initial commit

.gitignore

@@ -0,0 +1,278 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/python,pycharm+all
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,pycharm+all
+
+### PyCharm+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm+all Patch ###
+# Ignores the whole .idea folder and all .iml files
+# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
+
+.idea/*
+
+# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
+
+*.iml
+modules.xml
+.idea/misc.xml
+*.ipr
+
+# Sonarlint plugin
+.idea/sonarlint
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/python,pycharm+all
+
+# JS
+node_modules/
+
+test.csv

.vscode/extensions.json

@@ -0,0 +1,13 @@
+{
+    "recommendations": [
+        "ms-python.black-formatter",
+        "ms-python.flake8",
+        "ms-python.isort",
+        "ms-toolsai.jupyter",
+        "ms-toolsai.datawrangler",
+        "ms-python.python",
+        "donjayamanne.python-environment-manager",
+        // optional
+        "usernamehw.errorlens"
+    ]
+}

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "mai-service",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "run.py",
+            "console": "integratedTerminal",
+            "justMyCode": true
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,38 @@
+{
+    "files.autoSave": "onFocusChange",
+    "files.exclude": {
+        "**/__pycache__": true
+    },
+    "editor.detectIndentation": false,
+    "editor.formatOnType": false,
+    "editor.formatOnPaste": true,
+    "editor.formatOnSave": true,
+    "editor.tabSize": 4,
+    "editor.insertSpaces": true,
+    "editor.codeActionsOnSave": {
+        "source.organizeImports": "explicit",
+        "source.sortImports": "explicit"
+    },
+    "editor.stickyScroll.enabled": false,
+    "diffEditor.ignoreTrimWhitespace": false,
+    "debug.showVariableTypes": true,
+    "workbench.editor.highlightModifiedTabs": true,
+    "git.suggestSmartCommit": false,
+    "git.autofetch": true,
+    "git.openRepositoryInParentFolders": "always",
+    "git.confirmSync": false,
+    "errorLens.gutterIconsEnabled": true,
+    "errorLens.messageEnabled": false,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+    },
+    "python.languageServer": "Pylance",
+    "python.analysis.typeCheckingMode": "basic",
+    "python.analysis.autoImportCompletions": true,
+    "isort.args": [
+        "--profile",
+        "black"
+    ],
+    "notebook.lineNumbers": "on",
+    "notebook.output.minimalErrorRendering": true,
+}

backend/__init__.py

@@ -0,0 +1,52 @@
+import importlib
+import os
+import traceback
+
+import matplotlib
+from apiflask import APIBlueprint, APIFlask
+from flask_cors import CORS
+
+matplotlib.use("agg")
+
+cors = CORS()
+api_bp = APIBlueprint("api", __name__, url_prefix="/api/v1")
+dataset_path: str | None = None
+
+
+class Config:
+    SECRET_KEY = "secret!"
+    SEND_FILE_MAX_AGE_DEFAULT = -1
+
+
+def create_app():
+    global dataset_path
+
+    # Create and configure app
+    app = APIFlask(
+        "MAI Service",
+        title="MAI Service API",
+        docs_path="/",
+        version="1.0",
+        static_folder="",
+        template_folder="",
+    )
+    app.config.from_object(Config)
+
+    dataset_path = os.path.join(app.instance_path, "dataset")
+    os.makedirs(dataset_path, exist_ok=True)
+
+    @app.errorhandler(Exception)
+    def my_error_processor(error):
+        traceback.print_exception(error)
+        return {"message": str(error), "detail": "No details"}, 500
+
+    # Import custom REST methods
+    importlib.import_module("backend.api")
+
+    # Enable REST API
+    app.register_blueprint(api_bp)
+
+    # Enable app extensions
+    cors.init_app(app)
+
+    return app

backend/api.py

@@ -0,0 +1,57 @@
+from apiflask import FileSchema, Schema, fields
+from flask import send_file
+
+from backend import api_bp, dataset_path
+from backend.service import Service
+
+
+class FileUpload(Schema):
+    file = fields.File(required=True)
+
+
+class ColumnInfoDto(Schema):
+    datatype = fields.String()
+    items = fields.List(fields.String())
+
+
+class TableColumnDto(Schema):
+    name = fields.String()
+    datatype = fields.String()
+    items = fields.List(fields.String())
+
+
+service = Service(dataset_path)
+
+
+@api_bp.post("/dataset")
+@api_bp.input(FileUpload, location="files")
+def upload_dataset(files_data):
+    uploaded_file = files_data["file"]
+    return service.upload_dataset(uploaded_file)
+
+
+@api_bp.get("/dataset")
+def get_all_datasets():
+    return service.get_all_datasets()
+
+
+@api_bp.get("/dataset/<string:name>")
+@api_bp.output(TableColumnDto(many=True))
+def get_dataset_info(name: str):
+    return service.get_dataset_info(name)
+
+
+@api_bp.get("/dataset/<string:name>/<string:column>")
+@api_bp.output(ColumnInfoDto)
+def get_column_info(name: str, column: str):
+    return service.get_column_info(name, column)
+
+
+@api_bp.get("/dataset/draw/hist/<string:name>/<string:column>")
+@api_bp.output(
+    FileSchema(type="string", format="binary"), content_type="image/png", example=""
+)
+def get_dataset_hist(name: str, column: str):
+    data = service.get_hist(name, column)
+    data.seek(0)
+    return send_file(data, download_name=f"{name}.hist.png", mimetype="image/png")

backend/service.py

@@ -0,0 +1,59 @@
+import io
+import os
+import pathlib
+from typing import BinaryIO, Dict, List
+
+import pandas as pd
+from matplotlib.figure import Figure
+from werkzeug.datastructures import FileStorage
+from werkzeug.utils import secure_filename
+
+
+class Service:
+    def __init__(self, dataset_path: str | None) -> None:
+        if dataset_path is None:
+            raise Exception("Dataset path is not defined")
+        self.__path: str = dataset_path
+
+    def __get_dataset(self, filename: str) -> pd.DataFrame:
+        full_file_name = os.path.join(self.__path, secure_filename(filename))
+        return pd.read_csv(full_file_name)
+
+    def upload_dataset(self, file: FileStorage) -> str:
+        if file.filename is None:
+            raise Exception("Dataset upload error")
+        file_name: str = file.filename
+        full_file_name = os.path.join(self.__path, secure_filename(file_name))
+        file.save(full_file_name)
+        return file_name
+
+    def get_all_datasets(self) -> List[str]:
+        return [file.name for file in pathlib.Path(self.__path).glob("*.csv")]
+
+    def get_dataset_info(self, filename) -> List[Dict]:
+        dataset = self.__get_dataset(filename)
+        dataset_info = []
+        for column in dataset.columns:
+            items = dataset[column].astype(str)
+            column_info = {
+                "name": column,
+                "datatype": dataset.dtypes[column],
+                "items": items,
+            }
+            dataset_info.append(column_info)
+        return dataset_info
+
+    def get_column_info(self, filename, column) -> Dict:
+        dataset = self.__get_dataset(filename)
+        datatype = dataset.dtypes[column]
+        items = sorted(dataset[column].astype(str).unique())
+        return {"datatype": datatype, "items": items}
+
+    def get_hist(self, filename, column) -> BinaryIO:
+        dataset = self.__get_dataset(filename)
+        bytes = io.BytesIO()
+        plot: Figure | None = dataset.plot.hist(column=[column], bins=80).get_figure()
+        if plot is None:
+            raise Exception("Can't create hist plot")
+        plot.savefig(bytes, dpi=300, format="png")
+        return bytes

poetry.toml

@@ -0,0 +1,2 @@
+[virtualenvs]
+in-project = true

pyproject.toml

@@ -0,0 +1,24 @@
+[tool.poetry]
+name = "mai"
+version = "1.0.0"
+description = "MAI Examples"
+authors = ["Aleksey Filippov <al.filippov@ulstu.ru>"]
+readme = "readme.md"
+package-mode = false
+
+[tool.poetry.dependencies]
+python = "^3.12"
+jupyter = "^1.1.1"
+numpy = "^2.1.0"
+pandas = "^2.2.2"
+matplotlib = "^3.9.2"
+flask = "^3.0.3"
+apiflask = "^2.2.0"
+flask-cors = "^5.0.0"
+scikit-learn = "^1.5.2"
+imbalanced-learn = "^0.12.3"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

run.py

@@ -0,0 +1,16 @@
+from backend import create_app
+
+app = create_app()
+
+
+def __main():
+    app.run(
+        host="127.0.0.1",
+        port=8080,
+        debug=True,
+        use_reloader=False,
+    )
+
+
+if __name__ == "__main__":
+    __main()