Merge pull request #6 from frederikhoengaard/ingestion

Initial commit Ingestion - non-functional

Author: frederikhoengaard

.github/workflows/verify.yaml

@@ -4,7 +4,7 @@ on:
   pull_request:
 
 env:
-  PYTHONPATH: ./python/src/main/
+  PYTHONPATH: ./python/src/lazylearn/
 
 jobs:
   testing:
@@ -54,12 +54,12 @@ jobs:
 
       - name: black
         run: |
-          python -m black --check python/src/main/
+          python -m black --check python/src/lazylearn/
 
       - name: isort
         run: |
-          python -m isort python/src/main/ --multi-line 3 --profile black --check
+          python -m isort python/src/lazylearn/ --multi-line 3 --profile black --check
 
       - name: flake8
         run: |
-          python -m flake8 python/src/main/
+          python -m flake8 python/src/lazylearn/

.gitignore

@@ -13,6 +13,9 @@ __pycache__/
 # JetBrains
 .idea
 
+# local
+notebooks/
+
 # Distribution / packaging
 .Python
 build/

Pipfile

@@ -6,6 +6,9 @@ verify_ssl = true
 [packages]
 loguru = "==0.6.*"
 pandas = "==1.5.*"
+scikit-learn = "*"
+tqdm = "*"
+jupyter = "*"
 
 [dev-packages]
 black = "==23.*"

Pipfile.lock

@@ -1,12 +1,29 @@
-# lazy-learn
 
----
+<img width="500" src="doc/logo/transparent_small.png">
 
-## About
-
-lazy-learn is a high-level Python interface for automated machine learning (AutoML). While there are many AutoML libraries available each typically solves a niche area of the overall ML pipeline without providing a covering and approachable end-to-end system.
+**lazy-learn** is a high-level Python interface for automated machine learning (AutoML). While there are many AutoML libraries available each typically solves a niche area of the overall ML pipeline without providing a covering and approachable end-to-end system.
 
 The aim of lazy-learn is exactly that. Given a dataset, easy-learn will analyse types and distributions of attributes, preprocess, feature-engineer and ultimately train models to be used for further evaluation or inference. 
 
 ## Usage
 
+Using lazy-learn revolves around the `LazyLearner` class. You can think of it as a kind of project, and it is the wrapper for any experiment within lazy-learn.
+
+## Installation
+
+### Dependencies
+
+lazy-learn requires:
+
+- pandas
+- scikit-learn
+
+### User Installation 
+```
+pip install lazy-learn
+```
+
+## Help and Support
+### Documentation
+
+### Citation

README.md

@@ -8,7 +8,7 @@ version = "0.0.1"
 authors = [
   { name="Frederik P. Høngaard", email="mail@frederikhoengaard.com" },
 ]
-description = "A small example package"
+description = "lazy-learn is a high-level Python interface for automated machine learning (AutoML) for the lazy data scientist. While there are many AutoML libraries available each typically solves a niche area of the overall ML pipeline without providing a covering and approachable end-to-end system. lazy-learn aims at providing the most approachable and fastest access to building baseline models."
 readme = "README.md"
 requires-python = ">=3.7"
 classifiers = [
@@ -18,4 +18,4 @@ classifiers = [
 ]
 
 [project.urls]
-"Homepage" = "https://github.com/pypa/sampleproject"
+"Homepage" = "https://github.com/frederikhoengaard/lazy-learn"