anta-database 0.1__tar.gz → 0.1.2__tar.gz

{anta_database-0.1 → anta_database-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anta_database
-Version: 0.1
+Version: 0.1.2
 Summary: SQLite database for the AntArchitecture Community Data
 Home-page: https://github.com/antoinehermant/anta_database
 Author: Antoine Hermant
@@ -10,7 +10,7 @@ License-File: LICENSE
 Requires-Dist: pandas
 Requires-Dist: pyproj
 Requires-Dist: matplotlib
-Requires-Dist: seaborn
+Requires-Dist: colormaps
 Dynamic: author
 Dynamic: author-email
 Dynamic: home-page

{anta_database-0.1 → anta_database-0.1.2}/anta_database/database/database.py

@@ -4,7 +4,7 @@ import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
 from matplotlib.colors import LinearSegmentedColormap
-import seaborn as sns
+import colormaps as cmaps
 from typing import Union, List, Dict, Tuple
 
 class Database:
@@ -93,7 +93,42 @@ class Database:
         }
         return metadata
 
-    def query(self, age: Union[None, str, List[str]]=None, var: Union[None, str, List[str]]=None,author: Union[None, str, List[str]]=None, trace_id: Union[None, str, List[str]]=None) -> Dict:
+    def __repr__(self):
+        """Return a pretty-printed string representation of the metadata."""
+        md = self.md
+        output = []
+        output.append("Metadata from query:")
+
+        output.append("\n  - author:")
+        for author in md['author']:
+            output.append(f"    {author}")
+
+        output.append("\n  - age:")
+        ages = " ".join(md['age'])
+        output.append(f"    {ages}")
+
+        output.append("\n  - var:")
+        for var in md['var']:
+            output.append(f"    {var}")
+
+        output.append("\n  - trace_id:")
+        trace_ids = " ".join(md['trace_id'])
+        output.append(f"    {trace_ids}")
+
+        output.append("\n  - reference:")
+        for ref in md['reference']:
+            output.append(f"    {ref}")
+
+        output.append("\n  - DOIs:")
+        for doi in md['doi']:
+            output.append(f"    {doi}")
+
+        output.append(f"\n  - database: {md['database_path']}/{md['file_db']}")
+        output.append(f"  - query params: {md['_query_params']}")
+
+        return "\n".join(output)
+
+    def query(self, age: Union[None, str, List[str]]=None, var: Union[None, str, List[str]]=None,author: Union[None, str, List[str]]=None, trace_id: Union[None, str, List[str]]=None) -> 'MetadataResult':
         select_clause = 'a.name, a.citation, a.doi, d.age, d.var, d.trace_id'
         query, params = self._build_query_and_params(age, var, author, trace_id, select_clause)
 
@@ -134,7 +169,7 @@ class Database:
         metadata['trace_id'] = list(set(metadata['trace_id']))
 
         self.md = metadata
-        return metadata
+        return MetadataResult(metadata)
 
     def _get_file_paths_from_metadata(self, metadata) -> List:
         query_params = metadata.get('_query_params', {})
@@ -172,7 +207,7 @@ class Database:
             print('Please provide metadata of the files you want to generate the data from. Exiting ...')
             sys.exit()
 
-        query_params = md.get('_query_params', {})
+        query_params = md['_query_params']
         age = query_params.get('age')
         var = query_params.get('var')
         author = query_params.get('author')
@@ -208,14 +243,14 @@ class Database:
 
     def custom_cmap(self):
 
-        flare = plt.colormaps['magma_r']  # Sequential (yellow/orange/red)
-        crest = plt.colormaps['mako']  # Diverging (blue/white/red)
+        cm1 = cmaps.torch_r
+        cm2 = cmaps.deep_r
 
-        flare_colors = flare(np.linspace(0, 0.8, 256))  # Shape: (256, 4) RGBA
-        crest_colors = crest(np.linspace(0.2, 1, 256))  # Shape: (256, 4) RGBA
-        combined_colors = np.vstack((flare_colors, crest_colors))
+        cm1_colors = cm1(np.linspace(0.05, 0.8, 256))  # Shape: (256, 4) RGBA
+        cm2_colors = cm2(np.linspace(0.1, 1, 256))  # Shape: (256, 4) RGBA
+        combined_colors = np.vstack((cm1_colors, cm2_colors))
         custom_cmap = LinearSegmentedColormap.from_list(
-            'flare_crest',  # Name your colormap
+            'custom_cmap',  # Name your colormap
             combined_colors,
             N=512  # Double the resolution (256 + 256)
         )
@@ -286,3 +321,39 @@ class Database:
         else:
             plt.show()
             plt.close()
+
+class MetadataResult:
+    def __init__(self, metadata):
+        self._metadata = metadata
+
+    def __getitem__(self, key):
+        return self._metadata[key]
+
+    def __repr__(self):
+        """Pretty-print the metadata."""
+        md = self._metadata
+        output = []
+        output.append("Metadata from query:")
+        output.append(f"\n  - author:")
+        for author in md['author']:
+            output.append(f"    {author}")
+        output.append(f"\n  - age:")
+        output.append(f"    {' '.join(md['age'])}")
+        output.append(f"\n  - var:")
+        for var in md['var']:
+            output.append(f"    {var}")
+        output.append(f"\n  - trace_id:")
+        output.append(f"    {' '.join(md['trace_id'])}")
+        output.append(f"\n  - reference:")
+        for ref in md['reference']:
+            output.append(f"    {ref}")
+        output.append(f"\n  - DOIs:")
+        for doi in md['doi']:
+            output.append(f"    {doi}")
+        output.append(f"\n  - database: {md['database_path']}/{md['file_db']}")
+        output.append(f"  - query params: {md['_query_params']}")
+        return "\n".join(output)
+
+    def to_dict(self):
+        """Return the raw metadata dictionary."""
+        return self._metadata

{anta_database-0.1 → anta_database-0.1.2}/anta_database.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anta_database
-Version: 0.1
+Version: 0.1.2
 Summary: SQLite database for the AntArchitecture Community Data
 Home-page: https://github.com/antoinehermant/anta_database
 Author: Antoine Hermant
@@ -10,7 +10,7 @@ License-File: LICENSE
 Requires-Dist: pandas
 Requires-Dist: pyproj
 Requires-Dist: matplotlib
-Requires-Dist: seaborn
+Requires-Dist: colormaps
 Dynamic: author
 Dynamic: author-email
 Dynamic: home-page

{anta_database-0.1 → anta_database-0.1.2}/anta_database.egg-info/SOURCES.txt

@@ -1,5 +1,4 @@
 LICENSE
-README.md
 setup.py
 anta_database/__init__.py
 anta_database/anta_database.py

{anta_database-0.1 → anta_database-0.1.2}/anta_database.egg-info/requires.txt

@@ -1,4 +1,4 @@
 pandas
 pyproj
 matplotlib
-seaborn
+colormaps

{anta_database-0.1 → anta_database-0.1.2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='anta_database',
-    version="0.1",
+    version="0.1.2",
     author="Antoine Hermant",
     author_email= "antoine.hermant@etik.com",
     url="https://github.com/antoinehermant/anta_database",
@@ -17,6 +17,6 @@ setup(
         'pandas',
         'pyproj',
         'matplotlib',
-        'seaborn',
+        'colormaps',
     ]
 )

anta_database-0.1/README.md

@@ -1,240 +0,0 @@
-
-# Table of Contents
-
-1.  [SQLite Database](#org7c02cbe)
-    1.  [Datasets currently included:](#orge88c16b)
-2.  [Key Features](#orgda9a069)
-3.  [Installation](#org0ae2129)
-4.  [How to use with examples](#org94cd2fd)
-    1.  [Browsing Metadata](#org89a166a)
-    2.  [Visualization](#orgf9cf6be)
-    3.  [Generate Data](#org6e8f9a4)
-5.  [Advanced: Managing the database](#org213a1d3)
-    1.  [Reindexing](#orge03e052)
-    2.  [(Re)compile the database](#org841514e)
-6.  [Support and contact](#org87c7675)
-7.  [Contribution](#org2896907)
-8.  [Acknowledgments](#org7ea1cbb)
-
-This Python module provides an efficient SQLite database for browsing, visualizing and processing Internal Reflecting Horizons (isochrones) across Antarctica, curated by the AntArchitecture action group. It is specifically designed for ice dynamic modelers who need a fast, memory-efficient data structure to constrain their models.
-
-
-<a id="org7c02cbe"></a>
-
-# SQLite Database
-
-The database uses SQLite for efficient indexing. Data is sourced from the associated DOIs and stored as binary DataFrame files for each layer (IRH) and trace ID. This structure enables:
-
--   Browsing by author (region), layer age, or trace ID.
--   Memory efficiency: Only relevant data is read when needed.
--   Fast read performance: Lightweight and optimized for speed.
-
-
-<a id="orge88c16b"></a>
-
-## Datasets currently included:
-
--   Winter et al. 2018, (<https://doi.org/10.1594/PANGAEA.895528>)
--   Cavitte et al. 2020, (<https://doi.org/10.15784/601411>)
--   Beem et al. 2021, (<https://doi.org/10.15784/601437>)
--   Wang et al. 2023, (<https://doi.org/10.1594/PANGAEA.958462>)
--   Sanderson et al. 2024, (<https://doi.org/10.5285/cfafb639-991a-422f-9caa-7793c195d316>)
--   Franke et al. 2025, (<https://doi.org/10.1594/PANGAEA.973266>)
-
-
-<a id="orgda9a069"></a>
-
-# Key Features
-
--   Efficient SQLite indexing
--   Quick visualization on Antarctica map
--   Generate lazy data for later use
-
-
-<a id="org0ae2129"></a>
-
-# Installation
-
-1- Clone this repository:
-
-    git clone git@github:antoinehermant/anta_database.git
-    cd anta_database
-
-2- Create a specific python environment (optional but recommended):
-
-    '''Using conda'''
-    conda create -n anta_database
-    conda activate anta_database
-    conda install pip
-    
-    '''Using venv'''
-    python -m venv /path/to/environment/anta_database # Replace the path with your desired environment path
-    source /path/to/environment/anta_database
-
-3- Install the Python module:
-
-    pip install .
-
-Note: The database is not included in this repository. Contact me for access.
-
-
-<a id="org94cd2fd"></a>
-
-# How to use with examples
-
-Also see the Jupyter Notebook &rsquo;example.ipynb&rsquo; for a more integrated tutorial.
-
-
-<a id="org89a166a"></a>
-
-## Browsing Metadata
-
--   First, initialize the Database class:
-
-    from anta_database import Database
-    database = Database('/path/to/AntADatabase/') # insert the path of the downloaded database, absolute path is recommanded
-
-Then use the query() function to browse the database. query() without argument will return all metadata from the database:
-
-    database.query()
-
-By default, a dictionary with all available trace IDs is included in the query results. This can seem a lot, but it is actually useful for grepping traces with descriptive names such as &rsquo;DC<sub>LDC</sub><sub>DIVIDE</sub>&rsquo;.
-
--   Refine your search either by author, age, or trace<sub>id</sub>, or by combining arguments. Lists are also allowed:
-
-    database.query(author='Cavitte_2020') # all data from Cavitte et al. 2020
-    database.query(age='38100') # all datasets with the 38.1ka isochrone
-    database.query(var='IceThk') # all datasets with IceThk variable
-    database.query(trace_id='DC_LDC_DIVIDE') # all layers with the trace ID DC_LDC_DIVIDE
-    database.query(author=['Franke_2025', 'Winter_2018'], age='38100') # example of multiple criteria
-
-Note: &rsquo;IceThk&rsquo;, &rsquo;SurfElev&rsquo; and &rsquo;BedElev&rsquo; are possible extra variables included in the database when the datasets contain the relevant data.
-
-
-<a id="orgf9cf6be"></a>
-
-## Visualization
-
-Use the results of the query in the plotting functions:
-
-    results = database.query(age='38100')
-    database.plotXY(results,
-                    downscale_factor=1000, # downscale the datasets n times, which makes no visual difference but it is much lighter
-                    title='AntArchitecture 38.1ka layer',
-                    xlim=(-500, 2400), ylim=(-2200, 2200), # set the plot extent in km
-                    scale_factor=0.5, # adjust the size of the plot
-                    latex=True, # use latex compilers for plotting if you have them installed on your system
-                    # save='AntA_38ka.pdf', # Uncomment to save the figure, otherwise it we visualize with pyplot
-                    )
-
-![img](./anta_database/figures/AntA_38ka.png "Example figure")
-
-
-<a id="org6e8f9a4"></a>
-
-## Generate Data
-
-Note: This part could be developed further in the future if there is the need. But for now, I am designing a separate Python module for constraining my ice sheet model of use, which is tailored to this database and other parallel processing libraries.
-
-The data<sub>generator</sub>() function reads the query and &rsquo;yield&rsquo; the dataframes for later use.
-Here is a quick example of how this can be used for computing the mean layer depth:
-
-    results = database.query(age='38100')
-    lazy_dfs = database.data_generator(results)
-    
-    mean_depth_trs = []
-    for df, md in lazy_dfs:
-        mean_depth_trs.append(np.mean(df['38100']))
-    
-    mean_depth = np.mean(mean_depth_trs)
-    print('The mean depth of the 38ka isochrone across East Antarctica is', mean_depth, 'm')
-
-The downscale<sub>factor</sub> argument in the data<sub>generator</sub> reduces the size of the generated data by n times. This is useful when dealing with large data where the downscaling has a neglectable influence on the results:
-
-    lazy_dfs = database.data_generator(results, downscale_factor=10)
-
-Note: In the database, the file paths are relative to the database path. When initiating the database, you provide the absolute path to the database. So the data<sub>generator</sub> function uses the relative path given in the results from the query and the absolute path to the database to read the files. The second argument returned by data<sub>generator</sub> (&rsquo;md&rsquo; in the example above) is the unique metadata for the current df.
-
-
-<a id="org213a1d3"></a>
-
-# Advanced: Managing the database
-
-
-<a id="orge03e052"></a>
-
-## Reindexing
-
-You may want for example to update the age of the layers in a particular dataset.
-For this, you just need to modify the ages in the file called &rsquo;IRH<sub>ages.tab</sub>&rsquo; located under a dataset directory. Then, reindex with the IndexDatabase class:
-
-    from anta_database import IndexDatabase
-    
-    db_path = '/path/to/root/of/the/database/' # path to 'AntADatabase/'
-    indexing = IndexDatabase(db_path)
-    indexing.index_database()
-
-
-<a id="org841514e"></a>
-
-## (Re)compile the database
-
-You can (re)compile the database, if for example you modify some data in the raw directories or if you add a dataset.
-For this, make sure to follow the structure:
-
-    AntADatabase/
-    ├── AntADatabase.db
-    ├── database_index.csv #List of directories to index: Author_YYYY,Author et al. YYYY,doi
-    ├── Author_YYYY
-        ├── IRH_ages.tab #IRH file names without .ext followed by there respective age in years
-        ├── original_new_column_names.csv #first row: names of columns to keep from raw files, second row: how the columns should be renamed
-        ├── raw/
-        └── pkl/
-
-Then use the CompileDatabase class to compile the database.
-
-    from anta_database import CompileDatabase
-    
-    dir_path_list = [ # list of the dataset subdirectories to compile
-        './Winter_2018',
-        './Sanderson_2024',
-        './Franke_2025',
-        './Cavitte_2020',
-        './Beem_2021',
-    ]
-    
-    compiler = CompileDatabase(dir_path_list)
-    compiler.compile()
-
-Then reindex (see above).
-By default, it assumes that the files in raw/ are sorted by IRH (one file = one layer and multiple traces). If the files are sorted the other way around (one file = one trace and multiple layers), you can set file<sub>type</sub>=&rsquo;trace&rsquo; in CompileDatabase(). Furthermore, if the depth is not given in meters but TWT, you should set the wave<sub>speed</sub> (units should match values in the file) for conversion and firn<sub>correction</sub> (meters):
-
-    dir_path = './Wang_2023'
-    compiler = CompileDatabase(dir_path, file_type='trace', wave_speed=0.1685, firn_correction=15.5)
-    compiler.compile()
-
-
-<a id="org87c7675"></a>
-
-# Support and contact
-
-You can email me for downloading the database: antoine.hermant@unibe.ch
-
-Feel free to raise an issue on the GitHub if you find any bug or if you would like a feature added.
-
-
-<a id="org2896907"></a>
-
-# Contribution
-
-If you like this database and wish to help me develop this module, do not hesitate to contact me. You should then fork the repo, build feature branches and pull request. That would be much appreciated!
-
-
-<a id="org7ea1cbb"></a>
-
-# Acknowledgments
-
-I am developing this tool as part of my PhD project, which is funded by the Swiss National Science Foundation (grant no. 211542, Project CHARIBDIS)
-Any data used through this database should be cited at source. For this, use the DOI provided in the metadata.
-If you used this tool for your work and this was useful, please cite this repo, so other people get to know that it exists.
-