"""Calculate the area between the coordinates and the X-axis
"""
import typing
from pandas import read_parquet
def calc_area(file_name: str) -> typing.Any:
    """?積計算.
    Args:
    file_name: parquet?件路徑, eg: data.parquet
    Returns:
    計算后的結果
    """
    res = []
    # Load data from .parquet
    initial_data = read_parquet(file_name)
    # Get number of groups
    group_numbers = initial_data["gid"].drop_duplicates().unique()
    # Loop through the results for each group
    for i in group_numbers:
        data = initial_data[initial_data["gid"] == i]
        data = data.reset_index(drop=True)
        # Extract the list of x\y
        x_coordinates = data["x"]
        y_coordinates = data["y"]
        # Calculate area between (x[i], y[i]) and (x[i+1], y[i+1])
        rect_areas = [
            (x_coordinates[i + 1] - x_coordinates[i])
            * (y_coordinates[i + 1] + y_coordinates[i])
            / 2
            for i in range(len(x_coordinates) - 1)
        ]
        # Sum the total area
        result = sum(rect_areas)
        res.append(result)
        # Also we can use np for convenience
        # import numpy as np
        # result_np = np.trapz(y_coordinates, x_coordinates)
    return res
calc_area("./data.parquet")

"""Calculate the area between the coordinates and the X-axis
"""
import typing
from pyspark.sql import Window
from pyspark.sql.functions import lead, lit
from pyspark.sql import SparkSession
def calc_area(file_name: str) -> typing.Any:
    """?積計算.
    Args:
    file_name: parquet?件路徑, eg: data.parquet
    Returns:
    計算后的結果
    """
    res = []
    # Create a session with spark
    spark = SparkSession.builder.appName("Area Calculation").getOrCreate()
    # Load data from .parquet
    initial_data = spark.read.parquet(file_name, header=True)
    # Get number of groups
    df_unique = initial_data.dropDuplicates(subset=["gid"]).select("gid")
    group_numbers = df_unique.collect()
    # Loop through the results for each group
    for row in group_numbers:
        # Select a set of data
        data = initial_data.filter(initial_data["gid"] == row[0])
        # Adds a column of delta_x to the data frame representing difference
        # from the x value of an adjacent data point
        window = Window.orderBy(data["x"])
        data = data.withColumn("delta_x", lead("x").over(window) - data["x"])
        # Calculated trapezoidal area
        data = data.withColumn(
            "trap",
            (
                data["delta_x"]
                * (data["y"] + lit(0.5) * (lead("y").over(window) - data["y"]))
            ),
        )
        result = data.agg({"trap": "sum"}).collect()[0][0]
        res.append(result)
    return res
calc_area("./data.parquet")