Aster is a python based bot (or a module), which is capabale of writing baseline starter kernels for competitions or datasets hosted on Kaggle. As of now, It can work with two types of datasets - numerical dataset (having continuous and / or categorical columns) and text datasets having single text / document field.

1. Can create kernels on Compeititon and Datasets both
2. Can create kernels on datasets with binary / multi classification
3. Can create kernels on text datasets and numerical datasets
4. Performs Quick Exploration, Preprocessing, Feature Engineering, and Modelling
5. Changes the visuals according to data, for example - generates word clouds for text data and pairplots for numerical datasets
6. Uses a config to create new kernels

Aster first understands the inputs given in the config by the user and the types of columns present in the dataset. According to this information, aster dynamically chooses the most relevant code / text templates and appends them to the baseline kernel. For example, if the dataset is belongs to text classification category, then aster will generate some wordclouds, will not perform correlation charts, pair plots or categorical variable distributions. While if the dataset is non text classification type, then aster will choose the most relevant templates, for example - distribution of categorical variables, missing value treatments etc.

Aster creates following contents based on the type of data.

1. Environment Preparation
2. Quick Exploration
        2.1 Load Dataset
        2.2 Dataset Snapshot and Summary
        2.3 Target Variable Distribution
        2.4 Missing Values
        2.5 Variable Types
        2.6 Variable Correlations
3. Preprocessing
        3.1 Label Encoding
        3.2 Missing Values Treatment
        3.3 Feature Engineering (text fields)
            3.3.1 TF-IDF Vectorizor
            3.3.2 Top Keywords - Wordcloud
        3.4 Train Test Split
4. Modelling
        4.1 Logistic Regression
        4.2 Decision Tree
        4.3 Random Forest
        4.4 ExtraTrees Classifier
        4.5 Extereme Gradient Boosting
5. Feature Importance
6. Model Ensembling
        6.1 A simple Blender
7. Creating Submission

from aster.aster import aster

config = {	"COMPETITION" : "titanic", 
            "_TARGET_COL" : "Survived", 
            "_ID_COL" : "PassengerId"}

ast = aster(config) # aster object with config 
ast._prepare() # prepare the kernel
ast._push() # push the kernel on kaggle

from aster.aster import aster

config = {	"COMPETITION" : "spooky-author-identification", 
            "_TARGET_COL" : "author", 
            "_ID_COL" : "id",
            "_TAG" : "doc",
            "_TEXT_COL" : "text"}

ast = aster(config) # aster object with config 
ast._prepare() # prepare the kernel
ast._push() # push the kernel on kaggle

Aster uses config and its key-value pairs to write kernels on different datasets. All of the keys are not mandatory and most of them are optional. Check the following table.

• Titanic Baseline Kernel :

• Spooky Author Baseline Kernel

• Iris Dataset

• Diabetes Dataset

• Mushrooms Dataset

Aster can be installed directly from github using following commands

git clone https://github.com/shivam5992/aster.git
cd textstat
python setup.py install

• Dynamic Code Selection Improvements
• Add More Content
      - Automated Feature Engineering
      - Hyperparameter Tuning
• Extend Datatypes
      - Regression Problems - Numerical Data
      - Image Classifiication