├── LICENSE
├── README.md
└── clickstream_analysis.R


/LICENSE:
--------------------------------------------------------------------------------
 1 | MIT License
 2 | 
 3 | Copyright (c) 2017 Blendo.co
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # ClickstreamAnalysis
 2 | This R code is an example of analyzing Clickstream Data using Markov Chains and data mining SPADE algorithm.
 3 | 
 4 | You can find the whole analysis here: https://www.blendo.co/blog/clickstream-data-mining-techniques-introduction/
 5 | 
 6 | ## Usage
 7 | 
 8 | I have used R version 3.3.3 (2017-03-06) -- "Another Canoe"
 9 | 
10 | All packages needed are mentioned in the code.
11 | 
12 | You just need to import the data as a .csv file, install the required packages and run the code!
13 | 
14 | ## License
15 | 
16 | The [MIT](https://opensource.org/licenses/MIT) License
17 | 


--------------------------------------------------------------------------------
/clickstream_analysis.R:
--------------------------------------------------------------------------------
 1 | library("clickstream")
 2 | library("arulesSequences")
 3 | 
 4 | ## Load Data
 5 | cls <- readClickstreams(file = "path_to_file", sep = ",", header = F)
 6 | cls
 7 | summary(cls)
 8 | 
 9 | ## Fitting Markov Chain
10 | mc <- fitMarkovChain(clickstreamList = cls, order = 3)
11 | options(digits = 2)
12 | 
13 | ##compute transition probabilities
14 | mc
15 | options(digits = 7)
16 | summary(mc)
17 | 
18 | ##plot transition diagram and heatmap
19 | plot(mc)
20 | hmPlot(mc)
21 | 
22 | ##clustering
23 | set.seed(42)
24 | clusters <- clusterClickstreams(clickstreamList = cls, order = 1, centers = 2)
25 | clusters
26 | #To produce the  clustering plot of the post in the code of function clusterClickstreams
27 | #add tthe following in line 17:
28 | #  ggplot(transitionData, aes(StatesChanged,id, colour=fit$cluster))+geom_point()
29 | summary(clusters)
30 | 
31 | #Predict clicks
32 | pattern <- new("Pattern", sequence = c("Action14", "Action4"))
33 | resultPattern <- predict(mc, startPattern = pattern, dist = 1) # set dist = n to predict n steps ahead
34 | resultPattern
35 | 
36 | ##cSPACE data mining
37 | frequencyDF <- frequencies(cls)
38 | frequencyDF
39 | trans <- as.transactions(cls)
40 | sequences <- as(cspade(trans, parameter = list(support = 0)), "data.frame")
41 | sequences
42 | 


--------------------------------------------------------------------------------