michael021997

"""
General Classification Framework

A flexible framework for classification tasks with feature importance analysis,
hyperparameter tuning, threshold optimization, and visualization.
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

michael021997

"""
General Classification Framework for PySpark

A flexible framework for classification tasks with feature importance analysis,
hyperparameter tuning using Optuna, threshold optimization, and visualization.
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

michael021997

# Enhanced PySpark Classification Framework
# This framework combines PySpark's distributed processing capabilities with 
# scikit-learn's visualization and evaluation metrics from the General Classification Framework

import optuna
from pyspark.sql import SparkSession
from pyspark.sql.functions import col, when, count, lit, variance, corr, row_number, udf
from pyspark.sql.types import FloatType
from pyspark.sql import Window
from pyspark.sql import functions as F

michael021997

"""
Enhanced Classification Framework

A flexible framework for classification tasks with feature selection, 
class imbalance handling, hyperparameter tuning, threshold optimization, and visualization.
Combines elements from both scikit-learn and PySpark frameworks.
"""

import pandas as pd
import numpy as np

michael021997

import pandas as pd
import numpy as np

pd.set_option('display.max_columns', None)  # Show all columns

import matplotlib.pyplot as plt
from datetime import datetime, timedelta
from dateutil.relativedelta import relativedelta
from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error
from sklearn.ensemble import RandomForestRegressor

michael021997

import pandas as pd
import numpy as np
from datetime import datetime
from dateutil.relativedelta import relativedelta
import matplotlib.pyplot as plt

from prophet_model import *
 
# Feature tracking dictionary to store information about each feature
feature_tracking = {}

michael021997

import pandas as pd
import os
import glob
from datetime import datetime, timedelta
import concurrent.futures
import numpy as np
from calendar import monthrange

def convert_to_monthly(df):
    """

michael021997

import pandas as pd
import numpy as np
from datetime import datetime
from dateutil.relativedelta import relativedelta
import matplotlib.pyplot as plt

from prophet_model import *
 
# Feature tracking dictionary to store information about each feature
feature_tracking = {}

michael021997

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from datetime import datetime

def calculate_monthly_yoy_fuel_burn(input_file, output_file=None):
    """
    Calculate YoY monthly fuel burn from monthly historical data.
    
    Args:

michael021997

"""
Enhanced Fuel Burn Prediction Module (Part 1: Feature Engineering)

This combined module provides two approaches for predicting fuel burn metrics:
1. Original approach: Directly predict YoY Fuel Burn
2. New approach: Predict raw Fuel Burn values and derive YoY metrics
"""

import pandas as pd
import numpy as np