Hands-On Deep Learning for IoT by Mohammad Abdur Razzaque PhD

Author:Mohammad Abdur Razzaque, PhD
Language: eng
Format: epub
Tags: COM044000 - COMPUTERS / Neural Networks, COM016000 - COMPUTERS / Computer Vision and Pattern Recognition, COM004000 - COMPUTERS / Intelligence (AI) and Semantics
Publisher: Packt Publishing
Published: 2019-06-27T06:26:31+00:00

Exploratory analysis

The exploratory analysis of data using the Python pandas library provides many powerful features–no doubt. However, using df.describe(), df.dtypes, or using df.isnull().sum() and plotting them separately is always time-consuming. Sometimes, you won't even get the required information in a sophisticated way. In fact, you'll have to write extra lines of code to convert them into a presentable format. However, to make your life easier, you can now start using the pandas_profiling library (see https://github.com/pandas-profiling/pandas-profiling). Just one line of code will give the information you need:

pandas_profiling.ProfileReport(df)

Surely, it would be worth using pandas_profiling to get a quick understanding of your data. Let's try it out! First, we read the training data by explicitly passing header=0 to be able to replace the existing names:

trainDF = pd.read_csv("trainingData.csv",header = 0)

To retrieve the list of variables that are rejected due to high correlation, you can use the following command:

profile = pandas_profiling.ProfileReport(trainDF)

This will produce a report showing information on the dataset:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.