Merge pull request #187 from iomega/classes_in_sqlite

Classes in sqlite
iomega · May 18, 2023 · cc16f33 · cc16f33
2 parents 32ca7d5 + 662e3d2
commit cc16f33
Show file tree

Hide file tree

Showing 5 changed files with 26 additions and 19 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.0.1]
+Small bug fixes
+- Allow URLLiberror when loading in compound classes
+- Update readme with zenodo files
+
+
 ## [1.0.0]
 ### Added
 - Added compound classes to sqlite file

diff --git a/README.md b/README.md
@@ -69,8 +69,8 @@ ms2query --library .\folder_to_store_the_library --download --ionmode positive
 ```
 
 Alternatively all model files can be manually downloaded from 
-https://zenodo.org/record/7753249#.ZBmO_sLMJPY for positive mode and 
-https://zenodo.org/record/7753267#.ZBmPYsLMJPY for negative mode.
+https://zenodo.org/record/6124552 for positive mode and 
+https://zenodo.org/record/7104184 for negative mode.
 
 #### Preprocessing mass spectra
 MS2Query is run on all MS2 spectra in a spectrum file. 
@@ -126,7 +126,6 @@ Before running the script, replace the variables `ms2query_library_files_directo
 
 This script will first download files for a default MS2Query library.
 This default library is trained on the [GNPS library](https://gnps.ucsd.edu/) from 2021-15-12.
-Automatic downloading can take long, alternatively all model files can be manually downloaded from https://zenodo.org/record/7753249 for positive mode and https://zenodo.org/record/7753267 for negative mode. When manually downloading, store all these files in one directory and set ms2query_library_files_directory to this directory.
 
 After downloading, a **library search** and an **analog search** is performed on the query spectra in your directory (`ms2_spectra_directory`).
 The results generated by MS2Query, are stored as csv files in a results directory within the same directory as your query spectra.

diff --git a/ms2query/__version__.py b/ms2query/__version__.py
@@ -1 +1 @@
-__version__ = '1.0.0'
+__version__ = '1.0.1'
diff --git a/ms2query/create_new_library/add_classifire_classifications.py b/ms2query/create_new_library/add_classifire_classifications.py
@@ -1,5 +1,6 @@
 import json
 import urllib
+from http.client import InvalidURL
 from typing import List, Optional
 
 import pandas as pd
@@ -33,7 +34,7 @@ def do_url_request(url: str) -> [bytes, None]:
     try:
         with urllib.request.urlopen(url) as inf:
             result = inf.read()
-    except (urllib.error.HTTPError, urllib.error.URLError):
+    except (urllib.error.HTTPError, urllib.error.URLError, InvalidURL):
         # apparently the request failed
         result = None
     except ConnectionAbortedError:

diff --git a/tests/test_train_models.py b/tests/test_train_models.py
@@ -3,17 +3,18 @@
 from ms2query.create_new_library.train_models import clean_and_train_models
 from ms2query.ms2library import create_library_object_from_one_dir, MS2Library
 
-# @pytest.mark.integration
-# def test_train_all_models(path_to_general_test_files, tmp_path):
-#     path_to_test_spectra = os.path.join(path_to_general_test_files, "1000_test_spectra.pickle")
-#     models_folder = os.path.join(tmp_path, "models")
-#     clean_and_train_models(path_to_test_spectra,
-#                            "positive",
-#                            models_folder,
-#                            {"ms2ds_fraction_validation_spectra": 2,
-#                             "ms2ds_epochs": 2,
-#                             "spec2vec_iterations": 2,
-#                             "ms2query_fraction_for_making_pairs": 400}
-#                            )
-#     ms2library = create_library_object_from_one_dir(models_folder)
-#     assert isinstance(ms2library, MS2Library)
+
+@pytest.mark.integration
+def test_train_all_models(path_to_general_test_files, tmp_path):
+    path_to_test_spectra = os.path.join(path_to_general_test_files, "1000_test_spectra.pickle")
+    models_folder = os.path.join(tmp_path, "models")
+    clean_and_train_models(path_to_test_spectra,
+                           "positive",
+                           models_folder,
+                           {"ms2ds_fraction_validation_spectra": 2,
+                            "ms2ds_epochs": 2,
+                            "spec2vec_iterations": 2,
+                            "ms2query_fraction_for_making_pairs": 400}
+                           )
+    ms2library = create_library_object_from_one_dir(models_folder)
+    assert isinstance(ms2library, MS2Library)