How to use dump_nodes method in ATX

Best Python code snippet using ATX

summarize_dmp_files.py

Source:summarize_dmp_files.py

1#!/usr/bin/env python2import pandas as pd3import sys4import os5import gc6def build_lineage(taxid_list, mapping):7    """Given a list of taxIDs, generate a NCBI LineageEx-like list."""8    temp_list = []9    for taxid in taxid_list:10        temp_dict = {}11        if taxid == "":12            pass13        else:14            temp_dict["TaxId"] = taxid15            if taxid in mapping.keys():16                temp_dict["Rank"] = mapping[taxid]17            else:18                temp_dict["Rank"] = "NA"19        temp_list.append(temp_dict)20    return temp_list21NCBI_dmp_dir_path = sys.argv[1]22assembly_gb_path = os.path.join(NCBI_dmp_dir_path, "assembly_summary_genbank.txt")23assembly_rs_path = os.path.join(NCBI_dmp_dir_path, "assembly_summary_refseq.txt")24dump_names_path = os.path.join(NCBI_dmp_dir_path, "names.dmp")25dump_nodes_path = os.path.join(NCBI_dmp_dir_path, "nodes.dmp")26dump_taxidlineage_path = os.path.join(NCBI_dmp_dir_path, "taxidlineage.dmp")27assembly_to_taxID_out_path = os.path.join(NCBI_dmp_dir_path, "assembly_to_taxID.pkl")28taxid_to_lineage_out_path = os.path.join(NCBI_dmp_dir_path, "taxid_to_lineage.pkl")29print("Combining genome assembly records from both GenBank and RefSeq sources...")30assembly_gb = pd.read_csv(assembly_gb_path, sep = "\t", skiprows = [0], low_memory = False)31assembly_rs = pd.read_csv(assembly_rs_path, sep = "\t", skiprows = [0], low_memory = False)32assembly_gb_filtered = assembly_gb[["# assembly_accession", "taxid"]]33assembly_rs_filtered = assembly_rs[["# assembly_accession", "taxid"]]34combined_df = pd.concat([assembly_gb_filtered, assembly_rs_filtered], ignore_index=True)35combined_df = combined_df.rename(columns = {"# assembly_accession": "Accession", "taxid": "taxID"})36combined_df =  combined_df.astype({"Accession": "str", "taxID": "str"})37del assembly_gb, assembly_rs, assembly_gb_filtered, assembly_rs_filtered38gc.collect()39combined_df.to_pickle(assembly_to_taxID_out_path, protocol = 4)40print("File output completed!")41print("Retrieving scientific names for different taxIDs...")42dump_names = pd.read_csv(dump_names_path, sep = "\t\|\t", header = None, engine = "python")43dump_names.iloc[:, 0] = dump_names.iloc[:, 0].astype("str")44dump_names.iloc[:, 3] = dump_names.iloc[:, 3].str.rstrip("\t\|")45dump_names_sci = dump_names[dump_names.iloc[:, 3]=="scientific name"].iloc[:, [0, 1]]46dump_names_final = dump_names_sci.rename(columns = {0: "taxID", 1: "Scientific_Name"}).reset_index(drop = True)47del dump_names, dump_names_sci48gc.collect()49print("Retrieving taxonomic ranks for different taxIDs...")50dump_nodes = pd.read_csv(dump_nodes_path, sep = "\t\|\t", header = None, engine = "python")51dump_nodes.iloc[:, 0] = dump_nodes.iloc[:, 0].astype("str")52dump_nodes_final = dump_nodes.iloc[:, [0, 2]].rename(columns = {0: "taxID", 2: "Rank"})53taxid_to_rank_dict = dict(zip(dump_nodes_final.loc[:, "taxID"], dump_nodes_final.loc[:, "Rank"]))54del dump_nodes55gc.collect()56print("Retrieving complete taxonomic lineage information for different taxIDs...")57dump_taxidlineage = pd.read_csv(dump_taxidlineage_path, sep = "\t\|\t", header = None, engine = "python")58dump_taxidlineage.iloc[:, 0] = dump_taxidlineage.iloc[:, 0].astype("str")59dump_taxidlineage.iloc[:, 1] = dump_taxidlineage.iloc[:, 1].str.rstrip(" \t\|")60dump_taxidlineage["lineage_list"] = dump_taxidlineage.iloc[:, 1].str.split(" ")61dump_taxidlineage = dump_taxidlineage.rename(columns = {0: "taxID"})62dump_taxidlineage["Lineage"] = dump_taxidlineage["lineage_list"].apply(build_lineage, args = (taxid_to_rank_dict,))63dump_taxidlineage_final = dump_taxidlineage.loc[:, ["taxID", "Lineage"]]64del dump_taxidlineage65gc.collect()66print("Retrieving information for merged taxIDs...")67dump_merged_path = os.path.join(NCBI_dmp_dir_path, "merged.dmp")68dump_merged = pd.read_csv(dump_merged_path, sep = "\t\|\t", header = None, engine = "python")69dump_merged.iloc[:, 0] = dump_merged.iloc[:, 0].astype("str")70dump_merged.iloc[:, 1] = dump_merged.iloc[:, 1].str.rstrip("\t\|")71dump_merged = dump_merged.rename(columns = {0: "previous", 1: "current"})72print("Combining all gathered infomation...")73comp_summary = pd.DataFrame({"taxID": dump_names_final["taxID"],74                             "Scientific_Name": dump_names_final["Scientific_Name"]})75comp_summary = comp_summary.merge(dump_nodes_final, how = "inner", left_on = "taxID", right_on = "taxID")76comp_summary = comp_summary.merge(dump_taxidlineage_final, how = "inner", left_on = "taxID", right_on = "taxID")77comp_summary = comp_summary.astype({"taxID": "str", "Scientific_Name": "str", "Rank": "str"})78comp_summary["CurrentID"] = comp_summary["taxID"]79temp_cond_main = comp_summary["taxID"].isin(dump_merged["previous"])80temp_cond_merged = dump_merged["previous"].isin(comp_summary["taxID"])81temp_ind_main = comp_summary.index[temp_cond_main]82temp_ind_merged = dump_merged.index[temp_cond_merged]83comp_summary.loc[temp_ind_main, "CurrentID"] = dump_merged.loc[temp_ind_merged, "current"]84comp_summary.to_pickle(taxid_to_lineage_out_path, protocol = 4)...

94_tree_middle_travel.py

Source:94_tree_middle_travel.py

1# ç»å®ä¸ä¸ªäºåæ ï¼è¿åå®çä¸åº éåã2#3# ç¤ºä¾:4#5# è¾å¥: [1,null,2,3]6#    17#     \8#      29#     /10#    311#12# è¾åº: [1,3,2]13class BinaryTreeNode(object):14    def __init__(self, val='', left=None, right=None):15        self.val = val16        self.left = left17        self.right = right18class BTree(object):19    def __init__(self):20        self.root = None21        self.dump_nodes=[]22    def create_binary_tree(self, root, lst, i):23        if i < len(lst):24            if lst[i] == None:25                return None26            root = BinaryTreeNode(lst[i])27            root.left = self.create_binary_tree(root, lst, i*2 + 1)28            root.right = self.create_binary_tree(root, lst, i*2 + 2)29            return root30        return None31    def build_binary_tree(self, lst):32        nodes = [None if v is None else BinaryTreeNode(v) for v in lst]33        for index in range(1,len(nodes)):34            node = nodes[index]35            if node is not None:36                parent_index = (index-1)//237                parent_node = nodes[parent_index]38                if index % 2:39                    parent_node.left = node40                else:41                    parent_node.right = node42        return nodes[0] if nodes else None43    def add_node(self, data):44        if data == '#':45            node = '#'46        else:47            node = BinaryTreeNode(data)48        if self.root is None:49            self.root = node50            return51        tmp_queue = [self.root]52        while True:53            current_node = tmp_queue.pop(0)54            if current_node is None:55                return56            if current_node.left is None:57                current_node.left = node58                return59            elif current_node.right is None:60                current_node.right = node61                return62            tmp_queue.append(current_node.left)63            tmp_queue.append(current_node.right)64    def inorder(self, node):65        if node is None:66            return67        if node.left is not None:68            self.inorder(node.left)69        self.dump_nodes.append(node.val)70        if node.right is not None:71            self.inorder(node.right)72    def front_travel(self, node):73        if node == None:74            return75        if node.left != None:76            self.middle_travel(node.left)77        self.dump_nodes.append(node.val)78        if node.right != None:79            self.middle_travel(node.right)80    def front_travel(self, node):81        if node == None:82            return83        if node.left != None:84            self.middle_travel(node.left)85        if node.right != None:86            self.middle_travel(node.right)87        self.dump_nodes.append(node.val)88if __name__=="__main__":89    t = BTree()90    lst = [1, 2,3,None,4]91    print('lst=',lst)92    #import pdb; pdb.set_trace()93    t.root = t.build_binary_tree(lst)94    t.inorder(t.root)...

parser.py

Source:parser.py

1import ipaddress2from pyrser import grammar, meta3from pyrser.directives import ignore4from pyrser.hooks import dump_nodes5from pyrser.hooks.echo import echo_nodes6from pyrser.passes import to_yml7text = """810.100.0.19"""10class Bind(grammar.Grammar):11    entry = "zone"12    grammar="""13        zone = [ [ipv4 | octet]:>_ eof? #dump_nodes]14        ipv4 = [ [octet '.' octet '.' octet '.' octet]:ipv4 #is_ipv4(_, ipv4) ]15        octet = [ 16            [ '2' [ '0'..'5' ] [ '0'..'5' ] |17              '1' [ '0'..'9' ] [ '0'..'9' ] |18              [ '1'..'9' ] [ '0'..'9' ] |19              [ '0'..'9' ]20            ]: octet #is_int(_, octet)21            #dump_nodes22        ]23    """24    25@meta.hook(Bind)26def is_int(self, ast, octet):27    ast.node = int(self.value(octet))28    return True29@meta.hook(Bind)30def is_ipv4(self, ast, ipv4):31    print(f"{ipv4.node=}")32    ast.node = ipaddress.IPv4Address(self.value(ipv4))33    return True34if __name__ == "__main__":35    bind = Bind()...

Automation Testing Tutorials

Learn to execute automation testing from scratch with LambdaTest Learning Hub. Right from setting up the prerequisites to run your first automation test, to following best practices and diving deeper into advanced test scenarios. LambdaTest Learning Hubs compile a list of step-by-step guides to help you be proficient with different test automation frameworks i.e. Selenium, Cypress, TestNG etc.