Skip to main content

Learn which Are The Best Plots For Data Visualization in just 5 min ?

Python is a cool language when it comes to machine learning.

Data visualization is the keys to building best machine learning model. And Without  data visualization machine learning is just a waste of time data visualization helps us understand data and relationships between features.

Here we will learn which are the best plots to visualize what type of data.

Data is basically of two two types---
1.Numeric
2.Categorical 


1. Draw distribution for single feature --
  • If the feature is of categorical type then its better to use bar plots. in diagram given below you can see the different company names that produces automobiles these company names are categorical and graph shows which company manufactured how many autos   
  • If the feature is  numerical its better to draw histogram with bins. in diagram below you might see that engine size is plotted against number of autos . notice that engine size is a numerical feature
  • if the feature is numerical then there are two more things we can do to get more views. first is using kde plot(kernel density estimate plot).and the other is using kde and histogram at same time. now look the fig given below you may find similarities with above histogram its because the are just different representations of same data. given below is example kde plot area under that curve is 1 if we take integration. 
  • And the last one is using kde along with histogram . This gives better view of the data .observe there is bunch of lines on the x axis they are called rug the shoe frequency of observation.
2 .   Analiysing two features at a time/ two dimensional plot --
  • 2D plots help us understand relationship between two features . specially between feature and labels.in this case we plot one feature on one axis say on x axis and other on y axis . below in diagram you will find there are two features engine size and price of the auto there we can see relation that as the size of engine increases price of the automobile increases. observe there is to much overlapping  of points is going on at engine size approximately 100 or 90.we cant clearly see the points. to deal with this problem we use 3 techniques as following 
  • first is changing transparency so that points below can be visible. for example see fig below which is just modified version of above fig. you may notice now you can see through that mess of points .
     
  • second is using contour plots  see the dark area in plot shows that most observations or max observations . you may realize that that most autos are in engine size 100 and price 10000 range . note that different views reviles different understanding of data.
     
  • Third is to use using hex bin plot. remember darker the area is more the observation are present there. 
  • To find relation between categorical and numeric data its better to use box plot as it shows more precisely the relation  between different categories and of same column against some other numeric column data.  observe how well you can distinguish different categories of number of cylinders.   in box plot box shows interquartile range mid line between box determines median outer line called Vickers 
  • There is also one more way to do this is using violin plot.  like i said earlier it just another view of same data.





Labels:

Comments

Post a Comment

Popular posts from this blog

Data preparation : Dealing with missing values

Missing values are probably the most common headache you are going to have as machine learning engineer. missing values are the ones who screw the whole algorithm and make model give wired results(predictions). Treating missing values--- 1. Use exploration to detect the missing values -- detecting missing values is crucial because  lot of machine learning models fail because of missing values. 2.Find how are missing values are coded-- missing values could be codded in the data in one or more of following formats.     -NULL     -a string or number--eg.-9999,0,"NA","?"etc. 3. Treatment strategy--     - if some column has lot of missing values then its better to get rid of that column.     - remove row-- suppose very few rows have missing values then remove those rows.     -Forward or backward fill-- sometimes its just better to use fill which work by filling value of  nearest           neighbours  in null cell. it is useful when data is in some order say in order of
Post a Comment
Read more

Feature Engineering is easy ..!!

Features are input to machine learning algorithm. and the row features that are provided to us are not the best, they are just whatever just has to be in data.  Feature engineering have a goal to convert given features into much more predictive ones so that the can predict label more precisely . feature engineering can make simple algorithm to give good results. at a same time if you apply the best algorithm and do not perform feature engineering well you are going to get poor results.  feature engineering is a broad subject people dedicate their entire careers to feature engineering. there are some steps in feature engg that we need to follow and repeat most of the times to get job done. steps--- 1. Explore and understand data relationships 2. Transform feature  3.Compute new features from other by applying some  maths on it 4. Visualization to check results   5. Test with ML model 6. Repeat above steps as needed Transforming feature--- Why transform feature ?-- 1. To improve distribu
Post a Comment
Read more