feature: add boxplot script

Author: iraedeus

boxplotting.py

@@ -0,0 +1,98 @@
+from pathlib import Path
+
+import pandas as pd
+from matplotlib import pyplot as plt
+
+from experimental_env.analysis.analyze_summarizers.boxplot_error_summarizer import BoxplotErrorSummarizer
+from experimental_env.analysis.metrics import SquaredError
+from experimental_env.experiment.experiment_parser import ExperimentParser
+import os
+import seaborn as sns
+
+box_plots_dir = input("Enter the directory where boxplots will be saved.")
+WORKING_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/boxplots")
+
+EM_200_dir = input("Enter the path to the results of the EM algorithm in the second stage with sample size 200.")
+ELM_200_dir = input("Enter the path to the results of the ELM algorithm in the second stage with sample size 200.")
+
+EM_500_dir = input("Enter the path to the results of the EM algorithm in the second stage with sample size 500.")
+ELM_500_dir = input("Enter the path to the results of the ELM algorithm in the second stage with sample size 500.")
+
+EM_1000_dir = input("Enter the path to the results of the EM algorithm in the second stage with sample size 1000.")
+ELM_1000_dir = input("Enter the path to the results of the ELM algorithm in the second stage with sample size 1000.")
+
+# Compare results
+LMOMENTS_200_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/experiment_200/stage_2/ELM")
+LIKELIHOOD_200_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/experiment_200/stage_2/EM")
+
+LMOMENTS_500_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/experiment_500/stage_2/ELM")
+LIKELIHOOD_500_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/experiment_500/stage_2/EM")
+
+LMOMENTS_1000_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/experiment_1000/stage_2/ELM")
+LIKELIHOOD_1000_DIR = Path("/home/iraedeus/Projects/EM-algo-experiment/experiment_1000/stage_2/EM")
+
+ELM_200_results = ExperimentParser().parse(LMOMENTS_200_DIR)
+EM_200_results = ExperimentParser().parse(LIKELIHOOD_200_DIR)
+
+ELM_500_results = ExperimentParser().parse(LMOMENTS_500_DIR)
+EM_500_results = ExperimentParser().parse(LIKELIHOOD_500_DIR)
+
+ELM_1000_results = ExperimentParser().parse(LMOMENTS_1000_DIR)
+EM_1000_results = ExperimentParser().parse(LIKELIHOOD_1000_DIR)
+
+os.makedirs(WORKING_DIR, exist_ok=True)
+
+mixture_keys = EM_200_results.keys()
+
+for mixture in mixture_keys:
+    ELM_200_results_mixture = ELM_200_results[mixture]
+    EM_200_results_mixture = EM_200_results[mixture]
+
+    ELM_500_results_mixture = ELM_500_results[mixture]
+    EM_500_results_mixture = EM_500_results[mixture]
+
+    ELM_1000_results_mixture = ELM_1000_results[mixture]
+    EM_1000_results_mixture = EM_1000_results[mixture]
+
+    summarizer = BoxplotErrorSummarizer(SquaredError())
+
+    ELM_200_errors = summarizer.calculate(ELM_200_results_mixture)
+    EM_200_errors = summarizer.calculate(EM_200_results_mixture)
+
+    ELM_500_errors = summarizer.calculate(ELM_500_results_mixture)
+    EM_500_errors = summarizer.calculate(EM_500_results_mixture)
+
+    ELM_1000_errors = summarizer.calculate(ELM_1000_results_mixture)
+    EM_1000_errors = summarizer.calculate(EM_1000_results_mixture)
+
+    all_data_list = []
+
+    for error in EM_200_errors:
+        all_data_list.append({'size': 200, 'Algorithm': 'EM', 'Error': error})
+    for error in ELM_200_errors:
+        all_data_list.append({'size': 200, 'Algorithm': 'ELM', 'Error': error})
+
+    for error in EM_500_errors:
+        all_data_list.append({'size': 500, 'Algorithm': 'EM', 'Error': error})
+    for error in ELM_500_errors:
+        all_data_list.append({'size': 500, 'Algorithm': 'ELM', 'Error': error})
+
+    for error in EM_1000_errors:
+        all_data_list.append({'size': 1000, 'Алгоритм': 'EM', 'Error': error})
+    for error in ELM_1000_errors:
+        all_data_list.append({'size': 1000, 'Algorithm': 'ELM', 'Error': error})
+
+    combined_data = pd.DataFrame(all_data_list)
+
+    fig, ax = plt.subplots(figsize=(10, 6))
+
+    sns.boxplot(x='size', y='Error', hue='Algorithm', data=combined_data, ax=ax)
+
+    ax.set_title(f'{mixture}')
+    ax.set_xlabel('Sample size')
+    ax.set_ylabel('Metric value')
+    ax.set_yscale('log')
+
+    plt.tight_layout()
+    plt.savefig(WORKING_DIR / f'boxplot_{mixture}.png')
+    plt.close(fig)