{"cells":[{"metadata":{"_uuid":"051d70d956493feee0c6d64651c6a088724dca2a","_execution_state":"idle","trusted":true},"cell_type":"code","source":"# This R environment comes with many helpful analytics packages installed\n# It is defined by the kaggle/rstats Docker image: https://github.com/kaggle/docker-rstats\n# For example, here's a helpful package to load\n\nlibrary(tidyverse) # metapackage of all tidyverse packages\nlibrary(magrittr)\nlibrary(data.table)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nlist.files(path = \"../input\")\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_folder <- '../input/siim-isic-melanoma-classification/'\ntrain_raw <- fread(paste(input_folder,'train.csv',sep=''))\ntest_raw <- fread(paste(input_folder,'test.csv',sep=''))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"head(train_raw)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_raw %>% group_by(patient_id) %>% summarise(count = n()) %>% arrange(desc(count)) %>% head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"table(train_raw$sex)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_raw %>% distinct(patient_id) %>% count()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_age <- train_raw %>% group_by(patient_id) %>% summarise(min_age = min(age_approx), max_age = max(age_approx)) \ntrain_age %>% mutate(age_range = max_age - min_age) %>% arrange(desc(age_range)) %>% head()\n## Age Range could be an indicator of how long they have been suffering from melanoma","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_affected <- train_raw %>% group_by(patient_id) %>% summarise(count_affected_parts = n_distinct(anatom_site_general_challenge)) %>% arrange(desc(count_affected_parts)) \ntrain_affected %>% head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"table(train_raw$diagnosis, train_raw$target)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"table(train_raw$benign_malignant, train_raw$target)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"name":"ir","display_name":"R","language":"R"},"language_info":{"name":"R","codemirror_mode":"r","pygments_lexer":"r","mimetype":"text/x-r-source","file_extension":".r","version":"3.6.3"}},"nbformat":4,"nbformat_minor":4}