extract-data-csv plugin

utils/extract-data-csv-plugin/.bumpversion.cfg

@@ -0,0 +1,29 @@
+[bumpversion]
+current_version = 0.1.0
+commit = False
+tag = False
+parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
+serialize = 
+	{major}.{minor}.{patch}-{release}{dev}
+	{major}.{minor}.{patch}
+
+[bumpversion:part:release]
+optional_value = _
+first_value = dev
+values = 
+	dev
+	_
+
+[bumpversion:part:dev]
+
+[bumpversion:file:pyproject.toml]
+search = version = "{current_version}"
+replace = version = "{new_version}"
+
+[bumpversion:file:VERSION]
+
+[bumpversion:file:README.md]
+
+[bumpversion:file:plugin.json]
+
+[bumpversion:file:src/polus/mm/utils/extract_data_csv/__init__.py]

utils/extract-data-csv-plugin/.dockerignore

@@ -0,0 +1,4 @@
+.venv
+out
+tests
+__pycache__

utils/extract-data-csv-plugin/.gitattributes

@@ -0,0 +1 @@
+*.csv filter=lfs diff=lfs merge=lfs -text

utils/extract-data-csv-plugin/.gitignore

@@ -0,0 +1 @@
+poetry.lock

utils/extract-data-csv-plugin/CHANGELOG.md

@@ -0,0 +1,5 @@
+# CHANGELOG
+
+## 0.1.0
+
+Initial release.

utils/extract-data-csv-plugin/Dockerfile

@@ -0,0 +1,22 @@
+FROM condaforge/mambaforge
+
+ENV EXEC_DIR="/opt/executables"
+ENV POLUS_LOG="INFO"
+RUN mkdir -p ${EXEC_DIR}
+
+
+# Work directory defined in the base container
+# WORKDIR ${EXEC_DIR}
+
+COPY pyproject.toml ${EXEC_DIR}
+COPY VERSION ${EXEC_DIR}
+COPY README.md ${EXEC_DIR}
+COPY CHANGELOG.md ${EXEC_DIR}
+
+# Install needed packages here
+
+COPY src ${EXEC_DIR}/src
+
+RUN pip3 install ${EXEC_DIR} --no-cache-dir
+
+CMD ["--help"]

utils/extract-data-csv-plugin/README.md

@@ -0,0 +1,18 @@
+# extract_data_csv (0.1.0)
+
+Extract data from a CSV file
+
+## Options
+
+This plugin takes 6 input arguments and 2 output argument:
+
+| Name          | Description             | I/O    | Type   | Default |
+|---------------|-------------------------|--------|--------|---------|
+| input_csv_path | Path to the input csv file, Type: string, File type: input, Accepted formats: csv | Input | File | File |
+| query | query str to search the dataset, Type: string, File type: input, Accepted formats: txt | Input | string | string |
+| min_row | The row min inex, Type: int | Input | int | int |
+| max_row | The row max inex, Type: int | Input | int | int |
+| column_name | The name of the column to load data, Type: string, File type: input, Accepted formats: txt | Input | string | string |
+| output_txt_path | Path to the txt datoutput file, Type: string, File type: output, Accepted formats: txt | Input | string | string |
+| output_txt_path | Path to the txt output file | Output | File | File |
+| output_data | The output data | Output | {'type': 'array', 'items': 'string'} | {'type': 'array', 'items': 'string'} |

utils/extract-data-csv-plugin/VERSION

@@ -0,0 +1 @@
+0.1.0

utils/extract-data-csv-plugin/build-docker.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+version=$(<VERSION)
+docker build . -t polusai/extract-data-csv-tool:${version}

utils/extract-data-csv-plugin/extract_data_csv_0@1@0.cwl

@@ -0,0 +1,141 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+
+class: CommandLineTool
+
+label: Extract data from a CSV file
+
+doc: |-
+  Extract data from a CSV file
+
+baseCommand: ["python",  "-m", "polus.mm.utils.extract_data_csv"]
+
+hints:
+  DockerRequirement:
+    dockerPull: polusai/extract-data-csv-tool@sha256:2ef6682340ba4e34b826f5028bc4377b523c635975777f50deaf6d7278baa344
+
+requirements:
+  InlineJavascriptRequirement: {}
+  # Enabling InitialWorkDirRequirement will stage the input csv file
+  InitialWorkDirRequirement:
+    listing:
+    - $(inputs.input_csv_path)
+
+inputs:
+  input_csv_path:
+    label: Path to the input csv file
+    doc: |-
+      Path to the input csv file
+      Type: string
+      File type: input
+      Accepted formats: csv
+    type: File
+    format: edam:format_3752
+    inputBinding:
+      prefix: --input_csv_path
+
+  query:
+    label: query str to search the dataset
+    doc: |-
+      query str to search the dataset
+      Type: string
+      File type: input
+      Accepted formats: txt
+    type: string?
+    format:
+    - edam:format_2330
+    inputBinding:
+      prefix: --query
+
+  min_row:
+    label: The row min index
+    doc: |-
+      The row min inex
+      Type: int
+    type: int?
+    format:
+    - edam:format_2330
+    inputBinding:
+      prefix: --min_row
+    default: 1
+
+  max_row:
+    label: The row max index
+    doc: |-
+      The row max inex
+      Type: int
+    type: int?
+    format:
+    - edam:format_2330
+    inputBinding:
+      prefix: --max_row
+    default: -1
+
+  column_name:
+    label: The name of the column to load data
+    doc: |-
+      The name of the column to load data
+      Type: string
+      File type: input
+      Accepted formats: txt
+    type: string
+    format:
+    - edam:format_2330
+    inputBinding:
+      prefix: --column_name
+
+  output_txt_path:
+    label: Path to the txt output file
+    doc: |-
+      Path to the txt datoutput file
+      Type: string
+      File type: output
+      Accepted formats: txt
+    type: string
+    format:
+    - edam:format_2330
+    inputBinding:
+      prefix: --output_txt_path
+    default: system.log
+
+outputs:
+  output_txt_path:
+    label: Path to the txt output file
+    doc: |-
+      Path to the txt output file
+    type: File
+    outputBinding:
+      glob: $(inputs.output_txt_path)
+    format: edam:format_2330
+
+  output_data:
+    label: The output data
+    doc: |-
+      The output data
+    type:
+      type: array
+      items: string
+    outputBinding:
+      glob: $(inputs.output_txt_path)
+      loadContents: true
+      outputEval: |
+        ${
+            var lines = self[0].contents.split("\n");
+            // remove black lines
+            lines = lines.filter(function(line) {return line.trim() !== '';});
+            var data = [];
+            for (var i = 0; i < lines.length; i++) {
+              // The format of the lines is as follows: data
+                var words = lines[i].split(",").map(function(item) {return item.trim();});
+                data.push(words[0]);
+
+              }
+            return data;
+        }
+
+
+$namespaces:
+  edam: https://edamontology.org/
+
+$schemas:
+- https://raw.githubusercontent.com/edamontology/edamontology/master/EDAM_dev.owl

utils/extract-data-csv-plugin/ict.yml

@@ -0,0 +1,87 @@
+specVersion: "0.1.0"
+name: extract_data_csv
+version: 0.1.0
+container: extract-data-csv-plugin
+entrypoint:
+title: extract_data_csv
+description: Extract data from a CSV file
+author: Brandon Walker, Nazanin Donyapour
+contact: [email protected], [email protected]
+repository:
+documentation:
+citation:
+
+inputs:
+  - name: input_csv_path
+    required: true
+    description: Path to the input csv file, Type string, File type input, Accepted formats csv
+    type: File
+    format:
+      uri: edam:format_3752
+  - name: query
+    required: true
+    description: query str to search the dataset, Type string, File type input, Accepted formats txt
+    type: string
+    format:
+      uri: edam:format_2330
+  - name: min_row
+    required: true
+    description: The row min inex, Type int
+    type: int
+    format:
+      uri: edam:format_2330
+  - name: max_row
+    required: true
+    description: The row max inex, Type int
+    type: int
+    format:
+      uri: edam:format_2330
+  - name: column_name
+    required: true
+    description: The name of the column to load data, Type string, File type input, Accepted formats txt
+    type: string
+    format:
+      uri: edam:format_2330
+  - name: output_txt_path
+    required: true
+    description: Path to the txt datoutput file, Type string, File type output, Accepted formats txt
+    type: string
+    defaultValue: system.log
+    format:
+      uri: edam:format_2330
+outputs:
+  - name: output_txt_path
+    required: true
+    description: Path to the txt output file
+    type: File
+    format:
+      uri: edam:format_2330
+  - name: output_data
+    required: true
+    description: The output data
+    type: {'type': 'array', 'items': 'string'}
+ui:
+  - key: inputs.input_csv_path
+    title: "input_csv_path: "
+    description: "Path to the input csv file, Type string, File type input, Accepted formats csv"
+    type: File
+  - key: inputs.query
+    title: "query: "
+    description: "query str to search the dataset, Type string, File type input, Accepted formats txt"
+    type: string
+  - key: inputs.min_row
+    title: "min_row: "
+    description: "The row min inex, Type int"
+    type: int
+  - key: inputs.max_row
+    title: "max_row: "
+    description: "The row max inex, Type int"
+    type: int
+  - key: inputs.column_name
+    title: "column_name: "
+    description: "The name of the column to load data, Type string, File type input, Accepted formats txt"
+    type: string
+  - key: inputs.output_txt_path
+    title: "output_txt_path: "
+    description: "Path to the txt datoutput file, Type string, File type output, Accepted formats txt"
+    type: string

utils/extract-data-csv-plugin/pyproject.toml

@@ -0,0 +1,31 @@
+[tool.poetry]
+name = "polus-mm-utils-extract-data-csv"
+version = "0.1.0"
+description = "Extract data from a CSV file"
+authors = ["Nazanin Donyapour <[email protected]>", "Brandon Walker <[email protected]>"]
+readme = "README.md"
+packages = [{include = "polus", from = "src"}]
+
+[tool.poetry.dependencies]
+python = ">=3.9,<3.13"
+typer = "^0.7.0"
+sophios = "0.1.4"
+pandas = "2.2.2"
+
+[tool.poetry.group.dev.dependencies]
+bump2version = "^1.0.1"
+pytest = "^7.4"
+pytest-sugar = "^0.9.6"
+pre-commit = "^3.2.1"
+black = "^23.3.0"
+mypy = "^1.1.1"
+ruff = "^0.0.270"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+pythonpath = [
+  "."
+]

utils/extract-data-csv-plugin/src/polus/mm/utils/extract_data_csv/__init__.py

@@ -0,0 +1,7 @@
+"""extract_data_csv."""
+
+__version__ = "0.1.0"
+
+from polus.mm.utils.extract_data_csv.extract_data_csv import (  # noqa # pylint: disable=unused-import
+    extract_data_csv,
+)