Visualize, Hyper-tuning, and Modeling with Pywedge Python Package

Explore exploratory data analysis for machine learning and data science

Amit Chauhan
4 min readFeb 18


In many scenarios, we are dealing with messy data and sometimes hard to understand with statistics. To understand data more deeply and fast with the help of visualization by charts, and graphs.

For machine learning and data science learners, visualization is an easy process to choose the cleaning or wrangling techniques that help for exploratory data analysis (EDA).

Pywedge python package comes with multiple interactive charts to enable the learners to interact with the charts.

Features of Pywedge

  1. It can create 8 interactive charts with axis widgets selection.
  2. It also manages to use pre-processing analysis.
  3. The most important feature, it can create 10 baseline models for our datasets which helps in hyper-tuning for maximum accuracy.

Below is the code to install the Pywedge library in your python environment.

# to install the pywedge package in jupyter 
!pip install pywedge

# to install the pywedge package in the anaconda terminal
pip install pywedge

Pywedge for Visualization

To use the package, we need to import the csv file with the help of pandas library.

import pywedge as pw
import pandas as pd

Importing the train.csv data.

df = pd.read_csv("train.csv")

To use the visualization of Pywedge, we need to call the Pywedge_Charts method from the Pywedge package.

mc = pw.Pywedge_Charts(df, c=None, y="Fare" )
# For Visualization
chart = mc.make_charts()
Visualization graphs. An image by the Author

In the above image, we can see that there are different types of plots we can visualize the data.

Pywedge for Machine learning and Hyper-Tuning



Amit Chauhan

Data Scientist, AI/ML/DL, Azure Cloud