Phone wifi visible inspection (WIP)

src/features/all_cleaning_individual/straw/main.py

@@ -22,8 +22,6 @@ def straw_cleaning(sensor_data_files, provider):
         target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config
         features = features[features['phone_esm_straw_' + target].notna()].reset_index()
 
-    test_cols = [col for col in features.columns if 'phone_calls' in col or 'phone_messages' in col]
-
     # TODO: reorder the cleaning steps so it makes sense for the analysis
     # TODO: add conditions that differentiates cleaning steps for standardized and nonstandardized features, for this
     # the snakemake rules will also have to come with additional parameter (in rules/features.smk)
@@ -69,7 +67,7 @@ def straw_cleaning(sensor_data_files, provider):
     # (3) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved)
     features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]]
 
-    # (4) REMOVE COLS WHERE VARIANCE IS 0
+    # (4) REMOVE COLS WHERE VARIANCE IS 0 TODO: preveri za local_segment stolpce
     if provider["COLS_VAR_THRESHOLD"]:
         features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True)
     
@@ -104,12 +102,10 @@ def straw_cleaning(sensor_data_files, provider):
     ## STANDARDIZATION - should it happen before or after kNN imputation?
     # TODO: check if there are additional columns that need to be excluded from the standardization
     excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']
-    excluded_columns += [col for col in features.columns if "level_1" in col]
-    
     features.loc[:, ~features.columns.isin(excluded_columns)] = StandardScaler().fit_transform(features.loc[:, ~features.columns.isin(excluded_columns)])
 
     # KNN IMPUTATION
-    impute_cols = [col for col in features.columns if col not in ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime']]
+    impute_cols = [col for col in features.columns if col not in excluded_columns]
     features[impute_cols] = impute(features[impute_cols], method="knn")
 
 

src/features/phone_wifi_visible/rapids/main.R

@@ -9,9 +9,11 @@ compute_wifi_feature <- function(data, feature, time_segment){
               "countscans" = data %>% summarise(!!feature := n()),
               "uniquedevices" = data %>% summarise(!!feature := n_distinct(bssid)))
     return(data)
+
    } else if(feature == "countscansmostuniquedevice"){
      # Get the most scanned device
-    mostuniquedevice <- data %>% 
+    mostuniquedevice <- data %>%
+      filter(bssid != "") %>% 
       group_by(bssid) %>% 
       mutate(N=n()) %>% 
       ungroup() %>%
@@ -21,12 +23,19 @@ compute_wifi_feature <- function(data, feature, time_segment){
 
     data <- data %>% filter_data_by_segment(time_segment)
 
+    print(data %>% 
+             filter(bssid == mostuniquedevice) %>%
+             group_by(local_segment) %>% 
+             summarise(!!feature := n()))
+
+    raise
+
     return(data %>% 
              filter(bssid == mostuniquedevice) %>%
              group_by(local_segment) %>% 
-             summarise(!!feature := n()) %>%
+             summarise(!!feature := n())
-             mutate_all(~replace(., is.na(.), 0))
     )
+
   }
 }
 
@@ -46,7 +55,6 @@ rapids_features <- function(sensor_data_files, time_segment, provider){
     feature <- compute_wifi_feature(wifi_data, feature_name, time_segment)
     features <- merge(features, feature, by="local_segment", all = TRUE)
   }
-
+  # features <- features %>% mutate_all(~replace(., is.na(.), 0))
-  features <- features %>% mutate_all(~replace(., is.na(.), 0))
   return(features)
 }