feat: Add configuration files and database requirements

Created comprehensive configuration framework:

Configuration files (config/):
- data_sources.yaml: Data source settings, retry/rate limiting config
- leagues.yaml: League mappings to soccerdata library IDs
- logging.yaml: Logging configuration (level, directory, handlers)

Environment configuration:
- .env.example: Database connection template and extraction settings

Dependencies:
- requirements-database.txt: Additional dependencies for database
  (psycopg2-binary, python-dotenv, PyYAML)

All configuration is centralized and environment-based for easy deployment.

Author: claude

.env.example

@@ -0,0 +1,16 @@
+# Database Configuration
+# Copy this file to .env and fill in your actual credentials
+
+# PostgreSQL Database Connection
+DB_HOST=localhost
+DB_PORT=5432
+DB_NAME=football_stats
+DB_USER=postgres
+DB_PASSWORD=your_password_here
+
+# Historical Loader Configuration
+START_SEASON=2021
+END_SEASON=2425
+BATCH_SIZE=100
+PARALLEL_WORKERS=1
+SKIP_COMPLETED=true

config/data_sources.yaml

@@ -0,0 +1,81 @@
+# Data Sources Configuration
+# Defines which data sources are enabled and extraction settings
+
+sources:
+  fbref:
+    enabled: true
+    priority: 1
+    description: "Football Reference (Opta data) - Most comprehensive statistics"
+    tables: 44
+
+  fotmob:
+    enabled: true
+    priority: 2
+    description: "FotMob - League tables and match statistics"
+    tables: 11
+
+  understat:
+    enabled: true
+    priority: 3
+    description: "Understat - Advanced xG metrics and shot coordinates"
+    tables: 7
+
+  whoscored:
+    enabled: true
+    priority: 4
+    description: "WhoScored - Detailed Opta event stream"
+    tables: 4
+
+  sofascore:
+    enabled: true
+    priority: 5
+    description: "Sofascore - Standings and schedules"
+    tables: 4
+
+  espn:
+    enabled: true
+    priority: 6
+    description: "ESPN - Schedules, matchsheets, and lineups"
+    tables: 3
+
+  clubelo:
+    enabled: true
+    priority: 7
+    description: "ClubElo - ELO ratings"
+    tables: 2
+
+  matchhistory:
+    enabled: true
+    priority: 8
+    description: "MatchHistory - Betting odds from 13+ bookmakers"
+    tables: 1
+
+  sofifa:
+    enabled: true
+    priority: 9
+    description: "SoFIFA - EA Sports FC player/team ratings"
+    tables: 6
+
+# Extraction settings
+extraction:
+  # Retry configuration for failed API calls
+  retry:
+    max_attempts: 3
+    initial_delay: 2  # seconds
+    max_delay: 60  # seconds
+    exponential_base: 2
+
+  # Rate limiting to avoid overloading APIs
+  rate_limiting:
+    enabled: true
+    requests_per_minute: 20
+    delay_between_requests: 3  # seconds
+
+  # Batch processing
+  batch:
+    size: 100  # records per batch for database insertion
+
+  # Error handling
+  error_handling:
+    continue_on_error: true  # Continue with next source if one fails
+    max_consecutive_failures: 5  # Stop after this many consecutive failures

config/leagues.yaml

@@ -0,0 +1,33 @@
+# Leagues Configuration
+# Maps standardized league names to soccerdata library IDs
+
+leagues:
+  - name: "ENG-Premier League"
+    soccerdata_id: "ENG-Premier League"
+    country: "England"
+    tier: 1
+    enabled: true
+
+  - name: "ESP-La Liga"
+    soccerdata_id: "ESP-La Liga"
+    country: "Spain"
+    tier: 1
+    enabled: true
+
+  - name: "GER-Bundesliga"
+    soccerdata_id: "GER-Bundesliga"
+    country: "Germany"
+    tier: 1
+    enabled: true
+
+  - name: "ITA-Serie A"
+    soccerdata_id: "ITA-Serie A"
+    country: "Italy"
+    tier: 1
+    enabled: true
+
+  - name: "FRA-Ligue 1"
+    soccerdata_id: "FRA-Ligue 1"
+    country: "France"
+    tier: 1
+    enabled: true

config/logging.yaml

@@ -0,0 +1,19 @@
+# Logging Configuration
+
+# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
+log_level: INFO
+
+# Directory for log files
+log_dir: logs
+
+# Enable file logging
+log_to_file: true
+
+# Enable console logging
+log_to_console: true
+
+# Log rotation (optional - implement in future)
+rotation:
+  enabled: false
+  max_bytes: 10485760  # 10 MB
+  backup_count: 5

requirements-database.txt

@@ -0,0 +1,11 @@
+# Additional Requirements for Football Statistics Database
+
+# Database
+psycopg2-binary>=2.9.0
+
+# Configuration
+python-dotenv>=1.0.0
+PyYAML>=6.0
+
+# Note: This extends the main requirements.txt file
+# Install both with: pip install -r requirements.txt -r requirements-database.txt