diff --git a/LeQua2024/util_scripts/prior_shift_plot.py b/LeQua2024/util_scripts/prior_shift_plot.py
index d3e3c8c..0f06f57 100644
--- a/LeQua2024/util_scripts/prior_shift_plot.py
+++ b/LeQua2024/util_scripts/prior_shift_plot.py
@@ -2,31 +2,31 @@ import os
from os.path import join
import pandas as pd
+from scripts.data import load_vector_documents
from quapy.data.base import LabelledCollection
import sys
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../')))
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), './')))
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../../')))
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../')))
+# sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), './')))
#from LeQua2024.scripts import constants
#from LeQua2024._lequa2024 import fetch_lequa2024
import quapy as qp
import numpy as np
import matplotlib.pyplot as plt
-import seaborn as sns
+# import seaborn as sns
from pathlib import Path
import glob
+from scripts.constants import SAMPLE_SIZE
-os.chdir('/home/moreo/QuaPy/LeQua2024')
-print(os.getcwd())
+# os.chdir('/home/moreo/QuaPy/LeQua2024')
+# print(os.getcwd())
+TASK=2
+qp.environ['SAMPLE_SIZE']=SAMPLE_SIZE[f'T{TASK}']
-qp.environ['SAMPLE_SIZE']=250
-
-TASK=1
-
-true_prevs_path = f'./TruePrevalences/T{TASK}.test_prevalences/T{TASK}/public/test_prevalences.txt'
-folder = F'./Results_CODALAB_2024/extracted/TASK_{TASK}'
+true_prevs_path = f'../TruePrevalences/T{TASK}.test_prevalences/T{TASK}/public/test_prevalences.txt'
+folder = F'../Results_CODALAB_2024/extracted/TASK_{TASK}'
def load_result_file(path):
df = pd.read_csv(path, index_col=0)
@@ -85,30 +85,12 @@ else:
err_function = err_function_
-def load_vector_documents(path):
- """
- Loads vectorized documents. In case the sample is unlabelled,
- the labels returned are None
-
- :param path: path to the data sample containing the raw documents
- :return: a tuple with the documents (np.ndarray of shape `(n,256)`) and the labels (a np.ndarray of shape `(n,)` if
- the sample is labelled, or None if the sample is unlabelled), with `n` the number of instances in the sample
- (250 for T1 and T4, 1000 for T2, and 200 for T3)
- """
- D = pd.read_csv(path).to_numpy(dtype=float)
- labelled = D.shape[1] == 257
- if labelled:
- X, y = D[:,1:], D[:,0].astype(int).flatten()
- else:
- X, y = D, None
- return X, y
-
#train_prevalence = fetch_lequa2024(task=f'T{TASK}', data_home='./data')
-train = LabelledCollection.load(f'/home/moreo/QuaPy/LeQua2024/data/lequa2024/T{TASK}/public/training_data.txt', loader_func=load_vector_documents)
+train = LabelledCollection.load(f'../data/lequa2024/T{TASK}/public/training_data.txt', loader_func=load_vector_documents)
train_prev = train.prevalence()
#train_prev = np.tile(train_prev, (len(true_id),1))
-from quapy.plot import error_by_drift
+from quapy.plot import error_by_drift, binary_diagonal
# load the participant and baseline results
method_names, estim_prevs = [], []
@@ -123,46 +105,17 @@ for method_file in method_files:
estim_prevs.append(method_prevs)
true_prevs = [true_prevs]*len(method_names)
+savepath = f'./t{TASK}_diagonal.png'
+if TASK==1:
+ binary_diagonal(method_names, true_prevs, estim_prevs, pos_class=1, title=None, show_std=True, legend=True,
+ train_prev=train.prevalence(), savepath=savepath, method_order=None)
+
+
tr_prevs =[train.prevalence()]*len(method_names)
-error_by_drift(method_names,
- true_prevs,
- estim_prevs,
- tr_prevs,
- error_name='mrae', show_std=True,
- show_density=True, vlines=True, savepath=f'./util_scripts/t{TASK}_{error_name}_pcc.png')
-sys.exit()
-
-shift=qp.error.ae(train_prev, true_prevs)
-
-n_bins = 5
-bins = np.linspace(shift.min(), shift.max(), n_bins + 1)
-
-# Crear un DataFrame para los datos
-df = pd.DataFrame({'dom_A_prevs': shift})
-for method, err in errors.items():
- df[method] = err
-
-# Asignar cada valor de dom_A_prevs a un bin
-df['bin'] = pd.cut(df['dom_A_prevs'], bins=bins, labels=False, include_lowest=True)
-
-# Convertir el DataFrame a formato largo
-df_long = df.melt(id_vars=['dom_A_prevs', 'bin'], value_vars=errors.keys(), var_name='Método', value_name='Error')
-
-# Crear etiquetas de los bins para el eje X
-bin_labels = [f"[{bins[i]:.3f}-{bins[i + 1]:.3f}" + (']' if i == n_bins-1 else ')') for i in range(n_bins)]
-df_long['bin_label'] = df_long['bin'].map(dict(enumerate(bin_labels)))
-
-# Crear el gráfico de boxplot en Seaborn
-plt.figure(figsize=(14, 8))
-sns.boxplot(x='bin', y='Error', hue='Método', data=df_long, palette='Set2', showfliers=False)
-
-# Configurar etiquetas del eje X con los rangos de los bins
-plt.xticks(ticks=range(n_bins), labels=bin_labels, rotation=0)
-plt.xlabel("Amount of PPS between the training prevalence and the test prevalences, in terms of AE ")
-plt.ylabel(error_name)
-#plt.title("Boxplots de Errores por Método dentro de Bins de dom_A_prevs")
-plt.legend(loc='upper left', bbox_to_anchor=(1, 1))
-plt.tight_layout()
-plt.grid(True, which='both', linestyle='--', linewidth=0.5)
-#plt.show()
-plt.savefig(f'./util_scripts/t{TASK}_{error_name}_pcc.png')
+savepath = f'./t{TASK}_{error_name}_pps.png'
+error_by_drift(method_names,
+ true_prevs,
+ estim_prevs,
+ tr_prevs, title=None,
+ error_name='rae', show_std=True, n_bins=1000,
+ show_density=True, vlines=[tr_prevs[0][1]], savepath=savepath)