XspecT 0.2.5__py3-none-any.whl → 0.2.7__py3-none-any.whl

xspect-0.2.7.dist-info/RECORD

@@ -0,0 +1,33 @@
+xspect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+xspect/definitions.py,sha256=Z6RiCOQnsA_i8DPIq-7SUhrKo7KYf1Azp36UZZpcOX4,1419
+xspect/download_models.py,sha256=lml8pSyM0pF-MxghgSRC9noDT4pkUcBZraaTTImVfbA,739
+xspect/fastapi.py,sha256=FDiGXJmLEeTLD83Hem8yV5aoPJ-GhSG5WmDIQRAA_w4,3257
+xspect/file_io.py,sha256=zKhl6Fd9KZAYiD8YgIyje5TbDYk5lxMp1WUrNkGSBo8,2779
+xspect/main.py,sha256=3HqmnMowjkLNwhaZWtY4aeJCyCyT6h_nZWzYIunHfKg,5325
+xspect/model_management.py,sha256=xF-wjVNJbXYv64RajsIcpLfZUvicDyalJEdSeCx3nQI,3542
+xspect/pipeline.py,sha256=kgxClqnm-5BaZ8BlcCYDCKhBpavt5vIONs8aBdEnjuE,7217
+xspect/run.py,sha256=pastcT-IFNLkWQvl0BL-h1mPheDK8mrHH-UytZWbyUI,1187
+xspect/train.py,sha256=wVGhirXyFK5yPWd24Ai35z7iRGiYyO6QR94xZgoWJ6I,9300
+xspect/mlst_feature/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+xspect/mlst_feature/mlst_helper.py,sha256=cPl-8ZASEef4ElF1dqYFjdmpoeLMOU_lvx-yBEqYlss,5914
+xspect/mlst_feature/pub_mlst_handler.py,sha256=oss3CkJNt6041p3qnMdOfoX8ZgUfpB93CUim-Yakc9A,5031
+xspect/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+xspect/models/probabilistic_filter_mlst_model.py,sha256=JMc0yBJPo7J9b-GpvhDmzhwWPIKOwatAq0edDgM72PE,11735
+xspect/models/probabilistic_filter_model.py,sha256=zCn5dcuq5Z4pvmsV9igS0lQ1plUi9-Kky_zRflfrIkI,9659
+xspect/models/probabilistic_filter_svm_model.py,sha256=uabDrF1_CSuIWf9wWyQAkqjAuRUBzEZLkv3J6YHfJsM,5641
+xspect/models/probabilistic_single_filter_model.py,sha256=TdGbQp8ylOif7dD13OSWaS-zFNJo8mXOb6BaQ0mcPdo,3810
+xspect/models/result.py,sha256=_pvWERp-9SHsftyhVnbe05jfOOE6GdENr6_9t-prR-M,4832
+xspect/train_filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+xspect/train_filter/create_svm.py,sha256=w6gq40yHINVfNzLhJfYFykUaNCwpU9AEDcbkUfis3DY,1504
+xspect/train_filter/extract_and_concatenate.py,sha256=g6iUTlZYoemddHdXzxL-Hq8AtE3va6bFaSBxiKd2gHE,4838
+xspect/train_filter/ncbi_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+xspect/train_filter/ncbi_api/download_assemblies.py,sha256=PTXs22T_fH-_skAemzCfD1uS26qJ3Huw3MdqDciu0v8,1285
+xspect/train_filter/ncbi_api/ncbi_assembly_metadata.py,sha256=_G5oo281WyLQspI-hYzeWcizK0DKRLiDiL0u9l53NAo,3843
+xspect/train_filter/ncbi_api/ncbi_children_tree.py,sha256=Tbiu740BTvXvRPBslPp9fSTL3pA3UolMKwrIrNtW8fc,1819
+xspect/train_filter/ncbi_api/ncbi_taxon_metadata.py,sha256=y0a2RnXsXiIBleMpCM-mYnQSjtsxJ4cjhIXl-Xr5oLA,1866
+xspect-0.2.7.dist-info/LICENSE,sha256=bhBGDKIRUVwYIHGOGO5hshzuVHyqFJajvSOA3XXOLKI,1094
+xspect-0.2.7.dist-info/METADATA,sha256=mzC1AwcjQzSJl1N0bf1uJWjZEhi4cKI9hI8ye7hIf7Y,4714
+xspect-0.2.7.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
+xspect-0.2.7.dist-info/entry_points.txt,sha256=L7qliX3pIuwupQxpuOSsrBJCSHYPOPNEzH8KZKQGGUw,43
+xspect-0.2.7.dist-info/top_level.txt,sha256=hdoa4cnBv6OVzpyhMmyxpJxEydH5n2lDciy8urc1paE,7
+xspect-0.2.7.dist-info/RECORD,,

{XspecT-0.2.5.dist-info → xspect-0.2.7.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (74.1.2)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

XspecT-0.2.5.dist-info/RECORD

@@ -1,30 +0,0 @@
-xspect/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/definitions.py,sha256=gg6NvT8ypNzlnJvMMo3nHsyh8DHFFu41lOfnILkRDpE,1215
-xspect/download_filters.py,sha256=ByE7Oggx-AyJ02Wirk_wcJHNdRDrJMfjwhmUe5tgWbE,741
-xspect/fastapi.py,sha256=C8pBBiqM6UdedLZgzfL_YYRuy98aPj8dcw_CLFrtMMc,3260
-xspect/file_io.py,sha256=zKhl6Fd9KZAYiD8YgIyje5TbDYk5lxMp1WUrNkGSBo8,2779
-xspect/main.py,sha256=eOA9PAeq3VvPWWoOZxXFErvPNW-ANzOxqMsbQJPCvDw,3651
-xspect/model_management.py,sha256=w0aqjLUoixCokyKTYrcN1vih5IoLYLJG9p8aeYdVc8Y,3560
-xspect/pipeline.py,sha256=h7duhVZ-hupwO_KQPstzFo8KMfMI2yleb9HmtTiMjic,7219
-xspect/run.py,sha256=OJ7pCFqva3AhIYklKjVnqWGooVRO7S3b56kIAy-xabY,1189
-xspect/train.py,sha256=khC1lldqfr4NvzLUiSJjSlh7DBG1ePielvQMiB29Hl8,10399
-xspect/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/models/probabilistic_filter_model.py,sha256=ImyNRzR7jf2CBPGI65ItG0_eYmrQjo9soQYlsM0r-P0,9829
-xspect/models/probabilistic_filter_svm_model.py,sha256=Z_aAigE_fC_gm80hRfxvROHGs6LuBqZnATHPpAkQGQE,5466
-xspect/models/probabilistic_single_filter_model.py,sha256=nDAd_-_Ci2eH0KOJtf4wA-w63FMq9rGSR1LGiIA-gdw,3884
-xspect/models/result.py,sha256=vHUEFXvbFyB8WmasXp99IrztjwaxH1f9QMFiRUPe40Q,4824
-xspect/train_filter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/train_filter/create_svm.py,sha256=w6gq40yHINVfNzLhJfYFykUaNCwpU9AEDcbkUfis3DY,1504
-xspect/train_filter/extract_and_concatenate.py,sha256=lLrczGgfZi2vAGqxq8fcEmJi5pvqyK33JkB_ZoCNYG8,4840
-xspect/train_filter/html_scrap.py,sha256=76VV_ZbvD2I3IxRb62SiQwRPu2tr4fwn1HkfJQYaosM,3809
-xspect/train_filter/ncbi_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-xspect/train_filter/ncbi_api/download_assemblies.py,sha256=MB_mxSjCTL05DqIt1WQem8AGU3PjtJnzPndeI9J-AOI,1285
-xspect/train_filter/ncbi_api/ncbi_assembly_metadata.py,sha256=puzDIws-yyBAEHwSAIYUM7g8FpLFmvOKh5xH1EsY8ZE,3830
-xspect/train_filter/ncbi_api/ncbi_children_tree.py,sha256=_8puOsnsKp5lsMV2gZY1ijkfD_BZKG9eXZCX09qph5E,1819
-xspect/train_filter/ncbi_api/ncbi_taxon_metadata.py,sha256=O6JDXC4E6AYaf7NPnb34eSJyZhMB8r--bjoVF_ZsEdA,1868
-XspecT-0.2.5.dist-info/LICENSE,sha256=bhBGDKIRUVwYIHGOGO5hshzuVHyqFJajvSOA3XXOLKI,1094
-XspecT-0.2.5.dist-info/METADATA,sha256=NDw2i1MawAjAkybDXzaQfIIGFI4sw86MSlQJ8z6vkWs,4834
-XspecT-0.2.5.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-XspecT-0.2.5.dist-info/entry_points.txt,sha256=L7qliX3pIuwupQxpuOSsrBJCSHYPOPNEzH8KZKQGGUw,43
-XspecT-0.2.5.dist-info/top_level.txt,sha256=hdoa4cnBv6OVzpyhMmyxpJxEydH5n2lDciy8urc1paE,7
-XspecT-0.2.5.dist-info/RECORD,,

xspect/train_filter/html_scrap.py

@@ -1,114 +0,0 @@
-""" HTML Scraping for the taxonomy check results from NCBI."""
-
-__author__ = "Berger, Phillip"
-
-import datetime
-import pickle
-import sys
-import time
-import requests
-from loguru import logger
-from xspect.definitions import get_xspect_root_path
-
-
-class TaxonomyCheck:
-    """Class to get the GCFs that passed the taxonomy check from NCBI."""
-
-    _main_url = "https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/ANI_report_prokaryotes.txt"
-    _test_url = "https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/"
-    _main_path = get_xspect_root_path() / "taxonomy_check.txt"
-    _test_path = get_xspect_root_path() / "tax_check_date.txt"
-    _new_time: list
-    _tax_check_ok = []
-
-    def __init__(self):
-        old_time = self._get_old_tax_date()
-        self._new_time = self._get_new_tax_date()
-        # Both Dates could be found.
-        # Check if the html file was updated since the last time it was downloaded.
-        # If yes than update the file.
-        if self._new_time and old_time:
-            if self._new_time == old_time:
-                logger.info("File was not updated")
-                self._get_old_file()
-            else:
-                logger.info("Updating file")
-                self._update_tax_check()
-
-        # The old date does not exist.
-        # Get the html file for the taxonomy check results.
-        elif self._new_time and not old_time:
-            logger.info("No file was found. Creating new file")
-            self._update_tax_check()
-
-        elif not self._new_time and old_time:
-            self._get_old_file()
-
-        else:
-            logger.error("Nothing was found")
-            logger.error("Aborting")
-            sys.exit()
-
-    def _get_old_tax_date(self):
-        try:
-            with open(self._test_path, "rb") as f:
-                old_time = pickle.load(f)
-                return old_time
-        except FileNotFoundError:
-            return None
-
-    def _get_new_tax_date(self):
-        raw_response = requests.get(self._test_url, timeout=5)
-        data = raw_response.text.split("\n")
-        for line in data:
-            if "ANI_report_prokaryotes.txt" in line:
-                line_parts = line.split()
-                date_parts = line_parts[-3].split("-")
-                date = datetime.date(
-                    int(date_parts[0]), int(date_parts[1]), int(date_parts[2])
-                )
-                time_parts = line_parts[-2].split(":")
-                combined_time = datetime.time(int(time_parts[0]), int(time_parts[1]))
-                new_time = [date, combined_time]
-
-                return new_time
-
-        return None
-
-    def _update_tax_check(self):
-        raw_response = requests.get(self._main_url, timeout=5)
-        all_tax_checks = raw_response.text.split("\n")[1:-1]
-        self._get_gcf_ok(all_tax_checks)
-        self._save_time()
-        self._save_file()
-
-    def _get_gcf_ok(self, all_tax_checks: list):
-        tax_check_ok = []
-        for line in all_tax_checks:
-            line_parts = line.split("\t")
-            gcf = line_parts[1]
-            tax_check_status = line_parts[-1]
-            if tax_check_status == "OK":
-                tax_check_ok.append(gcf)
-
-        self._tax_check_ok = tax_check_ok
-
-    def _save_time(self):
-        with open(self._test_path, "wb") as f:
-            pickle.dump(self._new_time, f)
-
-    def _save_file(self):
-        with open(self._main_path, "wb") as f:
-            pickle.dump(self._tax_check_ok, f)
-
-    def _get_old_file(self):
-        with open(self._main_path, "rb") as f:
-            self._tax_check_ok = pickle.load(f)
-
-    @staticmethod
-    def _get_current_time():
-        return time.asctime(time.localtime()).split()[3]
-
-    def ani_gcf(self):
-        """Returns ANI GCFs that passed the taxonomy check."""
-        return self._tax_check_ok