Simplifying the code structure... Primarily combining the two separate data frames for data and flows to make analysis less complex and cumbersome.

defs/computing.py

@@ -196,10 +196,11 @@ class OFRSample:
 
 class OFRAnalyser:
 
-    def __init__(self, data_source_file, sample_number_list, data_separator = ',') -> None:
+    def __init__(self, data_source_file, flows_source_file, sample_number_list, data_separator = ',') -> None:
         
         self.data_source_file = data_source_file
-        self.flow_source_file = None
+        self.flows_source_file = flows_source_file
+        self.sample_number_list = sample_number_list
         self.__data_separator = data_separator
 
         with open(self.data_source_file, 'r', errors = 'ignore') as file:
@@ -211,14 +212,12 @@ class OFRAnalyser:
                     continue
 
         self.max_samples = max_sample_number
-        self.sample_number_list = sample_number_list
-
         self.data = None
-        self.flow_data = None
-
 
     def __sample_number_list_check(self, sample_number_list) -> None:
 
+        # TODO: implement a similar check for the flow data file!
+
         last_sample = sample_number_list[-1]
 
         if last_sample > self.max_samples:
@@ -228,24 +227,83 @@ class OFRAnalyser:
 
         self.__sample_number_list_check(self.sample_number_list)
 
-        numbers = []
-        lengths = []
-        surfaces = []
-        volumes = []
-        densities = []
-        masses = []
-        times = []
+        numbers_of_sample       = []
+        number_concentrations   = []
+        length_concentrations   = []
+        surface_concentrations  = []
+        volume_concentrations   = []
+        aerosol_densities       = []
+        mass_concentrations     = []
+        starting_times          = []
+        stopping_times          = []
+        sampling_times          = []
+        dry_air_flows           = []
+        ozone_flows             = []
+        species_flows           = []
+        total_flows             = []
+        cnc_flows               = []
 
         for sample_number in self.sample_number_list:
             sample = OFRSample(source_file=self.data_source_file, sample_number = sample_number, data_separator = self.__data_separator)
 
-            numbers.append(sample.Count.integrate())
-            lengths.append(sample.Length.integrate() / 1E6)
-            surfaces.append(sample.Surface.integrate() / 1E12)
-            volumes.append(sample.Volume.integrate() / 1E9)
-            densities.append(sample.SOA_density)
-            masses.append(sample.Mass.integrate() / 1E12)
-            times.append(sample_number * sample.sample_time)
+            numbers_of_sample.append(sample_number)
+            number_concentrations.append(sample.Count.integrate())
+            length_concentrations.append(sample.Length.integrate() / 1E6)
+            surface_concentrations.append(sample.Surface.integrate() / 1E12)
+            volume_concentrations.append(sample.Volume.integrate() / 1E9)
+            aerosol_densities.append(sample.SOA_density)
+            mass_concentrations.append(sample.Mass.integrate() / 1E12)
+
+            if sample_number == 1:
+                starting_times.append(0.00)
+                stopping_times.append(sample.sample_time)
+            
+            starting_times.append(stopping_times[-1])
+            stopping_times.append(stopping_times[-1] + sample.sample_time)
+
+        local_dry_air_flows     = []
+        local_ozone_flows = []
+        local_species_flows = []
+        local_cpc_flows = []
+
+        out_flag = False
+
+        with open(self.flow_source_file, 'r', errors='ignore') as file:
+            for line_counter, line in enumerate(file.readlines()):
+
+                if out_flag == True:
+                    continue
+
+                i = 0
+
+                if line_counter == 6:
+                    items = line.split()
+
+                    while i <= items:
+                        pass
+
+                    dry_air_flows.append(float(items[0]))
+                    species_flows.append(float(items[1]))
+                    ozone_flows.append(float(items[2]))
+                    cnc_flows.append(float(items[-1]))
+                    starts.append(0)
+                    stops.append(float(items[3]) * float(items[4]))
+                    smpls.append(float(items[4]))
+                    i += 1
+                elif line_counter > 6 and not line.startswith('-'):
+                    items = line.split()
+                    dry_air_flows.append(float(items[0]))
+                    species_flows.append(float(items[1]))
+                    ozone_flows.append(float(items[2]))
+                    cnc_flows.append(float(items[-1]))
+                    starts.append(stops[i-1])
+                    stops.append(stops[i-1] + float(items[3]) * float(items[4]))
+                    smpls.append(float(items[4]))
+                    i += 1
+                if line_counter > 6 and line.startswith('-'):
+                    out_flag = True
+                else:
+                    continue
 
         self.data = pd.DataFrame({'Sample': self.sample_number_list,
                                   'Number (#/cm^3)': numbers,

main.py

@@ -7,13 +7,11 @@ from pathlib import Path
 
 # Path to the source file
 source_file = Path(r"C:\Users\tschan_d\Documents\data_local\20260612_SET02_EXP01_full.txt")
-flow_source_file = Path(r"C:\Users\tschan_d\Documents\data_local\20260612_SET02_EXP01_full_flows.txt")
+flows_source_file = Path(r"C:\Users\tschan_d\Documents\data_local\20260612_SET02_EXP01_full_flows.txt")
 
-analyser = OFRAnalyser(data_source_file=source_file, sample_number_list=range(1, 157))
+analyser = OFRAnalyser(data_source_file=source_file, flows_source_file=flows_source_file, sample_number_list=range(1, 157))
 analyser.GetData()
-analyser.GetFlowData(flow_source_file=flow_source_file)
-print(analyser.flow_data)
-analyser.GetMassProductionRates()
+print(analyser.data)
 
 
 # %%

run/OFR_Analysis/202607023_OFR_Analysis_01.ipynb

@@ -91,7 +91,7 @@
    "id": "041fc7b6",
    "metadata": {},
    "source": [
-    "## Now let's load the data for the entire sampling experiment:"
+    "## Now let's load the data for the entire sampling experiment and process it!"
    ]
   },
   {