From b92a3aa37a1968b7129cdb2b7ebaf9beda981428 Mon Sep 17 00:00:00 2001 From: Primoz Date: Tue, 25 Oct 2022 15:25:22 +0000 Subject: [PATCH] Remove unwanted output or other error producing code. --- src/data/datetime/assign_to_time_segment.R | 10 ---------- src/features/all_cleaning_overall/straw/main.py | 4 ++-- 2 files changed, 2 insertions(+), 12 deletions(-) diff --git a/src/data/datetime/assign_to_time_segment.R b/src/data/datetime/assign_to_time_segment.R index c18f042a..b7b9d8da 100644 --- a/src/data/datetime/assign_to_time_segment.R +++ b/src/data/datetime/assign_to_time_segment.R @@ -5,15 +5,11 @@ options(scipen=999) assign_rows_to_segments <- function(data, segments){ # This function is used by all segment types, we use data.tables because they are fast - print(nrow(data)) - print(ncol(data)) data <- data.table::as.data.table(data) data[, assigned_segments := ""] for(i in seq_len(nrow(segments))) { segment <- segments[i,] - print(segment) - print(data[segment$segment_start_ts<= timestamp & segment$segment_end_ts >= timestamp]) data[segment$segment_start_ts<= timestamp & segment$segment_end_ts >= timestamp, assigned_segments := stringi::stri_c(assigned_segments, segment$segment_id, sep = "|")] @@ -21,12 +17,6 @@ assign_rows_to_segments <- function(data, segments){ data[,assigned_segments:=substring(assigned_segments, 2)] data - - test <- # print multiple columns - data %>% - dplyr::filter(is.na(assigned_segments)) - - test %>% as_tibble() %>% print(n=50) } assign_to_time_segment <- function(sensor_data, time_segments, time_segments_type, include_past_periodic_segments, most_common_tz){ diff --git a/src/features/all_cleaning_overall/straw/main.py b/src/features/all_cleaning_overall/straw/main.py index 9474a514..642d0a44 100644 --- a/src/features/all_cleaning_overall/straw/main.py +++ b/src/features/all_cleaning_overall/straw/main.py @@ -14,7 +14,7 @@ def straw_cleaning(sensor_data_files, provider, target): features = pd.read_csv(sensor_data_files["sensor_data"][0]) - features = features[features['local_segment_label'] == 'working_day'] # Filtriranje ustreznih časovnih segmentov + # features = features[features['local_segment_label'] == 'working_day'] # Filtriranje ustreznih časovnih segmentov # print(features) # sys.exit() @@ -191,7 +191,7 @@ def straw_cleaning(sensor_data_files, provider, target): if esm not in features: features[esm] = esm_cols[esm] - graph_bf_af(features, "11correlation_drop") + graph_bf_af(features, "10correlation_drop") # (10) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME if features.isna().any().any():