chore: Remove commented code and unused imports in mapper-evaluation-single-pod.py and test.py

Author: argahsuknesib

mapper/e.py

@@ -0,0 +1,40 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Dummy data
+data_with_aggregator = {
+    'seconds_to_monitor': [10, 20, 30],
+    'stream_reader': [15, 25, 35],
+    'stream_processor': [20, 30, 40]
+}
+
+data_without_aggregator = {
+    'seconds_to_monitor': [10, 20, 30],
+    'stream_reader': [10, 20, 30],
+    'stream_processor': [18, 28, 38]
+}
+
+# Create DataFrames from dummy data
+df_with_aggregator = pd.DataFrame(data_with_aggregator)
+df_without_aggregator = pd.DataFrame(data_without_aggregator)
+
+# Set the index to 'seconds_to_monitor' for plotting
+df_with_aggregator.set_index('seconds_to_monitor', inplace=True)
+df_without_aggregator.set_index('seconds_to_monitor', inplace=True)
+
+# Plotting a stacked bar plot
+fig, ax = plt.subplots()
+
+# Stacked bar plot for 'stream_reader' and 'stream_processor' for each seconds_to_monitor
+df_with_aggregator.plot(kind='bar', stacked=True, ax=ax, color=['blue', 'orange'], width=0.4, position=1.5)
+df_without_aggregator.plot(kind='bar', stacked=True, ax=ax, color=['green', 'red'], width=0.4, position=-0.5)
+
+plt.xlabel('Seconds to Monitor')
+plt.ylabel('Latency')
+plt.title('Comparison of Latency with and without Aggregator')
+plt.legend(['Reader with Aggregator', 'Processor with Aggregator', 'Reader without Aggregator', 'Processor without Aggregator'])
+plt.xticks(rotation=45)
+plt.tight_layout()
+
+# Show the plot
+plt.show()

mapper/mapper-evaluation-single-pod.py

@@ -1,18 +1,16 @@
-import logging
-import sys
 from datetime import datetime
 import pandas as pandas
 import pytz
 
 # configure logging
-logger = logging.getLogger(__name__)
-logger.setLevel(logging.DEBUG)
-handler = logging.StreamHandler(sys.stdout)
-handler.setLevel(logging.DEBUG)
-formatter = logging.Formatter(
-    '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-handler.setFormatter(formatter)
-logger.addHandler(handler)
+# logger = logging.getLogger(__name__)
+# logger.setLevel(logging.DEBUG)
+# handler = logging.StreamHandler(sys.stdout)
+# handler.setLevel(logging.DEBUG)
+# formatter = logging.Formatter(
+#     '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+# handler.setFormatter(formatter)
+# logger.addHandler(handler)
 
 # template definitions
 TEMPLATE_TIME_MS = '<TIME_MS>'
@@ -304,15 +302,21 @@ def remove_whitespace(given_str):
     return ' '.join(given_str.split())
 
 
-def map_feather(file, sensors_to_map):
+def map_feather(file, sensors_to_map, number_of_events, sample_rate):
+    counter = 0
     file = pandas.read_feather(file)
     for sensor in sensors_to_map:
         df = file[file['Metric'] == sensor]
+        df['Sampling-Timestamp'] = pandas.to_datetime(df['Timestamp'].astype(str))
+        df.set_index('Sampling-Timestamp', inplace=True)
+        df.index = pandas.to_datetime(df.index)
         for index in df.index:
-            source = (df['Sensor'][index])
-            metric = (df['Metric'][index])
-            value = (df['Value'][index])
-            timestamp = (df['Timestamp'][index])
+            # df_resampled = df.resample(f'{sample_rate}S').first().reset_index()
+            df_resampled = df
+            source = (df_resampled['Sensor'][index])
+            metric = (df_resampled['Metric'][index])
+            value = (df_resampled['Value'][index])
+            timestamp = (df_resampled['Timestamp'][index])
             timestamp_str = str(timestamp)
             hour = timestamp_str[0:2]
             minute = timestamp_str[3:5]
@@ -323,7 +327,6 @@ def map_feather(file, sensors_to_map):
             else:
                 millisecond = timestamp_str[9:13] + 'Z'
 
-
             current_time = datetime.now()
             year = current_time.strftime("%Y")
             month = current_time.strftime("%m")
@@ -340,13 +343,18 @@ def map_feather(file, sensors_to_map):
                 'value': value,
                 'timestamp': time_value
             }
-            result = annotate_event(event)          
-
-            with open('/home/kush/Code/feather-RDF-mapper/data/rdfData/participant6.nt', 'a') as file:
+            result = annotate_event(event)  
+            with open('/home/kush/Code/feather-RDF-mapper/data/rdfData/accelerometer/acc-x-2min.nt', 'a') as file:
                 pass
-                file.write('\n')
-                file.write(result)
+                counter = counter + 1
+                if counter > number_of_events:
+                    break
+                else:
+                    file.write('\n')
+                    file.write(result)
 if __name__ == '__main__':
     file = 'data/dataset_participant6.feather'  
-    sensors = ['wearable.bvp']
-    map_feather(file= file, sensors_to_map= sensors)
+    # sensors = ['wearable.bvp']
+    # sensors = ['org.dyamand.types.health.SpO2']
+    sensors = ['wearable.acceleration.x']
+    map_feather(file= file, sensors_to_map= sensors, number_of_events= 120*32, sample_rate= 2)

mapper/read.py

@@ -0,0 +1,31 @@
+import os
+import pandas as pd
+
+# Initialize an empty DataFrame to store the final results
+final_dataframe = pd.DataFrame()
+
+# Define the folder path
+folder_path = '/home/kush/Dataset/protego_day/Protego_anom/'
+
+# Iterate through each folder
+for foldername in os.listdir(folder_path):
+    folder = os.path.join(folder_path, foldername)
+    
+    # Check if it's a directory
+    if os.path.isdir(folder):
+        file_path = os.path.join(folder, 'data.feather')
+        
+        # Check if the data.feather file exists
+        if os.path.exists(file_path):
+            # Read the feather file into a DataFrame
+            df = pd.read_feather(file_path)
+            print(df)
+            
+            # Filter for 'org.dyamand.types.health.SpO2' in the 'Metric' column
+            filtered_data = df[df['Metric'] == 'org.dyamand.types.health.SpO2']
+            
+            # Append the filtered data to the final DataFrame
+            final_dataframe = final_dataframe.concat(filtered_data)
+
+# Display the final DataFrame
+print(final_dataframe)