first commit

2025-05-17 03:52:41 -04:00
commit e869785624
24 changed files with 44883 additions and 0 deletions
@@ -0,0 +1,72 @@
+"""
+Configuration settings for the salary analytics package.
+"""
+
+import os
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Base directories
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+OUTPUT_DIR = os.path.join(BASE_DIR, "output")
+PLOTS_DIR = os.path.join(OUTPUT_DIR, "plots")
+CSV_DIR = os.path.join(OUTPUT_DIR, "csv")
+MODEL_DIR = os.path.join(OUTPUT_DIR, "models")
+
+# Create directories if they don't exist
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+os.makedirs(PLOTS_DIR, exist_ok=True)
+os.makedirs(CSV_DIR, exist_ok=True)
+os.makedirs(MODEL_DIR, exist_ok=True)
+
+# Database Configuration
+DB_CONFIG = {
+    "user": os.getenv("DB_USER", "salaryloan"),  # Default value as fallback
+    "password": os.getenv("DB_PASSWORD", "salaryloan"),
+    "name": os.getenv("DB_NAME", "salaryloan"),
+    "port": os.getenv("DB_PORT", "10532"),
+    "host": os.getenv("DB_HOST", "dev-data.simbrellang.net")
+}
+
+# Table Configuration
+TABLE_NAME = "customer_account_transaction_hx"
+BATCH_RESULTS_TABLE = "salary_analytics_batch_results"
+
+# Salary Keywords
+SALARY_KEYWORDS = [
+    "salary", "payroll", "income", "wage", "wages",
+    "earnings", "earning", "monthly pay", "net pay", "gross pay", "compensation",
+    "monthlypay", "netpay", "grosspay",
+    "remuneration", "stipend", "allowance", "bonus", "commission",
+    "pension", "retirement", "dividend", "benefits", "reimbursement",
+    "overtime", "incentive", "paycheck", "paycheque", "salary advance",
+    "monthly income", "income tax refund", "employer deposit",
+    "payroll deposit", "salary credit", "income credit", "salary transfer",
+    "income transfer", "salary received", "income received", "hr deposit",
+    "company deposit", "employer payment", "employee payment",
+    "sal",
+]
+
+# Model Configuration
+MODEL_CONFIG = {
+    "cv_threshold": 0.10,
+    "min_transactions": 3,
+    "threshold": 0.7,
+    "high_earner_threshold": 10000
+}
+
+# File Paths
+OUTPUT_PATHS = {
+    "high_earner_details": os.path.join(CSV_DIR, "high_earner_details.csv"),
+    "likely_salary_earner": os.path.join(CSV_DIR, "likely_salary_earner.csv"),
+    "final_table": os.path.join(CSV_DIR, "final_table.csv"),
+    "consistent_earners_plot": os.path.join(PLOTS_DIR, "consistent_earners_predictions.png"),
+    "inconsistent_earners_plot": os.path.join(PLOTS_DIR, "inconsistent_earners_predictions.png"),
+    "hypothesis_overlap_plot": os.path.join(PLOTS_DIR, "hypothesis_overlap.png"),
+    "consistent_model": os.path.join(MODEL_DIR, "consistent_model.joblib"),
+    "inconsistent_model": os.path.join(MODEL_DIR, "inconsistent_model.joblib"),
+    "consistent_scaler": os.path.join(MODEL_DIR, "consistent_scaler.joblib"),
+    "inconsistent_scaler": os.path.join(MODEL_DIR, "inconsistent_scaler.joblib")
+}