bondziot / bigdata

data mining and analysis on paper title

bigdata

Big data cheat sheet

1. Data share space

Put all the data file or code file to the github to make us can share all these, which could makes us work more efficient. Github url:https://github.com/CnBDM-Su/bigdata Just click the button update , u could upload what you want.

2. the main object:

(1) discovery:some thing about background and aim

(2) Data preparation:

• Data learning and mining(done)
• Data conditioning(clean data) (processing): word count ,word clean...
• Data visualization(not yet)

(3) Model planning and building

• Association rules : using this model to find the word group but only word.

• Clustering: using k-means model to find some relation like( x is one of the avg(times in each year) for a word, y is Standard Deviation for each year of one word....

• Regression: get some prediction for the technology like it will rise or drop

(4) Analyse the result and so some conclusion

(5) Write report