For Feedbacks | Enquiries | Questions | Comments - Contact us @ firstname.lastname@example.org
- Exploratory Data analysis(EDA) is an approach to extract insights, outliers, required variables and anomalies out of data.
- EDA is an effective technique to understand summary of data present in spreadsheet.
- Exploratory Data analysis can be used to
- Spot anomalies
- Test hypothesis
- Check assumptions
- Perform Investigations
- Exploratory Data analysis(EDA) is performed using statistics and graphical representations.
- In the area of Data Science, Exploratory Data Analysis is important approach to be taken before stepping into machine learning or creating models phase.
- Some of the graphical techniques used in EDA are:
- Box plot
- Multi-vari chart
- Run chart
- Pareto chart
- Scatter plot
- Stem-and-leaf plot
- Parallel coordinates
- Odds ratio
- Open source python library autoplotter made this analysis easy by providing Graphical User Interface. Autoplotter library is built on top of Dash.
- Python 3.6
- Internet to download packages
- Any Structured Data can be loaded through Pandas(few lines of code) to Autoplotter and we are ready to get started with different types visualizations, statistical analysis, plotting as per the selected columns and create all the major graphical information.
- Let us explore Relational dataset from IOT devices(temperaure readings) available in Kaggle. For the demonstration purpose we have used only 1000 rows.
pip install autoplotter
from autoplotter import run_app import plotly.express as px import pandas as pd df = pd.read_csv('IOT-temp_1000.csv') run_app(df)