Skip to content

Instantly share code, notes, and snippets.

@dkhurana1306
Last active September 5, 2016 13:30
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save dkhurana1306/b4cac9fbbc4efa23be666126d5331d30 to your computer and use it in GitHub Desktop.
Save dkhurana1306/b4cac9fbbc4efa23be666126d5331d30 to your computer and use it in GitHub Desktop.
data_higgs_undefined = data[data$higgs_defined == 0,]
data_higgs_0 = data[data$higgs_defined == 1 & data$num_jet == 0,]
data_higgs_1 = data[data$higgs_defined == 1 & data$num_jet == 1,]
data_higgs_2_3 = data[data$higgs_defined == 1 & data$num_jet == 2,]
data.submission_higgs_undefined = data.submission[data.submission$higgs_defined == 0,]
data.submission_higgs_0 = data.submission[data.submission$higgs_defined == 1 & data.submission$num_jet == 0,]
data.submission_higgs_1 = data.submission[data.submission$higgs_defined == 1 & data.submission$num_jet == 1,]
data.submission_higgs_2_3 = data.submission[data.submission$higgs_defined == 1 & data.submission$num_jet == 2,]
drop_columns_0 = as.character(c("DER_deltaeta_jet_jet","DER_mass_jet_jet","DER_prodeta_jet_jet","DER_lep_eta_centrality",
"PRI_jet_num", "PRI_jet_leading_pt","PRI_jet_leading_eta","PRI_jet_leading_phi","PRI_jet_subleading_pt",
"PRI_jet_subleading_eta","PRI_jet_subleading_phi","PRI_jet_all_pt","higgs_defined","num_jet"))
drop_columns_1 = as.character(c("DER_deltaeta_jet_jet","DER_mass_jet_jet","DER_prodeta_jet_jet","DER_lep_eta_centrality","PRI_jet_num",
"PRI_jet_subleading_pt", "PRI_jet_subleading_eta","PRI_jet_subleading_phi","PRI_jet_all_pt","higgs_defined","num_jet"))
drop_columns_2_3 = as.character(c("higgs_defined","num_jet"))
data_higgs_0_cleaned = data_higgs_0[,-which(names(data_higgs_0) %in% drop_columns_0)]
data_higgs_1_cleaned = data_higgs_1[,-which(names(data_higgs_1) %in% drop_columns_1)]
data_higgs_2_3_cleaned = data_higgs_2_3[,-which(names(data_higgs_2_3) %in% drop_columns_2_3)]
data.submission_higgs_0_cleaned = data.submission_higgs_0[,-which(names(data.submission_higgs_0) %in% drop_columns_0)]
data.submission_higgs_1_cleaned = data.submission_higgs_1[,-which(names(data.submission_higgs_1) %in% drop_columns_1)]
data.submission_higgs_2_3_cleaned = data.submission_higgs_2_3[,-which(names(data.submission_higgs_2_3) %in% drop_columns_2_3)]
data_higgs_0_cleaned_scaled = as.data.frame(scale(data_higgs_0_cleaned[,-c(1,ncol(data_higgs_0_cleaned),ncol(data_higgs_0_cleaned)-1)]))
data_higgs_0_cleaned_scaled$EventId = data_higgs_0_cleaned$EventId
data_higgs_0_cleaned_scaled$Weight = data_higgs_0_cleaned$Weight
data_higgs_0_cleaned_scaled$Label = data_higgs_0_cleaned$Label
data_higgs_1_cleaned_scaled = as.data.frame(scale(data_higgs_1_cleaned[,-c(1,ncol(data_higgs_1_cleaned),ncol(data_higgs_1_cleaned)-1)]))
data_higgs_1_cleaned_scaled$EventId = data_higgs_1_cleaned$EventId
data_higgs_1_cleaned_scaled$Weight = data_higgs_1_cleaned$Weight
data_higgs_1_cleaned_scaled$Label = data_higgs_1_cleaned$Label
data_higgs_2_3_cleaned_scaled = as.data.frame(scale(data_higgs_2_3_cleaned[,-c(1,ncol(data_higgs_2_3_cleaned),ncol(data_higgs_2_3_cleaned)-1)]))
data_higgs_2_3_cleaned_scaled$EventId = data_higgs_2_3_cleaned$EventId
data_higgs_2_3_cleaned_scaled$Weight = data_higgs_2_3_cleaned$Weight
data_higgs_2_3_cleaned_scaled$Label = data_higgs_2_3_cleaned$Label
data.submission_higgs_0_cleaned_scaled = as.data.frame(scale(data.submission_higgs_0_cleaned[,-1]))
data.submission_higgs_0_cleaned_scaled$EventId = data.submission_higgs_0_cleaned$EventId
data.submission_higgs_1_cleaned_scaled = as.data.frame(scale(data.submission_higgs_1_cleaned[,-1]))
data.submission_higgs_1_cleaned_scaled$EventId = data.submission_higgs_1_cleaned$EventId
data.submission_higgs_2_3_cleaned_scaled = as.data.frame(scale(data.submission_higgs_2_3_cleaned[,-1]))
data.submission_higgs_2_3_cleaned_scaled$EventId = data.submission_higgs_2_3_cleaned$EventId
(nrow(data_higgs_2_3_cleaned_scaled)* (ncol(data_higgs_2_3_cleaned_scaled)-3)+
nrow(data_higgs_1_cleaned_scaled)* (ncol(data_higgs_1_cleaned_scaled)-3)+
nrow(data_higgs_0_cleaned_scaled)*(ncol(data_higgs_0_cleaned_scaled)-3)) / (nrow(data)*(ncol(data)-3))
# 0.6051578
(nrow(data.submission_higgs_2_3_cleaned_scaled)* (ncol(data.submission_higgs_2_3_cleaned_scaled)-1)+
nrow(data.submission_higgs_1_cleaned_scaled)* (ncol(data.submission_higgs_1_cleaned_scaled)-1)+
nrow(data.submission_higgs_0_cleaned_scaled)*(ncol(data.submission_higgs_0_cleaned_scaled)-1)) / (nrow(data.submission)*(ncol(data.submission)-1))
#0.6054414
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment