generate_report

docs/tools.rst

@@ -179,7 +179,7 @@ The absolute expression format aims to visualize absolute expression (AE) result
 iBAQ values and store the AE results of each protein on each sample.
 
 - If you have generated project.json, you can use this parameter ``--project_file`` to add project information for AE files.
-- IF you want to know ibaq, please read `ibaqpy <https://github.com/bigbio/ibaqpy>`__
+- If you want to know ibaq, please read `ibaqpy <https://github.com/bigbio/ibaqpy>`__
 - If you want to know more, please read :doc:`ae`.
 
 Example: 
@@ -338,6 +338,21 @@ Example:
       --parquet_path_two res_lfq2_no_cache.parquet
       --report_path report.txt
 
+Generate report about files 
+-----------------------------
+This tool is used to generate report about all feature files or psm files.
+You can build ``psm parquet`` or ``feature parquet`` multiple times for the same project and use this command to verify its consistency.
+
+- ``--label`` contains two options: ``psm`` and ``feature`
+
+Example: 
+
+.. code:: python
+
+   python generate_report_command.py generate_report_about_files
+      --check_dir file_path
+      --label psm
+
 Register file 
 --------------------------
 This tool is used to register the file to ``project.json``.

python/quantmsio/quantms_io/commands/generate_report_command.py

@@ -0,0 +1,32 @@
+import click
+
+from quantms_io.core.tools import generate_report_of_psms_or_features
+CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
+
+
+@click.group(context_settings=CONTEXT_SETTINGS)
+def cli():
+    """
+    This is the main tool that gives access to all commands.
+    """
+
+@click.command(
+    "generate_report_about_files",
+    short_help="generateb report of psm or feature files " "format",
+)
+@click.option(
+    "--check_dir", help="Folder to generate the df expression file.", required=True
+)
+@click.option('--label', type=click.Choice(['feature', 'psm'], case_sensitive=False),help='parquet type')
+@click.pass_context
+def generate_report_about_files(ctx, check_dir: str, label: str):
+    '''
+    ckeck_dir: psm or feature file file directory
+    label: psm or feature
+    '''
+    generate_report_of_psms_or_features(check_dir=check_dir,label=label)
+
+cli.add_command(generate_report_about_files)
+
+if __name__ == '__main__':
+    cli()

python/quantmsio/quantms_io/core/tools.py

@@ -23,7 +23,7 @@
 from quantms_io.core.psm import PSMHandler
 from quantms_io.core.project import ProjectHandler
 from quantms_io.utils.file_utils import extract_len
-
+from quantms_io.core.project import create_uuid_filename
 
 
 
@@ -323,3 +323,45 @@ def register_file_to_json(project_file,attach_file,category,replace_existing):
     Register= ProjectHandler(project_json_file=project_file)
     Register.add_quantms_file(attach_file,category,replace_existing)
     Register.save_updated_project_info(output_file_name=project_file)
+
+#check result of psms or features
+def generate_report_of_psms_or_features(check_dir,label):
+    if not os.path.exists(check_dir):
+        raise Exception("not file path")
+    file_list = os.listdir(check_dir)
+    if label == 'psm':
+        check_list = [file for file in file_list if file.endswith(".psm.parquet")]
+    elif label == 'feature':
+        check_list = [file for file in file_list if file.endswith(".feature.parquet")]
+
+    output_lines = ''
+    for file_path in check_list:
+        output_lines += 'Name: ' + file_path + '\n'
+        file_path = check_dir + "/" + file_path
+        file_size = getFileSize(file_path)
+        output_lines += 'File size: ' + file_size + '\n'
+        df = pd.read_parquet(file_path,columns=['protein_accessions','peptidoform','charge'])
+        output_lines += 'Total number of Peptides: ' + str(len(df.groupby(['peptidoform','charge']))) + '\n'
+        proteins = set()
+        df['protein_accessions'].apply(lambda x: proteins.update(set(x)))
+        output_lines += 'Total number of Proteins: ' + str(len(proteins)) + '\n\n'
+
+    output_path =  create_uuid_filename(label+'s_report','.txt')
+    with open(output_path, "w",encoding='utf8') as f:
+            f.write(output_lines)
+
+def getFileSize(filePath):
+    fsize = os.path.getsize(filePath)
+    if fsize < 1024:
+        return str(round(fsize,2)) + 'Byte'
+    else: 
+        KBX = fsize/1024
+        if KBX < 1024:
+            return str(round(KBX,2)) + 'K'
+        else:
+            MBX = KBX /1024
+            if MBX < 1024:
+                return str(round(MBX,2)) + 'M'
+            else:
+                return str(round(MBX/1024)) + 'G'
+

python/quantmsio/quantms_io/quantmsio_cli.py

@@ -15,6 +15,7 @@
 from quantms_io.commands.get_unanimous_command import get_unanimous_for_parquet,get_unanimous_for_tsv
 from quantms_io.commands.feature_command import convert_feature_file
 from quantms_io.commands.psm_command import convert_psm_file, compare_set_of_psms
+from quantms_io.commands.generate_report_command import generate_report_about_files
 
 CONTEXT_SETTINGS = dict(help_option_names=["-h", "--help"])
 
@@ -39,6 +40,7 @@ def cli():
 cli.add_command(attach_file_to_json)
 cli.add_command(get_unanimous_for_parquet)
 cli.add_command(get_unanimous_for_tsv)
+cli.add_command(generate_report_about_files)
 
 def quantms_io_main():
     """