Publications by Vasileios Tsakalos

Data wrangling : I/O (Part-1)

24.05.2017

Data wrangling is a task of great importance in data analysis. Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief ...

2824 sym 4 img

Data wrangling : I/O (Part-2)

07.06.2017

Data wrangling is a task of great importance in data analysis. Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief ...

4367 sym 4 img

Data wrangling : Reshaping

22.06.2017

Data wrangling is a task of great importance in data analysis. Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief ...

3867 sym 4 img

Data wrangling : Transforming (1/3)

05.07.2017

Data wrangling is a task of great importance in data analysis. Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief ...

2839 sym 2 img

Data wrangling : Transforming (2/3)

19.07.2017

Data wrangling is a task of great importance in data analysis. Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief ...

3563 sym 4 img

Data wrangling : Transforming (3/3)

02.08.2017

Data wrangling is a task of great importance in data analysis. Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief ...

3682 sym 4 img

Data wrangling : Cleansing – Regular expressions (1/3)

16.08.2017

Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief series with goal to craft the reader’s skills on the data wran...

3650 sym 4 img

Data wrangling : Cleansing – Regular expressions (2/3)

30.08.2017

Data wrangling, is the process of importing, cleaning and transforming raw data into actionable information for analysis. It is a time-consuming process which is estimated to take about 60-80% of analyst’s time. In this series we will go through this process. It will be a brief series with goal to craft the reader’s skills on the data wran...

2761 sym 4 img

Data wrangling : Cleansing – Regular expressions (3/3)

13.09.2017

Data wrangling is the process of importing, cleaning, and transforming raw data into actionable information for analysis. It is a time-consuming process that is estimated to take about 60-80% of analysts’ time. In this series, we will go through this process. It will be a brief series with the goal of crafting the reader’s skills in data wran...

2964 sym 4 img

Tensorflow – Neural Network Training: Exercises

01.04.2018

Deep learning is under active development. Papers with new approaches are being published every day. In this set of exercises we will go through some of the newer methods that boost the neural network’s performance. By the end of this post, you will be able to train neural networks with adaptive learning rates and apply methods to avoid (overfi...

4006 sym 2 img