PyCon Pune 2017

In a typical data science project, 60%-70% of total time is consumed in extracting, cleaning, preparing and analyzing the data before the actual model building and validation phase begins.
Pandas is the data wrangling library written in Python which makes all these activities super easy.

Outline

Below are some of the highlights of this talk which will be covered using Case Study

• Pandas Data Structures and basics

• Data import and export in Pandas

• Data Wrangling (Clean, Transform, Merge)

• Data Aggregation and grouping operations

• Exploratory Data Analysis and Descriptive Statistics

• Plotting and Visualization

Speaker bio

I am a Data Engineer and Data Science Enthusiast working with NEC Corporation of America (NEC Japan). I have completed B.E. in computers from Pune University and have total 6+ years of IT experience. My skillset includes Data Warehousing, Data Integration, Data analysis, Python, R Programming, Tableau, Feature Engineering and Machine Learning. I have been active part of Python Pune group and have conducted several sessions on Data Analysis and Machine Learning.