Merge pull request #1 from wizeline/feature-template-files

Feature template files

.gitignore

@@ -1,7 +1,3 @@
-
-# Dependency directories
-node_modules/
-
 # dotenv environment variable files
 .env
 
@@ -21,4 +17,6 @@ node_modules/
 *.mov
 *.wmv
 
-# Output files from project
+# Input and Output files from project
+/output_files
+/input_files

README.md

@@ -37,9 +37,9 @@ ___
 * **@author:** Fabián Portillo González 
 * **@github user:** fabianpg95
 * **@author:** Narda Ballesteros
-* **@github user:** 
+* **@github user:** NardaBallesterosW
 * **@author:** Fernanda Meza
-* **@github user:** 
+* **@github user:** fernanda-meza-wizeline
 * **@author:** José Manuel Hidalgo
-* **@github user:** 
+* **@github user:** JoseHidalgoW
 ___

requirements.txt

@@ -0,0 +1,12 @@
+certifi==2024.7.4
+charset-normalizer==3.3.2
+idna==3.7
+numpy==2.0.0
+pandas==2.2.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+requests==2.32.3
+six==1.16.0
+tzdata==2024.1
+urllib3==2.2.2

scripts/run_tests.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+# Activate the virtual environment
+python3 -m venv venv
+source venv/bin/activate
+
+# Run tests with pytest
+pytest src/tests
+
+# Deactivate the virtual environment
+deactivate

setup.py

@@ -0,0 +1,36 @@
+from setuptools import setup, find_packages
+
+with open("README.md", "r") as fh:
+    long_description = fh.read()
+
+setup(
+    name="sports-highlight-genai",
+    version="0.1.0",
+    author="Fabián Portillo, Narda Ballesteros, Jose Hialgo, Fernanda Meza",
+    author_email="[email protected], [email protected], [email protected], [email protected]",
+    description="Develop a GenAI-powered tool that automatically identifies key moments in sports events to generate highlight reels. This project leverages real-time statistical data, video processing, and image analysis to create engaging sports highlights. Optional features include video editing capabilities and social media integration for sharing highlights.",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/wizeline/sports-highlight-genai",
+    packages=find_packages(where="src"),
+    package_dir={"": "src"},
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.7',
+    install_requires=[
+        "boto3==1.24.28",
+        "requests==2.28.1",
+        "flask==2.1.3",
+        "python-dotenv==0.19.2",
+        "gunicorn==20.1.0",
+        "pytest==7.1.2",
+    ],
+    entry_points={
+        'console_scripts': [
+            'sports-highlight-genai=src.app:main',
+        ],
+    },
+)

src/app.py

@@ -0,0 +1,83 @@
+# src/app.py
+
+from services.mlb_api import MLBAPI
+from handlers.data_management import (
+    process_player_data, process_free_agent_data, process_schedule_data,
+    process_team_data, process_team_history_data, process_team_coaches_data,
+    process_team_personnel_data, process_team_affiliates_data, process_team_roster_data
+)
+from config import Config
+
+def run_data_processing():
+    api = MLBAPI(auth_key=Config.MLB_API_KEY)
+
+    # Process player data
+    person_ids = [660271]  # Reemplaza con IDs de jugadores reales como una lista de enteros
+    print("Fetching and processing player data...")
+    player_data = api.get_players(person_ids)
+    processed_player_data = process_player_data(player_data)
+    print("Processed Player Data:")
+    print(processed_player_data)
+
+    # Process free agent data
+    season_id = 2024  # Reemplaza con un ID de temporada real
+    print("Fetching and processing free agent data...")
+    free_agent_data = api.get_free_agents(season_id)
+    processed_free_agent_data = process_free_agent_data(free_agent_data)
+    print("Processed Free Agent Data:")
+    print(processed_free_agent_data)
+
+    # Process schedule data
+    date = '2024-07-02'  # Reemplaza con una fecha real
+    print("Fetching and processing schedule data...")
+    schedule_data = api.get_schedule(date)
+    processed_schedule_data = process_schedule_data(schedule_data)
+    print("Processed Schedule Data:")
+    print(processed_schedule_data)
+
+    # Process team data
+    team_id = 119  # Reemplaza con un ID de equipo real
+    print("Fetching and processing team data...")
+    team_data = api.get_teams(team_id)
+    processed_team_data = process_team_data(team_data)
+    print("Processed Team Data:")
+    print(processed_team_data)
+
+    # Process team history data
+    team_ids = [119]  # Reemplaza con IDs de equipos reales como una lista de enteros
+    print("Fetching and processing team history data...")
+    team_history_data = api.get_teams_history(team_ids)
+    processed_team_history_data = process_team_history_data(team_history_data)
+    print("Processed Team History Data:")
+    print(processed_team_history_data)
+
+    # Process team coaches data
+    print("Fetching and processing team coaches data...")
+    team_coaches_data = api.get_teams_coaches(team_ids)
+    processed_team_coaches_data = process_team_coaches_data(team_coaches_data)
+    print("Processed Team Coaches Data:")
+    print(processed_team_coaches_data)
+
+    # Process team personnel data
+    print("Fetching and processing team personnel data...")
+    team_personnel_data = api.get_teams_personnel(team_ids)
+    processed_team_personnel_data = process_team_personnel_data(team_personnel_data)
+    print("Processed Team Personnel Data:")
+    print(processed_team_personnel_data)
+
+    # Process team affiliates data
+    print("Fetching and processing team affiliates data...")
+    team_affiliates_data = api.get_teams_affiliates(team_ids)
+    processed_team_affiliates_data = process_team_affiliates_data(team_affiliates_data)
+    print("Processed Team Affiliates Data:")
+    print(processed_team_affiliates_data)
+
+    # Process team roster data
+    print("Fetching and processing team roster data...")
+    team_roster_data = api.get_teams_roster(team_ids)
+    processed_team_roster_data = process_team_roster_data(team_roster_data)
+    print("Processed Team Roster Data:")
+    print(processed_team_roster_data)
+
+if __name__ == '__main__':
+    run_data_processing()

src/config.py

@@ -0,0 +1,33 @@
+# src/config.py
+
+import os
+from dotenv import load_dotenv
+
+# Load environment variables from a .env file
+load_dotenv()
+
+class Config:
+    MLB_API_KEY = os.getenv('MLB_API_KEY')
+
+    """
+    # AWS credentials
+    AWS_ACCESS_KEY_ID = os.getenv('AWS_ACCESS_KEY_ID')
+    AWS_SECRET_ACCESS_KEY = os.getenv('AWS_SECRET_ACCESS_KEY')
+    
+    # Facebook credentials
+    FACEBOOK_APP_ID = os.getenv('FACEBOOK_APP_ID')
+    FACEBOOK_APP_SECRET = os.getenv('FACEBOOK_APP_SECRET')
+    FACEBOOK_ACCESS_TOKEN = os.getenv('FACEBOOK_ACCESS_TOKEN')
+    
+    # Instagram credentials
+    INSTAGRAM_ACCESS_TOKEN = os.getenv('INSTAGRAM_ACCESS_TOKEN')
+    
+    # YouTube credentials
+    YOUTUBE_API_KEY = os.getenv('YOUTUBE_API_KEY')
+
+    # TikTok credentials
+    TIKTOK_ACCESS_TOKEN = os.getenv('TIKTOK_ACCESS_TOKEN')
+    """
+
+if __name__ == "__main__":
+    print("MLB_API_KEY:", Config.MLB_API_KEY)

src/handlers/data_management.py

@@ -0,0 +1,149 @@
+import pandas as pd
+
+def process_player_data(data):
+    if 'players' in data:
+        data = data['players']
+    if not data or not isinstance(data, list):
+        print("No player data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    # Convert JSON data to DataFrame
+    df = pd.DataFrame(data)
+
+    if 'status' in df.columns:
+        # Example of filtering data: select players with a specific attribute
+        filtered_df = df[df['status'] == 'active']
+    else:
+        print("Column 'status' not found in player data.")
+        filtered_df = pd.DataFrame()
+
+    return filtered_df
+
+def process_free_agent_data(data):
+    if 'free_agents' in data:
+        data = data['free_agents']
+    if not data or not isinstance(data, list):
+        print("No free agent data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of adding a new column
+    if 'available_since' in df.columns:
+        df['available_since'] = pd.to_datetime(df['available_since'])
+
+    return df
+
+def process_schedule_data(data):
+    if 'schedule' in data:
+        data = data['schedule']
+    if not data or not isinstance(data, list):
+        print("No schedule data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of sorting data by a specific column
+    if 'game_date' in df.columns:
+        df_sorted = df.sort_values(by='game_date')
+    else:
+        print("Column 'game_date' not found in schedule data.")
+        df_sorted = df
+
+    return df_sorted
+
+def process_team_data(data):
+    if 'teams' in data:
+        data = data['teams']
+    if not data or not isinstance(data, list):
+        print("No team data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of handling missing values
+    df.fillna('Unknown', inplace=True)
+    return df
+
+def process_team_history_data(data):
+    if data is None:
+        print("Received None for team history data.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    if 'team_history' in data:
+        data = data['team_history']
+    if not data or not isinstance(data, list):
+        print("No team history data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of grouping data
+    if {'year', 'wins', 'losses'}.issubset(df.columns):
+        df_grouped = df.groupby('year').agg({'wins': 'sum', 'losses': 'sum'})
+    else:
+        print("Columns 'year', 'wins', or 'losses' not found in team history data.")
+        df_grouped = pd.DataFrame()  # Retorna un DataFrame vacío si las columnas no están presentes
+
+    return df_grouped
+
+def process_team_coaches_data(data):
+    if 'team_coaches' in data:
+        data = data['team_coaches']
+    if not data or not isinstance(data, list):
+        print("No team coaches data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of merging with another DataFrame (uncomment and replace 'other_df' with actual DataFrame if needed)
+    # other_df = pd.DataFrame()  # Replace this with actual DataFrame
+    # df_merged = pd.merge(df, other_df, on='coach_id', how='left')
+
+    return df
+
+def process_team_personnel_data(data):
+    if 'team_personnel' in data:
+        data = data['team_personnel']
+    if not data or not isinstance(data, list):
+        print("No team personnel data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of filtering data by role
+    if 'role' in df.columns:
+        filtered_df = df[df['role'] == 'manager']
+    else:
+        print("Column 'role' not found in team personnel data.")
+        filtered_df = pd.DataFrame()
+
+    return filtered_df
+
+def process_team_affiliates_data(data):
+    if 'team_affiliates' in data:
+        data = data['team_affiliates']
+    if not data or not isinstance(data, list):
+        print("No team affiliates data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of renaming columns
+    df.rename(columns={'affiliation': 'affiliate_name'}, inplace=True)
+
+    return df
+
+def process_team_roster_data(data):
+    if 'team_roster' in data:
+        data = data['team_roster']
+    if not data or not isinstance(data, list):
+        print("No team roster data or data is not in expected format.")
+        return pd.DataFrame()  # Retorna un DataFrame vacío
+
+    df = pd.DataFrame(data)
+
+    # Example of adding a new column
+    df['roster_status'] = 'active'
+
+    return df