LibFM parameter Summary

The code here generates a histogram of all numerical parameters included in libFM computation with its quantiles The variables are outlier treated(replaced with mean) For categorical values, the factors are displayed.

library(rpart)
library(mlr)
library(dummies)
library(lattice) 
library(knitr)

setwd("/Users/adarsa/ilimi/github/Learning-Platform-Analytics/platform-scripts/shell/local/libfm.input")
opts_knit$set(root.dir = '/Users/adarsa/ilimi/github/Learning-Platform-Analytics/platform-scripts/shell/local/libfm.input/libfm_input/')

libfm_input<-read.csv("libfm_input")
col_names<-colnames(libfm_input)
libfm_input<-libfm_input[libfm_input$c1_total_ts!=0,]
libfm_input_onehot <- dummy.data.frame(libfm_input, names=c("c1_subject","c1_contentType","c1_language","c2_subject","c2_contentType","c2_language","device_spec"), sep="_")



print("###########################################")
## [1] "###########################################"
print("Categorical Variables :")
## [1] "Categorical Variables :"
cat_features<-c("c1_subject","c1_contentType","c1_language","c2_subject","c2_contentType","c2_language","device_spec")
print("Numeric Variables:")
## [1] "Numeric Variables:"
for (i in cat_features){
  print("###########################################")
  print(unique(libfm_input[i]))
}
## [1] "###########################################"
##            c1_subject
## 1            literacy
## 160          numeracy
## 534 literacy,numeracy
## [1] "###########################################"
##    c1_contentType
## 1            Game
## 2           Story
## 4       Worksheet
## 14     Collection
## [1] "###########################################"
##      c1_language
## 1        English
## 2          Hindi
## 74       Kannada
## 570       Telugu
## 583        Other
## 1026       Tamil
## [1] "###########################################"
##            c2_subject
## 1            literacy
## 8            numeracy
## 24            Unknown
## 574 literacy,numeracy
## [1] "###########################################"
##    c2_contentType
## 1            Game
## 2           Story
## 4       Worksheet
## 14     Collection
## 24        Unknown
## [1] "###########################################"
##      c2_language
## 1        English
## 2          Hindi
## 24       Unknown
## 74       Kannada
## 570       Telugu
## 637        Other
## 1033       Tamil
## [1] "###########################################"
##                                                      device_spec
## 1                                                   MicromaxP480
## 2                                                Motorola MotoE2
## 54                                              Samsung SCH-I535
## 55                                               Motorola XT1052
## 63                                               Motorola XT1033
## 73                                                 Xiaomi MI PAD
## 100                                                Micromax A311
## 101                                         LENOVO Lenovo K50a40
## 336                                                Micromax A093
## 349                                            IBall 3G 1026-Q18
## 354                                          LENOVO Lenovo A6000
## 356                                                Micromax A089
## 357                                                  LYF LS-5501
## 365                                      Motorola MotoE2(4G-LTE)
## 370                                                  XOLO Opus 3
## 371                                                LAVA Flair Z1
## 374                                               Lava X1 Selfie
## 375                                                   HTC One_M8
## 437                                              Micromax AQ4501
## 438                                              Motorola XT1068
## 444                                              Motorola XT1562
## 445                                             Samsung SM-G925I
## 447                                                 Letv Le X507
## 467                                                Micromax A102
## 471                                              Motorola MotoG3
## 532                                             Samsung SM-N910G
## 694                                 HTC Desire 526GPLUS dual sim
## 896           Unknown Google Nexus 7 - 5.1.0 - API 22 - 800x1280
## 911                                               Xiaomi 2014818
## 913                                             Lava iris Fuel50
## 914                                                Micromax A107
## 932                                                OnePlus A0001
## 952                                        LENOVO Lenovo S5000-H
## 953                                           IBall 3G 7345Q-800
## 1024                                              LGE LG-VS450PP
## 1025                                               Micromax Q340
## 1040                                        Samsung Galaxy Nexus
## 1118                                                    ZTE U950
## 1125                                                 LGE Nexus 5
## 1136                                        IBall 3G Q7271-IPS20
## 1138                                            Samsung GT-N7100
## 1190                                              LAVA iris 450P
## 1191                                            Samsung SM-J200G
## 1204                                             Huawei Nexus 6P
## 1207                                                  Sony D2502
## 1209                                             Samsung SM-N750
## 1227                                     Hewlett-Packard HP 7 G2
## 1230                                            Samsung GT-S7582
## 1231                                           Samsung SM-T116NY
## 1239                                             Samsung SM-N900
## 1248                                            Samsung Nexus 10
## 1261                                              HUAWEI KIW-L22
## 1278                                            Samsung GT-I9060
## 1279                                 LENOVO Lenovo TAB 2 A7-30HC
## 1281                                                Asus Nexus 7
## 1296                                                MicromaxP680
## 1322                                                 LAVA irisX8
## 1326                                   LENOVO Lenovo TAB S8-50LC
## 1328                                             Asus ASUS_Z010D
## 1338                                            RELIANCE LS-5501
## 1402                                           OnePlus ONE A2003
## 1432 Genymotion Google Nexus 7 2013 - 6.0.0 - API 23 - 1200x1920
## 1472                                             Samsung SM-T231
## 1534                                                  Sony C1904
## 1535                                         LENOVO Lenovo P1a42
## 1539                                              Intex Cloud M6
## 1541                                         INTEX Cloud 4G Star
## 1542                                             Samsung SM-T800
## 1543                                            Samsung SM-G531F
## 1616                                             Asus ASUS_Z00AD
## 1636                                               Micromax E313
## 1637                           Unknown Android SDK built for x86
## 1642                                                     HTC One
## 1813                                               Micromax P666
## 1826                                           Intex Aqua Y2 Pro
## 1856                                            Samsung SM-G7102
## 1893                                            Samsung SM-G355H
## 1931                                            Motorola Nexus 6
## 1932                                             Micromax AQ5001
## 1933                                               Micromax D321
## 1935                                             Motorola XT1022
## 1944                                                IBall 3G Q27
## 1945                                                LGE Nexus 5X
## 1982                                           Dell Venue 8 3830
## 2003                                               Micromax Q392
## 2006                                                   Asus K012
## 2050                                               Micromax E311
## 2051                                          Motorola MotoG3-TE
## 2064                                           Samsung SM-G316HU
## 2066                                               Micromax A290
## 2085                                              XOLO A500 Club
## 2089                                             Samsung SM-T211
## 2210                                    HTC Desire 816G dual sim
## 2213                                            Samsung GT-I9300
## 2217                                                Xiaomi Mi 4i
## 2358                                            SWIPE ACE Strike
## 2367                                                 LGE LG-D855
## 2369                                            Samsung GT-I9500
## 2374                                           Samsung GT-I9060I
## 2384                                        Dell Venue7 3740 LTE
## 2385                                                  Sony C6603
## 2401                                         Xiaomi Redmi Note 3
## 2444                                                   OPPO A33f
## 2475                                               Micromax Q331
## 2692                                          INTEX Aqua_LifeIII
features_index<-c(101:124,225:251,371:375)
remove_outliers <- function(x,outlier ) {
  for (i in outlier){
    x[x==i]=max(0,mean(x))  #outlier replaced with mean value
  }
  return (x)
}

for ( i in features_index){
  outlier_values <- boxplot.stats(libfm_input_onehot[[i]])$out
  libfm_input_onehot[[i]]<-remove_outliers(libfm_input_onehot[[i]],outlier_values)

print("##########################################")
print(paste("LibFM Parameter:",colnames( libfm_input_onehot)[[i]]))
print(quantile( libfm_input_onehot[[i]]))
hist(libfm_input_onehot[[i]], breaks = 200,xlab =colnames( libfm_input_onehot)[[i]], main =paste("histogram of",colnames( libfm_input_onehot)[[i]], sep=" ") )
}
## [1] "##########################################"
## [1] "LibFM Parameter: c1_total_ts"
##        0%       25%       50%       75%      100% 
##    1.0000   40.0375  145.7300  402.0000 1250.8000

## [1] "##########################################"
## [1] "LibFM Parameter: c1_avg_interactions_min"
##    0%   25%   50%   75%  100% 
##  0.00  8.42 17.68 27.45 66.18

## [1] "##########################################"
## [1] "LibFM Parameter: c1_download_date"
##           0%          25%          50%          75%         100% 
## 0.000000e+00 0.000000e+00 1.463380e+12 1.465294e+12 1.470302e+12

## [1] "##########################################"
## [1] "LibFM Parameter: c1_downloaded"
##   0%  25%  50%  75% 100% 
##    0    0    1    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c1_last_played_on"
##           0%          25%          50%          75%         100% 
## 1.446302e+12 1.453534e+12 1.462362e+12 1.464949e+12 1.470306e+12

## [1] "##########################################"
## [1] "LibFM Parameter: c1_mean_play_time_interval"
##       0%      25%      50%      75%     100% 
##  -510.00     0.00     0.00   372.75 86065.67

## [1] "##########################################"
## [1] "LibFM Parameter: c1_num_group_user"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.005939124

## [1] "##########################################"
## [1] "LibFM Parameter: c1_num_individual_user"
##       0%      25%      50%      75%     100% 
##  0.00000  1.00000  2.00000  4.44001 11.00000

## [1] "##########################################"
## [1] "LibFM Parameter: c1_num_sessions"
##        0%       25%       50%       75%      100% 
##  1.000000  1.000000  2.000000  4.446235 11.000000

## [1] "##########################################"
## [1] "LibFM Parameter: c1_start_time"
##           0%          25%          50%          75%         100% 
## 1.446046e+12 1.453463e+12 1.462356e+12 1.464943e+12 1.470306e+12

## [1] "##########################################"
## [1] "LibFM Parameter: c1_total_interactions"
##       0%      25%      50%      75%     100% 
##   0.0000  12.0000  45.0000 114.2056 341.0000

## [1] "##########################################"
## [1] "LibFM Parameter: c1_subject_literacy"
##        0%       25%       50%       75%      100% 
## 0.9732739 1.0000000 1.0000000 1.0000000 1.0000000

## [1] "##########################################"
## [1] "LibFM Parameter: c1_subject_literacy,numeracy"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.002227171

## [1] "##########################################"
## [1] "LibFM Parameter: c1_subject_numeracy"
##         0%        25%        50%        75%       100% 
## 0.00000000 0.00000000 0.00000000 0.00000000 0.02449889

## [1] "##########################################"
## [1] "LibFM Parameter: c1_contentType_Collection"
##         0%        25%        50%        75%       100% 
## 0.00000000 0.00000000 0.00000000 0.00000000 0.08389013

## [1] "##########################################"
## [1] "LibFM Parameter: c1_contentType_Game"
##         0%        25%        50%        75%       100% 
## 0.00000000 0.00000000 0.00000000 0.00000000 0.08314774

## [1] "##########################################"
## [1] "LibFM Parameter: c1_contentType_Story"
##   0%  25%  50%  75% 100% 
##    0    0    1    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c1_contentType_Worksheet"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.1889384

## [1] "##########################################"
## [1] "LibFM Parameter: c1_language_English"
##   0%  25%  50%  75% 100% 
##    0    0    1    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c1_language_Hindi"
##   0%  25%  50%  75% 100% 
##    0    0    0    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c1_language_Kannada"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.0155902

## [1] "##########################################"
## [1] "LibFM Parameter: c1_language_Other"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.002227171

## [1] "##########################################"
## [1] "LibFM Parameter: c1_language_Tamil"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.002227171

## [1] "##########################################"
## [1] "LibFM Parameter: c1_language_Telugu"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.004083148

## [1] "##########################################"
## [1] "LibFM Parameter: c2_total_ts"
##       0%      25%      50%      75%     100% 
##   0.0000   0.0000  55.9800 251.4013 829.0000

## [1] "##########################################"
## [1] "LibFM Parameter: c2_avg_interactions_min"
##    0%   25%   50%   75%  100% 
##  0.00  0.00 10.10 21.49 60.79

## [1] "##########################################"
## [1] "LibFM Parameter: c2_download_date"
##           0%          25%          50%          75%         100% 
## 1.108090e+12 1.459158e+12 1.463512e+12 1.465447e+12 1.470396e+12

## [1] "##########################################"
## [1] "LibFM Parameter: c2_downloaded"
##   0%  25%  50%  75% 100% 
##    0    0    1    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c2_last_played_on"
##           0%          25%          50%          75%         100% 
## 0.000000e+00 0.000000e+00 1.454567e+12 1.464156e+12 1.470562e+12

## [1] "##########################################"
## [1] "LibFM Parameter: c2_mean_play_time_interval"
##       0%      25%      50%      75%     100% 
##   -29.00     0.00     0.00 21669.77 91297.96

## [1] "##########################################"
## [1] "LibFM Parameter: c2_num_group_user"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.002598367

## [1] "##########################################"
## [1] "LibFM Parameter: c2_num_individual_user"
##   0%  25%  50%  75% 100% 
##    0    0    1    3   10

## [1] "##########################################"
## [1] "LibFM Parameter: c2_num_sessions"
##   0%  25%  50%  75% 100% 
##    0    0    1    3   10

## [1] "##########################################"
## [1] "LibFM Parameter: c2_start_time"
##           0%          25%          50%          75%         100% 
## 0.000000e+00 0.000000e+00 1.454566e+12 1.464144e+12 1.470562e+12

## [1] "##########################################"
## [1] "LibFM Parameter: c2_total_interactions"
##        0%       25%       50%       75%      100% 
##   0.00000   0.00000  19.00000  70.15285 227.00000

## [1] "##########################################"
## [1] "LibFM Parameter: c2_subject_literacy"
##        0%       25%       50%       75%      100% 
## 0.8314774 1.0000000 1.0000000 1.0000000 1.0000000

## [1] "##########################################"
## [1] "LibFM Parameter: c2_subject_literacy,numeracy"
##           0%          25%          50%          75%         100% 
## 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0007423905

## [1] "##########################################"
## [1] "LibFM Parameter: c2_subject_numeracy"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.0237565

## [1] "##########################################"
## [1] "LibFM Parameter: c2_subject_Unknown"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.1440238

## [1] "##########################################"
## [1] "LibFM Parameter: c2_contentType_Collection"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.0701559

## [1] "##########################################"
## [1] "LibFM Parameter: c2_contentType_Game"
##         0%        25%        50%        75%       100% 
## 0.00000000 0.00000000 0.00000000 0.00000000 0.07089829

## [1] "##########################################"
## [1] "LibFM Parameter: c2_contentType_Story"
##   0%  25%  50%  75% 100% 
##    0    0    1    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c2_contentType_Unknown"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.1440238

## [1] "##########################################"
## [1] "LibFM Parameter: c2_contentType_Worksheet"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.1625835

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_English"
##   0%  25%  50%  75% 100% 
##    0    0    0    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_Hindi"
##   0%  25%  50%  75% 100% 
##    0    0    0    1    1

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_Kannada"
##         0%        25%        50%        75%       100% 
## 0.00000000 0.00000000 0.00000000 0.00000000 0.01336303

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_Other"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.001484781

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_Tamil"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.001484781

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_Telugu"
##          0%         25%         50%         75%        100% 
## 0.000000000 0.000000000 0.000000000 0.000000000 0.003340757

## [1] "##########################################"
## [1] "LibFM Parameter: c2_language_Unknown"
##        0%       25%       50%       75%      100% 
## 0.0000000 0.0000000 0.0000000 0.0000000 0.1440238

## [1] "##########################################"
## [1] "LibFM Parameter: screen_size"
##   0%  25%  50%  75% 100% 
## 3.89 4.65 5.46 5.71 7.42

## [1] "##########################################"
## [1] "LibFM Parameter: external_disk"
##      0%     25%     50%     75%    100% 
##  1.2700  5.0800 11.5800 12.9575 25.5900

## [1] "##########################################"
## [1] "LibFM Parameter: internal_disk"
##      0%     25%     50%     75%    100% 
##  0.0000  0.0000  0.0000  0.0000 13.2953

## [1] "##########################################"
## [1] "LibFM Parameter: primary_camera"
##   0%  25%  50%  75% 100% 
##    0    6    8   13   22

## [1] "##########################################"
## [1] "LibFM Parameter: secondary_camera"
##   0%  25%  50%  75% 100% 
##    0    2    3    5    8