elisim

name: Run PyTest

on:
  [ pull_request ]

jobs:
  pytest:
      name: Run Tests
      runs-on: ubuntu-latest
      steps:

elisim

# This workflow finds which files was changed, print them, and then
# run `pre-commit` on those files. I was inspired by sktime:
# https://github.com/alan-turing-institute/sktime/blob/main/.github/workflows/build-and-test.yml

name: Code Quality

on:
  pull_request:
    branches:
      - main

elisim

repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v3.4.0
    hooks:
      # list of supported hooks: https://pre-commit.com/hooks.html
      - id: trailing-whitespace
      - id: end-of-file-fixer
      - id: check-yaml
      - id: check-added-large-files
      - id: debug-statements

elisim

import hydra
from omegaconf import DictConfig


@hydra.main(config_path="configs/", config_name="config.yaml")
def main(config: DictConfig):
  
    # instantiate our preprocessing pipeline to 
    # sklearn Pipeline object using hydra configuration
    preprocessing_pipeline = hydra.utils.instantiate(

elisim

# @package _global_

# specify here default preprocessing configuration
defaults:
    # can be any config file in the preprocessing_pipeline folder
    - preprocessing_pipeline: decision_tree.yaml

elisim

import hydra
from omegaconf import DictConfig
from sklearn.pipeline import Pipeline


def make_pipeline(steps_config: DictConfig) -> Pipeline:
    """Creates a pipeline with all the preprocessing steps specified in `steps_config`, ordered in a sequential manner

    Args:
        steps_config (DictConfig): the config containing the instructions for

elisim

# Hydra config file for the decision_tree preprocessing steps
_target_: hydra_sklearn_pipeline.make_pipeline

#StepName:
#    _target_: <class to instantiate the step>
#    param1: <step's first parameter>
#    param2: <step's second parameter, etc.>

steps_config: # use yaml list syntax to preserve to order
    - StandardScaler:

elisim

from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier

pipeline_lr = Pipeline(
    [
        ("imputer", SimpleImputer(strategy="constant", fill_value="-1")),
        ("VarianceThreshold", VarianceThreshold(threshold=0.1)),
        ("scalar1", StandardScaler()),

elisim

from sklearn.feature_selection import VarianceThreshold
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

num_pipeline = Pipeline(
    [
        ("scaler", StandardScaler()),
        ("VarianceThreshold", VarianceThreshold(threshold=0.1)),
        ("imputer", SimpleImputer(strategy="constant", fill_value="-1")),

elisim

# # This script will unrar the RARs in $src to $dest. Based on: 
# https://serverfault.com/questions/356184/powershell-unrar-with-wildcard/356208?newreg=44a1363382a04e7a95a915434574dec2

param (
    [Parameter(Mandatory=$true)][string]$src,
    [Parameter(Mandatory=$true)][string]$dest
 )

$files = @()