1

I have 2 data sets that represents the availability of internet connection. I want to find cross correlation between this 2 sets. My data is a two data frames :

First:

id  percent_availability    km
1   100               0.1
2   99.93437882       0.2
3   100               0.3
4   80                0.4

Second:

id  percent_availability    km
1   92.75525526         0.1
2   92.85714286         0.2
3   100                 0.3
4   20                  0.4

I transfere my data to an arrays and tried this methods: signal.correlate(array,array1,mode='same') np.correlatenp.correlate(array,array1,mode='same')

Also with dataframe I tried this df1.corrwith(df, axis = 1)

But the result is not that i expected. What I try to find is a km where i have more or less the stable percentage availability but not the big jumps. What can I use for this task? I would like to have new array or dataframe with the kilomiters and similarity of the percentage availability.

Barbaros Özhan
  • 59,113
  • 10
  • 31
  • 55
Kateryna Lubyk - Slava Ukraini
  • 185
  • 1
  • 12
  • Cannot quite comprehend what you are expecting. Have you checked out the solutions in this link? https://stackoverflow.com/questions/6991471/computing-cross-correlation-function – Ankur Sinha Sep 02 '19 at 11:27

0 Answers0