Amplo 0.5.4

Fully automated end to end machine learning pipeline

Amplo - AutoML (for Machine Data)

Welcome to the Automated Machine Learning package Amplo. Amplo's AutoML is designed specifically for machine data and works very well with tabular time series data (especially unbalanced classification!).

Though this is a standalone Python package, Amplo's AutoML is also available on Amplo's ML Developer Platform. With a graphical user interface and various data connectors, it is the ideal place for service engineers to get started on Predictive Maintenance development.

Amplo's AutoML Pipeline contains the entire Machine Learning development cycle, including exploratory data analysis, data cleaning, feature extraction, feature selection, model selection, hyper parameter optimization, stacking, version control, production-ready models and documentation.

Downloading Amplo

The easiest way is to install our Python package through PyPi:

pip install Amplo

2. Amplo AutoML Features

Exploratory Data Analysis

from Amplo.AutoML import DataExplorer Automated Exploratory Data Analysis. Covers binary classification and regression. It generates:

• Missing Values Plot
• Line Plots of all features
• Box plots of all features
• Co-linearity Plot
• SHAP Values
• Random Forest Feature Importance
• Predictive Power Score

Additionally fFor Regression:

• Seasonality Plots
• Differentiated Variance Plot
• Auto Correlation Function Plot
• Partial Auto Correlation Function Plot
• Cross Correlation Function Plot
• Scatter Plots

Data Processing

from Amplo.AutoML import DataProcesser Automated Data Cleaning. Handles the following items:

• Cleans Column Names
• Duplicate Columns and Rows
• Data Types
• Missing Values
• Outliers
• Constant Columns

Feature Processing

from Amplo.AutoML import FeatureProcesser Automatically extracts and selects features. Removes Co-Linear Features. Included Feature Extraction algorithms:

• Multiplicative Features
• Dividing Features
• Additive Features
• Subtractive Features
• Trigonometric Features
• K-Means Features
• Lagged Features
• Differencing Features

Included Feature Selection algorithms:

• Random Forest Feature Importance (Threshold and Increment)
• Predictive Power Score
• Boruta

Sequencing

from Amplo.AutoML import Sequencer For timeseries regression problems, it is often useful to include multiple previous samples instead of just the latest. This class sequences the data, based on which time steps you want included in the in- and output. This is also very useful when working with tensors, as a tensor can be returned which directly fits into a Recurrent Neural Network.

Modelling

from Amplo.AutoML import Modeller Runs various regression or classification models. Includes:

• Scikit's Linear Model
• Scikit's Random Forest
• Scikit's Bagging
• Scikit's GradientBoosting
• Scikit's HistGradientBoosting
• DMLC's XGBoost
• Catboost's Catboost
• Microsoft's LightGBM

Grid Search

from Amplo.GridSearch import * Contains three hyperparameter optimizers, a basic GridSearch, an implementation of Scikit's RandomHalvingSearch and an implementation of Optuna's Tree-structured Parzen Estimator. Generally we advice to use Optuna.

Automatic Documntation

from Amplo.AutoML import Documenter Contains a documenter for classification (binary and multiclass prolems), as well as for regression. Creates a pdf report for a Pipeline, including metrics, data processing steps, and everything else to recreate the result.