Added new salary-related terms and improved image outputs in salary.ipynb

salary_analytics/consistent_amount_analyzer.py

@@ -0,0 +1,58 @@
+"""
+Consistent amount transaction analysis module.
+"""
+
+import pandas as pd
+from .config import MODEL_CONFIG
+
+class ConsistentAmountAnalyzer:
+    def __init__(self, df):
+        self.df = df
+        self.const_df = None
+
+    def calculate_coefficient_of_variation(self, group):
+        """Calculate coefficient of variation for a group of transactions."""
+        amounts = group[group['initiated_by'] == 'C']['amount']
+        mean = amounts.mean()
+        std = amounts.std(ddof=0)
+
+        if mean == 0:
+            return float('nan')
+        return std / mean
+
+    def flag_consistent_amounts(self, group, cv_threshold=None):
+        """Flag accounts with low variance in transaction amounts."""
+        if cv_threshold is None:
+            cv_threshold = MODEL_CONFIG['cv_threshold']
+
+        filtered_group = group[group['initiated_by'] == 'C']
+        cv = self.calculate_coefficient_of_variation(filtered_group)
+        is_consistent = cv <= cv_threshold if not pd.isna(cv) else False
+
+        return pd.Series(
+            [is_consistent] * len(group),
+            index=group.index,
+            name='is_consistent_amount'
+        )
+
+    def identify_consistent_amount_accounts(self, cv_threshold=None):
+        """Identify accounts with consistent transaction amounts."""
+        if cv_threshold is None:
+            cv_threshold = MODEL_CONFIG['cv_threshold']
+
+        self.df = self.df.groupby('accountid').apply(
+            lambda group: self.flag_consistent_amounts(group, cv_threshold)
+        ).reset_index(level=0, drop=True)
+
+        self.const_df = self.df.copy()
+        return self.df
+
+    def get_consistent_amount_data(self):
+        """Get transactions identified as having consistent amounts."""
+        if self.const_df is None:
+            self.identify_consistent_amount_accounts()
+        
+        return self.const_df[
+            (self.const_df['is_consistent_amount']) &
+            (self.const_df['initiated_by'] == 'C')
+        ]