Commit 919940d6 authored by Illia Kolesnik's avatar Illia Kolesnik
Browse files

Added new doc scripts

parent fd781503

Benchmark/docs_seq_refine.py

0 → 100755
+85 −0
Original line number Diff line number Diff line 
#!/usr/bin/env python3



import os

import shutil

import sys

import pandas as pd

import matplotlib.pyplot as plt



if len(sys.argv) != 3:

    print("Usage: ./script <input_csv> <output_dir>")

    exit(1)



input_csv = sys.argv[1]

output_dir = sys.argv[2]



if os.path.exists(output_dir):

    shutil.rmtree(output_dir)

os.makedirs(output_dir)



# Load the data

# OPERATION;REFINES;SIZE;DISTRIBUTION;LINEAR;CLASSIC

data = pd.read_csv(input_csv, delimiter=';')



# Drop the REFINES column

data = data.drop(columns=['REFINES'])



# Filter the data for 'refinement' operation

refinement_data = data[data['OPERATION'] == 'refinement']



# Get the unique distributions

distributions = refinement_data['DISTRIBUTION'].unique()



# Loop through each distribution and create a plot

for dist in distributions:

    # Check if the directory exists, remove it if it does

    result_path = f"{output_dir}/{dist}"

    os.makedirs(result_path)



    # Filter data for the current distribution

    dist_data = refinement_data[refinement_data['DISTRIBUTION'] == dist]

    dist_data = dist_data.drop(columns=['DISTRIBUTION', 'OPERATION'])



    # Calculate the speedup

    dist_data['SPEEDUP'] = dist_data['LINEAR'] / dist_data['CLASSIC']



    # Calc avg, min, max for each size

    dist_data = dist_data.groupby('SIZE').agg(

        {

            'LINEAR': ['mean', 'min', 'max'],

            'CLASSIC': ['mean', 'min', 'max'],

            'SPEEDUP': ['mean', 'min', 'max']

        }

    )



    # Rename the columns

    dist_data.columns = [

        'LINEAR_AVG', 'LINEAR_MIN', 'LINEAR_MAX',

        'CLASSIC_AVG', 'CLASSIC_MIN', 'CLASSIC_MAX',

        'SPEEDUP_AVG', 'SPEEDUP_MIN', 'SPEEDUP_MAX'

    ]



    # Plotting times

    plt.plot(dist_data['LINEAR_AVG'], label='Linear', marker='o')

    plt.plot(dist_data['CLASSIC_AVG'], label='Classic', marker='x')

    plt.title(f"{dist} distribution")

    plt.xlabel('Size')

    plt.ylabel('Time (s)')

    plt.legend()

    plt.grid(True)

    plt.savefig(f"{result_path}/times.pdf")

    plt.close()



    # Plotting speedup, one is speedup, other is 1 for reference

    plt.plot(dist_data['SPEEDUP_AVG'], label='Speedup', marker='o')



    plt.title(f"{dist} distribution, speedup")

    plt.xlabel('Size')

    plt.ylabel('Speedup')

    plt.legend()

    plt.grid(True)

    plt.savefig(f"{result_path}/speedup.pdf")

    plt.close()



    # Save the data to csv

    dist_data.to_csv(f"{result_path}/data.csv", sep=';')

Benchmark/docs_seq_search.py

+18 −28
Original line number Diff line number Diff line
@@ -13,26 +13,25 @@ def group_by_size(df: pd.DataFrame) -> pd.DataFrame: 
    # LINEAR_MEAN, LINEAR_MIN, LINEAR_MAX

    # CLASSIC_MEAN, CLASSIC_MIN, CLASSIC_MAX

    # SPEEDUP_MEAN, SPEEDUP_MIN, SPEEDUP_MAX

    # But keep SIZE column!

    df = df.groupby("SIZE").agg(

        {

            "LINEAR": ["mean", "min", "max"],

            "CLASSIC": ["mean", "min", "max"],

            "SPEEDUP": ["mean", "min", "max"],

            "SPEEDUP": ["mean", "min", "max"]

        }

    )



    # Rename columns

    df.columns = [

        "LINEAR_AVG",

        "LINEAR_MIN",

        "LINEAR_MAX",

        "CLASSIC_AVG",

        "CLASSIC_MIN",

        "CLASSIC_MAX",

        "SPEEDUP_AVG",

        "SPEEDUP_MIN",

        "SPEEDUP_MAX",

        "LINEAR_AVG", "LINEAR_MIN", "LINEAR_MAX",

        "CLASSIC_AVG", "CLASSIC_MIN", "CLASSIC_MAX",

        "SPEEDUP_AVG", "SPEEDUP_MIN", "SPEEDUP_MAX"

    ]

    df = df.reset_index()



    df = df.reset_index()  # Reset index, so SIZE is a column again

    # print(df)



    return df
@@ -43,11 +42,8 @@ if len(sys.argv) != 3: 
input_csv = sys.argv[1]

output_dir = sys.argv[2]



TITLE_FORMAT = "{operation}, {refine} refines, {distribution} distribution"

DIRNAME_FORMAT = "{distribution}_{refine}"



# If create dir doesn't exist, create it

if not os.path.exists(output_dir):

if os.path.exists(output_dir):

    shutil.rmtree(output_dir)

os.makedirs(output_dir)



# CSV columns:
@@ -73,16 +69,12 @@ operations = [ 
for distribution in distributions:

    for refine in refines:

        # If directory exists, recreate it, even if it's empty

        dirname = DIRNAME_FORMAT.format(

            refine=refine, distribution=distribution

        )

        dirname = f"{distribution}_{refine}"

        result_dir = output_dir + "/" + dirname

        if os.path.exists(result_dir):

            shutil.rmtree(result_dir)

        os.makedirs(result_dir)

        os.makedirs(result_dir + "/times")

        os.makedirs(result_dir + "/speedup")

        os.makedirs(result_dir + "/txt")

        os.makedirs(result_dir + "/csv")



        for operation in operations:

            # Filter by distribution, refine, operation
@@ -90,9 +82,7 @@ for distribution in distributions: 
            filtered = filtered.loc[filtered["REFINES"] == refine]

            filtered = filtered.loc[filtered["OPERATION"] == operation]



            title = TITLE_FORMAT.format(

                operation=operation, refine=refine, distribution=distribution

            )

            title = f"{operation}, {refine} refines, {distribution} distribution"



            # Create dataframes

            all_df = filtered[["SIZE", "LINEAR", "CLASSIC", "SPEEDUP"]]
@@ -122,9 +112,9 @@ for distribution in distributions: 
            plt.ylabel("Speedup, times")

            plt.title(title)

            plt.legend(["Speedup, linear/classic"])

            plt.grid(True)

            plt.savefig(f"{result_dir}/speedup/{operation}.pdf")

            plt.close()



            # Save dataframe as table to file

            with open(f"{result_dir}/txt/{operation}.txt", "w") as f:

                f.write(all_df.to_string(index=False))
 
            all_df.to_csv(f"{result_dir}/csv/{operation}.csv", index=False)