From 89d4e48c969649ce34148a559364efb0a32dfc18 Mon Sep 17 00:00:00 2001 From: LukaszChrostowski Date: Mon, 27 Nov 2023 14:35:00 +0100 Subject: [PATCH] more data --- .DS_Store | Bin 6148 -> 6148 bytes data/.DS_Store | Bin 8196 -> 8196 bytes data/{data_test.csv => data3_test.csv} | 38 +- data/data4.csv | 10166 +++++++++++++++++++++++ notebooks/dataCleaning.R | 34 +- 5 files changed, 10216 insertions(+), 22 deletions(-) rename data/{data_test.csv => data3_test.csv} (70%) create mode 100644 data/data4.csv diff --git a/.DS_Store b/.DS_Store index 760fdac948d20057a81cb42423e3e3ba0e2252a5..455d0f79c80e87a28ec34ac334d629f3adb91ff2 100644 GIT binary patch delta 585 zcmZ8fJ#W)c6utL3q)sW=O^hj@67s?VSWGYx5+qciDiI0Afzrr!Ufd_#_sp}Kv@9v8 zKcH16X2ix)MNF`<^9MlUFLYyI!Ep>leaksI=iPJfmF}LsXYZS&Fn{pMJh*uci-*n6 z_FO2F^~(6D zPZT_+z0vxy*4~NIPsXv3r9PCD^5=nMy+*$u)5Q6Ycb>W1?SJuF>`M`bO%bz%3Eo-D zCQ0b#GVhDD`*fN{G_~SYD&rKp`shTF^CEOT8a8-MB#GGUxKg@2ptT)`r7KO>$lA9e z*JnJi?j1q)N>=syjOk#_2!K_s?`B*z{z^Gwsm%qaR<${rDOUASZmDns>hJ{CA%?f` z4nDvke1UK99gdKoju+9wTX+ZWVhtbQ3a;W)+(3pLhqDBNdD7J!bHLq{6rcw#B;XEO kl81r^<0a+yWKPx8^iU>mlwZnNGw!Qt1eumi9OI+%2OYbay#N3J delta 75 zcmZoMXfc=|#>B)qu~2NHo+2ab#(>?7jI5J+Shg}5n@>K>;=7rJotbg70>>BT&Fmcf d96+U;1v$PmPv#eKtqQ#TyH!u}^H^-OSFx!ch-WAg-(UbwS#2Hwr=94s7+yqnDgm$Pi% R%oD=AnO))=%f x1_threshold) # error here + } else { + res <- 0 + } + res + }, data$shot$freeze_frame, data$x1) + }, + error = function(e) { + # handle the error + print(paste("An error occurred:", e$message)) + }) + + data$shot <- data$shot %>% select(-freeze_frame, -statsbomb_xg, -key_pass_id) data$shot$body_part <- data$shot$body_part %>% select(-id) data$shot$technique <- data$shot$technique %>% select(-id) @@ -223,9 +243,17 @@ get_shots2 <- function(json_file) { file_names <- list.files(path = "data/la_liga_events/", pattern = "*.json") data_list <- lapply(paste("data/la_liga_events/", file_names, sep = ""), get_shots2) -combined_data <- do.call(rbind, data_list[1:10]) +combined_data <- do.call(rbind, data_list) # sample data data_test <- get_shots2("data/la_liga_events/303377.json") -write.csv(data_test, file = "data/data_test.csv") +write.csv(data_test, file = "data/data3_test.csv") + +##################### The fourth dataset ############################## + +data4 <- read.csv("data/data4.csv", nrows = 1000) +data1 <- read.csv("data/data1.csv", nrows = 1000) +data2 <- read.csv("data/data2.csv", nrows = 1000) +data3 <- read.csv("data/data3_test.csv", nrows = 1000) +