Resolve "Frequency and average time Calculator"

Closes #14 (closed)

src/kg_maker.py

 import pandas as pd
+from loguru import logger
+from collections import defaultdict
 
 class KgMaker:
-
+    
     def __init__(self, df: pd.DataFrame, main_columns_dict: dict) -> None:
         self.df = df
         self.main_columns_dict = main_columns_dict
+        
+    def calculate_metrics(self):
+        
+        timestamp = self.main_columns_dict["timestamp"]
+        activity= self.main_columns_dict["activity"]
+        case_id = self.main_columns_dict["case_id"]
+        
+        self.df = self.df.sort_values(by=[case_id, timestamp])
+
+        transitions = defaultdict(int)
+        times = defaultdict(list)
+
+        grouped = self.df.groupby(case_id)
 
+        for case_id, group in grouped:
+            activities = list(group[activity])
+            timestamps = list(group[timestamp])
+            for i in range(len(activities) - 1):
+                transition = (activities[i], activities[i + 1])
+                transitions[transition] += 1
+                time_diff = (timestamps[i + 1] - timestamps[i]).total_seconds() / 3600  # Convert to hours
+                times[transition].append(time_diff)
+  
+        average_times = {transition: sum(times_list) / len(times_list) for transition, times_list in times.items()}
+
+        transitions_df = pd.DataFrame(transitions.items(), columns=['Transition', 'Frequency'])
+        average_times_df = pd.DataFrame(average_times.items(), columns=['Transition', 'Average Time'])
+
+        transitions_df[['Source', 'Target']] = pd.DataFrame(transitions_df['Transition'].tolist(), index=transitions_df.index)
+        average_times_df[['Source', 'Target']] = pd.DataFrame(average_times_df['Transition'].tolist(), index=average_times_df.index)
+        average_times_df = average_times_df.drop(columns=['Transition'])
+        transitions_df = transitions_df.drop(columns=['Transition'])
+        transitions_df = transitions_df.merge(average_times_df, on=['Source', 'Target'], how='left')
+        
+        return transitions_df
+    
     def group_meta_data(self)->pd.DataFrame:
         columns_all=self.df.columns
         meta_data=[]
@@ -15,8 +52,6 @@ class KgMaker:
                 
         columns_all=["activity"] + meta_data
         df_new=self.df[columns_all].copy()
-        
         aggregated_df_first = df_new.groupby("activity").first().reset_index()
+        
         return aggregated_df_first
-    
-    
\ No newline at end of file