap == None:
                         cmap = cmaps.torch_r
                     extend = 'both'
-                    vmin = None
-                    vmax = None
                     age = list(metadata['age'])
                     if len(age) > 1:
                         print('WARNING: Multiple layers provided: ', age,
@@ -507,7 +510,7 @@ class Plotting:
                 for age in metadata['age']:
                     scatter = plt.scatter(df['PSX']/1000, df['PSY']/1000, c=df[int(age)], cmap=cmap, s=marker_size, vmin=vmin, vmax=vmax, linewidths=0, rasterized=True)
 
-        if color_by == 'transect':
+        if color_by == 'transect_1D':
             flight_id = list(metadata['flight_id'])
             if len(flight_id) > 1:
                 flight_id = flight_id[0]
@@ -518,7 +521,7 @@ class Plotting:
 
             metadata_impl = self._db.query(flight_id=flight_id, dataset=metadata['dataset'], retain_query=False)
             if not title:
-                title = f'Transect {metadata['flight_id'][0]} from {metadata['reference'][0]}'
+                title = f'Transect {metadata_impl['flight_id'][0]} from {metadata_impl['reference'][0]}'
 
             f = self._db._get_file_paths_from_metadata(metadata_impl)[0]
             full_path = os.path.join(self._db._db_dir, f)
@@ -529,15 +532,49 @@ class Plotting:
                 print('Distance not in varibles, cannot plot along transect')
                 return
 
+            if elevation:
+                if 'SURF_ELEV' in ds.variables:
+                    ds['IRH_DEPTH'] = ds.SURF_ELEV - ds.IRH_DEPTH
+
+                elif 'ICE_THK' in ds.variables and 'BED_ELEV' in ds.variables:
+                    ds['SURF_ELEV'] = (ds.ICE_THK + ds.BED_ELEV) - ds.IRH_DEPTH
+                    ds['IRH_DEPTH'] = ds.SURF_ELEV - ds.IRH_DEPTH
+                else:
+                    print('Cannot plot IRH Elevation from the variables in the file, missing either ICE_THK and BED_ELEV or SURF_ELEV')
+                    return
+
             cmap = self._custom_cmap_density()
-            colors = [cmap(i) for i in np.linspace(0.1, 0.9, ds.sizes['IRH_AGE'])]
-            for age, color in zip(ds.IRH_AGE, colors):
+            colors = [cmap(i) for i in np.linspace(0.1, 0.9, len(metadata_impl['age']))]
+            for age, color in zip(list(map(int, metadata['age'])), colors):
+                if age not in ds.IRH_AGE:
+                    print(f'{metadata_impl['flight_id'][0]} does not contain age {age}, skipping')
+                    continue
+
                 ax.scatter(ds.Distance/1000, ds.IRH_DEPTH.sel(IRH_AGE=age),
-                           color=color, s=marker_size, linewidths=0.1)
-                plt.plot([], [], color=color, label=age.values, linewidth=3)
-                # ds.IRH_DEPTH.sel(IRH_AGE=age).where(~np.isnan(ds.IRH_DEPTH.sel(IRH_AGE=age)), drop=True).plot()
-            scatter = ax.scatter(ds.Distance/1000, ds.ICE_THK, color='k', s=marker_size, linewidths=0.1)
-            plt.plot([], [], color='k', label='Bed Depth', linewidth=3)
+                        color=color, s=marker_size, linewidths=0.1)
+                plt.plot([], [], color=color, label=age, linewidth=3)
+
+            if elevation:
+                if 'BED_ELEV' in ds.variables:
+                    scatter = ax.scatter(ds.Distance/1000, ds.BED_ELEV, color='k', s=marker_size, linewidths=0.1)
+                    plt.plot([], [], color='k', label='Bed Elevation', linewidth=3)
+                elif 'ICE_THK' in ds.variables and 'SURF_ELEV' in ds.variables:
+                    ds['BED_ELEV'] = ds.SURF_ELEV - ds.ICE_THK
+                    scatter = ax.scatter(ds.Distance/1000, ds.BED_ELEV, color='k', s=marker_size, linewidths=0.1)
+                    plt.plot([], [], color='k', label='Bed Elevation', linewidth=3)
+                else:
+                    print('Cannot plot Bed Elevation from the variables in the file')
+                ax.scatter(ds.Distance/1000, ds.SURF_ELEV, color='grey', s=marker_size, linewidths=0.1)
+                plt.plot([], [], color='grey', label='Surface Elevation', linewidth=3)
+
+            else:
+                scatter = ax.scatter(ds.Distance/1000, ds.ICE_THK, color='k', s=marker_size, linewidths=0.1)
+                plt.plot([], [], color='k', label='Bed Depth', linewidth=3)
+
+            if elevation:
+                ylim = (ds.BED_ELEV.min() - 200, ds.SURF_ELEV.max()+200) if ylim == (None, None) else ylim
+            else:
+                ylim = (ds.ICE_THK.max() + 200, 0) if ylim == (None, None) else ylim
 
             if ncol == None:
                 if ds.sizes['IRH_AGE'] > 7:
@@ -556,7 +593,7 @@ 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)
@@ -578,7 +615,7 @@ class Plotting:
 
         ax.set_xlim(*xlim)
         ax.set_ylim(*ylim)
-        if color_by != 'transect':
+        if color_by != 'transect_1D':
             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
@@ -606,30 +643,70 @@ class Plotting:
             cbar.ax.xaxis.set_ticks_position('bottom')
             if label:
                 cbar.set_label(label)
-        elif color_by == 'transect':
+        elif color_by == 'transect_1D':
             ax.legend(ncols=2)
-            ax.set_xlabel('Distance [km]')
-            ax.set_ylabel('Depth below surface [m]')
+            ax.set_xlabel('Distance along transect [km]')
+            if elevation:
+                ax.set_ylabel('Elevation above sea level [m]')
+            else:
+                ax.set_ylabel('Depth below surface [m]')
             plt.gcf().set_size_inches(10 * scale_factor, 10 * 2/3)
 
         plt.tight_layout()
 
         # --- 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']):
-                if x0 <= x <= x1 and y0 <= y <= y1:  # Only plot if within current view
-                    ax.text(x, y, sub, fontsize=12, color='k', ha='center',
-                            path_effects=[path_effects.withStroke(linewidth=5, foreground=(1,1,1,0.7))]
-                            )
+        if basins and color_by != 'transect_1D':
+            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':
+        if stations and color_by != 'transect_1D':
             site_coords = pd.read_pickle(self._site_coords_path)
             for i in site_coords.index:
                 site = site_coords.loc[i]

{anta_database-0.3.1 → anta_database-0.3.3}/anta_database.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anta_database
-Version: 0.3.1
+Version: 0.3.3
 Summary: SQLite database for the AntArchitecture Community Data
 Author: Antoine Hermant
 Author-email: antoine.hermant@etik.com
@@ -27,6 +27,7 @@ Requires-Dist: scipy
 Requires-Dist: matplotlib
 Requires-Dist: colormaps
 Requires-Dist: tqdm
+Requires-Dist: pyshp
 Dynamic: license-file
 
 <h1 align="center">

{anta_database-0.3.1 → anta_database-0.3.3}/anta_database.egg-info/requires.txt

@@ -8,3 +8,4 @@ scipy
 matplotlib
 colormaps
 tqdm
+pyshp

{anta_database-0.3.1 → anta_database-0.3.3}/pyproject.toml

@@ -25,6 +25,7 @@ dependencies = [
   "matplotlib",
   "colormaps",
   "tqdm",
+  "pyshp",
 ]
 
 keywords = ["isochrones", "database", "IRH", "radar"]